CN117164103A

CN117164103A - Intelligent control method, terminal and system of domestic sewage treatment system

Info

Publication number: CN117164103A
Application number: CN202310804261.8A
Authority: CN
Inventors: 张亚文; 况钧耀; 赵勋; 吴敬瑞
Original assignee: Guangxi Zhibida Intelligent Environment Technology Co ltd
Current assignee: Guangxi Zhibida Intelligent Environment Technology Co ltd
Priority date: 2023-07-03
Filing date: 2023-07-03
Publication date: 2023-12-05

Abstract

The invention provides an intelligent control method, a terminal and a system of a domestic sewage treatment system, wherein the intelligent control method of the domestic sewage treatment system comprises the following steps: inputting organic matter parameters into a pre-constructed circulating neural network model when the first water level of the septic tank is larger than a preset first water level, and controlling an electromagnetic valve of a water outlet of the septic tank to be opened when the output first life sewage evaluation result meets the requirement; inputting the characteristic information of the main component into a pre-constructed main component analysis model when the second water level of the water collecting device is larger than a preset second water level, and controlling an electromagnetic valve of a water outlet of the water collecting device to be opened when the output second domestic sewage evaluation result meets the requirement; when the third water level of the ecological tank is larger than the preset third water level, inputting the water quality parameters into a pre-constructed random forest model, and when the output third domestic sewage evaluation result meets the requirement, controlling the electromagnetic valve of the water outlet of the ecological tank to be opened so as to improve the control precision of the domestic sewage treatment process.

Description

Intelligent control method, terminal and system of domestic sewage treatment system

Technical Field

The invention relates to the technical field of domestic sewage treatment, in particular to an intelligent control method, a terminal and a system of a domestic sewage treatment system.

Background

The unordered discharge of domestic sewage is an important cause of environmental pollution, often causes black and odorous water body, seriously affects the daily life of local residents, and has certain challenges in the control of the domestic sewage treatment process.

The existing domestic sewage treatment process control technology is still relatively backward, and although the sewage treatment process can be controlled by means of an artificial intelligence technology, the neural network model is generally adopted to evaluate the finally discharged domestic sewage after the treatment of the domestic sewage treatment system, so that whether the requirements of all sewage treatment stages are met or not is difficult to evaluate, and the control precision of the domestic sewage treatment is low.

In the technical scheme of application number CN202110603667.0, although the method receives data information uploaded by a plurality of integrated devices for rural domestic sewage treatment in real time, when the target device is determined to be in a first preset link in a current process treatment period according to the data information, a current treatment process reference model is obtained, a target treatment process is obtained by matching the treatment process reference model according to water inlet parameter information of the target device in the current process treatment period in the data information, when colony adjustment information of the target device is detected, the target treatment process is adjusted according to the colony adjustment information so as to timely adjust the sewage treatment process by combining the technology of Internet of things, the artificial intelligence technology, the big data technology, the ecological environment adjustment and the like, but effective monitoring and control of each stage of the domestic sewage treatment process are not realized, and the control accuracy is low.

Disclosure of Invention

The invention provides an intelligent control method, a terminal and a system of a domestic sewage treatment system, which are used for effectively monitoring and controlling each stage of the domestic sewage treatment process and improving the control precision of the domestic sewage treatment process.

In order to solve the problems, the invention adopts the following technical scheme:

the invention provides an intelligent control method of a domestic sewage treatment system, which is applied to control equipment of the domestic sewage treatment system, the domestic sewage treatment system also comprises a plurality of data acquisition devices, a water collecting device, a solar power supply device, a septic tank and an ecological tank, wherein each data acquisition device is respectively arranged on the water collecting device, the solar power supply device, the septic tank and the ecological tank, the water inlets or the water outlets of the water collecting device, the septic tank and the ecological tank are provided with electromagnetic valves for controlling the inlet and the outlet of the domestic sewage, the control equipment is respectively and electrically connected with the electromagnetic valves, the solar power supply device and each data acquisition device, the water inlet of the septic tank is connected with a sewage outlet of a toilet through a pipeline, the water outlet of the septic tank is connected with the water inlet of the water collecting device through a pipeline, the water inlet of the water collecting device is also connected with a sewage outlet of a kitchen and a bathroom through a pipeline, the water outlet of the water collecting device is connected with the ecological tank through a pipeline, the data acquisition device is used for acquiring domestic sewage information or equipment information, the septic tank and the water collecting device are buried underground, the septic tank is used for collecting, storing and decomposing organic matters in the excrement in the domestic sewage, the water collecting device is used for collecting the domestic sewage with the pollution degree lower than the preset degree or after preliminary purification treatment, the solar power supply device is used for supplying power to electric equipment of the domestic sewage treatment system, and the ecological tank is used for degrading and converting the organic matters and pollutants in the domestic sewage into harmless matters through interaction of microorganisms and plants, wherein the intelligent control method of the domestic sewage treatment system comprises the following steps:

When the domestic sewage treatment system enters a working state, monitoring the water level of domestic sewage in the septic tank in real time, and when the first water level of the septic tank is monitored to be larger than a preset first water level, receiving first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank, and extracting organic matter parameters of the first domestic sewage information; the first data acquisition device comprises a chemical oxygen demand sensor, a biochemical oxygen demand sensor and a suspended matter sensor;

inputting the organic matter parameters into a pre-constructed circulating neural network model to obtain a first living sewage evaluation result corresponding to the first living sewage information, and controlling an electromagnetic valve arranged at a water outlet of the septic tank to be opened when the first living sewage evaluation result is determined to meet the requirements so that the living sewage of the septic tank flows to a water collecting device; the circulating neural network model is used for analyzing and evaluating organic matter parameters in the domestic sewage;

the method comprises the steps of monitoring the water level of domestic sewage in the water collecting device in real time, when the second water level of the water collecting device is monitored to be larger than a preset second water level, receiving second domestic sewage information acquired by a second data acquisition device positioned at a water outlet of the water collecting device, and extracting main component characteristic information of the second domestic sewage information; the main component characteristic information comprises nitrogen and phosphorus parameters and microorganism parameters of domestic sewage, and the second data acquisition device comprises a nitrogen and phosphorus sensor and a microorganism sensor;

Inputting the principal component characteristic information into a pre-constructed principal component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the water collecting device to be opened when the second domestic sewage evaluation result is determined to meet the requirement so that the domestic sewage of the water collecting device flows to an ecological tank; the main component analysis model is used for analyzing and evaluating nitrogen and phosphorus parameters and microorganism parameters in the domestic sewage;

the method comprises the steps of monitoring the water level of domestic sewage in an ecological tank in real time, when the third water level of the ecological tank is monitored to be larger than a preset third water level, receiving third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank, and extracting water quality parameters of the first domestic sewage information; wherein, the quality of water parameter includes pH valve, dissolved oxygen and the conductivity of domestic sewage, third data acquisition device includes: a pH value sensor, a dissolved oxygen sensor and a conductivity sensor;

inputting the water quality parameters into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the ecological tank to be opened when the third domestic sewage evaluation result is determined to meet the requirements so as to discharge the domestic sewage of the ecological tank; the random forest model is used for analyzing and evaluating water quality parameters in domestic sewage.

Further, after the step of inputting the organic matter parameters into a pre-constructed cyclic neural network model to obtain the first life sewage evaluation result corresponding to the first life sewage information, the method further includes:

generating a plurality of first treatment schemes of the domestic sewage according to the first domestic sewage evaluation result when the first domestic sewage evaluation result is determined to not meet the requirement;

constructing a processing scheme evaluation model, and inputting the plurality of first processing schemes into the processing scheme evaluation model to obtain a grading value of each first processing scheme;

sorting the plurality of first processing schemes according to the order of the scoring values from large to small to obtain a sorting result;

and sequentially selecting a corresponding first treatment scheme according to the sequencing result to treat the domestic sewage until the first domestic sewage evaluation result meets the requirement.

