CN118128737A - Intelligent exhaust pressure control method and device for protecting unit - Google Patents
Intelligent exhaust pressure control method and device for protecting unit Download PDFInfo
- Publication number
- CN118128737A CN118128737A CN202410556067.7A CN202410556067A CN118128737A CN 118128737 A CN118128737 A CN 118128737A CN 202410556067 A CN202410556067 A CN 202410556067A CN 118128737 A CN118128737 A CN 118128737A
- Authority
- CN
- China
- Prior art keywords
- exhaust
- scheme
- information
- gas consumption
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 238000005457 optimization Methods 0.000 claims description 40
- 238000012360 testing method Methods 0.000 claims description 18
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013022 venting Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 230000008859 change Effects 0.000 description 9
- 230000001105 regulatory effect Effects 0.000 description 8
- 230000001276 controlling effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The application discloses an intelligent control method and device for exhaust pressure of a protection unit, belonging to the field of intelligent control, wherein the method comprises the following steps: collecting pipeline pressure information and engine operation information in an air compressor unit, and collecting a gas consumption information sequence and gas consumption characteristic information; obtaining predicted gas consumption; obtaining predicted pipeline pressure information, and obtaining an optimized exhaust scheme library according to the predicted pipeline pressure information; and performing error compensation analysis according to the optimal exhaust scheme and the plurality of suboptimal exhaust schemes to obtain a compensated optimal exhaust scheme, and performing exhaust control. The application solves the technical problems of low working efficiency and quality of the unit caused by repeated start and stop of the unit due to the fact that the oil-free mobile air compressor in the prior art cannot realize flexible pressure adjustment, and achieves the technical effects of performing pressure adjustment according to actual air pressure, preventing the pressure from being high, avoiding repeated start and stop of the unit and improving the working efficiency and the working quality of the unit.
Description
Technical Field
The invention relates to the field of intelligent control, in particular to an intelligent control method and device for exhaust pressure of a protection unit.
Background
With the rapid development of industrial production, the air compressor is increasingly widely applied, the pressure in a pipeline of the air compressor is changed when the air compressor provides compressed air for users, the pressure in the pipeline is continuously increased due to the accumulation of the compressed air in the loading operation process of the existing compressor, and when the pressure is increased to the highest pressure allowed by the compressor, the compressor is automatically stopped and the pressure is released; the change of the air consumption of the user can cause larger fluctuation of the pipeline pressure, the pressure fluctuation can trigger the start and stop of the compressor when exceeding the set pressure range of the compressor, if the air consumption of the user is smaller, the pressure can be rapidly increased, and the pressure can directly exceed the safety pressure range when serious, so that the compressor is abnormally stopped. The particularity of the oil-free mobile air compressor can not realize the real-time regulation of air pressure by using the air inlet capacity regulating function.
Disclosure of Invention
The application provides an intelligent control method and device for protecting exhaust pressure of a unit, and aims to solve the technical problems that in the prior art, the oil-free mobile air compressor cannot realize flexible pressure adjustment, and the unit is repeatedly started and stopped, so that the working efficiency and quality of the unit are low.
In view of the above problems, the application provides an intelligent exhaust pressure control method and device for a protection unit.
In a first aspect of the disclosure, an intelligent exhaust pressure control method for a protection unit is provided, the method comprising: collecting pipeline pressure information and engine operation information in a current air compressor unit, and collecting a gas consumption information sequence and gas consumption characteristic information in a preset historical time window; according to the gas consumption information sequence, performing experience prediction of gas consumption to obtain first predicted gas consumption, and according to the gas consumption characteristic information, performing prediction of gas consumption to obtain second predicted gas consumption; combining the first predicted gas consumption and the second predicted gas consumption, and calculating to obtain the predicted gas consumption; according to the pipeline pressure information and the engine operation information, the prediction processing obtains predicted pipeline pressure information at the next preset moment; according to the predicted pipeline pressure information, carrying out optimization processing on an exhaust scheme through an exhaust protection analysis unit to obtain an optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes; and according to the optimal exhaust scheme and the plurality of suboptimal exhaust schemes, performing exhaust control error compensation analysis through an exhaust control unit to obtain a compensated optimal exhaust scheme, and performing exhaust control through the exhaust control unit.
In another aspect of the disclosure, an intelligent exhaust pressure control device for a protection unit is provided, the device comprising: the air consumption information acquisition module is used for acquiring pipeline pressure information and engine operation information in the current air compressor unit, and acquiring an air consumption information sequence and air consumption characteristic information in a preset historical time window; the air consumption prediction module is used for performing experience prediction of air consumption according to the air consumption information sequence to obtain first predicted air consumption, and performing prediction of air consumption according to the air consumption characteristic information to obtain second predicted air consumption; the prediction gas consumption acquisition module is used for acquiring the prediction gas consumption by combining the first prediction gas consumption and the second prediction gas consumption and calculating; the pipeline pressure prediction module is used for obtaining predicted pipeline pressure information at the next preset moment through prediction processing according to the pipeline pressure information and the engine operation information; the exhaust scheme optimizing module is used for optimizing the exhaust scheme through the exhaust protection analyzing unit according to the predicted pipeline pressure information to obtain an optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes; and the exhaust scheme compensation module is used for carrying out exhaust control error compensation analysis through the exhaust control unit according to the optimal exhaust scheme and a plurality of suboptimal exhaust schemes to obtain a compensated optimal exhaust scheme, and carrying out exhaust control through the exhaust control unit.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Because the pipeline pressure information and the engine operation information in the current air compressor unit are collected, and the air consumption information sequence and the air consumption characteristic information in the preset historical time window are collected, basic data are provided for a follow-up air consumption prediction model and optimization control; according to the gas consumption information sequence, analyzing historical data by adopting an empirical prediction method to obtain first predicted gas consumption; predicting the gas consumption by adopting characteristic prediction to obtain a second predicted gas consumption; combining the first predicted gas consumption and the second predicted gas consumption, calculating to obtain predicted gas consumption, and obtaining comprehensively optimized terminal gas consumption prediction; according to the pipeline pressure information and the engine operation information, the prediction processing obtains predicted pipeline pressure information at the next preset moment; according to the predicted pipeline pressure information, the exhaust scheme is optimized through an exhaust protection analysis unit, an optimized exhaust scheme library is obtained, and screening and optimization of a plurality of optional exhaust control schemes are realized; according to the optimal exhaust scheme and a plurality of suboptimal exhaust schemes, performing exhaust control error compensation analysis through an exhaust control unit to obtain a compensated optimal exhaust scheme, and further obtaining a compensated final optimal exhaust scheme through the compensation analysis; according to the optimal exhaust scheme after compensation optimization, the technical scheme of carrying out exhaust control on the compressor unit solves the technical problems that in the prior art, the oil-free mobile air compressor cannot realize flexible pressure adjustment, so that the unit is repeatedly started and stopped, and the working efficiency and quality of the unit are low, and achieves the technical effects of carrying out pressure adjustment according to actual air pressure, preventing the pressure from being high, avoiding the repeated starting and stopping of the unit, and improving the working efficiency and the working quality of the unit.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of an intelligent control method for exhaust pressure of a protection unit according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of obtaining predicted pipeline pressure information in an intelligent control method for exhaust pressure of a protection unit according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an intelligent exhaust pressure control device for a protection unit according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a gas consumption information acquisition module 11, a gas consumption prediction module 12, a predicted gas consumption acquisition module 13, a pipeline pressure prediction module 14, an exhaust scheme optimization module 15 and an exhaust scheme compensation module 16.
