Artificial intelligence algorithm for optimizing secondary temperature supply curve of heat supply system of heating station in real time

Abstract

An artificial intelligence algorithm for optimizing a secondary temperature supply curve of a heat supply system of a heating station in real time comprises the following steps: (1) collecting indoor and outdoor temperature data in a certain time period according to the heat supply system, firstly, averaging the indoor temperature data, and taking the average value as a feedback value; averaging the outdoor temperature data by adopting outdoor temperature data issued by a monitoring platform and received by the heat supply system; (2) setting a target value in a program; and (3) setting in the program: when the room temperature feedback value is lower than the target value, the Y coordinate of the secondary temperature supply curve is moved upwards, when the room temperature feedback value is higher than the target value, the Y coordinate of the secondary temperature supply curve is moved downwards, and the X coordinate corresponding to the Y coordinate is the X coordinate closest to the average value of the outdoor temperature. According to the invention, heating station monitoring and a residential building heat metering system are organically combined, intelligent adjustment of a secondary temperature supply curve of the heating station is realized, and the automation and intelligent level of an intelligent heat supply network monitoring platform is improved.

Description

Technical Field

[0001] The present invention belongs to the field of centralized heating monitoring, and specifically relates to an artificial intelligence algorithm for real-time optimization of a secondary temperature supply curve of a heating system in a thermal power station. Background Art

[0002] At present, the smart heat network monitoring platform in the centralized heating industry is mainly divided into three parts in terms of monitoring and operation: heat source monitoring, thermal power station monitoring, and residential heat metering system, and the three parts operate independently.

[0003] Each heating station is divided into several heating systems, such as high-area floor heating system, low-area floor heating system, radiator system, etc. Each heating system automatically operates according to the secondary heating curve, that is, the lower the outdoor temperature, the higher the heating water temperature supplied to the user, and vice versa. The secondary heating is the user's heating water temperature. The setting of the secondary heating curve is as follows Figure 1 shown.

[0004] The X coordinate of the secondary heating curve is the outdoor temperature, and the Y coordinate is the secondary network water supply temperature. The Y coordinate setting directly affects the indoor temperature of the users of the heating system.

[0005] At present, the Y coordinate setting of the secondary heating curve is manually set based on experience, and there are deviations caused by human factors and untimely corrections, which affect the heating quality and have low efficiency. Summary of the invention

[0006] In order to solve the technical problems that the secondary temperature curve of the smart heating network monitoring platform in the centralized heating industry has deviations and is not corrected in time, which affects the heating quality and has low efficiency, the present invention provides an artificial intelligence algorithm for real-time optimization of the secondary temperature curve of the heating system of a thermal power station.

[0007] The technical solution of the present invention is as follows:

[0008] The artificial intelligence algorithm for real-time optimization of the secondary temperature curve of the heating system of a thermal power station is characterized by comprising the following steps:

[0009] (1) Indoor and outdoor temperature data of a certain period of time are collected according to the heating system to which it belongs. The indoor temperature data is first averaged and the average value is used as the feedback value. The outdoor temperature data is the outdoor temperature data sent by the monitoring platform received by the heating system and the average value is calculated;

[0010] (2) Set a target value in the program;

[0011] (3) Set in the program: when the room temperature feedback value is lower than the target value, the Y coordinate of the secondary heating curve is moved up; when the room temperature feedback value is higher than the target value, the Y coordinate of the secondary heating curve is moved down; the X coordinate corresponding to the Y coordinate is the X coordinate closest to the average value of the outdoor temperature.

[0012] Preferably, the method further comprises step (4): setting the frequency of analyzing and adjusting the Y coordinate of the secondary heating curve in the program to be once every 4 hours.

[0013] Further preferably, through adjustment in one heating period, a complete secondary heating curve for one heating period is obtained.

[0014] Preferably, in step (2), the target value is set to 22°C.

[0015] Further preferably, the percentage of users with a temperature between 20 and 24°C is analyzed. If the percentage is above 90%, it means that the hydraulic balance of the secondary network is good and the secondary heating curve is reasonable.