Further, before the step of inputting the principal component characteristic information into a pre-constructed principal component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, the method further includes:

acquiring a data set; the data set comprises a plurality of groups of principal component characteristic information and reference evaluation results corresponding to each group of principal component characteristic information;

Dividing the data set into a test set and a verification set according to a preset proportion, and inputting the test set into a pre-constructed convolutional neural network model to perform convolutional operation to obtain convolutional characteristics;

performing back propagation training on the convolution characteristics by using a cross entropy loss function until a first loss value of the convolution neural network model is lower than a preset first loss value, so as to obtain an initial principal component analysis model;

inputting the verification set into the initial principal component analysis model for verification, and when the verification result is determined to meet the preset requirement, storing parameters of the initial principal component analysis model to obtain a trained principal component analysis model.

Further, before the step of inputting the water quality parameters into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further includes:

acquiring a training sample data set; the training sample data set comprises 2N training samples, each training sample comprises a group of standard water quality parameters and corresponding standard domestic sewage evaluation results, and N is a positive integer;

equally dividing the training sample data set into a plurality of sub-data sets; wherein each sub-dataset comprises two training samples;

Randomly extracting a training sample from each sub-data set as a target training sample to obtain N target training samples;

randomly selecting the N target training samples to obtain K groups of training sets; wherein each set of training sets comprises a plurality of target training samples, and the number of target training samples of each set of training sets is the same but not repeated;

training the K groups of training sets by utilizing a decision tree algorithm to obtain K trained classification models;

respectively calculating a second loss value of each trained classification model by using the cross entropy loss function;

comparing the second loss value of each trained classification model with a preset second loss value respectively, screening classification models with second loss values lower than the preset second loss value, and obtaining a plurality of target classification models;

and combining the target classification models to obtain a random forest model.

Further, the intelligent control method of the domestic sewage treatment system further comprises the following steps:

acquiring the residual electric quantity of an energy storage battery in the solar power supply device, and calculating the power consumption required by electric equipment of the domestic sewage treatment system in a future preset time period;

Acquiring weather forecast information in the preset time period, and estimating the illumination time length and the average illumination intensity in the preset time period according to the weather forecast information; the weather forecast information comprises weather conditions, illumination duration and average illumination intensity of each time period;

the conversion rate of the solar power supply device is obtained, and the power supply quantity of the solar power supply device in the preset time period is calculated according to the illumination time length, the average illumination intensity and the conversion rate;

calculating the sum of the residual electric quantity and the power supply quantity to obtain the total power supply quantity;

and judging whether the power consumption is larger than the total power supply amount, and when the power consumption is judged to be larger than the total power supply amount, determining a trough time period of the mains supply in the current area, and charging the energy storage battery in the trough time period in the preset time period.

Preferably, the step of extracting the characteristic information of the main component of the second domestic sewage information includes:

converting the second domestic sewage information into a matrix to obtain a standard matrix;

randomly initializing two matrixes by using a uniform distribution function or a Gaussian distribution function to obtain a first matrix and a second matrix;

Judging whether the product of the first matrix and the second matrix is equal to the standard matrix or not;

when the product of the first matrix and the second matrix is not equal to the standard matrix, continuously updating the first matrix and the second matrix according to a method for minimizing reconstruction errors until the product of the first matrix and the second matrix is equal to the standard matrix, and obtaining a first target matrix and a second target matrix;

and respectively converting the first target matrix and the second target matrix into low-dimensional characteristic representation by using a principal component analysis method to obtain principal component characteristic information of the second domestic sewage information.

Further, after the step of inputting the water quality parameter into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further includes:

encrypting the first domestic sewage evaluation result, the second domestic sewage evaluation result and the second domestic sewage evaluation result by using an asymmetric encryption algorithm to obtain encrypted data;

carrying out hash processing on the encrypted data according to an MD5 algorithm to obtain a reference hash value, compressing and packaging the reference hash value and the encrypted data to obtain ciphertext data, and storing the ciphertext data to a cloud;

Responding to a data query request of a user, acquiring the ciphertext data from a cloud according to the data query request, and decompressing the ciphertext data to obtain decompressed data;

calculating the hash value of the decompressed data to obtain a target hash value;

comparing the target hash value with the reference hash value;

and when the target hash value is the same as the reference hash value, decrypting the decompressed data by using an asymmetric encryption algorithm to obtain plaintext data, and returning the plaintext data to the user.

Preferably, the step of encrypting the first domestic sewage evaluation result, the second domestic sewage evaluation result and the second domestic sewage evaluation result by using an asymmetric encryption algorithm to obtain encrypted data includes:

preprocessing the first living sewage evaluation result, the second living sewage evaluation result and the second living sewage evaluation result to obtain data to be encrypted; the preprocessing mode comprises the steps of removing abnormal values in data, carrying out normalization processing and standardization processing on the data, and filling the missing data by using a Lagrange interpolation method;

and encrypting the data to be encrypted to obtain encrypted data.

The invention provides a terminal comprising a memory and a processor, wherein the memory stores computer readable instructions which, when executed by the processor, cause the processor to execute the steps of the intelligent control method of the domestic sewage treatment system.

The invention provides a domestic sewage treatment system, which comprises control equipment, a plurality of data acquisition devices, a water collection device, a solar power supply device, a septic tank and an ecological tank, wherein the data acquisition devices are respectively arranged on the water collection device, the solar power supply device, the septic tank and the ecological tank; wherein the control device comprises a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the intelligent control method of the domestic sewage treatment system as described in any one of the above.

Compared with the prior art, the technical scheme of the invention has at least the following advantages:

according to the intelligent control method, terminal and system for the domestic sewage treatment system, when the domestic sewage treatment system enters a working state, the water level of domestic sewage in the septic tank is monitored in real time, when the monitored first water level of the septic tank is larger than the preset first water level, first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank is received, organic matter parameters of the first domestic sewage information are extracted, the organic matter parameters are input into a pre-constructed circulating neural network model, a first domestic sewage evaluation result corresponding to the first domestic sewage information is obtained, and when the first domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the septic tank is controlled to be opened, so that the domestic sewage of the septic tank flows to a water collecting device; when the second water level of the water collecting device is monitored to be larger than a preset second water level, second domestic sewage information acquired by a second data acquisition device positioned at a water outlet of the water collecting device is received, main component characteristic information of the second domestic sewage information is extracted, the main component characteristic information is input into a pre-built main component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and when the second domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the water collecting device is controlled to be opened, so that the domestic sewage of the water collecting device flows to an ecological tank; when the third water level of the ecological tank is monitored to be greater than a preset third water level, third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank is received, water quality parameters of the first domestic sewage information are extracted, the water quality parameters are input into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, when the third domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the ecological tank is controlled to be opened, the domestic sewage of the ecological tank is discharged, and accordingly, according to different sewage treatment stages of a domestic sewage treatment system, the corresponding neural network model is called to evaluate the domestic sewage of different stages, fine evaluation is achieved, the domestic sewage of the previous stage is ensured to enter the next stage after meeting the requirement, effective monitoring and control of each stage of the domestic sewage treatment process are achieved, and the control precision of the domestic sewage treatment process is improved.

Drawings

FIG. 1 is a flow chart of an embodiment of an intelligent control method of a domestic sewage treatment system of the present invention;

FIG. 2 is a block diagram showing the construction of an embodiment of a domestic sewage treatment system according to the present invention;

FIG. 3 is a block diagram of an embodiment of an intelligent control device of the domestic sewage treatment system of the present invention;

fig. 4 is a block diagram illustrating an internal structure of a terminal according to an embodiment of the present invention.

Detailed Description

In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.