Detailed Description
The technical scheme provided by the application has the following overall thought:
The embodiment of the application provides an intelligent exhaust pressure control method and device for a protection unit. Firstly, air consumption prediction and pressure prediction are carried out by acquiring pipeline pressure information and engine operation information in a current air compressor unit and acquiring an air consumption information sequence and air consumption characteristic information in a preset historical time window, so as to obtain predicted air consumption and predicted pipeline pressure information. And then screening a plurality of optional exhaust schemes according to the predicted pipeline pressure information, and obtaining an optimized scheme library through optimization processing. And then, compensating and adjusting the optimal exhaust scheme in the optimal scheme library, and further improving the control precision of the optimal exhaust scheme. And finally, controlling the exhaust of the compressor unit in real time according to the compensated and adjusted optimal exhaust scheme. In the whole control cycle, prediction, optimization and compensation are combined, so that intelligent closed-loop control of exhaust pressure is realized, pressure abnormality is effectively prevented, and safe and reliable operation of the unit is protected.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent exhaust pressure control method for a protection unit, where the method is applied to an intelligent exhaust pressure control device for a protection unit, and the device includes an exhaust control unit connected to an air compressor unit, an air pressure trend analysis unit, and an exhaust protection analysis unit.
Specifically, the embodiment of the application provides an intelligent control method for exhaust pressure of a protection unit, which can accurately predict the change trend of pipeline pressure so as to control exhaust and protect the unit. The method is applied to an intelligent exhaust pressure control device for a protection unit, and the device comprises an exhaust control unit, an air pressure trend analysis unit and an exhaust protection analysis unit, wherein the exhaust control unit is connected with an air compressor unit. The exhaust control unit is used for controlling the air compressor to exhaust, wherein the key component is a pressure regulating valve, and the flow of compressed air discharged by the air compressor is controlled by regulating the opening of the valve, so that the purpose of regulating the pressure in the pipeline is achieved; the air pressure trend analysis unit is used for analyzing and predicting the air pressure change trend in the pipeline and predicting the pipeline pressure trend in a period of time in the future according to historical data; the exhaust protection analysis unit is a unit for calculating an optimal exhaust control scheme to be adopted by the air compressor according to the predicted trend of the pipeline pressure, and determining which exhaust control scheme can provide the best air compressor protection effect in the current environment.
The exhaust pressure intelligent control method comprises the following steps:
Collecting pipeline pressure information and engine operation information in a current air compressor unit, and collecting a gas consumption information sequence and gas consumption characteristic information in a preset historical time window;
Further, the method comprises the following steps:
collecting pipeline pressure information in an air compressor unit at the current moment, and collecting rotating speed information and power information of an engine as engine operation information;
Collecting gas consumption information of a plurality of historical moments in a preset historical time window, and obtaining a gas consumption information sequence;
and acquiring production efficiency information and temperature information at the current moment to serve as the gas consumption characteristic information.
In a preferred embodiment, the pipeline pressure information refers to real-time air pressure parameters in the pipeline between the compression end and the exhaust end of the air compressor; the rotating speed information of the engine refers to the real-time rotating speed of the driving engine of the air compressor; the power information of the engine refers to real-time power output parameters of the engine. Firstly, arranging a pressure sensor in a pipeline of an air compressor unit, detecting the air pressure in the pipeline in real time, and outputting pipeline pressure information by using a standard signal; meanwhile, a rotating speed sensor and a power detection device are arranged on the engine, the rotating speed and the power parameters of the engine are monitored in real time, and the rotating speed information and the power information of the engine are obtained and are output as standard signals to be used as engine operation information.
Then, arranging a flowmeter in a pipeline of the air compressor unit, detecting air flow in the pipeline, outputting instantaneous air consumption information by using a standard signal, and storing the instantaneous air consumption information; presetting a historical time window of the air compressor according to data requirements, extracting stored air consumption information according to a time sequence according to the historical time window to form an air consumption information sequence, and taking the air consumption information sequence as air consumption time sequence data of the air compressor in the historical time window. Meanwhile, acquiring production efficiency related parameters from an industrial system, and converting the production efficiency related parameters into standardized production efficiency information; setting a temperature sensor, detecting the running environment temperature of the air compressor, and outputting temperature information; and taking the production efficiency information and the temperature information at the current moment as the gas consumption characteristic information. The production efficiency information is a parameter reflecting the production efficiency of the corresponding industrial system of the air compressor; the temperature information refers to the temperature of the running environment of the air compressor; when the production efficiency is improved, the demand for compressed air is increased, and the air consumption of the air compressor is increased; when the ambient temperature rises, the energy-saving performance of the air compressor is reduced, and the air consumption is increased.
The air pressure trend analysis unit is used for carrying out experience prediction of air consumption according to the air consumption information sequence to obtain first predicted air consumption, and carrying out prediction of air consumption according to the air consumption characteristic information to obtain second predicted air consumption;
Further, the method comprises the following steps:
based on historical operation data of the air compressor unit, extracting and obtaining a sample gas consumption information sequence set, a sample first prediction gas consumption set, a sample gas consumption characteristic information set and a sample second prediction gas consumption set;
Constructing a gas consumption prediction channel comprising a first gas consumption prediction branch and a second gas consumption prediction branch, and training and updating to a preset convergence requirement, wherein the first gas consumption prediction branch is trained and updated by adopting the sample gas consumption information sequence set and the sample first prediction gas consumption set, and the second gas consumption prediction branch is trained and updated by adopting the sample gas consumption characteristic information set and the sample second prediction gas consumption set;
And carrying out gas consumption prediction on the gas consumption information sequence and the gas consumption characteristic information based on the converged gas consumption prediction channel to obtain the first predicted gas consumption and the second predicted gas consumption.
In a preferred embodiment, the sample gas consumption information sequence set refers to a gas consumption information sample set generated by a gas consumption information sequence of the air compressor in a historical time window; the first predicted gas consumption set of the sample refers to a gas consumption information sample set after each gas consumption information sample is mapped in a gas consumption information sequence aiming at the gas consumption information sample; the sample gas consumption characteristic information set refers to a gas consumption characteristic sample extracted based on gas consumption characteristic information acquired in historical time; the second predicted gas usage set of samples refers to a predicted target gas usage set of samples generated based on the power usage feature samples.
Then, preprocessing a sample gas consumption information sequence set, including anomaly removal, smoothing, standardization and the like, to obtain normalized time sequence sample data, expanding the normalized sample sequence according to time, and converting each time sequence sample into multidimensional input features; the same pretreatment is carried out on the first prediction gas consumption set of the sample to obtain normalized prediction target output; and constructing a gas consumption time sequence prediction model based on the cyclic neural network LSTM, taking the gas consumption time sequence prediction model as a first gas consumption prediction branch, inputting the multidimensional time sequence characteristics of a sample by an input layer of the branch, and outputting a gas consumption predicted value by an output layer. Meanwhile, preprocessing a sample gas consumption characteristic information set, including outlier processing, normalization and the like, to obtain normalized characteristic sample data; the same pretreatment is carried out on the second prediction gas consumption set of the sample, so that normalized prediction target output is obtained; and constructing a gas consumption characteristic prediction model based on a multilayer feedforward neural network as a second gas consumption prediction branch, inputting a characteristic sample into an input layer of the branch, and outputting predicted gas consumption by an output layer of the branch. Training the two prediction branches respectively until convergence conditions are met, combining the first air consumption prediction branch and the second air consumption prediction branch to obtain a converged air consumption prediction channel, and embedding the air consumption prediction channel into an air pressure trend analysis unit to analyze air pressure trend of the air conditioner, so as to realize air consumption prediction analysis through a historical power consumption sequence and air consumption characteristics of a current user respectively.