[0016] Preferably, in step (1), the indoor temperature data is firstly eliminated from abnormal data and user data reporting suspension.

[0017] Preferably, in step (1), when the room temperature feedback value is 1°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 2°C; when the room temperature feedback value is 2°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 4°C; when the room temperature feedback value is 3°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 6°C.

[0018] The beneficial effects of the present invention are as follows:

[0019] The present invention utilizes the residential heat metering system installed in the newly built commercial and residential community. The indoor temperature of each user is uploaded to the smart heat network monitoring platform, and these indoor temperature data are summarized and analyzed according to the heating system to which they belong. The Y coordinate of the secondary heating curve is automatically corrected to reduce the deviation caused by human factors, make timely corrections, and improve the heating quality.

[0020] Specific:

[0021] 1. The residential heat metering system uploads the room temperature of each heat user to the smart heat network monitoring platform through the communication system.

[0022] 2. The smart heating network monitoring platform identifies, screens and analyzes the room temperature data according to the artificial intelligence algorithm of the present invention, and sends correction instructions for the secondary heating curve to the thermal power station monitoring system through the communication system based on the analysis results.

[0023] 3. The thermal power station monitoring system determines the heating water temperature supplied to users based on the newly revised secondary heating curve and operates automatically.

[0024] 4. The heating water temperature determines the user's room temperature, and the user's room temperature data is then uploaded to the smart heating network monitoring platform for analysis. This cycle continues automatically to achieve the best heating quality.

[0025] On this basis, the following effects are achieved:

[0026] 1. The present invention is used to automatically correct the Y coordinate of the secondary heating curve, reduce the deviation and delay caused by human factors, timely and accurately adjust the heating temperature, and improve the heating quality.

[0027] 2. The present invention replaces the arduous and inefficient labor of manually analyzing the indoor temperatures of thousands of users, improves work efficiency, and saves a lot of manpower and time.

[0028] 3. The revised secondary heating curve can be used as the standard heating curve of the heating system in the future. In the event of network interruption, the heating system can operate independently according to this secondary heating curve to ensure the normal heating operation of the heating system.

[0029] The present invention organically combines the thermal power station monitoring and the residential heat metering system to achieve intelligent adjustment of the secondary heating curve of the thermal power station and improve the automation and intelligence level of the smart heating network monitoring platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the setting of the secondary heating curve;

[0031] Figure 2 The present invention is a flow chart of an artificial intelligence algorithm for optimizing the secondary temperature supply curve of a heating system in a thermal power station in real time according to an embodiment. DETAILED DESCRIPTION

[0032] In order to better understand the present invention, the present invention is specifically described below by way of examples. It is necessary to point out here that the following examples are only used to further illustrate the present invention and cannot be understood as limiting the scope of protection of the present invention. Some non-essential improvements and adjustments made by professionals and technicians in this field according to the content of the present invention above still belong to the scope of protection of the present invention.

[0033] Example:

[0034] The artificial intelligence algorithm of this embodiment optimizes the secondary temperature supply curve of the heating system of the thermal power station in real time. It uses the intelligent heating network monitoring platform of the centralized heating industry. The monitoring operation is mainly divided into three parts: heat source monitoring, thermal power station monitoring, and residential heat metering system. Each thermal power station is divided into several heating systems, such as high-area floor heating system, low-area floor heating system, radiator system, etc. Each heating system automatically operates according to the secondary temperature supply curve, that is, the lower the outdoor temperature, the higher the heating water temperature supplied to the user, and vice versa. The secondary heating is the user's heating water temperature. The setting of the secondary temperature supply curve is as follows Figure 1As shown in the figure, the X coordinate of the secondary heating curve is the outdoor temperature, and the Y coordinate is the secondary network water supply temperature. The Y coordinate has 8 values. The high or low setting of the Y coordinate directly affects the indoor temperature of the users of the heating system. The residential heat metering system of the newly built commercial and residential area has uploaded the room temperature of each household to the smart heating network monitoring platform.