In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations appearing in a particular order are included, but it should be clearly understood that the operations may be performed in other than the order in which they appear herein or in parallel, the sequence numbers of the operations such as S11, S12, etc. are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by one of ordinary skill in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.

It will be understood by those of ordinary skill in the art that unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.

Referring to fig. 1, in combination with fig. 2, the present invention provides an intelligent control method for a domestic sewage treatment system, which is applied to a control device 1 of the domestic sewage treatment system, wherein the domestic sewage treatment system further comprises a plurality of data acquisition devices, a water collection device 3, a solar power supply device 5, a septic tank 2 and an ecological tank 4, each data acquisition device is respectively arranged on the water collection device 3, the solar power supply device 5, the septic tank 2 and the ecological tank 4, and each data acquisition device can comprise a ph value sensor, a dissolved oxygen sensor, a conductivity sensor, a chemical oxygen demand sensor, a biochemical oxygen demand sensor, a suspended matter sensor, an ammonia nitrogen sensor, a total nitrogen and total phosphorus sensor, a microorganism sensor and the like.

PH value sensor: the pH value measuring device is used for measuring the pH value in domestic sewage and comprises a glass electrode pH sensor and an ISFET (ion sensitive field effect transistor) pH sensor.

Dissolved oxygen sensor: the dissolved oxygen content in domestic sewage is measured by electrochemical or optical principle, and there are membrane type sensor and fluorescent oxygen sensor.

Conductivity sensor: the method is used for measuring the conductivity in the domestic sewage and reflecting the salinity and the ion concentration in the domestic sewage. There are electrode conductivity sensors and conductivity meters.

Chemical oxygen demand sensor: the COD value in domestic sewage is measured by chemical reaction, and the chemical sensor and the optical sensor are provided.

Biochemical oxygen demand sensor: the BOD value in domestic sewage is estimated by measuring oxygen consumption, and a biosensor and an electrode type sensor are included.

Suspension sensor: the device is used for measuring the concentration of suspended matters in domestic sewage, and comprises a turbidity sensor, a laser scattering sensor and the like.

Ammonia nitrogen sensor: the device is used for measuring the ammonia nitrogen content in domestic sewage, and comprises an electrode ammonia nitrogen sensor and an optical ammonia nitrogen sensor.

Total nitrogen and total phosphorus sensors: the total nitrogen and total phosphorus content in domestic sewage is estimated by chemical reaction or optical measurement, and there are chemical sensors and optical sensors.

Microbial sensor: is used for detecting microorganism indexes such as escherichia coli in domestic sewage. There are biosensors, immunosensors, and the like.

The water inlet or the water outlet of the water collecting device 3, the septic tank 2 and the ecological tank 4 are provided with electromagnetic valves for controlling the domestic sewage to enter and exit, the control equipment 1 is respectively electrically connected with the electromagnetic valves, the solar power supply device 5 and each data acquisition device (not shown in fig. 2), the water inlet of the septic tank 2 is connected with a sewage outlet of a toilet through a pipeline, the water outlet of the septic tank 2 is connected with the water inlet of the water collecting device 3 through a pipeline, the water inlet of the water collecting device 3 is also connected with the sewage outlet of a kitchen and a bathroom through a pipeline, the water outlet of the water collecting device 3 is connected with the ecological tank 4 through a pipeline, the data acquisition device is used for acquiring domestic sewage information or equipment information, the septic tank 2 and the water collecting device 3 are buried underground, the septic tank 2 is used for collecting, storing and decomposing organic matters of excrement in domestic sewage, the water collecting device 3 is used for collecting domestic sewage with a pollution degree lower than a preset degree (such as water after washing dishes, clothes or washing water after preliminary purification treatment), the solar power supply device 5 is used for converting the domestic sewage into electric equipment (such as a sewage system 1, a sewage power supply system and an intelligent control system, a sewage system and a biological degradation system are used for the electromagnetic valve, the biological degradation system is used for the control equipment, the sewage system is provided with the electromagnetic valve 4, and the method is used for performing the mutual degradation, and the biological control of the sewage system is provided with the control equipment, and the sewage is provided with the biological control equipment:

S11, when a domestic sewage treatment system enters a working state, monitoring the water level of domestic sewage in the septic tank in real time, and when the first water level of the septic tank is monitored to be larger than a preset first water level, receiving first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank, and extracting organic matter parameters of the first domestic sewage information; the first data acquisition device comprises a chemical oxygen demand sensor, a biochemical oxygen demand sensor and a suspended matter sensor;

s12, inputting the organic matter parameters into a pre-constructed circulating neural network model to obtain a first sewage evaluation result corresponding to the first sewage information, and controlling an electromagnetic valve arranged at a water outlet of the septic tank to be opened when the first sewage evaluation result is determined to meet the requirement so that the sewage of the septic tank flows to a water collecting device; the circulating neural network model is used for analyzing and evaluating organic matter parameters in the domestic sewage;

s13, monitoring the water level of domestic sewage in the water collecting device in real time, and when the second water level of the water collecting device is monitored to be larger than a preset second water level, receiving second domestic sewage information acquired by a second data acquisition device positioned at a water outlet of the water collecting device, and extracting main component characteristic information of the second domestic sewage information; the main component characteristic information comprises nitrogen and phosphorus parameters and microorganism parameters of domestic sewage, and the second data acquisition device comprises a nitrogen and phosphorus sensor and a microorganism sensor;

S14, inputting the principal component characteristic information into a pre-constructed principal component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the water collecting device to be opened when the second domestic sewage evaluation result is determined to meet the requirement so that the domestic sewage of the water collecting device flows to an ecological tank; the main component analysis model is used for analyzing and evaluating nitrogen and phosphorus parameters and microorganism parameters in the domestic sewage;

s15, monitoring the water level of domestic sewage in the ecological tank in real time, and when the third water level of the ecological tank is monitored to be larger than a preset third water level, receiving third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank, and extracting water quality parameters of the first domestic sewage information; wherein, the quality of water parameter includes pH valve, dissolved oxygen and the conductivity of domestic sewage, third data acquisition device includes: a pH value sensor, a dissolved oxygen sensor and a conductivity sensor;

s16, inputting the water quality parameters into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the ecological tank to be opened when the third domestic sewage evaluation result is determined to meet the requirements so as to discharge the domestic sewage of the ecological tank; the random forest model is used for analyzing and evaluating water quality parameters in domestic sewage.

As described in the above steps S11-S12, when the domestic sewage treatment system enters a working state, the water level sensor installed in the septic tank 2 first collects the water level in the septic tank 2 to obtain a first water level, and sends the first water level to the control device 1, the control device 1 compares the first water level with a preset first water level, and when the first water level of the septic tank 2 is detected to be greater than the preset first water level, the first domestic sewage information collected by the first data collecting device installed at the water outlet of the septic tank 2 is received. Wherein the preset first water level is smaller than the highest water level of the septic tank 2, the first domestic sewage information may include various data and parameters related to sewage treatment and discharge. The sewage treatment method specifically comprises the following sewage information contents:

1. water quality parameters:

pH value: reflecting the acidity and alkalinity of the water body.

Dissolved Oxygen (DO): the content of dissolved oxygen in the water body is represented, and is important to the ecological environment of the water body and the health of aquatic organisms.

Conductivity: the ability to dissolve ions in a water body is an index for evaluating the salinity and ion concentration of the water body.

2. Organic matter parameters:

chemical Oxygen Demand (COD): reflecting the total content of organic matters in the water body.

Biochemical Oxygen Demand (BOD): represents the amount of oxygen required by microorganisms in a body of water to decompose organic substances for assessing the self-cleaning ability of the body of water.

Suspension: solid particles suspended in water, such as suspended sediment, organic particles, and the like.

3. Nitrogen and phosphorus parameters:

ammonia nitrogen: represents the ammonia content in the water body and can be derived from urine, fertilizer and the like.