Then, inputting the acquired gas consumption information sequence and gas consumption characteristic information into a gas pressure trend analysis unit, inputting the information into a gas consumption prediction channel by the gas pressure trend analysis unit, and inputting the gas consumption information sequence into a first gas consumption prediction branch by the gas consumption prediction channel to obtain first predicted gas consumption; the gas consumption prediction channel inputs the gas consumption characteristic information into a second gas consumption prediction branch to obtain second predicted gas consumption, so that prediction analysis of actual operation data is completed, gas consumption prediction output of two angles is obtained, and a foundation is laid for subsequent prediction fusion use.
Combining the first predicted gas consumption and the second predicted gas consumption, and calculating to obtain predicted gas consumption;
Further, the method comprises the following steps:
testing the first gas consumption prediction branch and the second gas consumption prediction branch to obtain a first accuracy rate and a second accuracy rate, and distributing to obtain a first weight and a second weight;
And carrying out weighted calculation on the first predicted gas consumption and the second predicted gas consumption by adopting the first weight and the second weight to obtain the predicted gas consumption.
In a preferred embodiment of the present invention,
Firstly, respectively acquiring the prediction results of a first prediction branch and a second prediction branch and corresponding actual gas consumption, taking the prediction results as test samples, calculating errors between the prediction results and the actual values of the first prediction branch, and obtaining the average prediction accuracy of the first prediction branch on the test samples according to the error results, wherein the average prediction accuracy is taken as a first accuracy; similarly, the average prediction accuracy of the second prediction branch on the test sample is calculated as the second accuracy. And then, comparing the prediction accuracy of the two branches, and distributing corresponding weights according to the ratio of the first accuracy to the second accuracy, wherein the higher the accuracy is, the larger the weight is, so as to obtain a first weight corresponding to the first accuracy and a second weight corresponding to the second accuracy.
And after the first weight and the second weight are obtained, extracting the prediction output of the two prediction branches, namely the first prediction gas consumption and the second prediction gas consumption. Multiplying the first predicted gas consumption by a corresponding first weight to obtain a weight prediction result of a first gas consumption prediction branch; multiplying the second predicted gas consumption by a corresponding second weight to obtain a weight prediction result of the second branch; and carrying out summation and fusion on the weight prediction results of the two branches to obtain final prediction gas consumption, and providing a reliable basis for subsequent pipeline pressure prediction and intelligent exhaust control.
According to the pipeline pressure information and the engine operation information, the prediction processing obtains predicted pipeline pressure information at the next preset moment;
further, as shown in fig. 2, the embodiment of the present application further includes:
acquiring a sample pipeline pressure information set, a sample engine operation information set, a sample gas consumption set and a sample prediction pipeline pressure information set based on operation history data of the air compressor unit;
Taking sample pipeline pressure information, sample engine operation information and sample gas consumption as inputs, taking sample predicted pipeline pressure information as outputs, constructing a pipeline pressure prediction channel, and training and updating;
and based on the updated pipeline pressure prediction channel, predicting the pipeline pressure information at the next preset moment to the pipeline pressure information, the engine operation information and the predicted gas consumption, so as to obtain the predicted pipeline pressure information.
In a preferred embodiment, the sample line pressure information set refers to line pressure timing samples collected during historical operation; the sample engine operation information set refers to engine operation state information corresponding to the time; the sample gas consumption set refers to a gas consumption sample during historical operation; the sample predicted line pressure information set refers to a line pressure prediction target output sample generated based on the above-described samples. And acquiring the information by inquiring the operation history data of the air compressor unit, and providing data support for the subsequent establishment of the pressure prediction channel of the vertical pipeline.
Then constructing a pipeline pressure prediction channel based on a neural network, taking sample pipeline pressure information, sample engine operation information and sample gas consumption as inputs, and taking sample prediction pipeline pressure information as output to carry out channel training; gradually optimizing channel parameters through multiple rounds of iterative training, so that a predicted result is minimized to a loss function; after training, evaluating the prediction performance of the pipeline pressure prediction channel on the verification set; if the performance reaches the standard, obtaining a pipeline pressure prediction channel; and if the predicted pipeline pressure does not reach the standard, readjusting the channel parameters for training until a pipeline pressure predicted channel with satisfactory predicted performance is obtained.
And then inputting the collected pipeline pressure information, engine operation information and the obtained predicted gas consumption into a gas pressure trend analysis unit, inputting the information into a pipeline pressure prediction channel by the gas pressure trend analysis unit, inputting the pipeline pressure prediction channel into corresponding pipeline pressure information at the next preset moment to obtain predicted pipeline pressure information, and providing support for optimizing an exhaust scheme.
According to the predicted pipeline pressure information, carrying out optimization processing on an exhaust scheme through an exhaust protection analysis unit to obtain an optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes;
Further, the method comprises the following steps:
Constructing constraint conditions of optimization treatment of an exhaust scheme, wherein the constraint conditions comprise that the pressure of a pipeline after exhaust is not more than a pipeline pressure threshold value;
An exhaust function of the exhaust scheme optimization process is constructed as follows:
；
Wherein exh is exhaust fitness, w 1 and w 2 are first weight and second weight, P b is predicted pipeline pressure information, and P a is pipeline pressure information after exhaust according to an exhaust scheme;
Acquiring an exhaust pressure adjusting range, randomly generating a plurality of first exhaust schemes according to the constraint conditions, performing exhaust simulation, and calculating to obtain a plurality of first exhaust fitness by combining the exhaust functions;
dividing a plurality of first exhaust schemes into a plurality of excellent first exhaust schemes and a plurality of inferior first exhaust schemes according to the plurality of first exhaust fitness;
According to the first exhaust fitness of the first optimal exhaust schemes, calculating and distributing to obtain a plurality of clustering numbers, and clustering the first inferior exhaust schemes to obtain a plurality of exhaust scheme clusters;
Performing iterative optimization of the exhaust scheme in the plurality of exhaust scheme clusters until the optimization convergence requirement is met, and obtaining a plurality of final exhaust scheme clusters;
And calculating the total exhaust adaptability of the plurality of final exhaust scheme clusters, and outputting the final exhaust scheme cluster with the maximum total exhaust adaptability to obtain the optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes.
Further, the method further comprises the following steps:
Taking a first optimal exhaust scheme in the plurality of exhaust scheme clusters as an optimal scheme, and optimally adjusting the plurality of inferior first exhaust schemes according to a preset step length to obtain a plurality of inferior second exhaust schemes;
Performing exhaust simulation according to a plurality of inferior second exhaust schemes, calculating to obtain a plurality of second exhaust fitness, comparing the second exhaust fitness with the first exhaust fitness of a plurality of excellent first exhaust schemes, updating and replacing the excellent exhaust schemes, and obtaining a plurality of updated exhaust scheme clusters;
and continuing to iteratively update and optimize the plurality of exhaust scheme clusters until the optimization convergence requirement is met.