[0035] like Figure 2 As shown, the specific steps include:

[0036] (1) Indoor and outdoor temperature data of a certain time period (4 hours in this embodiment) are collected according to the heating system to which it belongs. The start and end time periods can be set. The indoor temperature data first removes abnormal data and user data reporting suspension, and removes several maximum and minimum values. The number can be set, for example, 3. First, the indoor temperature data is averaged, and the average value is used as the feedback value. The outdoor temperature data uses the outdoor temperature data sent by the monitoring platform received by the heating system to calculate the average value;

[0037] (2) Setting a target value in the program. The target value can be set manually. In this embodiment, the target value is set to 22°C.

[0038] (3) In the program, it is set that when the room temperature feedback value is lower than the target value, the Y coordinate of the secondary heating curve is moved up; when the room temperature feedback value is higher than the target value, the Y coordinate of the secondary heating curve is moved down; the X coordinate corresponding to the Y coordinate is the X coordinate closest to the average value of the outdoor temperature. Specifically, when the room temperature feedback value is 1°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 2°C; when the room temperature feedback value is 2°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 4°C; when the room temperature feedback value is 3°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 6°C, and vice versa. The above values ​​can comprehensively meet the balance between efficiency and energy consumption, and the feedback is accurate.

[0039] (4) The Y coordinate frequency of analyzing and adjusting the secondary heating curve can be set manually in the program, such as setting the analysis and adjustment once every few hours. This embodiment adopts once every 4 hours. Through adjustment over a period of time, a more accurate secondary heating curve corresponding to the average outdoor temperature during that period can be obtained. Through adjustment over a heating period, a more accurate secondary heating curve for a complete heating period can be obtained.

[0040] This secondary heating curve can be used as the standard heating curve of the heating system in the future. In the event of a network outage, the heating system can operate independently according to this secondary heating curve to ensure normal heating operation of the heating system.

[0041] (5) Analysis of the percentage of users with a temperature between 20 and 24°C shows that the percentage is over 90%, indicating that the hydraulic balance of the secondary network is good and the secondary heating curve is reasonable.

[0042] The above is only a preferred embodiment of the present invention and is not intended to limit the invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An artificial intelligence algorithm for real-time optimization of the secondary temperature curve of the heating system of a thermal power station, characterized by The following steps are involved: (1) Indoor and outdoor temperature data of a certain period of time are summarized according to the heating system to which it belongs. The indoor temperature data is first averaged and the average value is used as the feedback value. The outdoor temperature data is the outdoor temperature data sent by the monitoring platform received by the heating system and the average value is calculated; (2) Set a target value in the program; (3) Set in the program: when the room temperature feedback value is lower than the target value, the Y coordinate of the secondary heating curve is moved up; when the room temperature feedback value is higher than the target value, the Y coordinate of the secondary heating curve is moved down. The X coordinate corresponding to the Y coordinate is the X coordinate closest to the average value of the outdoor temperature.

2. The artificial intelligence algorithm according to claim 1, characterized in that The method also includes step (4): setting the frequency of analyzing and adjusting the Y coordinate of the secondary heating curve in the program to be once every 4 hours.

3. The artificial intelligence algorithm according to claim 2, characterized in that Through adjustment during a heating period, a complete secondary heating curve for a heating period is obtained.

4. The artificial intelligence algorithm according to claim 1, characterized in that In step (2), the target value is set to 22°C.

5. The artificial intelligence algorithm according to claim 4, characterized in that Analyze the percentage of users with a temperature between 20 and 24°C. If the percentage is above 90%, it means that the hydraulic balance of the secondary network is good and the secondary heating curve is reasonable.

6. The artificial intelligence algorithm according to claim 1, characterized in that In step (1), the indoor temperature data is firstly eliminated from abnormal data and user data reporting shutdown.

7. The artificial intelligence algorithm according to claim 1, characterized in that In step (1), when the room temperature feedback value is 1°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 2°C; when the room temperature feedback value is 2°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 4°C; when the room temperature feedback value is 3°C lower than the target value, the Y coordinate of the secondary heating curve is shifted upward by 6°C.

Images