Heat transfer heat supply control method and heat supply system based on intelligent heat recovery control

Abstract

The invention provides a heat transfer heat supply control method and a heat supply system based on intelligent heat recovery control, and the method comprises the steps: independently reporting the real-time working condition data Pi of a heat exchanger system through an IOT communication module disposed in each heat exchanger system of the heat supply system; a real-time monitoring data set Si of the heat exchanger system is constructed in combination with the current heat supply system operation parameter C; and the AI model monitors and identifies the operation characteristics of the heat supply system and the heat exchange working condition characteristics in the Si, and a corresponding heat exchanger heat control strategy is output in a matched mode. The heat exchanger heat control strategy is subsequently issued and executed to the heat exchanger system. Therefore, the working conditions of the heat supply system and the heat exchanger system can be combined, a corresponding heat exchanger heat control strategy is formulated through the AI model and issued for execution, remote and intelligent geothermal control is achieved, operation control of the heat exchanger system is dynamically supervised and adjusted, the heat recovery efficiency of the heat exchanger is prevented from being reduced, the working condition maintenance period is shortened, and the working condition maintenance efficiency is improved. And unfavorable supervision is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of heating systems, and in particular to a heat transfer heating control method based on intelligent heat recovery control, a heating system, an electronic device and a computer-readable storage medium. Background Art

[0002] The heating system is composed of multiple systems, including the air intake system, electronic control system, power system, pipeline system, separation system, cooling system, sound insulation system and heat recovery system of the heating system. The air intake system is composed of air filter assembly, air intake hose, air intake valve and other parts, which are responsible for the intake and preliminary treatment of air. The electronic control system is composed of computer version, emergency stop button and other parts, which can monitor the operation data of the machine in real time. The power system includes screw main engine, drive motor, etc., which is the main power source of the equipment. The pipeline system is composed of oil and gas pipes, hot oil pipes, etc., which connect various systems to form a closed loop. The separation system is composed of oil and gas barrels, drain valves, etc., which are used for oil and gas separation. The cooling system is composed of plate-fin coolers, etc., which affects the efficiency and life of the machine. The sound insulation system is composed of chassis, brackets and other parts, which can reduce noise and beautify the equipment. The heat recovery system of the heating system can recover the waste heat generated by the heating system during operation and convert it into usable heat energy, realizing the efficient recovery and utilization of waste heat.

[0003] The heat exchanger is the core component of the waste heat recovery system of the heating system. Its function is to efficiently transfer the heat generated by the heating system to the circulating medium.

[0004] The heating system generates a lot of heat during operation, and the heat is mainly generated from the following aspects: The first is the compression process. When air is compressed inside the compressor, its temperature will rise significantly. This is because under the action of external force, the molecular potential energy of compressed air is converted into molecular kinetic energy, the molecular kinetic energy increases, the molecular thermal motion is intense, and thus the molecular temperature rises.

[0005] The second is mechanical friction. The mechanical parts inside the heating system will generate friction heat during operation. For example, the spindle will generate friction with the bearing during operation, causing the spindle temperature to rise. This part of the heat will be carried away by the lubricating oil in the process of lubricating the running parts, thereby increasing the temperature of the lubricating oil.

[0006] The third is the heat generated by the motor. The motor that drives the heating system also generates heat when it is working.

[0007] In the traditional way, it mainly relies on There are several main methods for air compression heat recovery: The first is the hot water recovery system. It includes direct hot water recovery and indirect hot water recovery. Direct hot water recovery is to use the hot water in the cooling system of the heating system directly for occasions where hot water is needed, such as heating, bathing, cleaning, etc. Indirect hot water recovery is to transfer the heat generated by the heating system to water through a heat exchanger to form hot water for use.

[0008] The second is the steam recovery system. The heat generated by the heating system is used to generate steam through a heat exchanger, and the steam can be used in industrial production processes such as heating, drying, distillation, etc.

[0009] The third is the heating system. Using the waste heat from the heating system for heating buildings, especially in winter, can significantly reduce the energy consumption of the heating system.

[0010] However, these traditional compressed air heat recovery technologies also have some application disadvantages: The efficiency of heat recovery is affected by equipment performance and usage conditions. When converting the heat energy generated by the heating system into other usable energy, there will always be a certain amount of energy loss. When recovering the waste heat in the future, it is necessary to manually calculate and take into account the equipment performance and environmental parameters of the heat exchanger system of the heating system to recommend a suitable heat exchanger thermal control strategy. Manual calculations need to take into account many factors that affect the thermal control of the heat exchanger, which is computationally intensive and inefficient. In addition, the existing heating system equipment combinations are widely used. A heating system may involve several heat exchanger systems, and the administrator can only monitor manually, and cannot achieve remote supervision and intelligent management. It takes a long time to maintain and update the thermal control management program of the heat exchanger system, and it is impossible to dynamically supervise and adjust the operation control of the heat exchanger system (because of long-term operation, the original setting program will reduce the heat recovery efficiency due to system factors, and regular maintenance programs are required). Therefore, the operating maintenance cycle is inefficient and easily leads to unfavorable supervision.

[0011] In addition, choosing the right heat recovery device and control system is the key to the heat recovery technology of the heating system. This requires considering multiple factors such as the model of the heating system, working conditions, heat recovery efficiency, and compatibility of the equipment. Because different heating systems may produce different waste heat characteristics, the design of the heat recovery device and the configuration of the control system need to be tailored to ensure the best waste heat recovery effect. In traditional compressed air heat recovery technology, the configuration of the heat exchanger system is usually configured through on-site verification, so a lot of verification time costs are required to match the heat exchanger system with the heating system until the heat exchanger system with suitable parameters is finally debugged for the heating system. Therefore, on-site configuration and debugging are slow and delay heat recovery efficiency. Summary of the invention

[0012] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a heat transfer heating control method based on intelligent heat recovery control is provided, the method is implemented by an electronic device, and the method includes: S1. Deploy an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background of the heating system; S2, reading the current heating system operating parameter C through the heating system monitoring background, and constructing the real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); S3, inputting the real-time monitoring data set Si into a preset thermal control AI monitoring model, wherein the thermal control AI monitoring model respectively identifies the heating system operation characteristics and heat exchange working condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operation characteristics and heat exchange working condition characteristics; S4, binding the heat exchanger thermal control strategy with the corresponding heat exchanger system, and sending it to the corresponding heat exchanger system by the heating system monitoring background; S5, the heat exchanger system receives the heat exchanger thermal control strategy, responds to and executes the thermal control instructions in the heat exchanger thermal control strategy, and reports the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; S6. Log in to the monitoring background of the heating system through the management terminal, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger.

[0013] Preferably, in step S1, after deploying an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background of the heating system, it also includes: The heating system monitoring backend sends a configuration sampling instruction to the industrial computer of the heating system; The industrial computer executes the configuration sampling instruction, generates a corresponding configuration file collection instruction and sends it to the MCU of the heat exchanger system; The MCU responds to the configuration file collection instruction and feeds back the configuration file of the IOT communication module of the heat exchanger system to the industrial computer; The industrial computer reports the configuration file and feeds it back to the heating system monitoring background; The heating system monitoring background parses the configuration file, obtains the data format and data communication address supported by the heat exchanger system, and issues a communication instruction to the IOT communication module of the heat exchanger system; The IOT communication module of the heat exchanger system responds to the communication instruction and makes feedback, thereby establishing an IOT communication channel between the heat exchanger system and the heating system monitoring background.

[0014] Preferably, the S2, reading the current heating system operating parameter C through the heating system monitoring background, and building a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi), including: The monitoring background of the heating system simultaneously sends working condition sampling instructions to the industrial computer of the heating system and the MCU of the heat exchanger system; The industrial computer executes the working condition sampling instruction, collects the current heating system operating parameter C of the heating system and reports it to the heating system monitoring background; The IOT communication module of the heat exchanger system receives and forwards the working condition sampling instruction to the MCU of the heat exchanger system, and the MCU executes the working condition sampling instruction, collects the real-time working condition data Pi of the heat exchanger system and forwards it to the IOT communication module, and the IOT communication module of the heat exchanger system reports the real-time working condition data Pi to the monitoring background of the heating system; The heating system monitoring background records the current heating system operating parameters C and the real-time operating data Pi corresponding to the heat exchanger system, and generates the real-time monitoring data set Si corresponding to the heat exchanger system: Si (C, Pi).

[0015] Preferably, the method for generating the thermal control AI monitoring model comprises: Collecting historical thermal control big data of the heating system, including several historical operation data of the heating system and historical operating data of each type of the heat exchanger system, wherein the historical operation data of the heating system includes the model, environmental parameters, operation mode and operating information and thermal efficiency value of the heating system; the historical operating data includes version information of each type of the heat exchanger system and temperature, pressure and flow working data of cooling water / cooling oil / or other heat exchange media related to thermal control, wherein the version information is obtained by parsing the configuration file of the heat exchanger system; Performing feature engineering on the historical thermal control big data of the heating system, respectively extracting the heating system operation features in the historical operation data of the heating system under the corresponding operation mode and the heat exchange operating condition features in the historical operating condition data, wherein the heating system operation features include the operating condition feature values ​​of the heating system of the corresponding model, and the heat exchange operating condition features include the thermal control parameter features of the heat exchanger system of the corresponding version number; Count the heat exchange characteristics of the heating system under each operation mode: {heating system operation characteristics, heat exchange condition characteristics}, and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model, perform feature training and learning on the heat exchange characteristics of the heating system in each mode, and generate the thermal control AI monitoring model; The recognition performance of the thermal control AI monitoring model was verified using the transport validation set: If the verification is successful, the thermal control AI monitoring model is deployed in the heating system monitoring background and put into use; If the verification fails, repeat the above steps to rebuild the thermal control AI monitoring model.

[0016] On the other hand, a heating system is provided, the heating system is used to implement the above-mentioned heat transfer heating control method based on intelligent heat recovery control, and the system comprises: IOT communication module, used to report the real-time working condition data Pi of the heat exchanger system to the heating system monitoring background; The heating system monitoring backend is used to read the current heating system operating parameter C, and to construct a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); and, to input the real-time monitoring data set Si into a preset thermal control AI monitoring model, and the thermal control AI monitoring model respectively identifies the heating system operating characteristics and heat exchange operating condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operating characteristics and heat exchange operating condition characteristics; and, to bind the heat exchanger thermal control strategy to the corresponding heat exchanger system, and to send it to the corresponding heat exchanger system by the heating system monitoring backend; A heat exchanger system, used for receiving the heat exchanger thermal control strategy, responding to and executing the thermal control instructions in the heat exchanger thermal control strategy, and reporting the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; The management terminal is used to log in to the monitoring background of the heating system, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger; The heat exchanger system is connected to the heating system monitoring background communication through the IOT communication module; The management end is communicatively connected with the heating system monitoring backend.

[0017] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned heat transfer heating control methods based on intelligent heat recovery control is implemented.

[0018] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned heat transfer heating control methods based on intelligent heat recovery control.

[0019] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention adopts a remote intelligent monitoring method, by deploying an IOT communication module in each set of heat exchanger systems in the heating system, which is used to separately report the real-time operating data Pi of the heat exchanger system, and the background reads the current heating system operating parameters C, and combines each of the real-time operating data Pi to build a real-time monitoring data set Si of the heat exchanger system; then the real-time monitoring data set Si is input into a preset thermal control AI monitoring model, and the thermal control AI monitoring model respectively identifies the heating system operating characteristics and heat exchange operating characteristics in the real-time monitoring data set Si, and matches and outputs the heat exchanger thermal control strategy corresponding to the heating system operating characteristics and heat exchange operating characteristics. Subsequently, the heat exchanger thermal control strategy is issued to the heat exchanger system and executed. Therefore, it is possible to combine the heating system operating data and the real-time operating data of each heat exchanger system, and the AI ​​model can intelligently formulate the corresponding heat exchanger thermal control strategy for it and issue it for execution, so as to realize remote and intelligent geothermal control, dynamically supervise and adjust the operation control of the heat exchanger system, avoid reducing the heat recovery efficiency of the heat exchanger, improve the operating maintenance cycle and efficiency, and avoid causing unfavorable supervision.