In a preferred embodiment, firstly, the highest safety threshold of the pipeline pressure is determined according to the use environment and the safety requirement of the air compressor, and as the pipeline pressure threshold, the constraint condition to be met by the optimization of the exhaust scheme is set so that the pressure in the pipeline does not exceed the pipeline pressure threshold after a certain exhaust is carried out. Then, an exhaust function of the exhaust scheme optimization process is constructed as follows:
；
Wherein exh is exhaust fitness, w 1 and w 2 are first weight and second weight as objective functions for evaluating the advantages and disadvantages of an exhaust scheme, P b is predicted pipeline pressure information, and P a is pipeline pressure information after exhaust according to the exhaust scheme; indicating the degree of pressure decrease caused by the exhaust gas; /(I) Indicating the degree of stability of the pressure change; the exhaust function considers two factors of the depressurization degree and the pressure stability, and can evaluate the effect of the exhaust scheme more comprehensively, and the greater the exhaust fitness exh is, the better the exhaust scheme is.
Then, in the exhaust protection analysis unit, a current allowable exhaust pressure adjustment range is obtained according to a valve working range of a pressure adjustment valve, multiple groups of first exhaust schemes are randomly generated in the pressure adjustment range and under constraint conditions that the exhaust scheme optimization needs to meet, each generated group of first exhaust schemes is simulated, pipeline pressure information, engine operation information and the like in historical exhaust data are used as predicted pipeline pressure information P b, exhaust simulation is performed on P b to obtain pressure P a in an exhaust pipeline, the simulated pressure P a in the exhaust pipeline and the predicted pipeline pressure information P b are substituted into a constructed exhaust fitness function exh to be calculated, and exhaust fitness exh of each group of first exhaust schemes is calculated to obtain multiple first exhaust fitness.
Next, a fitness threshold value, for example, a mean value or a median value is set according to the calculated exhaust fitness of the plurality of first exhaust schemes. Determining a first exhaust scheme corresponding to the first exhaust fitness greater than or equal to a fitness threshold as a best scheme to obtain a plurality of best first exhaust schemes; and determining the corresponding first exhaust scheme with the first exhaust fitness smaller than the fitness threshold value as a bad scheme to obtain a plurality of bad first exhaust schemes. Then, calculating the ratio of the first exhaust fitness of each first optimal exhaust scheme to the sum of the first exhaust fitness of a plurality of first optimal exhaust schemes, multiplying the ratio by the number of a plurality of inferior first exhaust schemes, and rounding to obtain the clustering number; each first inferior exhaust scheme is matched into the class of the nearest first superior exhaust scheme, a plurality of first inferior first exhaust schemes are clustered, and if the adaptability ratio of one first superior exhaust scheme is larger, the first inferior first exhaust scheme matched to the first inferior first exhaust scheme is larger, and the clustering number of the first inferior first exhaust scheme is larger, so that a plurality of exhaust scheme clusters are generated. In the subsequent iterative optimization, each class aims at the first optimal exhaust scheme in the center of the class, and other inferior schemes in the class are optimized.
Then, in each exhaust scheme cluster, determining a first optimal exhaust scheme in the cluster as a current optimization target, and acquiring a plurality of first inferior exhaust schemes in the cluster; calculating the scheme difference degree between the first inferior exhaust scheme and the first optimal scheme; according to the preset step length, the first inferior scheme is adjusted according to the direction approaching to the first optimal scheme; the above operation is repeated until all the first inferior exhaustion scheme in the exhaustion scheme cluster is adjusted, so as to obtain a plurality of second inferior exhaustion schemes, and the second inferior exhaustion schemes approach the first superior exhaustion scheme on the basis of maintaining the characteristics of the first inferior scheme, so that better fitness is possible to be generated. Then, the obtained plurality of inferior second exhaust schemes are respectively subjected to exhaust simulation, the pipe pressure P a after the inferior second scheme is exhausted is predicted in the simulation, P a is substituted into an exhaust fitness function, the second fitness exh of the second inferior exhaust scheme is calculated, and the second fitness is compared with the first fitness of the first superior exhaust scheme in the same exhaust scheme cluster. If a certain second fitness is greater than the first fitness, then this second inferior venting scheme is substituted for the first superior venting scheme as the new superior scheme in the current scheme cluster. Repeating the operation until each exhaust scheme cluster completes the evaluation comparison and replacement updating of the scheme, and obtaining a plurality of exhaust scheme clusters after updating and optimization. Then, setting a convergence condition that the change amplitude of the adaptability of the schemes in the exhaust scheme cluster is smaller than a convergence threshold value set according to the control requirement; judging whether the updated and optimized exhaust scheme clusters meet preset convergence conditions, if not, carrying out new iteration optimization again on each exhaust scheme cluster, continuously adjusting the inferior scheme according to a fixed step length in a new round, simulating and calculating new fitness, comparing and replacing with the optimal scheme fitness, and repeatedly executing the iteration optimization process until the change amplitude of the fitness inside each cluster meets the convergence condition requirement, so as to obtain a plurality of final exhaust scheme clusters with optimized convergence.
Then, for a plurality of final exhaust scheme clusters with the completion of iterative optimization convergence, calculating the sum of exhaust fitness of all schemes in each exhaust scheme cluster in a statistical way, and taking the sum of exhaust fitness of each exhaust scheme cluster as the sum of exhaust fitness of each exhaust scheme cluster; and comparing the exhaust fitness sum of the plurality of final exhaust scheme clusters, and determining the final exhaust scheme cluster with the largest exhaust fitness sum as a final optimization result, wherein the final exhaust scheme cluster comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes to form an optimal exhaust scheme library.
And according to the optimal exhaust scheme and the plurality of suboptimal exhaust schemes, performing exhaust control error compensation analysis through an exhaust control unit to obtain a compensated optimal exhaust scheme, and performing exhaust control through the exhaust control unit.
Further, the embodiment of the application further comprises:
Acquiring simulated pipeline pressure information after simulated exhaust is performed by the optimal exhaust scheme;
Performing an exhaust test by adopting the optimal exhaust scheme to obtain actual pipeline pressure information;
And calculating errors of the simulated pipeline pressure information and the actual pipeline pressure information, traversing and selecting a suboptimal exhaust scheme from among the suboptimal exhaust schemes to carry out exhaust test until the errors are smaller than an error threshold value or the suboptimal exhaust schemes are traversed, and selecting the exhaust scheme with the smallest error as a compensation optimal exhaust scheme.
In a preferred embodiment, first, an exhaust simulation is performed for an optimal exhaust scheme, and simulated pipeline pressure information is acquired, reflecting the pressure change in the pipeline after the exhaust is performed according to the optimal exhaust scheme. Meanwhile, an optimal exhaust scheme is adopted for actual exhaust test, the valve opening of a pressure regulating valve in an exhaust control unit is regulated according to the control parameters of the optimal exhaust scheme, corresponding actual exhaust is realized, and after the exhaust test is finished, the actual pipeline pressure information is collected through a pressure sensor in a pipeline, so that the pipeline pressure after the exhaust is implemented according to the optimal exhaust scheme in the current actual environment is reflected.