Total nitrogen: including nitrogen in the form of ammonia nitrogen, nitrate nitrogen, nitrite nitrogen, etc.

Total phosphorus: indicating the total content of phosphorus in the body of water, possibly from detergents, fertilizers, etc.

4. Microbial parameters:

coli: as one of the bacterial indexes, the pollution degree of pathogenic bacteria possibly existing in the water body is reflected.

Total number of culturable bacteria: an indicator representing the total number of microorganisms in the body of water.

The control device 1 extracts organic matter parameters of the first living sewage information, inputs the organic matter parameters into a pre-constructed cyclic neural network model, and obtains a first living sewage evaluation result corresponding to the first living sewage information, wherein the first living sewage evaluation result comprises whether the chemical oxygen demand, the biochemical oxygen demand and the suspended matter parameters reach standards, and the cyclic neural network (RecurrentNeuralNetwork, RNN) is a neural network model for processing sequence data. Unlike feed-forward neural networks, RNNs have the ability to memorize and iterate, and can process input sequences of arbitrary length. A key feature of the RNN is its cyclic structure, allowing information to be transferred from a current time step to the next time step. At each time step, the RNN receives the current input and the hidden state of the previous time step and generates the output of the current time step and a new hidden state. This loop structure enables the RNN to model and learn the context information in the sequence. The basic units of the RNN are cyclic units (RecurrentUnit) including simple cyclic units (SimpleRecurrent Unit, SRU) and long short-term memory units (LongShort-TermMemory, LSTM). These cyclic units enable the transfer and memorization of information by activating functions and weighting parameters.

When the first living sewage evaluation result meets the requirements, such as the chemical oxygen demand, the biochemical oxygen demand and the suspended matter parameters reach the standards, the electromagnetic valve arranged at the water outlet of the septic tank 2 is controlled to be opened, so that the living sewage of the septic tank 2 flows to the water collecting device 3.

As described in the above steps S13-S14, when it is determined that the first sanitary sewage evaluation result meets the requirement and the electromagnetic valve of the water outlet of the septic tank 2 is opened, the water level sensor installed in the water collecting device 3 collects the water level in the water collecting device 3 to obtain a second water level and sends the second water level to the control device 1, the control device 1 compares the second water level with the preset second water level, and when it is monitored that the second water level of the water collecting device 3 is greater than the preset second water level, the second sanitary sewage information collected by the second data collecting device installed at the water outlet of the water collecting device 3 is received. Wherein, the preset second water level is smaller than the highest water level of the water collecting device 3, the water collecting device 3 can be in the form of a septic tank 2, and the second domestic sewage information can also comprise various data and parameters related to sewage treatment and discharge, which are not described herein.

The control device 1 extracts main component characteristic information of the second domestic sewage information, such as nitrogen and phosphorus parameters and microorganism parameters of the domestic sewage, inputs the main component characteristic information into a pre-constructed main component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, wherein the second domestic sewage evaluation result comprises whether the nitrogen and phosphorus parameters and the microorganism parameters in the domestic sewage reach standards or not so as to analyze and evaluate the nitrogen and phosphorus parameters and the microorganism parameters in the domestic sewage.

Wherein, the principal component analysis (PrincipalComponentAnalysis, PCA) is a dimension reduction technique and a data compression method. It converts the original high-dimensional data into a low-dimensional feature space by linear transformation to find the dominant pattern of change in the data. The goal of principal component analysis is to find a new set of orthogonal features, called principal components, that can preserve the variance of the original data to the maximum. Each principal component is a linear combination of the original features and is uncorrelated with each other. The first principal component interprets the largest variance in the data, the second principal component interprets the next largest variance, and so on.

When the second domestic sewage evaluation result meets the requirements, if the nitrogen and phosphorus parameters and the microbial parameters in the domestic sewage reach the standards, the electromagnetic valve arranged at the water outlet of the water collecting device 3 is controlled to be opened, so that the domestic sewage of the water collecting device 3 flows to the ecological tank 4, and further purification treatment is performed in the ecological tank 4.

As described in the above steps S15-S16, when it is determined that the second domestic sewage evaluation result meets the requirement and the electromagnetic valve of the water outlet of the water collecting device 3 is opened, the water level sensor installed in the ecological tank 4 collects the water level in the ecological tank 4 to obtain a third water level, and sends the third water level to the control device 1, the control device 1 compares the third water level with the preset third water level, and when it is monitored that the third water level of the ecological tank 4 is greater than the preset third water level, the third domestic sewage information collected by the third data collecting device installed in the water outlet of the ecological tank 4 is received. Wherein, the preset third water level is smaller than the highest water level of the ecological tank 4, the ecological tank 4 can be a pool where various aquatic plants are planted, the third domestic sewage information can also include various data and parameters related to sewage treatment and discharge, and the water quality parameters include the ph value, dissolved oxygen and conductivity of the domestic sewage, and the third data acquisition device includes: a pH value sensor, a dissolved oxygen sensor and a conductivity sensor.

The control device 1 extracts water quality parameters of third domestic sewage information, such as the pH value, dissolved oxygen and conductivity of the domestic sewage, inputs the water quality parameters into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, wherein the third domestic sewage evaluation result comprises whether the pH value, the dissolved oxygen and the conductivity of the domestic sewage reach the standards or not so as to analyze and evaluate the pH value, the dissolved oxygen and the conductivity of the domestic sewage.

The random forest (random forest) is an integrated learning algorithm and is a model built based on decision trees. It performs classification or regression tasks by combining multiple decision trees and derives the final output by voting or averaging the predicted results. Key features of random forests include:

decision tree integration: the random forest is composed of a plurality of decision trees, each of which is a weak learner. Each decision tree performs feature selection and splitting on the data to minimize the non-purity (e.g., coefficient of kunity, information gain, etc.).

Randomness: randomness is introduced in constructing random forests, including sample random sampling and feature random selection. By randomly sampling a subset of the training set, each decision tree is trained using only a portion of the samples. The feature random selection is to randomly select a part of the features from all the features at each split for calculating the optimal split.

Integrated voting or averaging: in the classification problem, the random forest counts the classification result of each decision tree in a voting mode, and the class with the largest vote is selected as the final classification result. In the regression problem, the random forest obtains the final output by averaging the predicted results of each decision tree.

When the third domestic sewage evaluation result meets the requirements, if the pH value, the dissolved oxygen and the conductivity in the domestic sewage reach the standards, the electromagnetic valve arranged at the water outlet of the ecological tank 4 is controlled to be opened, so that the domestic sewage of the ecological tank 4 is discharged.

According to the intelligent control method of the domestic sewage treatment system, when the domestic sewage treatment system enters a working state, the water level of domestic sewage in the septic tank 2 is monitored in real time, when the monitored first water level of the septic tank 2 is larger than the preset first water level, first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank 2 is received, organic matter parameters of the first domestic sewage information are extracted, the organic matter parameters are input into a pre-constructed circulating neural network model, a first domestic sewage evaluation result corresponding to the first domestic sewage information is obtained, and when the first domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the septic tank 2 is controlled to be opened, so that the domestic sewage of the septic tank 2 flows to the water collecting device 3; when the second water level of the water collecting device 3 is monitored to be larger than a preset second water level, receiving second domestic sewage information acquired by a second data acquisition device positioned at a water outlet of the water collecting device 3, extracting main component characteristic information of the second domestic sewage information, inputting the main component characteristic information into a pre-constructed main component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and when the second domestic sewage evaluation result is determined to meet the requirement, controlling an electromagnetic valve arranged at the water outlet of the water collecting device 3 to be opened to enable the domestic sewage of the water collecting device 3 to flow to the ecological tank 4; when the water level of the domestic sewage in the ecological tank 4 is monitored in real time, when the third water level of the ecological tank 4 is monitored to be larger than a preset third water level, third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank 4 is received, water quality parameters of the first domestic sewage information are extracted, the water quality parameters are input into a pre-built random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, when the third domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the ecological tank 4 is controlled to be opened, the domestic sewage of the ecological tank 4 is discharged, and accordingly, according to different sewage treatment stages of a domestic sewage treatment system, the corresponding neural network model is called to evaluate the domestic sewage of different stages, so that refined evaluation is realized, the domestic sewage of the previous stage is ensured to enter the next stage after meeting the requirement, effective monitoring and control of each stage of the domestic sewage treatment process are realized, and the control accuracy of the domestic sewage treatment process is improved.

In one embodiment, after the step of inputting the organic matter parameter into a pre-constructed cyclic neural network model to obtain the first sewage evaluation result corresponding to the first sewage information, the method further includes:

In the present embodiment, the control apparatus 1 may perform feature extraction based on the first sanitary sewage evaluation result, extract useful features, and then select an appropriate machine learning or optimization algorithm to build a model to generate a treatment plan based on the first sanitary sewage evaluation result. The model includes decision trees, random forests, neural networks, genetic algorithms, and the like.

And finally, training the model by using the evaluation data set, and carrying out parameter adjustment and optimization to ensure the accuracy and generalization capability of the model, and automatically generating a corresponding first treatment scheme by taking a first living sewage evaluation result as input according to the trained model. The first treatment scheme includes treatment techniques, process flows, equipment requirements, and the like.

And constructing a treatment scheme evaluation model which is a neural network model and is used for evaluating the treatment scheme and generating a grading value. According to the embodiment, the multiple first treatment schemes are input into the treatment scheme evaluation model to obtain the grading value of each first treatment scheme, the multiple first treatment schemes are ordered according to the order from big to small of the grading values to obtain the ordering result, the corresponding first treatment schemes are sequentially selected according to the ordering result to treat the domestic sewage until the first domestic sewage evaluation result meets the requirements, if the first treatment scheme with the highest grading value is selected to treat the domestic sewage, the treated domestic sewage is reevaluated, whether the evaluation result meets the requirements is judged, if the evaluation result does not meet the requirements, the first treatment scheme with the grading value arranged at the second position is selected to treat the domestic sewage again, the treated domestic sewage is reevaluated, and so on until the first domestic sewage evaluation result meets the requirements, the domestic sewage in the previous stage is ensured to enter the next stage after meeting the requirements, thereby realizing effective monitoring and control on each stage of the domestic sewage treatment process, and further improving the control precision of the domestic sewage treatment process.

In one embodiment, before the step of inputting the principal component characteristic information into a pre-constructed principal component analysis model to obtain the second domestic sewage evaluation result corresponding to the second domestic sewage information, the method further includes:

The embodiment obtains a data set, wherein the data set comprises a plurality of groups of principal component characteristic information and reference evaluation results corresponding to each group of principal component characteristic information, and prepares data for model training. And then dividing the data set into a test set and a verification set according to a preset proportion, and inputting the test set into a convolutional neural network model constructed in advance to perform convolutional operation to obtain convolutional features.

The convolutional neural network model (ConvolutionalNeuralNetwork, CNN) is a deep learning model and is mainly used for processing tasks with grid structure data. CNNs automatically learn and extract features in the data through components such as convolutional, pooling, and fully-connected layers. The main characteristics of the convolutional neural network include:

convolution layer: the convolutional layer is the core component of the CNN, and extracts features on the input data through a convolutional operation. The convolution operation uses a set of learnable filters (or convolution kernels) to perform a convolution operation on the input data by means of a sliding window, thereby obtaining an output signature. Each filter may detect some local feature of the input data.

Pooling layer: the pooling layer is used to reduce the size of the feature map and extract the main features. The pooling operation includes maximum pooling (selecting the maximum value within the window) and average pooling (calculating the average value within the window). The pooling operation can reduce the spatial dimension of the data, reduce the number of parameters, and retain key information.

Activation function: in convolutional neural networks, a nonlinear activation function, such as ReLU (RectifiedLinearUnit) function, is typically added after the convolutional layer. The activation function introduces nonlinearities so that the network can learn more complex features and patterns.

Full tie layer: after the convolution and pooling layers, a fully connected layer is typically used to perform the final classification or regression task. The fully connected layer flattens the features of the front layer into a one-dimensional vector, and predicts and outputs through fully connected neurons.

Weight sharing: convolutional neural networks reduce the number of parameters and the amount of computation by weight sharing. Each filter shares the same weight across the entire input data, allowing the network to learn local features efficiently and with translational invariance.

In the embodiment, the cross entropy loss function is utilized to perform back propagation training on the convolution characteristics until a first loss value of the convolution neural network model is lower than a preset first loss value, so as to obtain an initial principal component analysis model. The cross entropy loss function is a loss function that measures the difference between the predicted output and the actual label.

Back propagation training is a method for training a neural network with the aim of minimizing the error between the predicted output and the actual output by adjusting the weights and bias in the network. It gradually optimizes the network model by updating parameters along the negative gradient direction of the loss function based on a gradient descent algorithm. The idea of back propagation training is to calculate the partial derivatives of the weights and deviations of each neuron against the loss function using the chain rule (ChainRule). The method comprises the following specific steps:

Forward propagation: and (3) carrying out forward propagation on the input sample through a neural network to calculate the predicted output of the network.

Calculating loss: and comparing the predicted output of the network with the actual output, calculating the value of the loss function, and measuring the difference between the predicted output and the actual output.

Back propagation: starting from the output layer, the partial derivatives of the weights and deviations of each neuron against the loss function are calculated using the chain law. Gradient information about each parameter can thus be obtained.

Parameter updating: and updating the value of each parameter by using a gradient descent algorithm according to the gradient information, so that the loss function is gradually reduced. The learning rate is typically used to control the step size of each update.

Repeating the iteration: the process of forward propagation, loss calculation, backward propagation, and parameter updating is repeatedly performed until a predetermined number of training rounds or convergence conditions are reached.

Through back propagation training, the neural network can gradually adjust weights and deviations according to input samples, so that the model can better fit training data and has better generalization capability.

Finally, the verification set is input into the initial principal component analysis model for verification, when the verification result meets the preset requirement, parameters of the initial principal component analysis model are saved, and the initial principal component analysis model with the verification result meeting the preset requirement is used as a principal component analysis model after training is completed.

In one embodiment, before the step of inputting the water quality parameter into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further includes:

and combining the target classification models to obtain a random forest model.

In this embodiment, the training sample data set includes 2N training samples, each training sample includes a set of standard water quality parameters and a corresponding standard domestic sewage evaluation result, and the number of training samples is greater than a preset threshold.

The training sample data set is divided into a plurality of sub-data sets in average, each sub-data set comprises two training samples to obtain N sub-data sets, one training sample is randomly extracted from each sub-data set to serve as a target training sample to obtain N target training samples, then the N target training samples are randomly selected to obtain K groups of training sets, but each group of training sets needs to comprise a plurality of target training samples, and the number of the target training samples of each group of training sets is the same but not repeated.

In the embodiment, a decision tree algorithm is utilized to train K groups of training sets to obtain K trained classification models, a cross entropy loss function is utilized to calculate second loss values of each trained classification model respectively, classification models with the second loss values lower than a preset second loss value are screened out to obtain a plurality of target classification models, and the plurality of target classification models are combined to obtain a random forest model. The preset second loss value may be set to be custom, for example, set to 0.3.

The decision tree algorithm is a machine learning algorithm based on a tree structure and is used for solving the problems of classification and regression. The method constructs a tree-structured model by carrying out a series of judgment and splitting on input data so as to carry out prediction or decision. The idea of the decision tree algorithm is to classify or regress through a series of judgment conditions according to the characteristics and labels of the data. The algorithm divides the data set into different subsets by selecting the best features and cut points so that the data within each subset has a higher purity (classification problem) or a smaller variance (regression problem). The decision tree algorithm may include the steps of:

feature selection: according to a certain index (such as information gain, a coefficient of kunning, etc.), the optimal characteristic is selected as the judging condition of the current node. The selected features should be able to best distinguish between different categories or reduce variance.