[0020] When the AI ​​predicts the strategy, the present invention can also combine the model, working conditions and configuration information of the heating system to perform strategy matching prediction. Therefore, it is possible to perform customized strategy matching according to the parameters of different heating systems and heat recovery devices to ensure the best waste heat recovery effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1This is a flow chart of a heat transfer heating control method based on intelligent heat recovery control provided by an embodiment of the present invention; Figure 2 is a block diagram of a heating system provided by an embodiment of the present invention; Figure 3 It is a logical schematic diagram of a model training provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0024] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0025] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0026] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0027] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0028] like Figure 2 As shown in the figure, the traditional heating system is mainly controlled and managed by the industrial computer. The administrator operates the heat exchange system of the heating system through the setting program of the industrial computer, so regular maintenance is required. The industrial computer reads the operation data of the heating system, and then parses and analyzes the heat exchange condition data in the data file, which is relatively complicated and cannot be monitored independently. Because the existing heating system involves a variety of heat exchange systems, such as heat recovery of cooling oil, heat recovery of cooling water, etc., there are many heat source recovery parts, and the heat recovery involved is more complicated.

[0029] Therefore, the present invention proposes a method of independently supervising the heat exchange system, using an IOT module for independent communication, reporting the working condition data of the heat exchange system to the background, and reading the parameters of the industrial computer of the heating system at the same time, so as to obtain the real-time working condition data Pi of each heat exchange system and the current operating parameters C of the heating system, and construct the real-time monitoring data set Si of the heat exchange system in combination with the real-time working condition data Pi: Si (C, Pi). Subsequently, the working condition of each heat exchange system is predicted and the corresponding thermal control strategy is recommended, and the corresponding thermal control is implemented for it, so as to realize independent thermal control under the operation of the heating system, achieve remote and intelligent geothermal supervision and control effect, supervise and control separately, and reduce the control complexity of heat recovery.

[0030] The embodiment of the present invention provides a heat transfer heating control method based on intelligent heat recovery control, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The process flow chart of the heat transfer heating control method based on intelligent heat recovery control is shown, and the process flow of the method may include the following steps: S1. Deploy an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background (host computer, referred to as the background) of the heating system; S2, reading the current heating system operating parameter C through the heating system monitoring background, and constructing the real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); S3, inputting the real-time monitoring data set Si into a preset thermal control AI monitoring model, wherein the thermal control AI monitoring model respectively identifies the heating system operation characteristics and heat exchange working condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operation characteristics and heat exchange working condition characteristics; S4, binding the heat exchanger thermal control strategy with the corresponding heat exchanger system, and sending it to the corresponding heat exchanger system by the heating system monitoring background; S5, the heat exchanger system receives the heat exchanger thermal control strategy, responds to and executes the thermal control instructions in the heat exchanger thermal control strategy, and reports the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; S6. Log in to the monitoring background of the heating system through the management terminal, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger.

[0031] Combined with Figure 2 As shown, the heating system is controlled by an industrial computer and communicates with the background control.

[0032] The heating system may include heat exchanger systems such as cooling oil or cooling water. The present invention deploys an IOT communication module in each heat exchanger system to report the operating data of each heat exchanger system separately, thereby reducing the pressure on the industrial computer.

[0033] The IoT communication module is deployed in the heat exchanger system of the heating system to realize the separate reporting of the real-time working condition data Pi to the monitoring background of the heating system. The specific IoT communication deployment plan and functions are as follows: ‌1. Deployment plan‌ ‌Select IoT communication module‌: Select IoT communication modules that support low power consumption, long-distance transmission, and high stability, such as NB-IoT, LoRa, 4G / 5G modules, etc., and make selections based on the site environment and transmission requirements.

[0034] Ensure that the module supports standard communication protocols, such as MQTT, CoAP, etc., to facilitate data transmission with the heating system monitoring background.

[0035] ‌Module Integration and Connection‌: Integrate the IoT communication module into the control circuit of the heat exchanger system, or connect it to the controller of the heat exchanger system through an external interface.

[0036] Configure the module's network parameters, such as APN, IP address, port number, etc., to ensure that the module can access the network and send data normally.

[0037] ‌Data collection and reporting‌: A data acquisition program is written in the controller of the heat exchanger system to collect the working status, temperature, pressure and other working condition data Pi of the heat exchanger in real time.

[0038] The collected data is packaged and sent to the heating system monitoring background through the IoT communication module according to the preset communication protocol.

[0039] ‌Safety and Protection‌: Perform security configuration on the IoT communication module, such as setting up encrypted transmission and access control, to ensure the security of data transmission.

[0040] Protective facilities such as waterproofing, dustproofing, and lightning protection are installed on site at the heat exchanger system to protect the IoT communication module from environmental interference and damage.

[0041] ‌2. Function Implementation‌ ‌Real-time data reporting‌: The IoT communication module can report the operating data Pi of the heat exchanger system to the heating system monitoring background in real time, including key parameters such as temperature, pressure, and flow.

[0042] The background can receive and display this data in real time, providing timely monitoring information for operation and maintenance personnel.

[0043] Remote monitoring and diagnosis: The heating system monitoring background can remotely monitor the heat exchanger system and view the system's working status and performance parameters in real time.

[0044] Through data analysis, the background can promptly detect system anomalies or failures, conduct remote diagnosis, and provide maintenance guidance to operation and maintenance personnel.

[0045] ‌Warning and alarm‌: When the operating data Pi of the heat exchanger system exceeds the preset threshold, the IoT communication module can trigger a warning or alarm signal and send the signal to the heating system monitoring background.

[0046] The background can immediately notify the operation and maintenance personnel to handle it to avoid system failure or damage.

[0047] ‌Data Recording and Analysis‌: The heating system monitoring background can record the historical operating data Pi of the heat exchanger system and form data reports or curve graphs.

[0048] Operation and maintenance personnel can understand the system's operating trends and performance changes by analyzing these data, providing data support for system optimization and maintenance.

[0049] The specific IOT communication module to be configured is determined by the user. Each heat exchanger system has an MCU control chip to perform logical control and management of the heat exchanger system, such as controlling the internal sensors of each heat exchanger system (the system has its own collection ports for various working conditions, such as sensors and MCU to record system parameters, configuration files, etc. of each system, and the system has its own memory to cache data, etc.) to work and sample, collect the corresponding working condition data, process it, and then send it to the IOT communication module of the heat exchanger system, so that the IOT communication module can report the data to the background. ‌ Preferably, in step S1, after deploying an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background of the heating system, it also includes: The heating system monitoring backend sends a configuration sampling instruction to the industrial computer of the heating system; The industrial computer executes the configuration sampling instruction, generates a corresponding configuration file collection instruction and sends it to the MCU of the heat exchanger system; The MCU responds to the configuration file collection instruction and feeds back the configuration file of the IOT communication module of the heat exchanger system to the industrial computer; The industrial computer reports the configuration file and feeds it back to the heating system monitoring background; The heating system monitoring background parses the configuration file, obtains the data format and data communication address supported by the heat exchanger system, and issues a communication instruction to the IOT communication module of the heat exchanger system; The IOT communication module of the heat exchanger system responds to the communication instruction and makes feedback, thereby establishing an IOT communication channel between the heat exchanger system and the heating system monitoring background.

[0050] After deploying the above-mentioned IOT communication modules, the background must first establish communication with the IOT communication modules of each system and perform data communication according to the data formats supported by each system. Specifically: First, the background collects the configuration files of each system through the industrial computer and reports them to the background, so that the background can interpret the configuration information of each system through the industrial computer and activate communication.

[0051] Secondly, the MCU of each system reads the configuration information of each system and sends it to the industrial computer for uploading. The process steps are as follows: ‌Send configuration sampling instructions‌: ‌Heating system monitoring background‌: As a central control platform, it first sends a configuration sampling instruction to the ‌industrial control computer‌ (industrial control computer) of the heating system. The purpose of this instruction is to require the industrial control computer to start collecting configuration information of the heat exchanger system IOT communication module.

[0052] Generate and send configuration file collection instructions: ‌Industrial Computer‌: After receiving the configuration sampling instruction from the background, the industrial computer will generate a specific ‌configuration file collection instruction‌. This instruction is specifically used to request the ‌MCU‌ (microcontroller) of the heat exchanger system to provide the configuration file of the IOT communication module.

[0053] ‌Send to MCU‌: The industrial computer sends the configuration file collection instruction to the MCU of the heat exchanger system through the communication interface.

[0054] ‌Response and Feedback Configuration File‌ : ‌MCU‌: After receiving the configuration file collection instruction, the MCU will read the configuration file of the heat exchanger system IOT communication module and package it into a data packet.

[0055] ‌Feedback to the industrial computer‌: The MCU sends the configuration file data packet back to the industrial computer through the communication interface.

[0056] ‌Submit configuration files to the backend‌: ‌Industrial Computer‌: After receiving the configuration file feedback from the MCU, the industrial computer reports it to the heating system monitoring background.

[0057] ‌Parsing configuration files‌: ‌Heating system monitoring background‌: After receiving the configuration file reported by the industrial computer, the background will parse it. The purpose of the analysis is to extract the data format supported by the heat exchanger system (such as the representation of temperature, pressure and other data) and data communication address (such as the IP address and port number of the IOT communication module).

[0058] ‌Issuing communication commands‌: ‌Heating system monitoring background‌: Based on the parsed data format and data communication address, the background will send a communication instruction to the IOT communication module of the heat exchanger system. This instruction may require the module to start uploading real-time data or perform other types of communication operations.

[0059] ‌Respond to communication instructions and establish communication channels‌: ‌IoT communication module of the heat exchanger system‌: After receiving the communication instructions from the background, the module will respond according to the instructions and may exchange further data with the background.

[0060] ‌Establishing a communication channel‌: Through this series of command exchanges and responses, a stable IOT communication channel is established between the heat exchanger system and the heating system monitoring background. This channel can be used for operations such as uploading real-time data and issuing control commands.

[0061] The above method is to realize the remote configuration and monitoring of the heat exchanger system of the heating system. Through IOT technology, the monitoring background of the heating system can obtain the working status and data of the heat exchanger system in real time, and remotely monitor and manage it. This can not only improve the operating efficiency of the heating system, but also timely discover and deal with potential problems to ensure the stable operation of the heating system. At the same time, this IOT-based remote monitoring method can also reduce the cost and risk of manual maintenance.

[0062] Because the working premise of each heat exchanger system needs to be based on the operating status of the heating system, the administrator can adjust and maintain the thermal control parameters of each heat exchanger system only when he knows the operating status of the heating system.

[0063] The present invention uses AI to monitor and manage the thermal control strategies of various heat exchanger systems through a host computer, and dynamically adjusts the thermal control strategies of corresponding heat exchanger systems by combining the operating data of the heating system and the working conditions of the heat exchanger system.

[0064] Therefore, each time sampling is taken, it is necessary to combine the operating parameters of the heating system and the operating data of the corresponding heat exchanger system as the AI ​​prediction basis for each heat exchanger system, so as to accurately predict and adjust the thermal control maintenance strategy of the heat exchanger system.

[0065] Preferably, the S2, reading the current heating system operating parameter C through the heating system monitoring background, and building a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi), including: The monitoring background of the heating system simultaneously sends working condition sampling instructions to the industrial computer of the heating system and the MCU of the heat exchanger system; The industrial computer executes the working condition sampling instruction, collects the current heating system operating parameter C of the heating system and reports it to the heating system monitoring background; The IOT communication module of the heat exchanger system receives and forwards the working condition sampling instruction to the MCU of the heat exchanger system, and the MCU executes the working condition sampling instruction, collects the real-time working condition data Pi of the heat exchanger system and forwards it to the IOT communication module, and the IOT communication module of the heat exchanger system reports the real-time working condition data Pi to the monitoring background of the heating system; The heating system monitoring background records the current heating system operating parameters C and the real-time operating data Pi corresponding to the heat exchanger system, and generates the real-time monitoring data set Si corresponding to the heat exchanger system: Si (C, Pi).