And then calculating errors of the simulated pipeline pressure information and the actual pipeline pressure information, judging the magnitude relation between the errors and a preset error threshold value, and if the errors are larger than the preset error threshold value, entering a traversal test process of the suboptimal scheme. Firstly, according to the positive and negative of the error, selecting a suboptimal scheme of the simulated pressure which is closer to the actual pressure for testing, for example, if the error is positive and the simulated pipeline pressure information is larger than the actual pipeline pressure information, the suboptimal exhaust scheme with too much exhaust and too low air pressure is selected for testing; then, calculating new errors of the simulated pipeline pressure information and the actual pipeline pressure information of the selected suboptimal scheme; repeating the traversing test process until an exhaust scheme with the error smaller than the error threshold value is obtained and is used as a compensation optimal exhaust scheme; and if the errors are still larger than the preset error threshold after all the suboptimal exhaust schemes are traversed, outputting the exhaust scheme corresponding to the minimum error obtained by the traversal as a compensation optimal exhaust scheme. And finally, controlling the pressure regulating valve to exhaust the air compressor unit according to the optimal exhaust scheme by the exhaust control unit according to the actual air pressure of the customer, thereby not only playing a role in regulating the pressure and preventing the pressure from rising, but also playing a role in protecting the unit and avoiding repeated starting and stopping.
Taking a centrifugal air compressor as an example, the centrifugal air compressor supplies compressed air for the tire production process, and the design exhaust capacity is 138 Nm/min and the exhaust pressure is 0.8MPa (G). A pressure sensor is arranged on a centrifugal air compressor of the air compressor, and pipeline pressure information in an exhaust manifold, such as 0.65MPa (G), 0.73MPa (G) and the like, is acquired in real time; setting a rotating speed sensor and a power detection device on an engine of a centrifugal air compressor, and acquiring engine operation information; recording the instantaneous flow of the compressed air of the centrifugal air compressor in real time by using a flowmeter to form an air consumption information sequence, such as {120Nm, 132Nm, …,114 Nm; meanwhile, the production beat information of the tire production line and the workshop environment temperature information are obtained in real time to serve as air consumption characteristic information. And through the gas consumption prediction channel, a first gas consumption prediction branch based on experience prediction and a second gas consumption prediction branch based on characteristic prediction are adopted to respectively analyze a gas consumption information sequence and characteristic information of the gas consumption such as the current production takt, the ambient temperature and the like, so as to obtain a first predicted gas consumption and a second predicted gas consumption. And then carrying out weighted fusion on the two predicted gas consumption types to obtain the predicted gas consumption at the next moment.
On the basis, the exhaust pressure change trend at the next moment is predicted by the pipeline pressure prediction channel by utilizing the pipeline pressure information and the engine operation information, so as to obtain predicted exhaust pressure information. Further, by using the predicted exhaust pressure information, an exhaust optimization mathematical model is constructed by an exhaust fitness function in combination with the adjustment range of the exhaust valve. The model takes the exhaust pipeline pressure not exceeding the upper pressure limit as constraint and the maximum exhaust fitness as a target, and adopts a clustering algorithm to optimize the initial random exhaust scheme to form an optimized exhaust scheme library containing the optimal and suboptimal exhaust schemes. And finally, carrying out actual exhaust by adopting an optimal exhaust scheme in an optimal exhaust scheme library, comparing the actual exhaust pressure with the simulated predicted pipeline pressure, and calculating an error. If the error exceeds the threshold value, selecting one of the suboptimal exhaust schemes with the smallest error, compensating and correcting the selected suboptimal exhaust scheme to serve as the optimal exhaust scheme, and controlling the implementation of the exhaust valve. By optimizing the exhaust control, the exhaust pressure is stably controlled near 0.8MPa, so that the pressure fluctuation caused by the change of production beats is weakened, frequent unloading or stopping is avoided, the air supply is ensured, the energy efficiency is improved, and the service life of the air compressor is prolonged. In summary, the exhaust pressure intelligent control method for the protection unit provided by the embodiment of the application has the following technical effects:
And collecting pipeline pressure information and engine operation information in the current air compressor unit, and collecting a gas consumption information sequence and gas consumption characteristic information in a preset historical time window, so as to provide basic data support for realizing power consumption prediction and pressure information prediction. According to the gas consumption information sequence, the gas consumption is empirically predicted to obtain a first predicted gas consumption, the gas consumption is predicted according to the gas consumption characteristic information to obtain a second predicted gas consumption, the first predicted gas consumption and the second predicted gas consumption are combined, the predicted gas consumption is obtained through calculation, and the accuracy of the predicted gas consumption is improved through combination of the empirical prediction and the characteristic prediction. According to the pipeline pressure information and the engine operation information, the prediction processing obtains the predicted pipeline pressure information at the next preset moment, so that the prediction of the pipeline pressure information is realized, and support is provided for optimizing an exhaust scheme. And according to the predicted pipeline pressure information, the exhaust scheme is optimized through an exhaust protection analysis unit, so that an optimized exhaust scheme library is obtained, and the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes, so that control adaptability is improved. According to the optimal exhaust scheme and a plurality of suboptimal exhaust schemes, exhaust control error compensation analysis is carried out through an exhaust control unit, a compensated optimal exhaust scheme is obtained, exhaust control is carried out through the exhaust control unit, the control precision of the optimal exhaust scheme is further improved through the compensation analysis, real-time control is carried out according to the compensated optimal exhaust scheme, pressure regulation according to the actual air pressure of a user is achieved, pressure high flushing is prevented, repeated starting and stopping of a unit are avoided, and the working efficiency and the working quality of the unit are improved.
Example two
Based on the same inventive concept as the exhaust pressure intelligent control method for a protection unit in the foregoing embodiment, as shown in fig. 3, an embodiment of the present application provides an exhaust pressure intelligent control device for a protection unit, where the device includes an exhaust control unit connected to an air compressor unit, and an air pressure trend analysis unit, an exhaust protection analysis unit, and the device further includes:
The air consumption information acquisition module 11 is used for acquiring pipeline pressure information and engine operation information in the current air compressor unit, and acquiring an air consumption information sequence and air consumption characteristic information in a preset historical time window;
the air consumption prediction module 12 is configured to perform experience prediction of air consumption according to the air consumption information sequence by using an air pressure trend analysis unit, obtain a first predicted air consumption, and perform prediction of air consumption according to the air consumption characteristic information, so as to obtain a second predicted air consumption;
the predicted gas consumption obtaining module 13 is configured to obtain a predicted gas consumption by combining the first predicted gas consumption and the second predicted gas consumption;
a pipeline pressure prediction module 14, configured to obtain predicted pipeline pressure information at a next preset time through prediction processing according to the pipeline pressure information and engine operation information;
The exhaust scheme optimizing module 15 is configured to perform, according to the predicted pipeline pressure information, optimization processing of an exhaust scheme through an exhaust protection analysis unit, to obtain an optimized exhaust scheme library, where the optimized exhaust scheme library includes an optimal exhaust scheme and a plurality of suboptimal exhaust schemes;
And the exhaust scheme compensation module 16 is configured to perform exhaust control error compensation analysis by using an exhaust control unit according to the optimal exhaust scheme and the multiple suboptimal exhaust schemes, obtain a compensated optimal exhaust scheme, and perform exhaust control by using the exhaust control unit.