Segmenting the dataset: the data set is divided into different subsets according to the selected features and judgment conditions. Each subset corresponds to a branch or child node.

And (3) recursion construction: the above steps are repeated for each subset, recursively constructing child nodes until a termination condition is met. The termination condition may be reaching a predetermined tree depth, reaching a minimum number of samples or data in a subset belonging to the same category, etc.

Pruning the tree: to avoid overfitting, a tree pruning operation may be performed. Tree pruning reduces model complexity and improves generalization capability by merging adjacent leaf nodes or removing certain branches.

Prediction and decision: and using the constructed decision tree model to conduct prediction or decision. For classification problems, the tree is traversed step by step down from the root node according to the feature judgment conditions until the leaf node is reached and the predicted class is returned. For the regression problem, the leaf node stores a numerical value as the output of the prediction.

When a plurality of target classification models are combined to obtain a random forest model, each model carries out classification prediction on a sample for a plurality of independent classification models, and then a final classification result is determined in a voting mode. The votes may be simple majority votes or weighted votes, wherein the weight of each model may be determined based on its performance or confidence; the final classification result may also be determined by averaging. The average may be a simple arithmetic average or a weighted average.

In one embodiment, the intelligent control method of the domestic sewage treatment system further comprises:

In this embodiment, the control device 1 obtains the remaining power of the energy storage battery in the solar power supply device 5, calculates the average power consumption according to the historical power consumption condition, calculates the power consumption required by the power consumption of the electric equipment of the domestic sewage treatment system in the future preset time period based on the average power consumption, and obtains weather forecast information in the preset time period from the weather bureau website, where the weather forecast information includes weather conditions and weather data such as illumination time, humidity, air pressure, wind speed, rainfall probability and the like in each time period, and estimates the illumination time in the preset time period according to the weather forecast information, such as estimating the illumination time in the ten days in the future.

According to the embodiment, the conversion rate of the solar power supply device 5 under different illumination intensities is obtained, then the power supply quantity of the solar power supply device 5 in a preset time period is calculated according to the illumination duration, the average illumination intensity and the conversion rate, and the sum of the residual power and the power supply quantity is calculated to obtain the total power supply quantity, namely the power required in the future preset time period. The control device 1 judges whether the power consumption is larger than the total power supply amount, when the power consumption is judged to be larger than the total power supply amount, the trough time period of the commercial power in the current area is firstly determined, the electricity price of the trough time period is lower, and the energy storage battery is charged in the trough time period in the preset time period, so that the efficient and stable operation of the domestic sewage treatment system is ensured, and meanwhile, the cost is saved.

In one embodiment, the step of extracting the principal component characteristic information of the second domestic sewage information includes:

In the present embodiment, the method of converting the second domestic sewage information into the matrix depends on the data type and structure of the second domestic sewage information. As for numeric data, the matrix can be constructed directly using the raw data. Each sample may be represented as a row in a matrix and each feature may be represented as a column in the matrix. For example, if the second domestic sewage information has m samples and n features, a matrix of size m×n can be constructed. For text data, feature extraction or vectorization is typically required and then converted to a matrix representation. Text vectorization methods include bag of words model, TF-IDF vectorization, word embedding, etc. These methods convert text data into sparse or dense matrix representations. For image data, the numerical value of each pixel may be taken as an element in a matrix, thereby representing the image as a matrix. The gray-scale image may be represented as a two-dimensional matrix and the color image may be represented as a three-dimensional matrix (height×width×number of channels). For category type data, one-hot encoding (One-HotEncoding) may be used to convert it into a binary matrix form. Each class may be represented as a column in the matrix, with the corresponding sample having a value of 1 on that column and 0 on the other columns. For time series data, the observed value at each time point can be taken as an element in a matrix, thereby obtaining a matrix of time x features.

Given a standard matrix V, our goal is to find two non-negative matrices W and H such that v≡wh. Specifically, two matrices may be randomly initialized using a uniform distribution function or a gaussian distribution function to obtain a first matrix W and a second matrix H, and the first matrix W and the second matrix H are updated by a method of minimizing a reconstruction error. The method for minimizing the reconstruction error comprises gradient descent, multiplication updating rule and the like until the product of the first matrix and the second matrix is equal to the standard matrix, so that a first target matrix and a second target matrix are obtained, and feature extraction is respectively carried out on the first target matrix and the second target matrix through a principal component analysis method, so that more useful information can be extracted from the first target matrix and the second target matrix. The principal component analysis method can convert the high-dimensional matrix into the low-dimensional characteristic representation, thereby obtaining principal component characteristic information of the second domestic sewage information and reducing redundant information and noise.

Wherein a uniform distribution is a continuous probability distribution in which each data point has an equal probability density within a given interval. In a uniform distribution defined over the intervals a, b, the probability density of any one subinterval is equal. A gaussian distribution is also a continuous probability distribution, also known as a normal distribution. It is presented in the form of a bell curve with one peak and two symmetrical tails.

Minimizing reconstruction errors is an unsupervised learning method for dimension reduction or feature extraction of data. Its goal is to reconstruct the original data into a low-dimensional representation such that the result of the reconstruction is as close as possible to the original data.

In one embodiment, after the step of inputting the water quality parameter into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further includes:

comparing the target hash value with the reference hash value;

In this embodiment, the asymmetric encryption algorithm is an encryption method, using two different but related keys: public and private keys. The public key is used to encrypt data and the private key is used to decrypt data. This encryption method is also called public key encryption algorithm. According to the embodiment, the first domestic sewage evaluation result, the second domestic sewage evaluation result and the second domestic sewage evaluation result are encrypted by utilizing an asymmetric encryption algorithm to obtain encrypted data, then the encrypted data is subjected to hash processing according to an MD5 algorithm to obtain a reference hash value, the reference hash value and the encrypted data are compressed and packaged to obtain ciphertext data, and the ciphertext data are stored in a cloud. The MD5 algorithm is a hash function algorithm, which is used to convert data with any length into a hash value with a fixed length.

When a user needs to acquire data, acquiring ciphertext data from a cloud according to a data query request, decompressing the ciphertext data to obtain decompressed data, calculating a hash value of the decompressed data to obtain a target hash value, comparing the target hash value with a reference hash value, decrypting the decompressed data by using an asymmetric encryption algorithm when the target hash value is identical to the reference hash value to obtain plaintext data, and returning the plaintext data to the user, so that the integrity and the authenticity of the data can be ensured by combining the method using the asymmetric encryption algorithm and the MD5 hash algorithm. The asymmetric encryption algorithm provides a mechanism for digital signatures to verify the origin and integrity of the data, while the MD5 hash algorithm is used to check if the original data has been tampered with.

In one embodiment, the step of encrypting the first domestic sewage evaluation result, the second domestic sewage evaluation result, and the second domestic sewage evaluation result by using an asymmetric encryption algorithm to obtain encrypted data includes:

and encrypting the data to be encrypted to obtain encrypted data.

In this embodiment, the normalization process maps the data of different ranges into a unified standard range. It may allow for comparability between different features and help to improve the performance of the model. The normalization process is to convert the data into a standard normal distribution (also referred to as Z-score or standard distribution) with a mean of 0 and a standard deviation of 1. It may enable data to have zero mean and unit variance, helping to eliminate dimensional differences between different features and helping to improve the performance of the model.

When filling in missing data using Lagrangian interpolation, the target value of the missing data point can be estimated from the characteristic value and the target value of the known data point. The following is a step of filling in missing data by using Lagrange interpolation:

determining known data points: first, known data points present in the raw data, i.e. data points having complete eigenvalues and target values, are determined.