[0066] The thermal control AI monitoring model (AI model or model) needs to predict the thermal control strategy of the heat exchanger system corresponding to the mode and configuration information based on the current operating mode and operating parameters of the heating system, combined with the configuration information of the heat exchanger system. Because the heating system may produce different waste heat characteristics due to multiple factors such as different models, working conditions, heat recovery efficiency, and equipment compatibility. Therefore, the design of the heat recovery device and the configuration of the control system need to be tailored to ensure the best waste heat recovery effect. In traditional compressed air heat recovery technology, the configuration of the heat exchanger system is usually configured through on-site verification, so a lot of verification time cost is required to match the heat exchanger system with the heating system. Therefore, when the present invention is training the model, the model of the heating system under each operating mode and its historical working conditions and the version information of the heat exchanger system (the version information includes the version number, the maximum thermal control threshold supported by the heat exchange system, etc., because it involves different versions of control systems, the background needs to monitor its version features and provide the heating control parameters under the corresponding version) and the temperature, pressure and flow rate of cooling water / cooling oil or other heat exchange media related to thermal control, and the working data are extracted and trained respectively, so that the model can predict the thermal control strategy of the current version of the heat exchanger system under the current operating mode, that is, the temperature, pressure and flow rate of cooling water / cooling oil or other heat exchange media related to thermal control. In this way, the model can automatically predict the adaptation maintenance strategy under the corresponding mode and configuration according to the differences in the operating mode and the configuration of the equipment / system, and automatically adjust the thermal control strategy (including the control parameters of each control object in the heat exchange system) according to the working conditions under each mode and the configuration information of the equipment / system. For example, the thermal control parameters of the cooling oil heat recovery system under the empty / load mode.

[0067] Through the above model prediction, it is possible to perform thermal control adaptation adjustment and maintenance on each heat exchange system under the operating conditions and configuration differences in the current mode.

[0068] When collecting data sets, the process steps are as follows: Issue the working condition sampling instruction: ‌Heating system monitoring background‌: Send working condition sampling instructions to the ‌industrial computer‌ of the heating system and the ‌MCU‌ of the heat exchanger system at the same time. The purpose of this instruction is to require both to collect the current operating parameters of the heating system and the real-time working condition data of the heat exchanger system respectively.

[0069] ‌The industrial computer collects and reports operating parameters‌: Industrial computer: After receiving the operating condition sampling instruction, the industrial computer executes the instruction and collects the current operating parameters C of the heating system (such as pressure, temperature, speed, etc.).

[0070] ‌Report to the monitoring background‌: The industrial computer reports the collected operating parameters C to the heating system monitoring background through the communication network.

[0071] ‌The heat exchanger system collects and reports operating data‌: ‌IOT communication module receives instructions‌: The ‌IOT communication module‌ of the heat exchanger system receives the operating condition sampling instructions issued by the heating system monitoring background.

[0072] ‌Forward to MCU‌: The IOT communication module forwards the command to the ‌MCU‌ of the heat exchanger system.

[0073] ‌MCU executes instructions‌: After receiving the instructions, the MCU executes the operating condition sampling operation to collect the real-time operating condition data Pi (such as temperature, pressure, flow, etc.) of the heat exchanger system.

[0074] ‌Forward to IOT communication module‌: MCU forwards the collected working condition data Pi to the IOT communication module.

[0075] ‌Report to the monitoring background‌: The IOT communication module reports the operating condition data Pi to the heating system monitoring background through the communication network.

[0076] ‌Build and generate real-time monitoring data set‌: ‌Heating system monitoring background‌: After receiving the operating parameters C reported by the industrial computer and the operating data Pi reported by the heat exchanger system, the monitoring background associates the two sets of data to form a real-time monitoring data set Si for the corresponding heat exchanger system. The data set Si contains the current operating parameters C of the heating system and the real-time operating data Pi of the heat exchanger system at the corresponding moment, that is, Si (C, Pi).

[0077] By collecting the operating parameters of the heating system and the operating data of the heat exchanger system at the same time and associating them to form a real-time monitoring data set, the heating system monitoring background can understand the working status of the heating system and the heat exchanger system more comprehensively and accurately. This helps to discover and deal with potential problems in a timely manner, optimize the operating efficiency of the heating system, reduce maintenance costs, and improve production safety.

[0078] In addition, this real-time monitoring and data association method also provides strong support for subsequent data analysis, fault prediction and intelligent maintenance. Through in-depth analysis of the real-time monitoring data set Si, valuable information such as the working rules and abnormal modes of the heating system and heat exchanger system can be mined, providing a decision-making basis for the intelligent management and optimization of equipment.

[0079] Because, under different operating modes, the heat exchange systems in different parts will have different thermal control parameters of various thermal control valves, switches and other equipment in the system when they reach the optimal heat recovery conditions (maximum heat recovery efficiency) due to their configurations (version information, including system version number, maximum temperature and humidity, pressure and flow that can be tolerated, and maximum thermal efficiency values ​​set under different operating modes) and their working conditions under the operating environment of the heating system. Therefore, this department uses feature analysis to identify the thermal control strategies (control operating parameters of different thermal control facilities) possessed by different heat exchange systems under different operating modes. Through feature engineering, we collect the heat exchange characteristics of the heating system under each operating mode and form a feature set for model training and construction of a thermal control AI monitoring model.

[0080] The basic model of the thermal control AI monitoring model here can use a convolutional neural network or other algorithm models. Here we use a random forest model (RF for short). The model architecture and application training of RF mainly include the following points: 1 Data preparation: Prepare a dataset for training, including features and labels. Features are variables used for prediction, while labels are the results that the model needs to predict.

[0081] Make sure the dataset is cleaned and preprocessed, including handling missing values, outliers, and standardizing features.

[0082] 2 Dataset division: Divide the prepared dataset into training set and validation set.

[0083] Cross-validation or hold-out methods are often used to partition the dataset to ensure that the model is validated on unseen data.

[0084] 3 Model selection: Select Random Forest as the model. Random Forest is an ensemble learning method that builds multiple decision trees to make predictions and then combines the results of multiple decision trees to get the final prediction result.

[0085] 4 Model training: The random forest model is trained using the training set.

[0086] During the training process, random forests randomly select features and samples to build multiple decision trees, and use voting or averaging to combine the results of multiple decision trees.

[0087] 5. Model tuning: Tune the trained model, including adjusting hyperparameters and optimizing model structure, to improve the performance and generalization ability of the model.

[0088] 6 Model Evaluation: Use the validation set to evaluate the trained model.

[0089] Indicators such as accuracy, precision, recall, and F1 value are usually used to evaluate the performance of the model.

[0090] 7 Model Application: When the model passes the evaluation and meets the requirements, it can be used for actual predictions.

[0091] In practical applications, attention should be paid to the deployment and monitoring of the model to ensure the continued performance of the model.

[0092] In addition, there are two key steps to pay attention to in the process of building a random forest: 1 Sampling: Random forest samples the rows and columns of the input data.

[0093] Row sampling: It uses a method with replacement, that is, there may be duplicate samples in the sampled sample set. Assuming that the input samples are N, then the sampled samples are also N. In this way, during training, the input samples of each tree are not all samples, thereby reducing the risk of overfitting.

[0094] Column sampling: Select m features from M features (m is much smaller than M). The recommended value of m is the square root of M.

[0095] 2 Complete Split: Use the complete split method to build a decision tree for the sampled data, so that a leaf node of the decision tree is either unable to continue splitting, or all samples in it point to the same category. Decision trees in random forests generally do not need to be pruned because the previous two random sampling processes have ensured randomness, thereby reducing the risk of overfitting.

[0096] Through the above steps, the training of the random forest model can be completed, and a model that can be used for actual prediction can be obtained.

[0097] like Figure 3 As shown, preferably, the method for generating the thermal control AI monitoring model includes: Collect historical thermal control big data of the heating system, including several historical operation data of the heating system and historical working condition data of each type of the heat exchanger system, wherein the historical operation data of the heating system includes the model (version number) of the heating system, environmental parameters (temperature and humidity, density of people in the heating area, loss coefficient of heat supply to the heating address, etc.), operation mode (type of working mode and pipeline operation pressure under the corresponding mode, control valve opening, heat release efficiency, rated heat release time and heat release, etc.) and working condition information (parameters of each device in the system) and thermal efficiency value; the historical working condition data includes version information of each type of the heat exchanger system and temperature, pressure and flow working data of cooling water / cooling oil / or other heat exchange media related to thermal control, wherein the version information is obtained by parsing the configuration file of the heat exchanger system; Performing feature engineering on the historical thermal control big data of the heating system, respectively extracting the heating system operation features in the historical operation data of the heating system under the corresponding operation mode and the heat exchange operating condition features in the historical operating condition data, wherein the heating system operation features include the operating condition feature values ​​of the heating system of the corresponding model, and the heat exchange operating condition features include the thermal control parameter features of the heat exchanger system of the corresponding version number; Count the heat exchange characteristics of the heating system under each operation mode: {heating system operation characteristics, heat exchange condition characteristics}, and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model, perform feature training and learning on the heat exchange characteristics of the heating system in each mode, and generate the thermal control AI monitoring model; The recognition performance of the thermal control AI monitoring model was verified using the transport validation set: If the verification is successful, the thermal control AI monitoring model is deployed in the heating system monitoring background and put into use; If the verification fails, repeat the above steps to rebuild the thermal control AI monitoring model.

[0098] Data collection can be done through historical industrial computer operation logs, etc. Data collection, processing, and feature engineering can be described as follows: 1. Collection of historical operation data of heating system : , N: total number of historical data samples; Model i: equipment model of the i-th heating system (categorical variable); Ei: Environmental parameter vector, including: Tamb: ambient temperature (°C); ∅ hum : Ambient humidity (%); P atm : atmospheric pressure (kPa); Mi: operating mode (such as heating / cooling / standby, discrete value); Gi: operating condition information (continuous variables such as load rate and operating time); ȵi: Thermal efficiency value (%).

[0099] 2. Heat exchanger historical operating data collection : , K: Total number of heat exchanger types; Version j: the version number obtained by parsing the configuration file (semantic encoding); X j : Heat exchange medium parameters, ; T j : Medium temperature (°C); P j : Medium pressure (kPa); : Medium volume flow rate (m 3 / s).

[0100] 3. Feature Engineering 3.1 Heating system operation feature extraction , represents the heating system feature extraction function (determined by the feature extraction algorithm adopted by the user), Represents the running feature dimension (usually composed of: model encoding length + environmental parameter dimension + mode encoding length + 1).

[0101] 3.2 Heat exchange condition feature extraction , The heat exchanger feature extraction function is identified (determined by the feature extraction algorithm selected by the user). Indicates the working condition feature dimension (consisting of version code length + medium parameter dimension).

[0102] 4. Statistics of related features: features under each operating mode are analyzed in the following way 4.1 Grouping by operating mode: in, represents the feature sample set under the operation mode m; 4.2 Clustering statistics based on features , represents statistical aggregation functions (such as mean, standard deviation), Indicates the mean value of system operation characteristics under mode m (users can count and calculate the mean value), The standard deviation of the system operation characteristics under the indicated mode ( (calculated by the user using the mean calculation method).

[0103] Through the above methods, data can be collected and feature engineering can be performed to provide a training data basis for model construction and improve model efficiency.

[0104] In addition to the above-mentioned feature engineering methods, algorithm models such as principal component analysis can also be used. For example: ‌ Steps for feature engineering (feature optimization) of historical thermal control big data of heating system using linear discriminant analysis (LDA) algorithm‌: ‌Data preparation and preprocessing‌: Collect and organize historical thermal control big data of the heating system to ensure that the data is complete and in a unified format.

[0105] The data is divided into two parts: historical operation data of the heating system and historical operating data of the heat exchanger system.

[0106] Clean the data, remove outliers, missing values, etc., to ensure data quality.

[0107] Standardize or normalize the data to eliminate dimensional differences between different features.

[0108] ‌Determine category labels‌: The data is tagged with categories based on the operating mode of the heating system and the version number of the heat exchanger system.

[0109] The category labels of the heating system operation data can be different operation modes, such as continuous operation, intermittent operation, etc.

[0110] The category labels of the heat exchanger operating condition data may be different heat exchanger system version numbers or thermal control states.

[0111] And apply LDA algorithm to extract features: ‌For historical operation data of heating system‌: Taking the operation mode as the category label, the LDA algorithm is used to extract features of the historical operation data of the heating system.

[0112] LDA will look for linear combination features that can maximize the ratio of between-class variance to within-class variance. These features are the operating characteristics of the heating system.

[0113] The extracted features should include the operating characteristic values ​​of the corresponding model of the heating system, such as the working pressure, speed, temperature, etc. in a specific mode.

[0114] When applying the LDA algorithm to extract the operating characteristic values ​​of the corresponding model of the heating system, we are actually looking for a set of linear transformations (or projection directions) so that the projected data has the maximum inter-class separability in the new space.

[0115] The role of LDA is to find the optimal linear combination of these feature values ​​in the new space for better classification or dimensionality reduction.

[0116] In practical applications, LDA is usually implemented through matrix operations and numerical optimization methods.

[0117] The objective function of LDA can be expressed as: , Among them, w is the projection direction to be found (or called weight vector), S Bis the inter-class scatter matrix, S W is the intra-class scatter matrix. Maximizing the objective function J(w) means finding the projection direction that maximizes the ratio of the between-class variance to the intra-class variance.

[0118] The inter-class scatter matrix S B and the intra-class scatter matrix S W They are defined as: , Where c is the number of categories, n i is the number of samples in the i-th class, μ i is the mean vector of the i-th class, μ is the mean vector of all samples, X i is the sample set of the i-th class.

[0119] The solution process of LDA usually involves eigenvalue decomposition or generalized eigenvalue decomposition, that is, solving the following equation: , Among them, λ is the eigenvalue and w is the corresponding eigenvector. In practical applications, the eigenvectors corresponding to the largest eigenvalues ​​are usually selected as the projection direction.

[0120] However, the extraction of the operating characteristic values ​​(such as working pressure, speed, and temperature) of a specific model of heating system is actually to directly select these features in the original data set rather than to calculate them through LDA. The role of LDA is to find the optimal linear combination based on these features for better classification or dimensionality reduction. Therefore, before applying LDA, it is necessary to determine which features are relevant (here they can be labeled by the administrator, or identified based on the aforementioned labeled data) and provide them as input data to the LDA algorithm.

[0121] The LDA algorithm is used to find the optimal linear combination of these eigenvalues ​​in the new space. In practical applications, it is necessary to first determine the relevant operating condition eigenvalues ​​and provide them as input data to the LDA algorithm for feature extraction and classification.

[0122] ‌For historical operating data of heat exchanger system‌: The version number of the heat exchanger system is used as the category label (or other appropriate labels are selected according to actual needs), and the LDA algorithm is used to extract features of the heat exchange operating condition data.

[0123] Similarly, LDA will look for linear combination features that can maximize the ratio of between-class variance to within-class variance. These features are the heat exchange condition characteristics.

[0124] The extracted features should include the thermal control parameter features of the heat exchanger system of the corresponding version number, such as the temperature, pressure, flow rate, etc. of the cooling medium.

[0125] ‌Feature Verification and Selection‌: The extracted features are verified to evaluate whether they can effectively distinguish different categories.

[0126] Cross-validation and leave-one-out methods can be used to evaluate the classification performance of features.

[0127] According to the evaluation results, those features with better classification performance are selected as the final feature set.

[0128] ‌Build a feature set for subsequent analysis‌: The extracted heating system operation characteristics and heat exchange condition characteristics are combined to form a complete feature set.

[0129] This feature set will be used as input data for subsequent model training to train thermal control AI monitoring models or other related models.

[0130] Through the above steps, the linear discriminant analysis (LDA) algorithm can be used to perform feature engineering on the historical thermal control big data of the heating system, extract features that have important distinguishing effects on the operation of the heating system and the heat exchange conditions, and provide high-quality data input for subsequent model training and analysis.

[0131] For RF model training, please understand it in conjunction with the conventional training steps of the above RF model. We will not go into details here.

[0132] The above configuration information can be written into the MCU embedded program in advance, and the MCU adopts, for example, the STM32 series microcontroller.

[0133] Figure 2 is a block diagram of a heating system according to an exemplary embodiment, the system is used for a heat transfer heating control method based on intelligent heat recovery control. Figure 2 On the other hand, a heating system is provided, the heating system is used to implement the above-mentioned heat transfer heating control method based on intelligent heat recovery control, the system comprising: IOT communication module, used to report the real-time working condition data Pi of the heat exchanger system to the heating system monitoring background; The heating system monitoring backend is used to read the current heating system operating parameter C, and to construct a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); and, to input the real-time monitoring data set Si into a preset thermal control AI monitoring model, and the thermal control AI monitoring model respectively identifies the heating system operating characteristics and heat exchange operating condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operating characteristics and heat exchange operating condition characteristics; and, to bind the heat exchanger thermal control strategy to the corresponding heat exchanger system, and to send it to the corresponding heat exchanger system by the heating system monitoring backend; A heat exchanger system, used for receiving the heat exchanger thermal control strategy, responding to and executing the thermal control instructions in the heat exchanger thermal control strategy, and reporting the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; The management terminal is used to log in to the monitoring background of the heating system, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger; The heat exchanger system is connected to the heating system monitoring background communication through the IOT communication module; The management end is communicatively connected with the heating system monitoring backend.

[0134] Please understand the main functional services of the above system and their interactive application methods in conjunction with the corresponding steps in the above method, and will not be repeated here.

[0135] Figure 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device may include the above Figure 3 Optionally, the electronic device 410 may include a first processor 2001 .

[0136] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0137] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0138] Combine the following Figure 4 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0139] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0140] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in FIG.

[0141] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 4 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0142] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0143] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0144] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0145] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0146] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0147] It should be noted that Figure 4 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0148] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the heat transfer heating control method based on intelligent heat recovery control described in the above method embodiment, and will not be repeated here.

[0149] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0150] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A heat transfer heating control method based on intelligent heat recovery control, characterized in that: The method comprises: S1. Deploy an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background of the heating system; S2, reading the current heating system operating parameter C through the heating system monitoring background, and constructing the real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); S3, inputting the real-time monitoring data set Si into a preset thermal control AI monitoring model, wherein the thermal control AI monitoring model respectively identifies the heating system operation characteristics and heat exchange working condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operation characteristics and heat exchange working condition characteristics; S4, binding the heat exchanger thermal control strategy with the corresponding heat exchanger system, and sending it to the corresponding heat exchanger system by the heating system monitoring background; S5, the heat exchanger system receives the heat exchanger thermal control strategy, responds to and executes the thermal control instructions in the heat exchanger thermal control strategy, and reports the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; S6. Log in to the monitoring background of the heating system through the management terminal, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger.

2. The heat transfer heating control method based on intelligent heat recovery control according to claim 1 is characterized in that: In step S1, after deploying an IOT communication module in at least one heat exchanger system of the heating system to separately report the real-time operating data Pi of the heat exchanger system to the monitoring background of the heating system, it also includes: The heating system monitoring backend sends a configuration sampling instruction to the industrial computer of the heating system; The industrial computer executes the configuration sampling instruction, generates a corresponding configuration file collection instruction and sends it to the MCU of the heat exchanger system; The MCU responds to the configuration file collection instruction and feeds back the configuration file of the IOT communication module of the heat exchanger system to the industrial computer; The industrial computer reports the configuration file and feeds it back to the heating system monitoring background; The heating system monitoring background parses the configuration file, obtains the data format and data communication address supported by the heat exchanger system, and issues a communication instruction to the IOT communication module of the heat exchanger system; The IOT communication module of the heat exchanger system responds to the communication instruction and makes feedback, thereby establishing an IOT communication channel between the heat exchanger system and the heating system monitoring background.

3. The heat transfer heating control method based on intelligent heat recovery control according to claim 1 is characterized in that: S2, reading the current heating system operating parameter C through the heating system monitoring background, and building a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi), including: The monitoring background of the heating system simultaneously sends working condition sampling instructions to the industrial computer of the heating system and the MCU of the heat exchanger system; The industrial computer executes the working condition sampling instruction, collects the current heating system operating parameter C of the heating system and reports it to the heating system monitoring background; The IOT communication module of the heat exchanger system receives and forwards the working condition sampling instruction to the MCU of the heat exchanger system, and the MCU executes the working condition sampling instruction, collects the real-time working condition data Pi of the heat exchanger system and forwards it to the IOT communication module, and the IOT communication module of the heat exchanger system reports the real-time working condition data Pi to the monitoring background of the heating system; The heating system monitoring background records the current heating system operating parameters C and the real-time operating data Pi corresponding to the heat exchanger system, and generates the real-time monitoring data set Si corresponding to the heat exchanger system: Si (C, Pi).

4. The heat transfer heating control method based on intelligent heat recovery control according to claim 3 is characterized in that: The method for generating the thermal control AI monitoring model comprises: Collecting historical thermal control big data of the heating system, including several historical operation data of the heating system and historical operating data of each type of the heat exchanger system, wherein the historical operation data of the heating system includes the model, environmental parameters, operation mode and operating information and thermal efficiency value of the heating system; the historical operating data includes version information of each type of the heat exchanger system and temperature, pressure and flow working data of cooling water / cooling oil / or other heat exchange media related to thermal control, wherein the version information is obtained by parsing the configuration file of the heat exchanger system; Performing feature engineering on the historical thermal control big data of the heating system, respectively extracting the heating system operation features in the historical operation data of the heating system under the corresponding operation mode and the heat exchange operating condition features in the historical operating condition data, wherein the heating system operation features include the operating condition feature values ​​of the heating system of the corresponding model, and the heat exchange operating condition features include the thermal control parameter features of the heat exchanger system of the corresponding version number; Count the heat exchange characteristics of the heating system under each operation mode: {heating system operation characteristics, heat exchange condition characteristics}, and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model, perform feature training and learning on the heat exchange characteristics of the heating system in each mode, and generate the thermal control AI monitoring model; The recognition performance of the thermal control AI monitoring model was verified using the transport validation set: If the verification is successful, the thermal control AI monitoring model is deployed in the heating system monitoring background and put into use; If the verification fails, repeat the above steps to rebuild the thermal control AI monitoring model.

5. A heating system, the heating system being used to implement the heat transfer heating control method based on intelligent heat recovery control as claimed in any one of claims 1 to 4, characterized in that: The system comprises: IOT communication module, used to report the real-time working condition data Pi of the heat exchanger system to the heating system monitoring background; The heating system monitoring backend is used to read the current heating system operating parameter C, and to construct a real-time monitoring data set Si of the heat exchanger system in combination with the real-time operating condition data Pi: Si (C, Pi); and, to input the real-time monitoring data set Si into a preset thermal control AI monitoring model, and the thermal control AI monitoring model respectively identifies the heating system operating characteristics and heat exchange operating condition characteristics in the real-time monitoring data set Si, and matches and outputs a heat exchanger thermal control strategy corresponding to the heating system operating characteristics and heat exchange operating condition characteristics; and, to bind the heat exchanger thermal control strategy to the corresponding heat exchanger system, and to send it to the corresponding heat exchanger system by the heating system monitoring backend; A heat exchanger system, used for receiving the heat exchanger thermal control strategy, responding to and executing the thermal control instructions in the heat exchanger thermal control strategy, and reporting the real-time operating condition data Pi+1 after the response to the heating system monitoring background in real time; The management terminal is used to log in to the monitoring background of the heating system, read and view the real-time monitoring data set Si of the heat exchanger system and the heat control strategy of the heat exchanger; The heat exchanger system is connected to the heating system monitoring background communication through the IOT communication module; The management end is communicatively connected with the heating system monitoring backend.

6. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 4.

Images