Further, the air consumption information acquisition module 11 includes the following steps:
collecting pipeline pressure information in an air compressor unit at the current moment, and collecting rotating speed information and power information of an engine as engine operation information;
Collecting gas consumption information of a plurality of historical moments in a preset historical time window, and obtaining a gas consumption information sequence;
and acquiring production efficiency information and temperature information at the current moment to serve as the gas consumption characteristic information.
Further, the air consumption prediction module 12 includes the following steps:
based on historical operation data of the air compressor unit, extracting and obtaining a sample gas consumption information sequence set, a sample first prediction gas consumption set, a sample gas consumption characteristic information set and a sample second prediction gas consumption set;
Constructing a gas consumption prediction channel comprising a first gas consumption prediction branch and a second gas consumption prediction branch, and training and updating to a preset convergence requirement, wherein the first gas consumption prediction branch is trained and updated by adopting the sample gas consumption information sequence set and the sample first prediction gas consumption set, and the second gas consumption prediction branch is trained and updated by adopting the sample gas consumption characteristic information set and the sample second prediction gas consumption set;
And carrying out gas consumption prediction on the gas consumption information sequence and the gas consumption characteristic information based on the converged gas consumption prediction channel to obtain the first predicted gas consumption and the second predicted gas consumption.
Further, the prediction air consumption obtaining module 13 includes the following steps:
testing the first gas consumption prediction branch and the second gas consumption prediction branch to obtain a first accuracy rate and a second accuracy rate, and distributing to obtain a first weight and a second weight;
And carrying out weighted calculation on the first predicted gas consumption and the second predicted gas consumption by adopting the first weight and the second weight to obtain the predicted gas consumption.
Further, the pipe pressure prediction module 14 includes the following execution steps:
acquiring a sample pipeline pressure information set, a sample engine operation information set, a sample gas consumption set and a sample prediction pipeline pressure information set based on operation history data of the air compressor unit;
Taking sample pipeline pressure information, sample engine operation information and sample gas consumption as inputs, taking sample predicted pipeline pressure information as outputs, constructing a pipeline pressure prediction channel, and training and updating;
and based on the updated pipeline pressure prediction channel, predicting the pipeline pressure information at the next preset moment to the pipeline pressure information, the engine operation information and the predicted gas consumption, so as to obtain the predicted pipeline pressure information.
Further, the exhaust scheme optimization module 15 includes the following execution steps:
Constructing constraint conditions of optimization treatment of an exhaust scheme, wherein the constraint conditions comprise that the pressure of a pipeline after exhaust is not more than a pipeline pressure threshold value;
An exhaust function of the exhaust scheme optimization process is constructed as follows:
；
Wherein exh is exhaust fitness, w 1 and w 2 are first weight and second weight, P b is predicted pipeline pressure information, and P a is pipeline pressure information after exhaust according to an exhaust scheme;
Acquiring an exhaust pressure adjusting range, randomly generating a plurality of first exhaust schemes according to the constraint conditions, performing exhaust simulation, and calculating to obtain a plurality of first exhaust fitness by combining the exhaust functions;
dividing a plurality of first exhaust schemes into a plurality of excellent first exhaust schemes and a plurality of inferior first exhaust schemes according to the plurality of first exhaust fitness;
According to the first exhaust fitness of the first optimal exhaust schemes, calculating and distributing to obtain a plurality of clustering numbers, and clustering the first inferior exhaust schemes to obtain a plurality of exhaust scheme clusters;
Performing iterative optimization of the exhaust scheme in the plurality of exhaust scheme clusters until the optimization convergence requirement is met, and obtaining a plurality of final exhaust scheme clusters;
And calculating the total exhaust adaptability of the plurality of final exhaust scheme clusters, and outputting the final exhaust scheme cluster with the maximum total exhaust adaptability to obtain the optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes.
Further, the exhaust scheme optimization module 15 further includes the following execution steps:
Taking a first optimal exhaust scheme in the plurality of exhaust scheme clusters as an optimal scheme, and optimally adjusting the plurality of inferior first exhaust schemes according to a preset step length to obtain a plurality of inferior second exhaust schemes;
Performing exhaust simulation according to a plurality of inferior second exhaust schemes, calculating to obtain a plurality of second exhaust fitness, comparing the second exhaust fitness with the first exhaust fitness of a plurality of excellent first exhaust schemes, updating and replacing the excellent exhaust schemes, and obtaining a plurality of updated exhaust scheme clusters;
and continuing to iteratively update and optimize the plurality of exhaust scheme clusters until the optimization convergence requirement is met.
Further, the exhaust scheme compensation module 16 includes the following implementation steps:
Acquiring simulated pipeline pressure information after simulated exhaust is performed by the optimal exhaust scheme;
Performing an exhaust test by adopting the optimal exhaust scheme to obtain actual pipeline pressure information;
And calculating errors of the simulated pipeline pressure information and the actual pipeline pressure information, traversing and selecting a suboptimal exhaust scheme from among the suboptimal exhaust schemes to carry out exhaust test until the errors are smaller than an error threshold value or the suboptimal exhaust schemes are traversed, and selecting the exhaust scheme with the smallest error as a compensation optimal exhaust scheme.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (9)
1. An intelligent exhaust pressure control method for a protection unit is characterized in that the method is applied to an intelligent exhaust pressure control device for the protection unit, the device comprises an exhaust control unit, an air pressure trend analysis unit and an exhaust protection analysis unit, wherein the exhaust control unit is connected with an air compressor unit, and the method comprises the following steps:
Collecting pipeline pressure information and engine operation information in a current air compressor unit, and collecting a gas consumption information sequence and gas consumption characteristic information in a preset historical time window;
The air pressure trend analysis unit is used for carrying out experience prediction of air consumption according to the air consumption information sequence to obtain first predicted air consumption, and carrying out prediction of air consumption according to the air consumption characteristic information to obtain second predicted air consumption;
combining the first predicted gas consumption and the second predicted gas consumption, and calculating to obtain predicted gas consumption;
According to the pipeline pressure information and the engine operation information, the prediction processing obtains predicted pipeline pressure information at the next preset moment;
according to the predicted pipeline pressure information, carrying out optimization processing on an exhaust scheme through an exhaust protection analysis unit to obtain an optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes;
And according to the optimal exhaust scheme and the plurality of suboptimal exhaust schemes, performing exhaust control error compensation analysis through an exhaust control unit to obtain a compensated optimal exhaust scheme, and performing exhaust control through the exhaust control unit.
2. The method of claim 1, wherein collecting the pipeline pressure information and the engine operation information in the current air compressor unit, and collecting the gas consumption information sequence and the gas consumption characteristic information in the preset historical time window, comprises:
collecting pipeline pressure information in an air compressor unit at the current moment, and collecting rotating speed information and power information of an engine as engine operation information;
Collecting gas consumption information of a plurality of historical moments in a preset historical time window, and obtaining a gas consumption information sequence;
and acquiring production efficiency information and temperature information at the current moment to serve as the gas consumption characteristic information.
