CN113606649A - Intelligent heat supply station control prediction system based on machine learning algorithm - Google Patents
Intelligent heat supply station control prediction system based on machine learning algorithm Download PDFInfo
- Publication number
- CN113606649A CN113606649A CN202110836982.8A CN202110836982A CN113606649A CN 113606649 A CN113606649 A CN 113606649A CN 202110836982 A CN202110836982 A CN 202110836982A CN 113606649 A CN113606649 A CN 113606649A
- Authority
- CN
- China
- Prior art keywords
- data
- heat supply
- module
- machine learning
- learning algorithm
- 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.)
- Pending
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 27
- 238000012806 monitoring device Methods 0.000 claims abstract description 4
- 238000010438 heat treatment Methods 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
- F24D19/1006—Arrangement or mounting of control or safety devices for water heating systems
- F24D19/1009—Arrangement or mounting of control or safety devices for water heating systems for central heating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides an intelligent heat supply station control prediction system based on a machine learning algorithm, and relates to the field of heat supply station control prediction. The system comprises a cloud platform, wherein the cloud platform is connected with an enterprise counting bin, the enterprise counting bin is connected with an upper SCADA control system, and the upper SCADA control system is connected with a lower PLC control system; the lower PLC control system is connected with the heat exchange station heat supply equipment and the heat supply pipe network or the building heat supply terminal, and the heat supply pipe network or the building heat supply terminal is respectively connected with the enterprise warehouse and the upper SCADA control system through a pipe network monitoring device. The invention can realize accurate prediction of heat supply load.
Description
Technical Field
The invention provides an intelligent heat supply station control prediction system based on a machine learning algorithm, and relates to the field of heat supply station control prediction.
Background
Machine Learning (ML) is a branch of artificial intelligence, allowing computers to "learn" rules from data and experience, and predict unknown data using the rules, which can bring higher production efficiency, better service experience and better management thinking to the society.
More and more application cases show that: the theoretical innovation and the process change of the traditional industry are from data promotion rather than development by itself, and a current concept of data and the future suggests that: machine learning has a more positive impact on automation control systems.
In view of the fact that the heating automation control system is a complex system with the characteristics of time lag, nonlinearity, strong coupling and the like, the traditional load prediction method cannot realize accurate prediction of heating load.
Disclosure of Invention
The invention aims to provide an intelligent heating station control prediction system based on a machine learning algorithm, which can overcome the defects and realize accurate prediction of heating load.
In order to achieve the purpose, the invention provides an intelligent heating station control prediction system based on a machine learning algorithm, which comprises a cloud platform, wherein the cloud platform is connected with an enterprise number bin, the enterprise number bin is connected with an upper SCADA control system, and the upper SCADA control system is connected with a lower PLC control system; the lower PLC control system is connected with the heat exchange station equipment and the heat supply pipe network or the building heat supply terminal, and the heat supply pipe network or the building heat supply terminal is respectively connected with the enterprise warehouse and the upper SCADA control system through a pipe network monitoring device.
Preferably, the cloud platform comprises an AIRFLOW cloud deployment module, an EC2 cloud computing module, an S3 cloud storage module, and a load prediction model module based on a machine learning algorithm.
Preferably, the enterprise data warehouse comprises a Historian data module, a file recording data module and a comprehensive information data module.
Preferably, the upper SCADA control system comprises a data monitoring module, a trend query module, a real-time alarm module and a target issuing module.
Preferably, the lower PLC control system comprises a PID process controller, the PID process controller is connected with the intelligent unit through a primary regulating valve, the intelligent unit feeds back the PID process controller through a temperature controller, and the intelligent unit is connected with a heat supply pipe network or a building heat supply terminal.
Preferably, the load prediction model module based on the machine learning algorithm comprises model training, model parameter optimization and predicted value output;
the model training specifically comprises the following steps:
step (1.1), obtaining sample data: the sample data comprises secondary temperature supply historical data, outdoor air temperature historical data, first 3 x 24h secondary temperature supply historical data and 3 x 24h outdoor air temperature historical data;
step (1.2), sample data cleaning: cleaning and treating the sample data obtained in the step (1), removing invalid or unreasonable data, mending and leaking missing data, and performing data normalization treatment;
step (1.3), selecting characteristic engineering: selecting an outdoor air temperature historical value, the previous 3 × 24h outdoor air temperature historical value and the previous 3 × 24h secondary side water supply temperature historical value as characteristic projects;
the model parameter optimization comprises the following steps:
step (2.1), parameter tuning: training the model and carrying out related parameter tuning to prevent over-fitting and under-fitting;
step (2.2), error analysis: model verification and error analysis, namely performing relevant verification and error analysis on the model by using test set data;
preferably, the predicted value output module comprises the future 3h outdoor air temperature, the future 3h outdoor relative humidity, the future 3h indoor temperature set value, the previous 24h outdoor air temperature, the previous 24h outdoor relative humidity, the previous 24h indoor water temperature and the previous 24h indoor temperature.
Compared with the prior art, the invention has the beneficial effects that:
the intelligent heat supply station control prediction system based on the machine learning algorithm meets the actual working condition requirements of the existing heat supply system, has better fitting effect and correlation on load prediction and application of the complex heat supply system, does not need frequent parameter adjustment and excessive manual intervention, and realizes the self-adaptive optimization operation of the heat supply system.
Drawings
FIG. 1 is a schematic diagram of a heating load model architecture of the present invention;
FIG. 2 is a schematic diagram of the overall architecture of the present invention;
Detailed Description
Example 1
The invention is further illustrated in the following figures 1-2, in conjunction with the accompanying drawings: the intelligent heating station control prediction system based on the machine learning algorithm comprises a cloud platform, wherein the cloud platform is connected with enterprise data bins, the enterprise data bins are connected with an upper SCADA control system, and the upper SCADA control system is connected with a lower PLC control system; the lower PLC control system is connected with equipment in the heat exchange station and a heat supply pipe network or a building heat supply terminal, and the heat supply pipe network or the building heat supply terminal is respectively connected with the enterprise warehouse and the upper SCADA control system through a pipe network monitoring device.
The cloud platform comprises an AIRFLOW cloud deployment module, an EC2 cloud computing module, an S3 cloud storage module and a load prediction model module based on a machine learning algorithm.
The enterprise data warehouse comprises a Historian data module, a file recording data module and a comprehensive information data module.
The upper SCADA control system comprises a data monitoring module, a trend query module, a real-time alarm module and a target issuing module.
The lower PLC control system comprises a PID process controller, the PID process controller is connected with an intelligent unit through a primary regulating valve, the intelligent unit feeds back the PID process controller through a temperature controller, and the intelligent unit is connected with a heat supply pipe network or a building heat supply terminal.
The load prediction model module based on the machine learning algorithm comprises model training, model parameter optimization and predicted value output; the model training specifically comprises the following steps:
step (1.1), obtaining sample data: the sample data comprises secondary temperature supply historical data, outdoor air temperature historical data, first 3 x 24h secondary temperature supply historical data and 3 x 24h outdoor air temperature historical data;
step (1.2), sample data cleaning: cleaning and treating the sample data obtained in the step (1), removing invalid or unreasonable data, mending and leaking missing data, and performing data normalization treatment;
step (1.3), selecting characteristic engineering: selecting an outdoor air temperature historical value, the previous 3 × 24h outdoor air temperature historical value and the previous 3 × 24h secondary side water supply temperature historical value as characteristic projects;
the model parameter optimization comprises the following steps:
step (2.1), parameter tuning: training the model and carrying out related parameter tuning to prevent over-fitting and under-fitting;
step (2.2), error analysis: model verification and error analysis, namely performing relevant verification and error analysis on the model by using test set data;
preferably, the predicted value output module comprises the future 3h outdoor air temperature, the future 3h outdoor relative humidity, the future 3h indoor temperature set value, the previous 24h outdoor air temperature, the previous 24h outdoor relative humidity, the previous 24h indoor water temperature and the previous 24h indoor temperature.
The intelligent heat supply station control prediction system based on the machine learning algorithm fully excavates production historical data of an annual heat supply system by using advanced technologies such as big data analysis, a cloud platform and machine learning, performs data modeling on station control systems of energy-saving floor heating, non-energy-saving floor heating and non-energy-saving piece heating cells by combining meteorological data, building energy consumption characteristic data and the like, and pushes and stores heat supply historical and real-time data to an enterprise cloud data lake in an incremental or full-scale mode through an Internet of things communication technology on the basis of an SCADA heat supply automatic system, so that cloud storage and backup of heat supply data are realized, the safety performance of data storage is improved, and hardware investment of a machine room server and related storage equipment is reduced; secondly, the enterprise cloud carries out related cleaning treatment on the heat supply data through a cloud data treatment technology, invalid data are removed, missing and lost data are compensated, and the treated data are stored in corresponding data lakes for later use, so that the heat supply data treatment efficiency is greatly improved, the labor cost is saved, and the heat supply data quality is improved; and finally, placing the station load prediction control strategy at the cloud end, analyzing heat supply operation data in real time through a cloud computing technology, computing a control target in real time, and embedding the control target into the SCADA system through Internet of things communication and related data interfaces to preliminarily realize the cloud operation of a control system. Meanwhile, the SCADA can be freely switched between cloud intelligent control and manual control, and can be customized and adjusted according to individual requirements of different units; and the cloud computing result is issued to each station control system in real time, so that the conformity and the difference of manual adjustment and cloud control are reflected more visually.
The intelligent heat supply station control prediction system based on the machine learning algorithm meets the actual working condition requirements of the existing heat supply system, has good fitting effect and correlation on load prediction and application of a complex heat supply system, does not need frequent parameter adjustment and excessive manual intervention, and preliminarily realizes the self-adaptive optimization operation of the heat supply system.
Claims (7)
1. An intelligent heating station control prediction system based on a machine learning algorithm is characterized by comprising a cloud platform, wherein the cloud platform is connected with enterprise data bins, the enterprise data bins are connected with an upper SCADA control system, and the upper SCADA control system is connected with a lower PLC control system; the lower PLC control system is connected with the heat exchange station heat supply equipment and the heat supply pipe network or the building heat supply terminal, and the heat supply pipe network or the building heat supply terminal is respectively connected with the enterprise warehouse and the upper SCADA control system through a pipe network monitoring device.
2. The system of claim 1, wherein the cloud platform comprises an AIRFLOW cloud deployment module, an EC, and a machine learning algorithm based intelligent heating station control prediction system2Cloud computing module, S3The load prediction model module comprises a cloud storage module and a load prediction model module based on a machine learning algorithm.
3. The intelligent heating station control prediction system based on the machine learning algorithm as claimed in claim 1, wherein the enterprise data warehouse comprises a Historian data module, a file recording data module and a comprehensive information data module.
4. The intelligent heating station control prediction system based on the machine learning algorithm as claimed in claim 1, wherein the upper SCADA control system comprises a data monitoring module, a trend query module, a real-time alarm module, and a target issuing module.
5. The intelligent heating station control prediction system based on the machine learning algorithm as claimed in claim 1, wherein the lower PLC control system comprises a PID process controller, the PID process controller is connected with the intelligent unit through a primary regulating valve, the intelligent unit feeds back the PID process controller through a temperature controller, and the intelligent unit is connected with a heating pipe network or a building heating terminal.
6. The intelligent heating station control prediction system based on the machine learning algorithm as claimed in claim 2, wherein the load prediction model module based on the machine learning algorithm comprises data governance, model training, model parameter optimization, and predicted value output;
the model training specifically comprises the following steps:
step (1.1), obtaining sample data: the sample data comprises secondary temperature supply historical data, outdoor air temperature historical data, first 3 x 24h secondary temperature supply historical data and 3 x 24h outdoor air temperature historical data;
step (1.2), sample data cleaning: cleaning and treating the sample data obtained in the step (1), removing invalid or unreasonable data, mending and leaking missing data, and performing data normalization treatment;
step (1.3), selecting characteristic engineering: selecting an outdoor air temperature historical value, the previous 3 × 24h outdoor air temperature historical value and the previous 3 × 24h secondary side water supply temperature historical value as characteristic projects;
the model parameter optimization comprises the following steps:
step (2.1), parameter tuning: training the model and carrying out related parameter tuning to prevent over-fitting and under-fitting;
step (2.2), error analysis: and (3) model verification and error analysis, namely performing relevant verification and error analysis on the model by using the test set data.
7. The intelligent heating room temperature control system based on machine learning algorithm as claimed in claim 6,
the predicted value output module comprises the future 3h outdoor air temperature, the future 3h outdoor relative humidity, the future 3h indoor temperature set value, the first 24h outdoor air temperature, the first 24h outdoor relative humidity, the first 24h indoor water temperature and the first 24h indoor temperature.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110836982.8A CN113606649A (en) | 2021-07-23 | 2021-07-23 | Intelligent heat supply station control prediction system based on machine learning algorithm |
| ZA2022/07637A ZA202207637B (en) | 2021-07-23 | 2022-07-11 | Intelligent heat supply station control prediction system based on machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110836982.8A CN113606649A (en) | 2021-07-23 | 2021-07-23 | Intelligent heat supply station control prediction system based on machine learning algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113606649A true CN113606649A (en) | 2021-11-05 |
Family
ID=78305285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110836982.8A Pending CN113606649A (en) | 2021-07-23 | 2021-07-23 | Intelligent heat supply station control prediction system based on machine learning algorithm |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113606649A (en) |
| ZA (1) | ZA202207637B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114484584A (en) * | 2022-01-20 | 2022-05-13 | 国电投峰和新能源科技(河北)有限公司 | Heat supply control method and system based on offline reinforcement learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104791903A (en) * | 2015-04-30 | 2015-07-22 | 北京上庄燃气热电有限公司 | Intelligent heating network dispatching system |
| CN108734330A (en) * | 2017-04-24 | 2018-11-02 | 北京京东尚科信息技术有限公司 | Data processing method and device |
| US20190024928A1 (en) * | 2017-07-20 | 2019-01-24 | Carrier Corporation | Hvac system including energy analytics engine |
| CN109740787A (en) * | 2018-11-20 | 2019-05-10 | 第四范式（北京）技术有限公司 | Training Building air conditioning load prediction model and the method and apparatus predicted with it |
| CN110617549A (en) * | 2018-12-17 | 2019-12-27 | 南京国之鑫科技有限公司 | Heating installation wisdom energy-saving control system based on high in clouds |
-
2021
- 2021-07-23 CN CN202110836982.8A patent/CN113606649A/en active Pending
-
2022
- 2022-07-11 ZA ZA2022/07637A patent/ZA202207637B/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104791903A (en) * | 2015-04-30 | 2015-07-22 | 北京上庄燃气热电有限公司 | Intelligent heating network dispatching system |
| CN108734330A (en) * | 2017-04-24 | 2018-11-02 | 北京京东尚科信息技术有限公司 | Data processing method and device |
| US20190024928A1 (en) * | 2017-07-20 | 2019-01-24 | Carrier Corporation | Hvac system including energy analytics engine |
| CN109740787A (en) * | 2018-11-20 | 2019-05-10 | 第四范式（北京）技术有限公司 | Training Building air conditioning load prediction model and the method and apparatus predicted with it |
| CN110617549A (en) * | 2018-12-17 | 2019-12-27 | 南京国之鑫科技有限公司 | Heating installation wisdom energy-saving control system based on high in clouds |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114484584A (en) * | 2022-01-20 | 2022-05-13 | 国电投峰和新能源科技(河北)有限公司 | Heat supply control method and system based on offline reinforcement learning |
| CN114484584B (en) * | 2022-01-20 | 2022-11-11 | 国电投峰和新能源科技(河北)有限公司 | Heat supply control method and system based on offline reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| ZA202207637B (en) | 2022-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657031B (en) | Heat supply dispatching automation realization method, system and platform based on digital twin | |
| CN102360181B (en) | Low-temperature heat real-time optimization system based on general algorithm sequential quadratic programming (GA-SQP) mixed optimization strategy | |
| CN114383299B (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN112093025B (en) | Control system and control method for variable air volume air distributor air valve | |
| CN115220351B (en) | Intelligent energy-saving optimization control method for building air conditioning system based on cloud side end | |
| CN112413831A (en) | Energy-saving control system and method for central air conditioner | |
| CN103453580A (en) | Integrated and intelligent control method for heat exchange station | |
| CN113778215A (en) | Method for realizing data center PUE prediction and consumption reduction strategy based on big data | |
| CN113606649A (en) | Intelligent heat supply station control prediction system based on machine learning algorithm | |
| CN113606650B (en) | Intelligent heat supply room temperature regulation and control system based on machine learning algorithm | |
| CN115235050A (en) | Simulation method and device for energy-saving strategy of central air-conditioning water chilling unit | |
| CN117873237A (en) | Unmanned archive warehouse intelligent environment regulation and control system and method | |
| CN113535233A (en) | Artificial intelligence system for heating and ventilation cloud edge cooperation | |
| CN113587203A (en) | Multi-module combined control solar-heat pump composite heat collection system based on PLC | |
| CN116307024A (en) | Regional heating heat load prediction method | |
| CN113219897A (en) | Cold and heat combined supply intelligent regulation and control system and method based on big data and artificial intelligence | |
| CN114114995A (en) | A debug system for data center air conditioning system | |
| CN112984617A (en) | Constant heating two-network temperature supply one-network temperature control valve opening adjusting method based on artificial intelligence | |
| CN113112095A (en) | Multi-mode multi-heat supply unit load real-time optimization scheduling method and management system | |
| CN112432269A (en) | Method and system for optimizing set value of pressure difference of refrigerating water pump of refrigerating room | |
| CN114754396B (en) | Intelligent algorithm optimized central heating system and method for thermal power plant | |
| CN116258049A (en) | Indoor thermal environment intelligent prediction control method of modularized air conditioning system | |
| AU2021103181A4 (en) | Air Conditioning Load Forecasting Method Based on Artificial Intelligence | |
| CN110701029B (en) | Air compressor set allocation system and method based on pressure track prediction and pipe network pressure loss | |
| Qi et al. | Application of artificial intelligence control in the control system of cooling and heating energy stations |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211105 |