CN114912169B - Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion - Google Patents
Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion Download PDFInfo
- Publication number
- CN114912169B CN114912169B CN202210435341.6A CN202210435341A CN114912169B CN 114912169 B CN114912169 B CN 114912169B CN 202210435341 A CN202210435341 A CN 202210435341A CN 114912169 B CN114912169 B CN 114912169B
- Authority
- CN
- China
- Prior art keywords
- industrial building
- layer
- data
- information
- model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000004927 fusion Effects 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 title claims abstract description 14
- 238000010438 heat treatment Methods 0.000 claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 230000001105 regulatory effect Effects 0.000 claims abstract description 24
- 230000007246 mechanism Effects 0.000 claims abstract description 21
- 230000007613 environmental effect Effects 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000011217 control strategy Methods 0.000 claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 238000012806 monitoring device Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 17
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims 1
- 238000009434 installation Methods 0.000 abstract 1
- 239000010410 layer Substances 0.000 description 93
- 238000010586 diagram Methods 0.000 description 5
- 239000002356 single layer Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Architecture (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an industrial building heat supply autonomous optimization regulation method based on multisource information fusion, which comprises the following steps: establishing a digital twin model of the industrial building heating system; industrial building heating equipment installation includes at least: the method comprises the steps of installing a heat meter at the inlet of each layer of heat supply pipeline of an industrial building, installing an electric regulating valve at the inlet branch pipe of each layer of pipeline heat supply system of the industrial building, and arranging an environment temperature and humidity detection device and a video monitoring device in the industrial building; building an industrial building state sensing model based on a multisource information fusion technology system architecture to obtain heat supply operation data, people flow density and environment temperature and humidity in an industrial building area; based on a digital twin model of an industrial building heating system and according to historical heating operation data, weather data, people flow density, environmental temperature and humidity data and predicted heat load, a valve prediction control model is established by adopting an attention-based mechanism and an improved BiGRU algorithm, so that a control strategy of each layer of electric regulating valve of the industrial building is obtained; and verifying and issuing the control strategy based on the digital twin model of the industrial building heating system.
Description
Technical Field
The invention belongs to the technical field of intelligent heat supply, and particularly relates to an industrial building heat supply autonomous optimization and control method based on multisource information fusion.
Background
At present, industrial building heat supply including commercial buildings, enterprise office buildings and large stadiums is concerned by various levels of governments and society, is an industry which is mainly supported in the field of infrastructure in China, and is an important subject for researching the heat supply industry, and the heat supply quality is improved, the heat supply cost is reduced, and the pollution emission is reduced. For a long time, the existing management means at the tail end of the industrial building heat supply secondary network are mostly still in a manual regulation stage, the regulation fineness and flexibility can not meet the requirements, and the problems of poor precision and slow prediction speed in the optimization regulation are solved.
The multi-source information fusion is a comprehensive sensing, networking and calculating multi-dimensional complex system, the system can acquire a large amount of data from the external environment through various sensing devices, screen, compare and fuse the acquired large amount of data, acquire effective information required by a user from the acquired large amount of data, perform high-efficiency calculation according to the extracted information, and then make corresponding decisions to act on the external environment through a certain executive component. The energy-saving and efficient operation of the industrial building heat supply secondary network regulation is realized by fully applying the sensing capability, the computing capability and the execution capability of a physical information system to the heat supply secondary network regulation by adopting an information physical fusion system.
However, the accuracy of the existing heat supply regulation and control technology is low, the obtained heat supply data of the industrial building is less, the prediction accuracy and speed of the regulation and control model are low, and the problem of how to combine the regulation and control of the industrial building heat supply secondary network with the information physical fusion system to enable the industrial building heat supply regulation and control system to be more intelligent and to be capable of carrying out self-adaptive regulation according to environmental changes in the industrial building area is the problem to be solved urgently at present.
Based on the technical problems, a new industrial building heat supply autonomous optimization and control method based on multi-source information fusion needs to be designed.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the prior art and providing an industrial building heat supply autonomous optimization and control method based on multi-source information fusion.
In order to solve the technical problems, the technical scheme of the invention is as follows:
The invention provides an industrial building heat supply autonomous optimization regulation method based on multisource information fusion, which comprises the following steps:
s1, establishing a digital twin model of an industrial building heating system by adopting a mechanism modeling and data identification method;
Step S2, mounting industrial building heat supply equipment, which at least comprises the following steps: the method comprises the steps of installing a heat meter at the inlet of each layer of heat supply pipeline of an industrial building, installing an electric regulating valve at the inlet branch pipe of each layer of pipeline heat supply system of the industrial building, and arranging an environment temperature and humidity detection device and a video monitoring device in the industrial building;
s3, building an industrial building state sensing model based on a multisource information fusion technology system architecture to obtain heat supply operation data, people flow density and environment temperature and humidity in an industrial building area;
S4, establishing a valve predictive control model based on a digital twin model of the industrial building heating system and according to historical heating operation data, weather data, people flow density, environmental temperature and humidity data and predicted heat load by adopting an attention-based mechanism and an improved BiGRU algorithm to obtain a control strategy of each layer of electric regulating valve of the industrial building;
and S5, after verifying the control strategy based on the digital twin model of the industrial building heating system, issuing and executing the control strategy.
Further, in the step S1, a digital twin model of the industrial building heating system is established by adopting a mechanism modeling and data identification method, which specifically includes:
Establishing a digital twin model comprising physical entities, virtual entities, twin data services and connecting elements among the components of the industrial building heating system;
The physical entity is the basis of a digital twin model and is a data source driven by the whole digital twin model; the virtual entity and the physical entity are mapped one by one and interacted in real time, elements of the physical space are described from multiple dimensions and multiple scales, the actual process of the physical entity is simulated, and element data are analyzed, evaluated, predicted and controlled; the twin data service integrates the physical space information and the virtual space information, ensures the real-time performance of data transmission, provides knowledge base data comprising intelligent algorithms, models, rule standards and expert experiences, and forms a twin database by fusing the physical information, the multi-time space associated information and the knowledge base data; the connection between the components realizes the interconnection of the components, and the real-time acquisition and feedback of data are realized between the physical entity and the twin data service through the sensor and the protocol transmission specification; the physical entity and the virtual entity carry out data transmission through a protocol, physical information is transmitted to the virtual space in real time to update the correction model, and the virtual entity carries out real-time control on the physical entity through an executor; the information transfer between the virtual entity and the twin data service is realized through a database interface;
And identifying the digital twin model, accessing the multi-working-condition real-time operation data of the industrial building heating system into the established digital twin model, and adopting a reverse identification method to carry out self-adaptive identification correction on the simulation result of the digital twin model to obtain the digital twin model of the industrial building heating system after identification correction.
Further, in the step S3, an industrial building state sensing model is built based on the multi-source information fusion technology architecture, which specifically includes:
establishing an industrial building state perception model framework comprising an acquisition layer, a processing layer and a service layer;
The acquisition layer acquires data acquired by the environment temperature detection device and the video monitoring device, data of the heat metering device and the electric regulating valve and heat supply information stored in the history database, wherein the heat supply information comprises a heat supply related report form, data and a log; the processing layer comprises an industrial building information reasoning component and an information prediction component, and the industrial building state prediction analysis is carried out after the data submitted by the acquisition layer are subjected to abstraction, interpretation and logic reasoning; the service layer classifies the industrial building information processed by the processing layer according to services, including subscription, inquiry, management and application of industrial building states.
Further, the industrial building information reasoning component utilizes preset rules in an expert database to conduct fusion reasoning on data information transmitted by the acquisition layer in an information abstraction and semantic interpretation mode; the industrial building information prediction component takes the information after fusion reasoning as a sample for training, compares and judges the training result with the currently acquired real-time information, and then predicts the physical environment information of the industrial building area at the next time.
Further, the calculating to obtain the people flow density in the industrial building area based on the industrial building state perception model includes: according to the video monitoring device in the industrial building area, identifying, tracking and calculating personnel information in the video through an image processing technology to obtain the people flow density in the industrial building area;
Dividing the people stream density into different grades from low to high according to different scenes; identifying, tracking and calculating personnel information in the video through an image processing technology, wherein the steps include video image processing, pedestrian target detection, pedestrian target tracking and people flow calculation; the pedestrian target detection adopts a detection algorithm of a moving target, the region of an image is changed according to the motion process of the target in a video sequence, and the pedestrian target is obtained by extracting the changed region; the pedestrian target tracking is to track a moving target, find out the target position in each frame of video image, mark out and judge whether the moving target is the same pedestrian object; the people flow calculation adopts a people flow statistical method based on moving object classification and machine learning; the moving object classification classifies the object block according to the number of pedestrians in the object block, determines whether the object block contains pedestrians, single-row people or multiple pedestrians, does not count if the object information is a non-pedestrian object, and overlaps if the object information is a single-row people object; if the target information is a multi-row human target, the number of pedestrians in the multi-row human target is required to be determined, the pedestrian characteristics are extracted by adopting a machine learning algorithm, the pedestrian characteristics are trained, and the trained result is utilized to identify the human.
Further, the calculating to obtain the heat supply operation data and the environmental temperature and humidity in the industrial building area based on the industrial building state sensing model includes: the data collected by the environmental temperature and humidity detection device, the heat meter and the electric regulating valve in the industrial building area are processed and analyzed through the collecting layer, the processing layer and the service layer in the industrial building state sensing model, and then the water supply temperature, the backwater temperature, the water supply flow and the environmental temperature and humidity state information in the industrial building area are obtained.
Further, in step S4, a valve prediction control model is established by combining an improved BiGRU algorithm based on an attention mechanism based on a digital twin model of the industrial building heating system and according to historical heating operation data, weather data, people flow density and environmental temperature and humidity data and predicted heat load, so as to obtain a control strategy of each layer of electric control valve of the industrial building, which specifically comprises:
Step S401, setting a VMD based on an attention mechanism and establishing a valve prediction control model hierarchical structure by combining an improved BiGRU algorithm, wherein the valve prediction control model hierarchical structure comprises an input layer, a BiGRU layer and an attention layer;
Step S402, acquiring historical water supply temperature, backwater temperature, water supply flow, weather data, industrial building people flow density, environmental temperature and humidity data and predicted heat load based on a digital twin model of an industrial building heat supply system, taking the historical water supply temperature, backwater temperature, water supply flow, weather data, industrial building people flow density, environmental temperature and humidity data and predicted heat load as training samples of a valve predictive control model, preprocessing the training samples of the valve predictive control model in an input layer to obtain input data with a data sequence length of N, wherein the input data is expressed as: x= [ X 1、X2…XN]T;
step S403, extracting information among components in BiGRU layers, storing important information, forgetting unimportant information, learning the influence of history and future time on the current information by forward and backward BiGRU network units, and calculating and outputting hidden layer states at t time through BiGRU layers as follows: h t＝BiGRU(ht-1,Xt);
In step S404, the hidden layer state h t calculated and output by BiGRU layers is input into the attention layer, and the weights of different input features are adaptively calculated according to the attention mechanism, and the attention layer output at the time t is expressed as: e t＝utanh(wht +b); wherein e t is the probability distribution value of the hidden layer state h t output by the BiGRU layer at the time t; w and u represent weight coefficients; b represents a bias coefficient;
Step S405, calculating a prediction result of a control strategy of the electric regulating valve of each layer of the industrial building through an activation function of the full-connection layer in an output layer, and outputting a model at the time t as follows: y t＝Sigmoid(wost+bo);wo and b o are denoted as weight matrix and bias matrix, respectively.
Further, in the step S403, information between the components is extracted in BiGRU layers, which specifically includes:
The improved BiGRU algorithm comprises an input layer, a hidden layer and a full-connection layer, wherein the hidden layer is composed of three BiGRU network units which are connected in series, each layer BiGRU network processes information from the forward direction and the reverse direction at the same time, all output sequences are fused through an adder after the processing is completed and then transmitted to the next layer BiGRU network, the last layer BiGRU only returns the result of the last time step of the output sequence after the processing is completed, and finally the final prediction result is output through the full-connection layer.
Further, the valve prediction control model hierarchical structure further comprises a decomposition layer, wherein in the decomposition layer, input data is decomposed into a plurality of stable components by adopting a VMD variable mode decomposition method, and the decomposed ith component is expressed as: inputting the decomposed data into BiGRU layers through a sliding window; if the sliding window size is T, the input sequence at time T may be expressed as: x t＝[Xt-T+1,Xt-T+2…Xt]T.
Further, the valve predictive control model hierarchy structure further comprises: the shared layer, in which n BiGRU share the same weight matrix, i.e. the weights used when each component calculates BiGRU the hidden layer state h t are the same.
The beneficial effects of the invention are as follows:
According to the invention, the industrial building heat supply unit building equipment is installed, an industrial building state sensing model is built based on a multi-source information fusion technology architecture, heat supply operation data, people flow density and environment temperature and humidity in an industrial building area are obtained, an industrial building state sensing model hierarchy architecture based on multi-source information fusion is built aiming at complex and changeable physical environments in the industrial building, the multi-source information fusion system is utilized to have high sensing, calculating and executing capacities, heat supply operation data, people flow density and environment data in the industrial building area are obtained, theoretical basis is provided for controlling a two-level network industrial building valve, an electric regulating valve in the industrial building can be self-regulated according to real-time change of the industrial building environment, comfort requirements of users in the industrial building are met, energy consumption is reduced, and energy-saving and efficient operation is realized; in addition, a valve prediction control model is established by combining an attention mechanism with an improved BiGRU algorithm, a control strategy of each layer of electric regulating valve of the industrial building is obtained, the attention mechanism is introduced to the effect that important characteristics can be highlighted, and the improved BiGRU algorithm is utilized, a multilayer BiGRU network and weight sharing are adopted to extract common information among all components after VMD decomposition, so that model prediction accuracy and training speed are improved.
Additional features and advantages will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an independent optimal regulation and control method for industrial building heat supply based on multi-source information fusion;
FIG. 2 is a diagram of an industrial building state-aware model architecture of the present invention;
FIG. 3 shows a valve predictive control model structure according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. 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 be within the scope of the invention.
Fig. 1 is a flow chart of an industrial building heat supply autonomous optimization regulation method based on multi-source information fusion.
As shown in fig. 1, this embodiment provides an industrial building heat supply autonomous optimization and control method based on multi-source information fusion, which is characterized in that it includes:
s1, establishing a digital twin model of an industrial building heating system by adopting a mechanism modeling and data identification method;
Step S2, mounting industrial building heat supply equipment, which at least comprises the following steps: the method comprises the steps of installing a heat meter at the inlet of each layer of heat supply pipeline of an industrial building, installing an electric regulating valve at the inlet branch pipe of each layer of pipeline heat supply system of the industrial building, and arranging an environment temperature and humidity detection device and a video monitoring device in the industrial building;
s3, building an industrial building state sensing model based on a multisource information fusion technology system architecture to obtain heat supply operation data, people flow density and environment temperature and humidity in an industrial building area;
S4, establishing a valve predictive control model based on a digital twin model of the industrial building heating system and according to historical heating operation data, weather data, people flow density, environmental temperature and humidity data and predicted heat load by adopting an attention-based mechanism and an improved BiGRU algorithm to obtain a control strategy of each layer of electric regulating valve of the industrial building;
and S5, after verifying the control strategy based on the digital twin model of the industrial building heating system, issuing and executing the control strategy.
In this embodiment, in step S1, a digital twin model of an industrial building heating system is established by adopting a mechanism modeling and data identification method, which specifically includes:
Establishing a digital twin model comprising physical entities, virtual entities, twin data services and connecting elements among the components of the industrial building heating system;
The physical entity is the basis of a digital twin model and is a data source driven by the whole digital twin model; the virtual entity and the physical entity are mapped one by one and interacted in real time, elements of the physical space are described from multiple dimensions and multiple scales, the actual process of the physical entity is simulated, and the element data are analyzed, evaluated, predicted and controlled; the twin data service integrates physical space information and virtual space information, ensures the real-time performance of data transmission, provides knowledge base data comprising intelligent algorithms, models, rule standards and expert experiences, and forms a twin database by fusing physical information, multi-time space associated information and knowledge base data; the connection between the components is realized by the interconnection of the components, and the real-time acquisition and feedback of data are realized between the physical entity and the twin data service through the sensor and the protocol transmission standard; the physical entity and the virtual entity carry out data transmission through a protocol, physical information is transmitted to the virtual space in real time to update the correction model, and the virtual entity carries out real-time control on the physical entity through an executor; the information transfer between the virtual entity and the twin data service is realized through a database interface;
And identifying the digital twin model, accessing the multi-working-condition real-time operation data of the industrial building heating system into the established digital twin model, and adopting a reverse identification method to carry out self-adaptive identification correction on the simulation result of the digital twin model to obtain the digital twin model of the industrial building heating system after identification correction.
Fig. 2 is an architecture of an industrial building state-aware model in accordance with the present invention.
As shown in fig. 2, in the present embodiment, in step S3, an industrial building state sensing model is built based on a multi-source information fusion technology architecture, which specifically includes:
establishing an industrial building state perception model framework comprising an acquisition layer, a processing layer and a service layer;
The acquisition layer acquires the data acquired by the environment temperature detection device and the video monitoring device, the data of the heat metering device and the electric regulating valve and the heat supply information stored in the history database, wherein the heat supply information comprises a heat supply related report form, data and a log; the processing layer comprises an industrial building information reasoning component and an information prediction component, and the industrial building state prediction analysis is carried out after the data submitted by the acquisition layer are subjected to abstraction, interpretation and logic reasoning; the service layer classifies the industrial building information processed by the processing layer according to services, including subscription, inquiry, management and application of industrial building states.
In the embodiment, the industrial building information reasoning component utilizes preset rules in an expert database to conduct fusion reasoning on data information transmitted by the acquisition layer in an information abstraction and semantic interpretation mode; the industrial building information prediction component takes the information after fusion reasoning as a sample for training, compares and judges the training result with the currently acquired real-time information, and then predicts the physical environment information of the industrial building area at the next time.
In this embodiment, the calculating to obtain the people flow density in the industrial building area based on the industrial building state perception model includes: according to the video monitoring device in the industrial building area, identifying, tracking and calculating personnel information in the video through an image processing technology to obtain the people flow density in the industrial building area;
Dividing the people stream density into different grades from low to high according to different scenes; identifying, tracking and calculating personnel information in the video through an image processing technology, wherein the steps include video image processing, pedestrian target detection, pedestrian target tracking and people flow calculation; the pedestrian target detection adopts a detection algorithm of a moving target, the region of an image is changed according to the motion process of the target in a video sequence, and the pedestrian target is obtained by extracting the changed region; the pedestrian target tracking is to track a moving target, find out the target position in each frame of video image and mark out, and judge whether the target is the same pedestrian object; the people flow calculation adopts a people flow statistical method based on moving object classification and machine learning; classifying the moving target according to the number of pedestrians in the target block, determining whether the target block contains pedestrians, single-row people or multiple pedestrians, if the target information is a non-pedestrian target, not counting, and if the target information is a single-row people target, overlapping; if the target information is a multi-row human target, the number of pedestrians in the multi-row human target is required to be determined, the pedestrian characteristics are extracted by adopting a machine learning algorithm, the pedestrian characteristics are trained, and the trained result is utilized to identify the human.
In this embodiment, the calculation for obtaining the heat supply operation data and the environmental temperature and humidity in the industrial building area based on the industrial building state sensing model includes: the data collected by the environmental temperature and humidity detection device, the heat meter and the electric regulating valve in the industrial building area are processed and analyzed through the collecting layer, the processing layer and the service layer in the industrial building state sensing model, and then the water supply temperature, the backwater temperature, the water supply flow and the environmental temperature and humidity state information in the industrial building area are obtained.
Fig. 3 shows a valve predictive control model structure according to the present invention.
As shown in fig. 3, in step S4, a valve prediction control model is established by adopting an improved BiGRU algorithm in combination with an attention-based mechanism based on a digital twin model of an industrial building heating system and according to historical heating operation data, weather data, people flow density and environmental temperature and humidity data, and predicted heat load, so as to obtain a control strategy of each layer of electric control valve of the industrial building, which specifically comprises:
S401, setting a VMD based on an attention mechanism and establishing a valve prediction control model hierarchical structure by combining an improved BiGRU algorithm, wherein the valve prediction control model hierarchical structure comprises an input layer, a BiGRU layer and an attention layer;
S402, acquiring historical water supply temperature, backwater temperature, water supply flow, weather data, industrial building people flow density, environment temperature and humidity data and predicted heat load based on a digital twin model of an industrial building heat supply system, preprocessing a training sample of a valve prediction control model in an input layer to obtain input data with a data sequence length of N, wherein the input data is expressed as: x= [ X 1、X2…XN]T;
S403, extracting information among components in BiGRU layers, storing important information, forgetting unimportant information, learning the influence of history and future time on the current information through forward and backward BiGRU network units, and calculating and outputting hidden layer states at t time through BiGRU layers to be expressed as: h t＝BiGRU(ht-1,Xt);
s404, inputting hidden layer state h t which is calculated and output by BiGRU layers into an attention layer, adaptively calculating weights of different input features according to an attention mechanism, and expressing the attention layer output at the time t as follows: e t＝utanh(wht+b);et is the probability distribution value of the hidden layer state h t output by the BiGRU layer at the time t; w and u represent weight coefficients; b represents a bias coefficient;
S405, calculating a prediction result of a control strategy of the electric regulating valve of each layer of the industrial building through an activation function of the full-connection layer in an output layer, and outputting a model at the time t as follows: y t＝Sigmoid(wost+bo);wo and b o are denoted as weight matrix and bias matrix, respectively.
In this embodiment, the extracting information between the components in the BiGRU layers in step S403 specifically includes:
The improved BiGRU algorithm comprises an input layer, a hidden layer and a full-connection layer, wherein the hidden layer is composed of three BiGRU network units which are connected in series, each layer BiGRU network processes information from the forward direction and the reverse direction at the same time, all output sequences are fused through an adder after the processing is completed and then transmitted to the next layer BiGRU network, the last layer BiGRU only returns the result of the last time step of the output sequence after the processing is completed, and finally the final prediction result is output through the full-connection layer.
In this embodiment, the hierarchical structure of the valve prediction control model further includes a decomposition layer, in which the input data is decomposed into a plurality of stable components by using a VMD variable mode decomposition method, and the decomposed i-th component is expressed as: inputting the decomposed data into BiGRU layers through a sliding window; if the sliding window size is T, the input sequence at time T may be expressed as: x t＝[Xt-T+1,Xt-T+2…Xt]T.
In this embodiment, the valve predictive control model hierarchy structure further includes: the shared layer, in which n BiGRU share the same weight matrix, i.e. the weights used when each component calculates BiGRU the hidden layer state h t are the same.
It should be noted that, the single-layer BiGRU network is formed by overlapping a forward GRU and a reverse GRU up and down, and the BiGRU network inputs data into the model according to the forward sequence and the reverse sequence, so that the global data sequence information can be better mastered; however, because of the many factors affecting valve regulation, the single-layer BiGRU network has poor accuracy in processing data, and the deep network structure can extract data features in an omnibearing manner, so that the valve control is predicted through a plurality of BiGRU networks by adopting an improved deep network structure BiGRU model. In addition, if several components obtained by VMD algorithm are all subjected to independent modeling prediction, each model is completely and independently trained during model training, which not only results in excessive training parameters and too slow training speed, but also results in insufficient extraction of common information among the components, so that a sharing layer is introduced, and the training parameters are reduced, the model training speed is improved, and the common information among the components is fully extracted at the same time by sharing part of parameters
In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other manners as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.
Claims (6)
1. An industrial building heat supply autonomous optimization regulation method based on multisource information fusion is characterized by comprising the following steps:
s1, establishing a digital twin model of an industrial building heating system by adopting a mechanism modeling and data identification method;
Step S2, mounting industrial building heat supply equipment, which at least comprises the following steps: the method comprises the steps of installing a heat meter at the inlet of each layer of heat supply pipeline of an industrial building, installing an electric regulating valve at the inlet branch pipe of each layer of pipeline heat supply system of the industrial building, and arranging an environment temperature and humidity detection device and a video monitoring device in the industrial building;
s3, building an industrial building state sensing model based on a multisource information fusion technology system architecture to obtain heat supply operation data, people flow density and environment temperature and humidity in an industrial building area;
S4, establishing a valve predictive control model based on a digital twin model of the industrial building heating system and according to historical heating operation data, weather data, people flow density, environmental temperature and humidity data and predicted heat load by adopting an attention-based mechanism and an improved BiGRU algorithm to obtain a control strategy of each layer of electric regulating valve of the industrial building;
s5, after verifying the control strategy based on the digital twin model of the industrial building heating system, issuing and executing the control strategy;
In the step S4, a valve prediction control model is established by combining an improved BiGRU algorithm based on an attention mechanism based on a digital twin model of an industrial building heating system and according to historical heating operation data, weather data, people flow density, environmental temperature and humidity data and predicted heat load, so as to obtain a control strategy of each layer of electric regulating valve of the industrial building, which specifically comprises the following steps:
Step S401, setting a VMD based on an attention mechanism and establishing a valve prediction control model hierarchical structure by combining an improved BiGRU algorithm, wherein the valve prediction control model hierarchical structure comprises an input layer, a BiGRU layer and an attention layer;
Step S402, acquiring historical water supply temperature, backwater temperature, water supply flow, weather data, industrial building people flow density, environmental temperature and humidity data and predicted heat load based on a digital twin model of an industrial building heat supply system, and taking the historical water supply temperature, backwater temperature, water supply flow, weather data, industrial building people flow density, environmental temperature and humidity data and predicted heat load as training samples of a valve predictive control model, preprocessing the training samples of the valve predictive control model in an input layer to obtain input data with a data sequence length of N, wherein the input data is expressed as: x= [ X 1、X2…XN]T;
Step S403, extracting information among components in BiGRU layers, learning the influence of history and future time on the current information by using forward and backward BiGRU network units, and calculating and outputting hidden layer states at time t through BiGRU layers as follows: h t＝BiGRU(ht-1,Xt);
In step S404, the hidden layer state h t calculated and output by BiGRU layers is input into the attention layer, and the weights of different input features are adaptively calculated according to the attention mechanism, and the attention layer output at the time t is expressed as:
Wherein e t is the probability distribution value of the hidden layer state h t output by the BiGRU layer at the time t; w and u represent weight coefficients; b represents a bias coefficient;
Step S405, calculating a prediction result of a control strategy of the electric regulating valve of each layer of the industrial building through an activation function of the full-connection layer in an output layer, and outputting a model at the time t as follows: y t＝Sigmoid(wost+bo); wherein w o and b o are denoted as weight matrix and bias matrix, respectively;
In step S403, the extracting information between the components in the BiGRU layers specifically includes:
The improved BiGRU algorithm comprises an input layer, a hidden layer and a full-connection layer, wherein the hidden layer consists of three BiGRU network units which are connected in series, each layer BiGRU network processes information from the forward direction and the reverse direction at the same time, all output sequences are fused through an adder after the processing is completed and then transmitted to the next layer BiGRU network, the last layer BiGRU only returns the result of the last time step of the output sequence after the processing is completed, and finally the final prediction result is output through the full-connection layer;
The valve predictive control model hierarchical structure further comprises a decomposition layer, wherein in the decomposition layer, input data is decomposed into a plurality of stable components by adopting a VMD variable mode decomposition method, and the decomposed ith component is expressed as: Inputting the decomposed data into BiGRU layers through a sliding window; if the sliding window size is T, the input sequence at time T may be expressed as: x t＝[Xt-T+1,Xt-T+2…Xt]T;
the valve predictive control model hierarchical structure also comprises a sharing layer, wherein n BiGRU in the sharing layer share the same weight matrix.
2. The method for autonomous optimizing and controlling the heat supply of industrial building according to claim 1, wherein in step S1, a digital twin model of the heat supply system of industrial building is established by adopting a mechanism modeling and data identification method, and the method specifically comprises the following steps:
Establishing a digital twin model comprising physical entities, virtual entities, twin data services and connecting elements among the components of the industrial building heating system;
establishing a digital twin model comprising a physical entity, a virtual entity, a twin data service and connecting elements among the components of the two-level network unit building;
The physical entity is a data source of the whole digital twin model;
The virtual entity performs simulation on the actual process of the physical entity, and performs analysis data, evaluation, prediction and control on the element data;
The twin data service integrates the physical space information and the virtual space information, ensures the real-time performance of data transmission, provides knowledge base data comprising intelligent algorithms, models, rule standards and expert experiences, and forms a twin database by fusing the physical information, the multi-time space associated information and the knowledge base data;
The connection between the components is used for realizing interconnection of the components, and the real-time acquisition and feedback of data are realized between the physical entity and the twin data service through the sensor and the protocol transmission specification;
The physical entity and the virtual entity perform data transmission through a protocol, physical information is transmitted to the virtual space in real time to update the correction model, and the virtual entity performs real-time control on the physical entity through an actuator;
the virtual entity and the twin data service are subjected to information transfer through a database interface;
And identifying the digital twin model, accessing the multi-working-condition real-time operation data of the industrial building heating system into the established digital twin model, and adopting a reverse identification method to carry out self-adaptive identification correction on the simulation result of the digital twin model to obtain the digital twin model of the industrial building heating system after identification correction.
3. The method for autonomous optimizing and controlling the heat supply of industrial buildings according to claim 1, wherein in the step S3, an industrial building state sensing model is established based on a multi-source information fusion technology architecture, and the method specifically comprises the following steps:
establishing an industrial building state perception model framework comprising an acquisition layer, a processing layer and a service layer;
the acquisition layer acquires data acquired by the environment temperature detection device and the video monitoring device, data of the heat metering device and the electric regulating valve and heat supply information stored in the history database;
The processing layer comprises an industrial building information reasoning component and an information prediction component, and the industrial building state prediction analysis is carried out after the data submitted by the acquisition layer are subjected to abstraction, interpretation and logic reasoning;
The service layer classifies the industrial building information processed by the processing layer according to the service.
4. The autonomous optimization regulating method for industrial building heat supply according to claim 3, wherein: the industrial building information reasoning component utilizes preset rules in an expert database to conduct fusion reasoning on data information transmitted by the acquisition layer in an information abstraction and semantic interpretation mode; the industrial building information prediction component takes the information after fusion reasoning as a sample for training, compares and judges the training result with the currently acquired real-time information, and then predicts the physical environment information of the industrial building area at the next time.
5. The autonomous optimization regulating method for industrial building heat supply according to claim 3, wherein: the method also comprises the step of calculating and obtaining the people flow density in the industrial building area based on the industrial building state perception model, and specifically comprises the following steps:
According to the video monitoring device in the industrial building area, identifying, tracking and calculating personnel information in the video through an image processing technology to obtain the people flow density in the industrial building area;
Dividing the people stream density into different grades from low to high according to different scenes; identifying, tracking and calculating personnel information in the video through an image processing technology, wherein the steps include video image processing, pedestrian target detection, pedestrian target tracking and people flow calculation; the pedestrian target detection adopts a detection algorithm of a moving target, the region of an image is changed according to the motion process of the target in a video sequence, and the pedestrian target is obtained by extracting the changed region; the pedestrian target tracking is to track a moving target, find out the target position in each frame of video image, mark out and judge whether the moving target is the same pedestrian object; the people flow calculation adopts a people flow statistical method based on moving object classification and machine learning; the moving object classification classifies the object block according to the number of pedestrians in the object block, determines whether the object block contains pedestrians, single-row people or multiple pedestrians, does not count if the object information is a non-pedestrian object, and overlaps if the object information is a single-row people object; if the target information is a multi-row human target, the number of pedestrians in the multi-row human target is required to be determined, the pedestrian characteristics are extracted by adopting a machine learning algorithm, the pedestrian characteristics are trained, and the trained result is utilized to identify the human.
6. The autonomous optimization regulating method for industrial building heat supply according to claim 3, wherein: the method also comprises the step of calculating and obtaining heat supply operation data and environment temperature and humidity in the industrial building area based on the industrial building state perception model, and specifically comprises the following steps:
The data collected by the environmental temperature and humidity detection device, the heat meter and the electric regulating valve in the industrial building area are processed and analyzed through the collecting layer, the processing layer and the service layer in the industrial building state sensing model, and then the water supply temperature, the backwater temperature, the water supply flow and the environmental temperature and humidity state information in the industrial building area are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210435341.6A CN114912169B (en) | 2022-04-24 | 2022-04-24 | Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210435341.6A CN114912169B (en) | 2022-04-24 | 2022-04-24 | Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114912169A CN114912169A (en) | 2022-08-16 |
| CN114912169B true CN114912169B (en) | 2024-05-31 |
Family
ID=82765078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210435341.6A Active CN114912169B (en) | 2022-04-24 | 2022-04-24 | Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114912169B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882116B (en) * | 2023-09-07 | 2024-02-02 | 北京世纪黄龙技术有限公司 | Digital twin heating space division method, calculation method, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717334A (en) * | 2019-09-10 | 2020-01-21 | 上海理工大学 | Text emotion analysis method based on BERT model and double-channel attention |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
| CN113052214A (en) * | 2021-03-14 | 2021-06-29 | 北京工业大学 | Heat exchange station ultra-short term heat load prediction method based on long and short term time series network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107861478B (en) * | 2017-10-17 | 2018-08-14 | 广东工业大学 | A kind of parallel control method in intelligence workshop and system |
-
2022
- 2022-04-24 CN CN202210435341.6A patent/CN114912169B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717334A (en) * | 2019-09-10 | 2020-01-21 | 上海理工大学 | Text emotion analysis method based on BERT model and double-channel attention |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
| CN113052214A (en) * | 2021-03-14 | 2021-06-29 | 北京工业大学 | Heat exchange station ultra-short term heat load prediction method based on long and short term time series network |
Non-Patent Citations (1)
| Title |
|---|
| 基于三维GIS技术的公路交通数字孪生***;郑伟皓;周星宇;吴虹坪;李红梅;朱新童;文林江;;计算机集成制造***;20200115(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114912169A (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570651B (en) | Road network traffic situation prediction method and system based on deep learning | |
| CN109754605B (en) | Traffic prediction method based on attention temporal graph convolution network | |
| CN108205889B (en) | Method for predicting highway traffic flow based on convolutional neural network | |
| Wang et al. | Modeling inter-station relationships with attentive temporal graph convolutional network for air quality prediction | |
| CN113538910B (en) | Self-adaptive full-chain urban area network signal control optimization method | |
| Li et al. | Graph CNNs for urban traffic passenger flows prediction | |
| Bao et al. | Spatial–temporal complex graph convolution network for traffic flow prediction | |
| CN110675632B (en) | Vehicle short-time trajectory prediction control method aiming at multi-feature space and data sparseness | |
| CN110555551A (en) | air quality big data management method and system for smart city | |
| Sharma | Enhancing HVAC energy efficiency using artificial neural network-based occupancy detection | |
| Pranolo et al. | Robust LSTM With tuned-PSO and bifold-attention mechanism for analyzing multivariate time-series | |
| CN115376317B (en) | Traffic flow prediction method based on dynamic graph convolution and time sequence convolution network | |
| CN114912169B (en) | Industrial building heat supply autonomous optimization regulation and control method based on multisource information fusion | |
| CN114662791A (en) | Long time sequence pm2.5 prediction method and system based on space-time attention | |
| CN116049764A (en) | Cross-scale time sequence data fusion method and system for Internet of things | |
| CN116976702A (en) | Urban digital twin platform and method based on large-scene GIS lightweight engine | |
| Zhang et al. | Graph neural network-based spatio-temporal indoor environment prediction and optimal control for central air-conditioning systems | |
| CN115860286A (en) | Air quality prediction method and system based on time sequence door mechanism | |
| Akbarzadeh et al. | Heating-cooling monitoring and power consumption forecasting using lstm for energy-efficient smart management of buildings: A computational intelligence solution for smart homes | |
| CN116434569A (en) | Traffic flow prediction method and system based on STNR model | |
| CN115063972A (en) | Traffic speed prediction method and system based on graph convolution and gate control cyclic unit | |
| Chen et al. | A bidirectional context-aware and multi-scale fusion hybrid network for short-term traffic flow prediction | |
| Wang et al. | A Short-Term Od Distribution Prediction Model Combined with Deep Learning Frameworks and Destination Choice Behaviour in Urban Rail Transit Networks | |
| CN117744950B (en) | Travel demand analysis method, device, equipment and storage medium | |
| Bao et al. | Adjacent-DBSCAN Enhanced Time-Varying Multi-graph Convolution Network for Traffic Flow Prediction |
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 | ||
| GR01 | Patent grant |