3. The method of claim 1, wherein predicting the air consumption according to the air consumption information sequence to obtain a first predicted air consumption, and predicting the air consumption according to the air consumption characteristic information to obtain a second predicted air consumption, comprises:
based on historical operation data of the air compressor unit, extracting and obtaining a sample gas consumption information sequence set, a sample first prediction gas consumption set, a sample gas consumption characteristic information set and a sample second prediction gas consumption set;
Constructing a gas consumption prediction channel comprising a first gas consumption prediction branch and a second gas consumption prediction branch, and training and updating to a preset convergence requirement, wherein the first gas consumption prediction branch is trained and updated by adopting the sample gas consumption information sequence set and the sample first prediction gas consumption set, and the second gas consumption prediction branch is trained and updated by adopting the sample gas consumption characteristic information set and the sample second prediction gas consumption set;
And carrying out gas consumption prediction on the gas consumption information sequence and the gas consumption characteristic information based on the converged gas consumption prediction channel to obtain the first predicted gas consumption and the second predicted gas consumption.
4. A method according to claim 3, wherein calculating a predicted gas usage in combination with the first predicted gas usage and the second predicted gas usage comprises:
testing the first gas consumption prediction branch and the second gas consumption prediction branch to obtain a first accuracy rate and a second accuracy rate, and distributing to obtain a first weight and a second weight;
And carrying out weighted calculation on the first predicted gas consumption and the second predicted gas consumption by adopting the first weight and the second weight to obtain the predicted gas consumption.
5. The method according to claim 1, wherein the predicting process obtains predicted line pressure information at a next preset time based on the line pressure information and engine operation information, comprising:
acquiring a sample pipeline pressure information set, a sample engine operation information set, a sample gas consumption set and a sample prediction pipeline pressure information set based on operation history data of the air compressor unit;
Taking sample pipeline pressure information, sample engine operation information and sample gas consumption as inputs, taking sample predicted pipeline pressure information as outputs, constructing a pipeline pressure prediction channel, and training and updating;
and based on the updated pipeline pressure prediction channel, predicting the pipeline pressure information at the next preset moment to the pipeline pressure information, the engine operation information and the predicted gas consumption, so as to obtain the predicted pipeline pressure information.
6. The method according to claim 1, wherein the optimization of the exhaust scheme by the exhaust protection analysis unit based on the predicted pipe pressure information comprises:
Constructing constraint conditions of optimization treatment of an exhaust scheme, wherein the constraint conditions comprise that the pressure of a pipeline after exhaust is not more than a pipeline pressure threshold value;
An exhaust function of the exhaust scheme optimization process is constructed as follows:
；
Wherein exh is exhaust fitness, w 1 and w 2 are first weight and second weight, P b is predicted pipeline pressure information, and P a is pipeline pressure information after exhaust according to an exhaust scheme;
Acquiring an exhaust pressure adjusting range, randomly generating a plurality of first exhaust schemes according to the constraint conditions, performing exhaust simulation, and calculating to obtain a plurality of first exhaust fitness by combining the exhaust functions;
dividing a plurality of first exhaust schemes into a plurality of excellent first exhaust schemes and a plurality of inferior first exhaust schemes according to the plurality of first exhaust fitness;
According to the first exhaust fitness of the first optimal exhaust schemes, calculating and distributing to obtain a plurality of clustering numbers, and clustering the first inferior exhaust schemes to obtain a plurality of exhaust scheme clusters;
Performing iterative optimization of the exhaust scheme in the plurality of exhaust scheme clusters until the optimization convergence requirement is met, and obtaining a plurality of final exhaust scheme clusters;
And calculating the total exhaust adaptability of the plurality of final exhaust scheme clusters, and outputting the final exhaust scheme cluster with the maximum total exhaust adaptability to obtain the optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes.
7. The method of claim 6, wherein performing iterative optimization of the venting scheme within a plurality of venting scheme clusters comprises:
Taking a first optimal exhaust scheme in the plurality of exhaust scheme clusters as an optimal scheme, and optimally adjusting the plurality of inferior first exhaust schemes according to a preset step length to obtain a plurality of inferior second exhaust schemes;
Performing exhaust simulation according to a plurality of inferior second exhaust schemes, calculating to obtain a plurality of second exhaust fitness, comparing the second exhaust fitness with the first exhaust fitness of a plurality of excellent first exhaust schemes, updating and replacing the excellent exhaust schemes, and obtaining a plurality of updated exhaust scheme clusters;
and continuing to iteratively update and optimize the plurality of exhaust scheme clusters until the optimization convergence requirement is met.
8. The method of claim 1, wherein performing, by an exhaust control unit, an exhaust control error compensation analysis based on the optimal exhaust scheme and a plurality of sub-optimal exhaust schemes, obtains a compensated optimal exhaust scheme, comprising:
Acquiring simulated pipeline pressure information after simulated exhaust is performed by the optimal exhaust scheme;
Performing an exhaust test by adopting the optimal exhaust scheme to obtain actual pipeline pressure information;
And calculating errors of the simulated pipeline pressure information and the actual pipeline pressure information, traversing and selecting a suboptimal exhaust scheme from among the suboptimal exhaust schemes to carry out exhaust test until the errors are smaller than an error threshold value or the suboptimal exhaust schemes are traversed, and selecting the exhaust scheme with the smallest error as a compensation optimal exhaust scheme.
9. An intelligent control device for exhaust pressure of a protection unit, for implementing the intelligent control method for exhaust pressure of a protection unit according to any one of claims 1 to 8, the device comprising:
The air consumption information acquisition module is used for acquiring pipeline pressure information and engine operation information in the current air compressor unit, and acquiring an air consumption information sequence and air consumption characteristic information in a preset historical time window;
The air consumption prediction module is used for performing experience prediction of air consumption according to the air consumption information sequence through an air pressure trend analysis unit to obtain first predicted air consumption, and performing prediction of the air consumption according to the air consumption characteristic information to obtain second predicted air consumption;
the prediction gas consumption acquisition module is used for combining the first prediction gas consumption and the second prediction gas consumption, and calculating to obtain the prediction gas consumption;
The pipeline pressure prediction module is used for obtaining predicted pipeline pressure information of the next preset moment through prediction processing according to the pipeline pressure information and the engine operation information;
The exhaust scheme optimizing module is used for optimizing the exhaust scheme through an exhaust protection analysis unit according to the predicted pipeline pressure information to obtain an optimized exhaust scheme library, wherein the optimized exhaust scheme library comprises an optimal exhaust scheme and a plurality of suboptimal exhaust schemes;