Selecting the order of the interpolation polynomial: the order of the appropriate interpolation polynomial is selected based on the number and distribution of known data points. Typically, the order of the interpolation polynomial should be equal to or less than the number of known data points.

Constructing a Lagrange interpolation polynomial: a lagrangian interpolation polynomial is constructed using known data points. For each missing data point, an interpolation polynomial is constructed and interpolation calculations are performed using the eigenvalues and target values of the known data points.

Calculating a target value for the missing data point: substituting the characteristic value of the missing data point into the interpolation polynomial according to the constructed interpolation polynomial, and calculating to obtain the target value of the missing data point.

Referring to fig. 3, an embodiment of the present invention further provides an intelligent control device of a domestic sewage treatment system, including:

The first monitoring module 11 is configured to monitor, in real time, a water level of domestic sewage in the septic tank 2 when the domestic sewage treatment system is in a working state, and receive first domestic sewage information acquired by a first data acquisition device located at a water outlet of the septic tank 2 when the first water level of the septic tank 2 is monitored to be greater than a preset first water level, and extract an organic matter parameter of the first domestic sewage information; the first data acquisition device comprises a chemical oxygen demand sensor, a biochemical oxygen demand sensor and a suspended matter sensor;

the first input module 12 is configured to input the organic matter parameter into a pre-constructed cyclic neural network model, obtain a first sewage evaluation result corresponding to the first sewage information, and when determining that the first sewage evaluation result meets a requirement, control an electromagnetic valve arranged at a water outlet of the septic tank 2 to open, so that domestic sewage of the septic tank 2 flows to the water collecting device 3; the circulating neural network model is used for analyzing and evaluating organic matter parameters in the domestic sewage;

The second monitoring module 13 is configured to monitor a water level of the domestic sewage in the water collecting device 3 in real time, and when it is monitored that the second water level of the water collecting device 3 is greater than a preset second water level, receive second domestic sewage information collected by a second data collecting device located at a water outlet of the water collecting device 3, and extract main component characteristic information of the second domestic sewage information; the main component characteristic information comprises nitrogen and phosphorus parameters and microorganism parameters of domestic sewage, and the second data acquisition device comprises a nitrogen and phosphorus sensor and a microorganism sensor;

the second input module 14 is configured to input the principal component characteristic information into a pre-constructed principal component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and when it is determined that the second domestic sewage evaluation result meets the requirement, control an electromagnetic valve disposed at a water outlet of the water collecting device 3 to open, so that domestic sewage of the water collecting device 3 flows to the ecological tank 4; the main component analysis model is used for analyzing and evaluating nitrogen and phosphorus parameters and microorganism parameters in the domestic sewage;

the third monitoring module 15 is configured to monitor the water level of the domestic sewage in the ecological tank 4 in real time, and when it is monitored that the third water level of the ecological tank 4 is greater than a preset third water level, receive third domestic sewage information collected by a third data collecting device located at a water outlet of the ecological tank 4, and extract a water quality parameter of the first domestic sewage information; wherein, the quality of water parameter includes pH valve, dissolved oxygen and the conductivity of domestic sewage, third data acquisition device includes: a pH value sensor, a dissolved oxygen sensor and a conductivity sensor;

The third input module 16 is configured to input the water quality parameter into a pre-constructed random forest model, obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, and when determining that the third domestic sewage evaluation result meets a requirement, control an electromagnetic valve disposed at a water outlet of the ecological tank 4 to be opened, so as to drain domestic sewage of the ecological tank 4; the random forest model is used for analyzing and evaluating water quality parameters in domestic sewage.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

The terminal provided by the invention comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, enable the processor to execute the steps of the intelligent control method of the domestic sewage treatment system.

The invention provides a domestic sewage treatment system, which comprises a control device 1, a plurality of data acquisition devices, a water collection device 3, a solar power supply device 5, a septic tank 2 and an ecological tank 4, wherein each data acquisition device is respectively arranged on the water collection device 3, the solar power supply device 5, the septic tank 2 and the ecological tank 4, the water inlets or water outlets of the water collection device 3, the septic tank 2 and the ecological tank 4 are provided with electromagnetic valves for controlling the inlet and the outlet of domestic sewage, the control device 1 is respectively electrically connected with the electromagnetic valves, the solar power supply device 5 and each data acquisition device, the water inlets of the septic tank 2 are connected with the sewage drain of a toilet through pipelines, the water outlets of the septic tank 2 are connected with the water inlets of the water collection device 3 through pipelines, the water inlets of the water collection device 3 are also connected with the sewage drain of a kitchen and a bathroom through pipelines, the data acquisition device is used for acquiring domestic sewage information or equipment information, the septic tank 2 and the water collection device 3 are buried in the underground sewage, the sewage is subjected to the degradation of a sewage supply system of a sewage and the sewage in the sewage and the ecological sewage treatment system of a plant, and the sewage is subjected to the degradation of the sewage treatment system of the sewage and the sewage is subjected to the primary treatment by the sewage treatment system of the sewage and the sewage treatment device 5; wherein the control device 1 comprises a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the intelligent control method of the domestic sewage treatment system according to any one of the above.

In an embodiment, referring to fig. 4, the terminal provided in an embodiment of the present application may be a computer device, and the internal structure of the terminal may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing relevant data of the intelligent control method of the domestic sewage treatment system. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements the intelligent control method of the domestic sewage treatment system described in the above embodiments.

In one embodiment, the present application also provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the intelligent control method of the domestic sewage treatment system. Wherein the storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program stored in a storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-only memory (ROM), or a random access memory (RandomAccessMemory, RAM).

As can be seen from the above embodiments, the present invention has the following advantages:

according to the intelligent control method, terminal and system of the domestic sewage treatment system, when the domestic sewage treatment system enters a working state, the water level of domestic sewage in the septic tank 2 is monitored in real time, when the monitored first water level of the septic tank 2 is larger than the preset first water level, first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank 2 is received, organic matter parameters of the first domestic sewage information are extracted, the organic matter parameters are input into a pre-built circulating neural network model, a first domestic sewage evaluation result corresponding to the first domestic sewage information is obtained, and when the first domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the septic tank 2 is controlled to be opened, so that the domestic sewage of the septic tank 2 flows to the water collecting device 3; when the second water level of the water collecting device 3 is monitored to be larger than a preset second water level, receiving second domestic sewage information acquired by a second data acquisition device positioned at a water outlet of the water collecting device 3, extracting main component characteristic information of the second domestic sewage information, inputting the main component characteristic information into a pre-constructed main component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and when the second domestic sewage evaluation result is determined to meet the requirement, controlling an electromagnetic valve arranged at the water outlet of the water collecting device 3 to be opened to enable the domestic sewage of the water collecting device 3 to flow to the ecological tank 4; when the water level of the domestic sewage in the ecological tank 4 is monitored in real time, when the third water level of the ecological tank 4 is monitored to be larger than a preset third water level, third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank 4 is received, water quality parameters of the first domestic sewage information are extracted, the water quality parameters are input into a pre-built random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, when the third domestic sewage evaluation result is determined to meet the requirement, an electromagnetic valve arranged at the water outlet of the ecological tank 4 is controlled to be opened, the domestic sewage of the ecological tank 4 is discharged, and accordingly, according to different sewage treatment stages of a domestic sewage treatment system, the corresponding neural network model is called to evaluate the domestic sewage of different stages, so that refined evaluation is realized, the domestic sewage of the previous stage is ensured to enter the next stage after meeting the requirement, effective monitoring and control of each stage of the domestic sewage treatment process are realized, and the control accuracy of the domestic sewage treatment process is improved.

The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.

Claims

1. An intelligent control method of a domestic sewage treatment system is characterized in that the intelligent control method is applied to control equipment (1) of the domestic sewage treatment system, the domestic sewage treatment system further comprises a plurality of data acquisition devices, a water collection device (3), a solar power supply device (5), a septic tank and an ecological tank (4), wherein the data acquisition devices are respectively arranged on the water collection device (3), the solar power supply device (5), the septic tank and the ecological tank (4), the electromagnetic valves for controlling the inlet and the outlet of the domestic sewage are arranged on the water collection device (3), the water inlets or the water outlets of the septic tank (2) and the ecological tank (4), the control equipment (1) is respectively electrically connected with the electromagnetic valves, the solar power supply device (5) and the data acquisition devices, the water inlets of the septic tank (2) are connected with sewage discharge outlets of a toilet through pipelines, the water inlets of the septic tank (2) are also connected with sewage discharge outlets of a kitchen and a bathroom through pipelines, the water outlets of the septic tank (3) are connected with the sewage collection device (3) through pipelines, the sewage is used for collecting sewage in the sewage treatment system and the sewage treatment system, the sewage treatment system is decomposed by the sewage treatment system is stored in the sewage treatment system (2) or the sewage treatment system, and the sewage treatment system is decomposed by the sewage treatment system, the water collecting device (3) is used for collecting domestic sewage with pollution degree lower than preset degree or after preliminary purification treatment, the solar power supply device (5) is used for supplying power to electric equipment of the domestic sewage treatment system, the ecological tank (4) is used for degrading and converting organic substances and pollutants in the domestic sewage into harmless substances by means of interaction of microorganisms and plants, and the intelligent control method of the domestic sewage treatment system comprises the following steps:

When the domestic sewage treatment system enters a working state, monitoring the water level of domestic sewage in the septic tank (2) in real time, and when the first water level of the septic tank (2) is monitored to be larger than a preset first water level, receiving first domestic sewage information acquired by a first data acquisition device positioned at a water outlet of the septic tank (2), and extracting organic matter parameters of the first domestic sewage information; the first data acquisition device comprises a chemical oxygen demand sensor, a biochemical oxygen demand sensor and a suspended matter sensor;

inputting the organic matter parameters into a pre-constructed circulating neural network model to obtain a first living sewage evaluation result corresponding to the first living sewage information, and controlling an electromagnetic valve arranged at a water outlet of the septic tank (2) to be opened when the first living sewage evaluation result is determined to meet the requirements so that the living sewage of the septic tank (2) flows to a water collecting device (3); the circulating neural network model is used for analyzing and evaluating organic matter parameters in the domestic sewage;

the method comprises the steps of monitoring the water level of domestic sewage in a water collecting device (3) in real time, when the second water level of the water collecting device (3) is monitored to be larger than a preset second water level, receiving second domestic sewage information collected by a second data collecting device positioned at a water outlet of the water collecting device (3), and extracting main component characteristic information of the second domestic sewage information; the main component characteristic information comprises nitrogen and phosphorus parameters and microorganism parameters of domestic sewage, and the second data acquisition device comprises a nitrogen and phosphorus sensor and a microorganism sensor;

Inputting the principal component characteristic information into a pre-constructed principal component analysis model to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the water collecting device (3) to be opened when the second domestic sewage evaluation result is determined to meet the requirement so that the domestic sewage of the water collecting device (3) flows to the ecological groove (4); the main component analysis model is used for analyzing and evaluating nitrogen and phosphorus parameters and microorganism parameters in the domestic sewage;

the method comprises the steps of monitoring the water level of domestic sewage in an ecological tank (4) in real time, when the third water level of the ecological tank (4) is monitored to be larger than a preset third water level, receiving third domestic sewage information acquired by a third data acquisition device positioned at a water outlet of the ecological tank (4), and extracting water quality parameters of the first domestic sewage information; wherein, the quality of water parameter includes pH valve, dissolved oxygen and the conductivity of domestic sewage, third data acquisition device includes: a pH value sensor, a dissolved oxygen sensor and a conductivity sensor;

inputting the water quality parameters into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, and controlling an electromagnetic valve arranged at a water outlet of the ecological tank (4) to be opened when the third domestic sewage evaluation result is determined to meet the requirements so as to discharge the domestic sewage of the ecological tank (4); the random forest model is used for analyzing and evaluating water quality parameters in domestic sewage.

2. The intelligent control method of a domestic sewage treatment system according to claim 1, wherein after the step of inputting the organic matter parameter into a pre-constructed cyclic neural network model to obtain the first domestic sewage evaluation result corresponding to the first domestic sewage information, the method further comprises:

3. The intelligent control method of a domestic sewage treatment system according to claim 1, wherein before the step of inputting the principal component characteristic information into a principal component analysis model constructed in advance to obtain a second domestic sewage evaluation result corresponding to the second domestic sewage information, further comprises:

4. The intelligent control method of a domestic sewage treatment system according to claim 1, wherein before the step of inputting the water quality parameter into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further comprises:

and combining the target classification models to obtain a random forest model.

5. The intelligent control method of a domestic sewage treatment system according to claim 1, further comprising:

acquiring the residual electric quantity of an energy storage battery in the solar power supply device (5), and calculating the power consumption required by electric equipment of the domestic sewage treatment system in a future preset time period;

obtaining the conversion rate of the solar power supply device (5), and calculating the power supply quantity of the solar power supply device (5) in the preset time period according to the illumination time length, the average illumination intensity and the conversion rate;

6. The intelligent control method of a domestic sewage treatment system according to claim 1, wherein the step of extracting the main component characteristic information of the second domestic sewage information comprises:

7. The intelligent control method of a domestic sewage treatment system according to claim 1, wherein after the step of inputting the water quality parameter into a pre-constructed random forest model to obtain a third domestic sewage evaluation result corresponding to the third domestic sewage information, the method further comprises:

comparing the target hash value with the reference hash value;

8. The intelligent control method of a domestic sewage treatment system according to claim 7, wherein the step of encrypting the first domestic sewage evaluation result, the second domestic sewage evaluation result, and the second domestic sewage evaluation result by using an asymmetric encryption algorithm to obtain encrypted data comprises:

And encrypting the data to be encrypted to obtain encrypted data.

9. A terminal comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the intelligent control method of a domestic sewage treatment system according to any one of claims 1 to 8.

10. The domestic sewage treatment system is characterized by comprising control equipment (1), a plurality of data acquisition devices, a water collection device (3), solar power supply devices (5), a septic tank (2) and an ecological tank (4), wherein the data acquisition devices are respectively arranged on the water collection device (3), the solar power supply devices (5), the septic tank (2) and the ecological tank (4), an electromagnetic valve for controlling domestic sewage to enter and exit is arranged at the water inlets or the water outlets of the water collection device (3), the septic tank (2) and the ecological tank (4), the control equipment (1) is respectively connected with the electromagnetic valve, the solar power supply devices (5) and the data acquisition devices electrically, the water inlets of the septic tank (2) are connected with the sewage draining outlet of a toilet through pipelines, the water inlets of the septic tank (2) are also connected with the sewage draining outlet of a collecting tank and a bathroom through pipelines, the water outlets of the water collection device (3) are connected with the ecological tank (4) through pipelines, the sewage outlet of the septic tank is used for collecting sewage in a kitchen or the sewage in the septic tank (2) and is used for decomposing the sewage in the sewage treatment system and the sewage treatment system, the sewage treatment device is used for storing the sewage in the sewage treatment system, the water collecting device (3) is used for collecting domestic sewage with pollution degree lower than preset degree or after preliminary purification treatment, the solar power supply device (5) is used for supplying power to electric equipment of the domestic sewage treatment system, and the ecological tank (4) is used for degrading organic substances and pollutants in the domestic sewage into harmless substances by means of interaction of microorganisms and plants; wherein the control device (1) comprises a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the intelligent control method of a domestic sewage treatment system according to any one of claims 1 to 8.