And the exhaust scheme compensation module is used for carrying out exhaust control error compensation analysis through the exhaust control unit according to the optimal exhaust scheme and the plurality of suboptimal exhaust schemes to obtain a compensated optimal exhaust scheme, and carrying out exhaust control through the exhaust control unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410556067.7A CN118128737B (en) | 2024-05-07 | 2024-05-07 | Intelligent exhaust pressure control method and device for protecting unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410556067.7A CN118128737B (en) | 2024-05-07 | 2024-05-07 | Intelligent exhaust pressure control method and device for protecting unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118128737A true CN118128737A (en) | 2024-06-04 |
| CN118128737B CN118128737B (en) | 2024-07-23 |
Family
ID=91244354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410556067.7A Active CN118128737B (en) | 2024-05-07 | 2024-05-07 | Intelligent exhaust pressure control method and device for protecting unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118128737B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120023932A1 (en) * | 2010-07-28 | 2012-02-02 | Gm Global Technology Operations, Inc. | System and method for calculating a vehicle exhaust manifold pressure |
| CN103049625A (en) * | 2011-10-11 | 2013-04-17 | 新鼎***股份有限公司 | Forecast management method for air compressor operation |
| WO2017054596A1 (en) * | 2015-09-28 | 2017-04-06 | 苏州艾克威尔科技有限公司 | All-in-one machine for air compressor driving and intelligent energy conservation and method thereof |
| KR20170043796A (en) * | 2015-10-14 | 2017-04-24 | 쑤저우 앵커윌 테크놀러지 | Smart power-saving integrated air compressor startup device and method |
| CN108361186A (en) * | 2018-02-27 | 2018-08-03 | 首钢京唐钢铁联合有限责任公司 | Optimization method for air compressor system of steel plant |
| CN108960487A (en) * | 2018-06-13 | 2018-12-07 | 北京天泽智云科技有限公司 | Air compressor machine group system energy consumption optimization method and device based on big data analysis |
| CN109993364A (en) * | 2019-04-01 | 2019-07-09 | 北京恒华龙信数据科技有限公司 | A kind of prediction technique and device of natural gas gas consumption |
| CN114428803A (en) * | 2020-10-29 | 2022-05-03 | 上海浦昊节能环保科技有限公司 | Operation optimization method and system for air compression station, storage medium and terminal |
| WO2022124276A1 (en) * | 2020-12-07 | 2022-06-16 | ダイキン工業株式会社 | Indoor air quality prediction method and indoor air quality detection system |
| CN115143089A (en) * | 2022-08-15 | 2022-10-04 | 广州瑞鑫智能制造有限公司 | Intelligent variable-frequency drive control system and method for air compressor |
| CN115384561A (en) * | 2022-09-15 | 2022-11-25 | 中车株洲电力机车有限公司 | Train oxygen generation control method, device and equipment and readable storage medium |
| CN117028222A (en) * | 2023-08-24 | 2023-11-10 | 深圳市汇川技术股份有限公司 | Control method, device, equipment and storage medium of air compressor unit |
| CN117881889A (en) * | 2021-08-26 | 2024-04-12 | 阿特拉斯·科普柯空气动力股份有限公司 | Model predictive control of compressed air systems |
| CN117863947A (en) * | 2024-03-11 | 2024-04-12 | 北京云科领创信息技术有限公司 | Integrated power adjusting method and system based on charging station |
-
2024
- 2024-05-07 CN CN202410556067.7A patent/CN118128737B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120023932A1 (en) * | 2010-07-28 | 2012-02-02 | Gm Global Technology Operations, Inc. | System and method for calculating a vehicle exhaust manifold pressure |
| CN103049625A (en) * | 2011-10-11 | 2013-04-17 | 新鼎***股份有限公司 | Forecast management method for air compressor operation |
| WO2017054596A1 (en) * | 2015-09-28 | 2017-04-06 | 苏州艾克威尔科技有限公司 | All-in-one machine for air compressor driving and intelligent energy conservation and method thereof |
| KR20170043796A (en) * | 2015-10-14 | 2017-04-24 | 쑤저우 앵커윌 테크놀러지 | Smart power-saving integrated air compressor startup device and method |
| CN108361186A (en) * | 2018-02-27 | 2018-08-03 | 首钢京唐钢铁联合有限责任公司 | Optimization method for air compressor system of steel plant |
| CN108960487A (en) * | 2018-06-13 | 2018-12-07 | 北京天泽智云科技有限公司 | Air compressor machine group system energy consumption optimization method and device based on big data analysis |
| CN109993364A (en) * | 2019-04-01 | 2019-07-09 | 北京恒华龙信数据科技有限公司 | A kind of prediction technique and device of natural gas gas consumption |
| CN114428803A (en) * | 2020-10-29 | 2022-05-03 | 上海浦昊节能环保科技有限公司 | Operation optimization method and system for air compression station, storage medium and terminal |
| WO2022124276A1 (en) * | 2020-12-07 | 2022-06-16 | ダイキン工業株式会社 | Indoor air quality prediction method and indoor air quality detection system |
| CN117881889A (en) * | 2021-08-26 | 2024-04-12 | 阿特拉斯·科普柯空气动力股份有限公司 | Model predictive control of compressed air systems |
| CN115143089A (en) * | 2022-08-15 | 2022-10-04 | 广州瑞鑫智能制造有限公司 | Intelligent variable-frequency drive control system and method for air compressor |
| CN115384561A (en) * | 2022-09-15 | 2022-11-25 | 中车株洲电力机车有限公司 | Train oxygen generation control method, device and equipment and readable storage medium |
| CN117028222A (en) * | 2023-08-24 | 2023-11-10 | 深圳市汇川技术股份有限公司 | Control method, device, equipment and storage medium of air compressor unit |
| CN117863947A (en) * | 2024-03-11 | 2024-04-12 | 北京云科领创信息技术有限公司 | Integrated power adjusting method and system based on charging station |
Non-Patent Citations (1)
| Title |
|---|
| 黎章杰: "空压机组气量调节的智能控制", 压缩机技术, no. 04, 31 August 2016 (2016-08-31), pages 38 - 41 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118128737B (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913A (en) | Transformer area household variable relation abnormity diagnosis method and device | |
| CN110905792B (en) | Air compressor control system and method based on energy internet cloud computing | |
| CN109670625B (en) | NOx emission concentration prediction method based on unscented Kalman filtering least square support vector machine | |
| CN112819107B (en) | Artificial intelligence-based fault prediction method for gas pressure regulating equipment | |
| CN112465239B (en) | Desulfurization system operation optimization method based on improved PSO-FCM algorithm | |
| CN116226469B (en) | Intelligent diagnosis method and system for energy storage equipment faults | |
| CN112149903A (en) | Primary frequency modulation analysis and optimization method of thermal power generating unit based on BP neural network algorithm | |
| CN112270139B (en) | Pneumatic optimization design method for centrifugal compressor of fuel cell based on mother type library | |
| CN114722923B (en) | Lightweight electromechanical equipment fault diagnosis method | |
| CN112748665A (en) | Hydrogen fuel cell iteration control method and device based on fuzzy Kalman filtering | |
| CN118128737B (en) | Intelligent exhaust pressure control method and device for protecting unit | |
| CN117146382B (en) | Intelligent adaptive system optimization method | |
| CN116974234B (en) | Monitoring control method and system for thermal power plant carbon asset | |
| CN116743180B (en) | Intelligent storage method for energy storage power supply data | |
| CN111275320B (en) | Performance adjustment data processing method, system and storage medium of generator set | |
| CN116440670B (en) | Limestone slurry density stability control method | |
| CN112966399A (en) | Pulse tube refrigerator working condition prediction method and system based on machine learning | |
| CN116860027A (en) | Pressure control system and method for digital energy blasting station | |
| CN116757354A (en) | Tobacco redrying section key parameter screening method based on multilayer perceptron | |
| CN115726963A (en) | Screw compressor control method and system | |
| CN116187512A (en) | BP neural network-based carbon emission capacity prediction method and device | |
| CN117910550B (en) | Oil-free ultrahigh-speed centrifugal compressor automatic optimization system based on deep learning | |
| CN116613864B (en) | Online nuclear capacity inspection method and device for storage battery | |
| CN117519054B (en) | High-efficient cold station control system | |
| CN116596703B (en) | Electricity saver and intelligent control method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |