Control optimization method and system based on integrated industrial energy monitoring system

Abstract

The application provides a control optimization method and system based on an integrated industrial energy monitoring system. The method comprises the following steps: obtaining historical data of a subsystem, training a corresponding energy demand prediction model, obtaining real-time data of the subsystem, inputting the real-time data into the energy demand prediction model for processing, obtaining energy demand prediction data of the subsystem, processing the real-time energy supply data, obtaining a supply-demand deviation rate, comparing the threshold to obtain an energy supply-demand state of the subsystem, processing real-time energy consumption data and energy price data in combination with preset expected energy cost data, obtaining an energy cost deviation rate of the subsystem, processing the supply-demand deviation rate, obtaining a subsystem operation evaluation index of the subsystem, further processing to obtain a system operation evaluation index, and finally comparing the threshold to determine the operation state of the integrated industrial energy monitoring system, and optimizing energy supply between subsystems according to the operation state, so that the control optimization of energy within the subsystem and between the subsystems is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial energy management, in particular to a control optimization method and system based on a comprehensive industrial energy monitoring system. BACKGROUND

[0002] In modern industrial production processes, energy consumption is huge and involves multiple energy forms such as electricity, coal, natural gas, steam, etc. Traditional industrial energy management is often extensive, lacking precise monitoring and effective control of energy consumption, resulting in low energy utilization, increased production costs, and significant pressure on the environment. Traditional industrial energy monitoring systems often rely on centralized data processing and control, which has drawbacks such as data transmission delay, heavy cloud computing pressure, and high requirements for network stability, making it difficult to meet the real-time and autonomous needs of industrial sites. Existing systems still have many shortcomings in control optimization, making it difficult to achieve fast data processing and local decision-making, and the efficiency and reliability of industrial energy monitoring and control are insufficient.

[0003] In view of the above problems, there is an urgent need for effective technical solutions. SUMMARY

[0004] The purpose of the present application is to provide a control optimization method and system based on a comprehensive industrial energy monitoring system. The historical weather data and historical energy data of a historical preset time period of a subsystem of the comprehensive industrial energy monitoring system are obtained and processed to obtain a historical energy consumption influence coefficient. The historical operation parameter data and corresponding historical energy consumption data are trained to obtain an energy demand prediction model corresponding to the subsystem. The set operation parameter data, predicted weather data, and planned energy data of the subsystem for a preset time period are obtained and processed in combination with the energy demand prediction model to obtain energy demand prediction data corresponding to the subsystem. The real-time energy supply data of the subsystem is obtained and processed in combination with the energy demand prediction data to obtain a supply-demand deviation rate of the subsystem. Through threshold comparison, the energy supply and demand state of the subsystem is obtained, and the set operation parameter data is adjusted according to the energy supply state. The real-time energy consumption data and energy price data of multiple energies of the subsystem for a preset time period are obtained and processed in combination with the preset expected energy cost data to obtain an energy cost deviation rate of the subsystem. The supply-demand deviation rate is processed in combination with the supply-demand deviation rate to obtain a subsystem operation evaluation index of the subsystem. The system operation evaluation index of the comprehensive industrial energy monitoring system is further processed to obtain the system operation evaluation index of the comprehensive industrial energy monitoring system. Finally, the running state of the comprehensive industrial energy monitoring system is determined through threshold comparison results, and the energy supply between subsystems is optimized according to the running state, realizing the control optimization of energy within and between subsystems.

[0005] The present application also provides a control optimization method based on a comprehensive industrial energy monitoring system, comprising the following steps:

[0006] The historical operation parameter data, the historical energy consumption data, the historical weather data and the historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a historical preset time period are acquired, the historical weather data and the historical production capacity data are processed, and a historical energy consumption influence coefficient is obtained;

[0007] The historical operation parameter data, the historical energy consumption influence coefficient and the corresponding historical energy consumption data are trained to obtain an energy consumption demand prediction model corresponding to the subsystem;

[0008] The set operation parameter data, the predicted weather data and the planned production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are acquired, and the energy consumption demand prediction model is processed to obtain energy consumption demand prediction data corresponding to the subsystem;

[0009] Real-time energy supply data of the subsystem of the comprehensive industrial energy monitoring system are acquired, the real-time energy supply data and the energy consumption demand prediction data are processed to obtain a supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with a preset supply-demand deviation rate threshold, an energy supply and demand state of the subsystem is obtained, and the set operation parameter data is adjusted according to the energy supply state;

[0010] Real-time energy consumption data and energy price data of multiple energies of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are acquired, the real-time energy consumption data and the energy price data are processed in combination with preset expected energy cost data to obtain an energy cost deviation rate of the subsystem;

[0011] The supply-demand deviation rate and the energy cost deviation rate are processed to obtain a subsystem operation evaluation index corresponding to the subsystem, and the subsystem operation evaluation index is processed to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system;

[0012] The system operation evaluation index is compared with a preset system operation evaluation threshold, the operation state of the comprehensive industrial energy monitoring system is determined according to the comparison result, and the energy supply between the subsystems is optimized according to the operation state.

[0013] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the historical operation parameter data, the historical energy consumption data, the historical weather data and the historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a historical preset time period are acquired, the historical weather data and the historical production capacity data are processed, and a historical energy consumption influence coefficient is obtained, including:

[0014] The historical operation parameter data include device historical operation parameter data and energy historical operation parameter data;

[0015] The historical weather data include historical temperature difference average data and historical illumination duration data;

[0016] The historical energy production data includes historical yield data and historical single-machine energy consumption data;

[0017] The historical temperature difference average data and historical light duration data and the historical yield data and historical single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain historical energy consumption influence coefficients.

[0018] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the set running parameter data, the predicted weather data and the planned energy production data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained, and the energy demand prediction model is combined for processing to obtain energy demand prediction data corresponding to the subsystem, including:

[0019] The set running parameter data, the predicted weather data and the planned energy production data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained;

[0020] The set running parameter data includes device set running parameter data and energy set running parameter data;

[0021] The predicted weather data includes predicted temperature difference average data and predicted light duration data;

[0022] The planned energy production data includes planned yield data and calibrated single-machine energy consumption data;

[0023] The predicted temperature difference average data and predicted light duration data and the planned yield data and calibrated single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain predicted energy consumption influence coefficients;

[0024] The device set running parameter data, the energy set running parameter data and the predicted energy consumption influence coefficients are input into the energy demand prediction model for processing to obtain energy demand prediction data corresponding to the subsystem.

[0025] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the real-time energy supply data of the subsystem of the comprehensive industrial energy monitoring system is obtained, the real-time energy supply data and the energy demand prediction data are processed to obtain a supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with a preset supply-demand deviation rate threshold to obtain an energy supply-demand state of the subsystem, and the set running parameter data is adjusted according to the energy supply state, including:

[0026] The real-time energy supply data of the subsystem of the comprehensive industrial energy monitoring system is obtained;

[0027] The real-time energy supply data and the energy demand prediction data are processed to obtain a supply-demand deviation rate of the subsystem;

[0028] The supply-demand deviation rate is compared with a preset supply-demand deviation rate threshold to obtain an energy supply-demand state of the subsystem, including a supply-demand balanced state or a supply-demand unbalanced state.

[0029] If the supply-demand deviation rate is less than or equal to the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is in a supply-demand balanced state.

[0030] If the supply-demand deviation rate is greater than the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is in a supply-demand unbalanced state, and the set operating parameter data is adjusted.

[0031] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the real-time energy consumption data and energy price data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained, and the real-time energy consumption data and the energy price data are processed in combination with preset expected energy cost data to obtain an energy cost deviation rate of the subsystem, including:

[0032] The real-time energy consumption data and energy price data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained.

[0033] The real-time energy consumption data is multiplied by the energy price data and summed to obtain energy consumption cost data of the subsystem.

[0034] The energy consumption cost data and the preset expected energy cost data are processed to obtain an energy cost deviation rate of the subsystem.

[0035] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the supply-demand deviation rate and the energy cost deviation rate are processed to obtain a corresponding subsystem operating evaluation index of the subsystem, and the subsystem operating evaluation index is processed to obtain a system operating evaluation index of the comprehensive industrial energy monitoring system, including:

[0036] The supply-demand deviation rate and the energy cost deviation rate are processed to obtain a corresponding subsystem operating evaluation index of the subsystem.

[0037] Type characteristic data of the subsystem is obtained, a preset weight coefficient list is queried according to the type characteristic data, and a weight coefficient corresponding to the subsystem is obtained.

[0038] The plurality of subsystem operating evaluation indexes and the corresponding weight coefficients are processed to obtain a system operating evaluation index of the comprehensive industrial energy monitoring system.

[0039] Optionally, in the control optimization method based on the comprehensive industrial energy monitoring system, the system operation evaluation index is compared with a preset system operation evaluation threshold value, the running state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, and the energy supply between the subsystems is optimized according to the running state, including:

[0040] The system operation evaluation index is processed with a preset system operation evaluation benchmark index to obtain a running evaluation relative value.

[0041] The running evaluation relative value is compared with a preset system operation evaluation threshold value to obtain the running state of the comprehensive industrial energy monitoring system, including a normal running state or an abnormal running state.

[0042] If the running evaluation relative value is less than or equal to the preset system operation evaluation threshold value, it is determined that the running state of the comprehensive industrial energy monitoring system is an abnormal running state, and the energy supply between the subsystems is optimized according to the running state.

[0043] If the running evaluation relative value is greater than the preset system operation evaluation threshold value, it is determined that the running state of the comprehensive industrial energy monitoring system is a normal running state.

[0044] In a second aspect, the application provides a control optimization system based on a comprehensive industrial energy monitoring system, which comprises a memory and a processor, the memory comprising a program of a control optimization method based on a comprehensive industrial energy monitoring system, and the program of the control optimization method based on a comprehensive industrial energy monitoring system is executed by the processor to realize the following steps:

[0045] The historical running parameter data, historical energy consumption data, historical weather data and historical energy production data of the comprehensive industrial energy monitoring system subsystem in a historical preset time period are obtained, the historical weather data and the historical energy production data are processed to obtain a historical energy consumption influence coefficient;

[0046] The historical running parameter data, the historical energy consumption influence coefficient and the corresponding historical energy consumption data are trained to obtain an energy demand prediction model corresponding to the subsystem;

[0047] The set running parameter data, predicted weather data and planned energy production data of the comprehensive industrial energy monitoring system subsystem in a preset time period are obtained, and the energy demand prediction model is combined to process and obtain energy demand prediction data corresponding to the subsystem;

[0048] obtain the energy supply and demand state of the subsystem by comparing the supply and demand deviation rate with a preset supply and demand deviation rate threshold, and adjust the set operation parameter data according to the energy supply state;

[0049] obtain the energy cost deviation rate of the subsystem by processing the real-time energy consumption data and the energy price data in combination with the preset expected energy cost data;

[0050] obtain the subsystem corresponding sub-operation evaluation index by processing the supply and demand deviation rate and the energy cost deviation rate, and obtain the system operation evaluation index of the comprehensive industrial energy monitoring system by processing the sub-operation evaluation index;

[0051] compare the system operation evaluation index with a preset system operation evaluation threshold, determine the operation state of the comprehensive industrial energy monitoring system according to the threshold comparison result, and optimize the energy supply between the subsystems according to the operation state.

[0052] Optionally, in the control optimization system based on the comprehensive industrial energy monitoring system, the historical running parameter data, the historical energy consumption data, the historical weather data and the historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a historical preset time period are obtained, and the historical energy consumption influence coefficient is obtained by processing the historical weather data and the historical production capacity data, including:

[0053] The historical running parameter data includes device historical running parameter data and energy historical running parameter data;

[0054] The historical weather data includes historical temperature difference mean value data and historical illumination time length data;

[0055] The historical production capacity data includes historical production data and historical single machine energy consumption data;

[0056] The historical temperature difference mean value data and the historical illumination time length data and the historical production data and the historical single machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain the historical energy consumption influence coefficient.

[0057] Optionally, in the control optimization system based on the comprehensive industrial energy monitoring system, the set operation parameter data, the predicted weather data and the planned production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained, and the energy consumption demand prediction data corresponding to the subsystem is obtained by processing in combination with the energy consumption demand prediction model, including:

[0058] obtain setting operation parameter data of a subsystem of the comprehensive industrial energy monitoring system in a preset time period, predicted weather data and planned energy production data;

[0059] The setting operation parameter data comprises device setting operation parameter data and energy setting operation parameter data;

[0060] The predicted weather data comprises predicted temperature difference mean value data and predicted illumination duration data;

[0061] The planned energy production data comprises planned production data and calibrated single-machine energy consumption data;

[0062] The predicted temperature difference mean value data and the predicted illumination duration data and the planned production data and the calibrated single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain predicted energy consumption influence coefficients;

[0063] The device setting operation parameter data, the energy setting operation parameter data and the predicted energy consumption influence coefficients are input into the energy consumption demand prediction model for processing to obtain energy consumption demand prediction data corresponding to the subsystem.

[0064] As can be seen, the control optimization method and system based on the comprehensive industrial energy monitoring system provided in the application obtain historical weather data and historical energy production data of a subsystem of the comprehensive industrial energy monitoring system in a historical preset time period for processing to obtain historical energy consumption influence coefficients, train in combination with historical operation parameter data and corresponding historical energy consumption data to obtain an energy consumption demand prediction model corresponding to the subsystem, obtain setting operation parameter data of the subsystem in a preset time period, predicted weather data and planned energy production data, process in combination with the energy consumption demand prediction model to obtain energy consumption demand prediction data corresponding to the subsystem, obtain real-time energy supply data of the subsystem, process in combination with the energy consumption demand prediction data to obtain a supply-demand deviation rate of the subsystem, obtain an energy supply and demand state of the subsystem through threshold comparison, adjust the setting operation parameter data according to the energy supply state, obtain real-time energy consumption data of multiple energies of the subsystem in the preset time period and energy price data in combination with preset expected energy cost data for processing to obtain an energy cost deviation rate of the subsystem, process in combination with the supply-demand deviation rate to obtain a subsystem operation evaluation index of the subsystem, further process to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system, finally determine an operation state of the comprehensive industrial energy monitoring system through threshold comparison results, and optimize energy supply among subsystems according to the operation state, thereby realizing control optimization of energy within a subsystem and among subsystems.

[0065] Other features and advantages of the application will be set forth in the accompanying description, and in part will be apparent from the description, or can be learned by practice of the application. The objects and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0067] Figure 1 A flow chart of a control optimization method based on an integrated industrial energy monitoring system provided in an embodiment of the present application;

[0068] Figure 2 A flowchart of a control optimization method for an integrated industrial energy monitoring system according to an embodiment of the present application for obtaining energy demand forecast data corresponding to a subsystem;

[0069] Figure 3 A flow chart of obtaining the energy cost deviation rate of a subsystem in a control optimization method based on an integrated industrial energy monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0071] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0072] Please refer to Figure 1 , Figure 1 This is a flow chart of a control optimization method based on an integrated industrial energy monitoring system in some embodiments of the present application. The control optimization method based on an integrated industrial energy monitoring system is used in terminal devices, such as computers and mobile terminals. The control optimization method based on an integrated industrial energy monitoring system includes the following steps:

[0073] S11, obtain historical operation parameter data, historical energy consumption data, historical weather data and historical energy production data of a subsystem of the comprehensive industrial energy monitoring system in a preset time period, process the historical weather data and the historical energy production data to obtain a historical energy consumption influence coefficient;

[0074] S12, train the historical operation parameter data, the historical energy consumption influence coefficient and corresponding historical energy consumption data to obtain an energy demand prediction model corresponding to the subsystem;

[0075] S13, obtain set operation parameter data, predicted weather data and planned energy production data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period, process the energy demand prediction model to obtain energy demand prediction data corresponding to the subsystem;

[0076] S14, obtain real-time energy supply data of the subsystem of the comprehensive industrial energy monitoring system, process the real-time energy supply data and the energy demand prediction data to obtain a supply-demand deviation rate of the subsystem, compare the supply-demand deviation rate with a preset supply-demand deviation rate threshold to obtain an energy supply and demand state of the subsystem, and adjust the set operation parameter data according to the energy supply state;

[0077] S15, obtain real-time energy consumption data and energy price data of multiple types of energy of the subsystem of the comprehensive industrial energy monitoring system in a preset time period, process the real-time energy consumption data and the energy price data in combination with preset expected energy cost data to obtain an energy cost deviation rate of the subsystem;

[0078] S16, process the supply-demand deviation rate and the energy cost deviation rate to obtain a subsystem operation evaluation index corresponding to the subsystem, process the subsystem operation evaluation index to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system;

[0079] S17, compare the system operation evaluation index with a preset system operation evaluation threshold, determine an operation state of the comprehensive industrial energy monitoring system according to a comparison result, and optimize energy supply between subsystems according to the operation state.

[0080] It should be noted that, in order to realize the control optimization of the energy in each subsystem and between the subsystems in the comprehensive industrial energy monitoring system, each subsystem in the comprehensive industrial energy monitoring system can be determined by a person skilled in the art according to specific conditions, such as large motors, heating furnaces, production line distribution boxes, etc., and the comprehensive industrial energy involves multiple energy forms, such as electricity, coal, natural gas, steam, etc. First, the historical operation parameter data, historical energy consumption data, historical weather data and historical energy data of the multiple historical preset time periods of the subsystems of the comprehensive industrial energy monitoring system are acquired, including the historical operation parameter data and energy historical operation parameter data, the historical weather data and the historical energy data are processed to obtain the historical energy consumption influence coefficient, the initial energy demand prediction model is trained according to the historical operation parameter data, the historical energy consumption influence coefficient and the corresponding historical energy consumption data, and the trained energy demand prediction model corresponding to the subsystem is obtained, then the set operation parameter data, predicted weather data and planned energy data of the preset time period of the subsystem of the comprehensive industrial energy monitoring system are acquired, and after processing, the energy demand prediction data corresponding to the subsystem is obtained by inputting the energy demand prediction model for processing, while the real-time energy supply data of the subsystem is acquired, the energy demand prediction data is combined for processing to obtain the supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold, and the energy supply and demand state of the subsystem is obtained, including the supply-demand balance state or the supply-demand imbalance state, if it is the supply-demand imbalance state, the set operation parameter data is adjusted to optimize the energy supply and demand of the subsystem. After that, the real-time energy consumption data and energy price data of multiple energies of the subsystem in the preset time period are acquired, combined with the preset expected energy cost data for processing to obtain the energy cost deviation rate of the subsystem, the energy cost situation of the subsystem is evaluated, combined with the supply-demand deviation rate of the subsystem for processing to obtain the corresponding sub-operation evaluation index of the subsystem, the sub-operation evaluation index is processed to obtain the system operation evaluation index of the comprehensive industrial energy monitoring system, which is used to evaluate the operation of the entire comprehensive industrial energy system. Finally, the system operation evaluation index is compared with the preset system operation evaluation threshold, and the running state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, which is a normal running state or an abnormal running state, if it is an abnormal running state, the energy supply between the subsystems is optimized, so that the monitoring and control optimization of the energy at the subsystem side and between the subsystems are realized, the autonomy and independence of the subsystems are improved, the regional resources are fully coordinated, the resources are fully utilized, and the energy waste is reduced.

[0081] According to the embodiment of the application, the historical operation parameter data, historical energy consumption data, historical weather data and historical energy data of the subsystem of the comprehensive industrial energy monitoring system in the historical preset time period are acquired, and the historical energy consumption influence coefficient is obtained by processing the historical weather data and the historical energy data, including:

[0082] The historical operating parameter data includes equipment historical operating parameter data and energy historical operating parameter data;

[0083] The historical weather data includes historical temperature difference mean data and historical sunshine duration data;

[0084] The historical production capacity data includes historical production data and historical single-unit energy consumption data;

[0085] The historical temperature difference mean data and the historical sunshine duration data as well as the historical output data and the historical single-unit energy consumption data are input into a preset energy consumption impact coefficient evaluation model for processing to obtain a historical energy consumption impact coefficient.

[0086] It should be noted that the historical operating parameter data includes historical equipment operating parameter data and historical energy operating parameter data, wherein the historical equipment operating parameter data and the historical energy operating parameter data are specifically set by those skilled in the art according to the subsystem, such as the real-time speed, rated voltage, rated current, efficiency and power factor of the subsystem motor, the real-time current, real-time voltage, frequency fluctuation value, and harmonic content of the electric energy; the historical weather data includes historical temperature difference mean data and historical sunshine duration data, and the historical production capacity data includes historical output data and historical single-unit energy consumption data, wherein the historical temperature difference mean data refers to the average value of the difference between multiple historical temperatures and a preset standard temperature within a preset time period; the historical temperature difference mean data and historical sunshine duration data as well as the historical output data and the historical single-unit energy consumption data are input into a preset energy consumption impact coefficient evaluation model for processing to obtain the historical energy consumption impact coefficient;

[0087] The calculation formula for the historical energy consumption impact coefficient in the energy consumption impact coefficient evaluation model is:

[0088] ;

[0089] in, Historical energy consumption impact coefficient, 、 、 、 They are historical temperature difference average data, historical sunshine duration data, historical output data and historical single unit energy consumption data. 、 、 It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset comprehensive industrial energy monitoring platform).

[0090] Please refer to Figure 2 , Figure 2is a flowchart of use-energy demand prediction data corresponding to a control optimization method based on an integrated industrial energy monitoring system in some embodiments of the present application. According to an embodiment of the present application, the set running parameter data, the predicted weather data and the planned production capacity data of the subsystem of the integrated industrial energy monitoring system in a preset time period are obtained, and the use-energy demand prediction model is processed to obtain the use-energy demand prediction data corresponding to the subsystem, including:

[0091] S21, obtaining set running parameter data, predicted weather data and planned production capacity data of a subsystem of an integrated industrial energy monitoring system in a preset time period;

[0092] S22, the set running parameter data includes device set running parameter data and energy set running parameter data;

[0093] S23, the predicted weather data includes predicted temperature difference average data and predicted light duration data;

[0094] S24, the planned production capacity data includes planned production data and calibrated single-machine use-energy data;

[0095] S25, inputting the predicted temperature difference average data and the predicted light duration data and the planned production data and the calibrated single-machine use-energy data into a preset use-energy influence coefficient evaluation model for processing to obtain a predicted use-energy influence coefficient;

[0096] S26, inputting the device set running parameter data, the energy set running parameter data and the predicted use-energy influence coefficient into the use-energy demand prediction model for processing to obtain the use-energy demand prediction data corresponding to the subsystem.

[0097] It should be noted that in order to predict the use-energy demand of the subsystem, first, the set running parameter data of the subsystem in a preset time period is obtained, including device set running parameter data and energy set running parameter data, including predicted temperature difference average data and predicted light duration data, wherein the predicted temperature difference average data refers to the average value of the difference between a plurality of predicted temperatures and a preset standard temperature in a preset time period, including planned production data and calibrated single-machine use-energy data, inputting the predicted temperature difference average data and the predicted light duration data and the planned production data and the calibrated single-machine use-energy data into a preset use-energy influence coefficient evaluation model for processing to obtain a predicted use-energy influence coefficient;

[0098] The predicted use-energy influence coefficient calculation formula in the use-energy influence coefficient evaluation model is:

[0099] ;

[0100] wherein, the predicted use-energy influence coefficient, , , , are respectively predicted temperature difference average data, predicted light duration data, planned production data and calibrated single-machine energy consumption data, , , are preset characteristic coefficients (the characteristic coefficients are obtained by querying a preset comprehensive industrial energy monitoring platform) ;

[0101] The device setting operation parameter data, the energy setting operation parameter data and the predicted energy consumption influence coefficient are input into the trained energy demand prediction model for processing to obtain energy demand prediction data corresponding to the subsystem.

[0102] According to the embodiment of the present application, the real-time energy supply data of the comprehensive industrial energy monitoring system subsystem is obtained, the real-time energy supply data and the energy demand prediction data are processed to obtain the supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold to obtain the energy supply-demand state of the subsystem, and the setting operation parameter data is adjusted according to the energy supply state, including:

[0103] The real-time energy supply data of the comprehensive industrial energy monitoring system subsystem is obtained;

[0104] The real-time energy supply data and the energy demand prediction data are processed to obtain the supply-demand deviation rate of the subsystem;

[0105] The supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold to obtain the energy supply-demand state of the subsystem, including a supply-demand balance state or a supply-demand imbalance state;

[0106] If the supply-demand deviation rate is less than or equal to the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is in a supply-demand balance state;

[0107] If the supply-demand deviation rate is greater than the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is in a supply-demand imbalance state, and the setting operation parameter data is adjusted.

[0108] It should be noted that in order to evaluate the energy supply-demand situation of the subsystem, the real-time energy supply data of the subsystem is first obtained, and the obtained energy demand prediction data is processed to obtain the supply-demand deviation rate of the subsystem. The supply-demand deviation rate refers to the ratio of the absolute value of the difference between the real-time energy supply data and the energy demand prediction data to the real-time energy supply data. For example, the real-time energy supply data is 10, and the energy demand prediction data is 8, The obtained supply and demand deviation rate is compared with the preset supply and demand deviation rate threshold to obtain the energy supply and demand state of the subsystem. In this embodiment, the supply and demand deviation rate threshold is set to (0, 0.25] and (0.25, 1], corresponding to the supply and demand balance state and the supply and demand imbalance state, respectively. For example, if the obtained supply and demand deviation rate is 0.2, which is less than the preset supply and demand deviation rate threshold, the energy supply and demand state of the subsystem is determined to be in a supply and demand balance state. If the obtained supply and demand deviation rate is 0.3, which is greater than the preset supply and demand deviation rate threshold, the energy supply and demand state of the subsystem is determined to be in a supply and demand imbalance state, and the operating parameter data is adjusted according to the supply and demand deviation rate to balance the energy supply and demand of the subsystem.

[0109] Please refer to Figure 3 , Figure 3 This is a flow chart of obtaining the energy cost deviation rate of a subsystem in a control optimization method based on an integrated industrial energy monitoring system in some embodiments of the present application. According to an embodiment of the present invention, obtaining real-time energy usage data and energy price data of multiple energy sources in a preset time period of the integrated industrial energy monitoring system subsystem, processing the real-time energy usage data and energy price data in combination with preset expected energy cost data, and obtaining the energy cost deviation rate of the subsystem includes:

[0110] S31. Obtaining real-time energy consumption data and energy price data of multiple energy sources during a preset time period of the integrated industrial energy monitoring system subsystem;

[0111] S32: multiplying the real-time energy consumption data by the energy price data and performing sum processing to obtain energy consumption cost data of the subsystem;

[0112] S33: Process the energy cost data and the preset expected energy cost data to obtain the energy cost deviation rate of the subsystem.

[0113] It should be noted that in order to understand the energy usage cost, first obtain the real-time energy consumption data and energy price data of multiple energy sources in the subsystem preset time period, multiply the real-time energy consumption data by the energy price data and sum them to obtain the energy cost data of the subsystem;

[0114] The energy cost calculation formula is:

[0115] ;

[0116] in, For energy cost data, 、 are the real-time energy consumption data and energy price data of the i-th energy respectively;

[0117] The energy cost deviation rate of the subsystem is obtained by processing the obtained energy cost data and the preset expected energy cost data;

[0118] The energy cost deviation rate calculation formula is:

[0119] .

[0120] Wherein, is the energy cost deviation rate, , respectively, the energy cost data and the preset expected energy cost data.

[0121] According to the embodiment of the application, the supply and demand deviation rate and the energy cost deviation rate are processed to obtain a subsystem corresponding to a subsystem operation evaluation index, and the subsystem operation evaluation index is processed to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system, comprising:

[0122] According to the supply and demand deviation rate and the energy cost deviation rate, the subsystem corresponding to the subsystem operation evaluation index is obtained by processing;

[0123] Obtain the type characteristic data of the subsystem, and query the preset weight coefficient list according to the type characteristic data to obtain the weight coefficient corresponding to the subsystem;

[0124] According to the plurality of subsystem operation evaluation indexes and the corresponding weight coefficients, the system operation evaluation index of the comprehensive industrial energy monitoring system is obtained by processing.

[0125] It should be noted that the operation of the subsystem is comprehensively evaluated according to the energy supply and demand and the cost use of the subsystem, and first, the supply and demand deviation rate and the energy cost deviation rate are obtained by processing to obtain the subsystem corresponding to the subsystem operation evaluation index;

[0126] The subsystem operation evaluation index calculation formula is:

[0127] ;

[0128] Wherein, is the subsystem operation evaluation index, , respectively, the supply and demand deviation rate and the energy cost deviation rate, is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset comprehensive industrial energy monitoring platform);

[0129] Further, the type characteristic data of the subsystem is obtained, and the preset weight coefficient list is queried according to the type characteristic data to obtain the weight coefficient corresponding to the subsystem, wherein the preset weight coefficient list is obtained by querying the preset comprehensive industrial energy monitoring platform, and the system operation evaluation index of the comprehensive industrial energy monitoring system is obtained by processing the plurality of subsystem operation evaluation indexes and the corresponding weight coefficients;

[0130] The system operation evaluation index calculation formula is:

[0131]

[0132] wherein, is the system operation evaluation index, , is the jth subsystem operation evaluation index and weight coefficient, respectively, is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset comprehensive industrial energy monitoring platform).

[0133] According to the embodiment of the present application, the system operation evaluation index is compared with a preset system operation evaluation threshold value, the operation state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, and the energy supply between the subsystems is optimized according to the operation state, including:

[0134] The system operation evaluation index is processed with a preset system operation evaluation benchmark index to obtain an operation evaluation relative value;

[0135] The operation evaluation relative value is compared with a preset system operation evaluation threshold value to obtain the operation state of the comprehensive industrial energy monitoring system, including a normal operation state or an abnormal operation state;

[0136] If the operation evaluation relative value is less than or equal to the preset system operation evaluation threshold value, it is determined that the operation state of the comprehensive industrial energy monitoring system is an abnormal operation state, and the energy supply between the subsystems is optimized according to the operation state;

[0137] If the operation evaluation relative value is greater than the preset system operation evaluation threshold value, it is determined that the operation state of the comprehensive industrial energy monitoring system is a normal operation state.

[0138] ​It should be noted that the obtained system operation evaluation index is processed with the preset system operation evaluation benchmark index to obtain an operation evaluation relative value, for example, the system operation evaluation index is 7, the preset system operation evaluation benchmark index is 10, and 7 / 10=0.7 is the operation evaluation relative value, and the operation evaluation relative value is compared with the preset system operation evaluation threshold value to obtain the running state of the comprehensive industrial energy monitoring system. In the embodiment, the preset system operation evaluation threshold value is set to (0, 0.75], (0.75, 1], which respectively corresponds to a normal running state and an abnormal running state. For example, the obtained operation evaluation relative value is 0.7, which is less than the preset system operation evaluation threshold value, so the running state of the comprehensive industrial energy monitoring system is determined as an abnormal running state, and the energy supply between the subsystems is optimized according to the running state; if the obtained operation evaluation relative value is 0.9, which is greater than the preset system operation evaluation threshold value, it is determined that the running state of the comprehensive industrial energy monitoring system is a normal running state.

[0139] It is worth mentioning that, according to the embodiment of the application, further comprising:

[0140] Obtaining energy use time data, self-energy supply total data and total energy demand data of the comprehensive industrial energy monitoring system;

[0141] Comparing the self-energy supply total data with the total energy demand data;

[0142] If the self-energy supply total data is greater than the total energy demand data, processing the self-energy supply total data and the total energy demand data to obtain excess energy supply data;

[0143] According to the energy use time data, a preset energy price list is queried to obtain a real-time energy price;

[0144] According to the excess energy supply data and the real-time energy price, an excess energy value data is obtained by calculation;

[0145] The excess energy value data is compared with a preset energy value threshold value, and an excess energy disposal scheme is determined according to the threshold comparison result;

[0146] If it is greater than the preset energy value threshold value, it is sold on the grid;

[0147] If it is less than or equal to the preset energy value threshold value, the energy storage device is started to store energy.

[0148] It should be noted that, in order to reduce the energy operation cost, maximize the enterprise self-supply energy advantage, obtain the energy use time data, the total self-supply energy data and the total energy demand data of the comprehensive industrial energy monitoring system, first, compare the total self-supply energy data and the total energy demand data, if the total self-supply energy data is greater than the total energy demand data, the difference between the total self-supply energy data and the total energy demand data is the excess energy supply data, which indicates that there is a surplus in the self-supply energy of the enterprise, which needs to be reasonably arranged, then according to the energy use time data, the preset energy price list is queried to obtain the real-time energy price, then according to the excess energy supply data and the real-time energy price, the excess energy value data is obtained, for example, the excess energy supply data is 100, the real-time energy price is 0.55, then 100*0.55=55 is the excess energy value data; finally, the excess energy value data is compared with the preset energy value threshold, and the excess energy disposal scheme is determined according to the threshold comparison result, in the embodiment, the energy value threshold is set to 100, for example, the obtained excess energy value data is 55, which is less than the preset energy value threshold, then the energy storage device storage response is started, if the obtained excess energy value data is 101, then it is sold on the grid to improve the profitability.

[0149] It is worth mentioning that, according to the embodiment of the application, further comprising:

[0150] If the total self-supply energy data is less than the total energy demand data, the total self-supply energy data and the total energy demand data are processed to obtain the energy supply difference data;

[0151] The energy supply difference data is compared with the preset difference threshold, and the energy supply adjustment scheme is determined according to the threshold comparison result;

[0152] According to the preset difference threshold, a first preset difference threshold and a second preset difference threshold are extracted, and the first preset difference threshold is less than the second preset difference threshold;

[0153] If the energy supply difference data is less than or equal to the first preset difference threshold, the set parameters of the self-supply energy device are adjusted;

[0154] If the energy supply difference data is greater than the first preset difference threshold and less than or equal to the second preset difference threshold, the external network energy supply response is activated;

[0155] If the energy supply difference data is greater than the second preset difference threshold, the set parameters of the self-supply energy device are adjusted, and the external network energy supply response is activated.

[0156] It should be noted that if the total self-energy supply data is less than the total energy demand data, it indicates that the current self-energy supply is insufficient, and the energy supply capacity needs to be improved. In order to reduce the energy cost, the energy supply needs to be adjusted according to the specific situation. First, the total energy demand data is subtracted from the total self-energy supply data to obtain the energy supply difference data. For example, the total energy demand data is 100, and the total self-energy supply data is 80. Then 100-80=20 is the energy supply difference data. Then, the energy supply difference data is compared with the preset difference threshold value. According to the threshold comparison result, the energy supply adjustment scheme is determined. The preset difference threshold value includes a first preset difference threshold value and a second preset difference threshold value. In this embodiment, the first preset difference threshold value is set to 25, and the second preset difference threshold value is set to 30. For example, the obtained energy supply difference data is 20, which is less than the first preset difference threshold value, so the setting parameter of the self-energy supply equipment is adjusted. If the obtained energy supply difference data is 28, which is greater than the first preset difference threshold value and less than the second preset difference threshold value, the external network energy supply response is activated. If the obtained energy supply difference data is 35, which is greater than the second preset difference threshold value, the setting parameter of the self-energy supply equipment is adjusted, and the external network energy supply response is activated.

[0157] It is worth mentioning that according to the embodiment of the present application, if the energy supply difference data is greater than the second preset difference threshold value, the setting parameter of the self-energy supply equipment is adjusted, and the external network energy supply response is activated. Before that, it also includes:

[0158] Obtain the energy use information of the comprehensive industrial energy monitoring system subsystem;

[0159] According to the energy use information, query the preset energy use priority list to obtain the energy use priority corresponding to the subsystem;

[0160] Sort the energy use priority from high to low to obtain a subsystem energy use order table;

[0161] Adjust the energy distribution scheme according to the energy use order table.

[0162] It should be noted that if the self-energy supply is insufficient, the energy supply of important equipment should be ensured first. First, obtain the energy use information of the subsystem. According to the energy use information, query the preset energy use priority list to obtain the energy use priority corresponding to the subsystem. The preset energy use priority list is obtained by querying the preset comprehensive industrial energy monitoring platform. Then, the energy use priority is sorted from high to low to obtain a subsystem energy use order table. Finally, the energy distribution scheme is adjusted according to the energy use order table, and the subsystem with high energy use priority is preferentially ensured to use energy.

[0163] The application also discloses a control optimization system based on the comprehensive industrial energy monitoring system, which comprises a memory and a processor, the memory comprises a control optimization method program based on the comprehensive industrial energy monitoring system, and the control optimization method program based on the comprehensive industrial energy monitoring system is executed by the processor to realize the following steps:

[0164] The historical running parameter data, the historical energy consumption data, the historical weather data and the historical energy production data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are acquired, the historical weather data and the historical energy production data are processed to obtain a historical energy consumption influence coefficient;

[0165] The historical running parameter data, the historical energy consumption influence coefficient and the corresponding historical energy consumption data are trained to obtain an energy consumption demand prediction model corresponding to the subsystem;

[0166] The set running parameter data, the predicted weather data and the planned energy production data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are acquired, and the energy consumption demand prediction model is combined to process to obtain energy consumption demand prediction data corresponding to the subsystem;

[0167] The real-time energy supply data of the subsystem of the comprehensive industrial energy monitoring system is acquired, the real-time energy supply data and the energy consumption demand prediction data are processed to obtain a supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with a preset supply-demand deviation rate threshold to obtain an energy supply and demand state of the subsystem, and the set running parameter data is adjusted according to the energy supply state;

[0168] The real-time energy consumption data and the energy price data of multiple energies of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are acquired, the real-time energy consumption data and the energy price data are combined with preset expected energy cost data to process to obtain an energy cost deviation rate of the subsystem;

[0169] The supply-demand deviation rate and the energy cost deviation rate are processed to obtain a subsystem running evaluation index corresponding to the subsystem, and the subsystem running evaluation index is processed to obtain a system running evaluation index of the comprehensive industrial energy monitoring system;

[0170] The system running evaluation index is compared with a preset system running evaluation threshold, the running state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, and the energy supply between the subsystems is optimized according to the running state.

[0171] It should be noted that, in order to realize the control optimization of the energy in each subsystem and between the subsystems in the comprehensive industrial energy monitoring system, each subsystem in the comprehensive industrial energy monitoring system can be determined by a person skilled in the art according to specific conditions, such as large motors, heating furnaces, production line distribution boxes, etc., and the comprehensive industrial energy involves multiple energy forms, such as electricity, coal, natural gas, steam, etc. First, the historical operation parameter data, historical energy consumption data, historical weather data and historical energy data of the multiple historical preset time periods of the subsystems of the comprehensive industrial energy monitoring system are acquired, including the historical operation parameter data and energy historical operation parameter data, the historical weather data and the historical energy data are processed to obtain the historical energy consumption influence coefficient, the initial energy demand prediction model is trained according to the historical operation parameter data, the historical energy consumption influence coefficient and the corresponding historical energy consumption data, and the trained energy demand prediction model corresponding to the subsystem is obtained, then the set operation parameter data, predicted weather data and planned energy data of the preset time period of the subsystem of the comprehensive industrial energy monitoring system are acquired, and after processing, the energy demand prediction data corresponding to the subsystem is obtained by inputting the energy demand prediction model for processing, while the real-time energy supply data of the subsystem is acquired, the energy demand prediction data is combined for processing to obtain the supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold, and the energy supply and demand state of the subsystem is obtained, including the supply-demand balance state or the supply-demand imbalance state, if it is the supply-demand imbalance state, the set operation parameter data is adjusted to optimize the energy supply and demand of the subsystem. After that, the real-time energy consumption data and energy price data of multiple energies of the subsystem in the preset time period are acquired, combined with the preset expected energy cost data for processing to obtain the energy cost deviation rate of the subsystem, the energy cost situation of the subsystem is evaluated, combined with the supply-demand deviation rate of the subsystem for processing to obtain the corresponding sub-operation evaluation index of the subsystem, the sub-operation evaluation index is processed to obtain the system operation evaluation index of the comprehensive industrial energy monitoring system, which is used to evaluate the operation of the entire comprehensive industrial energy system. Finally, the system operation evaluation index is compared with the preset system operation evaluation threshold, and the running state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, which is a normal running state or an abnormal running state, if it is an abnormal running state, the energy supply between the subsystems is optimized, so that the monitoring and control optimization of the energy at the subsystem side and between the subsystems are realized, the autonomy and independence of the subsystems are improved, the regional resources are fully coordinated, the resources are fully utilized, and the energy waste is reduced.

[0172] According to the embodiment of the application, the historical operation parameter data, historical energy consumption data, historical weather data and historical energy data of the subsystem of the comprehensive industrial energy monitoring system are acquired, the historical weather data and historical energy data are processed to obtain the historical energy consumption influence coefficient, which comprises:

[0173] The historical operation parameter data includes device historical operation parameter data and energy historical operation parameter data.

[0174] The historical weather data includes historical temperature difference average data and historical illumination duration data.

[0175] The historical production capacity data includes historical yield data and historical single-machine energy consumption data.

[0176] The historical temperature difference average data and the historical illumination duration data and the historical yield data and the historical single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing, so as to obtain historical energy consumption influence coefficients.

[0177] It should be noted that the historical operation parameter data includes device historical operation parameter data and energy historical operation parameter data, wherein the device historical operation parameter data and the energy historical operation parameter data are specifically set by a person skilled in the art according to the subsystem, such as the real-time rotating speed, the rated voltage, the rated current, the efficiency and the power factor of the motor of the subsystem, and the real-time current, the real-time voltage, the frequency fluctuation value and the harmonic content of the electric energy; the historical weather data includes historical temperature difference average data and historical illumination duration data, and the historical production capacity data includes historical yield data and historical single-machine energy consumption data, wherein the historical temperature difference average data refers to the average value of the difference between a plurality of historical temperatures and a preset standard temperature in a preset time period; the historical temperature difference average data and the historical illumination duration data and the historical yield data and the historical single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing, so as to obtain historical energy consumption influence coefficients.

[0178] The historical energy consumption influence coefficient calculation formula in the energy consumption influence coefficient evaluation model is as follows:

[0179] ;

[0180] Wherein, the historical energy consumption influence coefficient, 、 、 、 the historical temperature difference average data, the historical illumination duration data, the historical yield data and the historical single-machine energy consumption data, 、 、 is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset comprehensive industrial energy monitoring platform).

[0181] According to the embodiment of the present application, the set operation parameter data, the predicted weather data and the planned production capacity data of the subsystem of the comprehensive industrial energy monitoring system in a preset time period are obtained, and the energy demand prediction model is combined for processing, so as to obtain the energy demand prediction data corresponding to the subsystem, which includes:

[0182] obtaining set running parameter data of a subsystem of the comprehensive industrial energy monitoring system for a preset time period, predicted weather data and planned energy production data;

[0183] The set running parameter data includes device set running parameter data and energy set running parameter data.

[0184] The predicted weather data includes predicted temperature difference mean data and predicted illumination duration data.

[0185] The planned energy production data includes planned production data and calibrated single-machine energy consumption data.

[0186] The predicted temperature difference mean data and the predicted illumination duration data and the planned production data and the calibrated single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain predicted energy consumption influence coefficients.

[0187] The device set running parameter data, the energy set running parameter data and the predicted energy consumption influence coefficients are input into the energy demand prediction model for processing to obtain energy demand prediction data corresponding to the subsystem.

[0188] It should be noted that, in order to predict the energy demand of the subsystem, first, set running parameter data of the subsystem for a preset time period is obtained, including device set running parameter data and energy set running parameter data, predicted weather data including predicted temperature difference mean data and predicted illumination duration data, wherein the predicted temperature difference mean data refers to the average value of the difference between a plurality of predicted temperatures and a preset standard temperature within the preset time period, and planned energy production data including planned production data and calibrated single-machine energy consumption data, the predicted temperature difference mean data and the predicted illumination duration data and the planned production data and the calibrated single-machine energy consumption data are input into a preset energy consumption influence coefficient evaluation model for processing to obtain predicted energy consumption influence coefficients.

[0189] The calculation formula of the predicted energy consumption influence coefficients in the energy consumption influence coefficient evaluation model is as follows:

[0190] ;

[0191] wherein, the predicted energy consumption influence coefficients, , , , the predicted temperature difference mean data, the predicted illumination duration data, the planned production data and the calibrated single-machine energy consumption data, , , are preset characteristic coefficients (the characteristic coefficients are obtained by querying a preset comprehensive industrial energy monitoring platform).

[0192] The device sets the running parameter data, the energy setting running parameter data and the predicted energy consumption influence coefficient into the trained energy consumption demand prediction model for processing to obtain the energy consumption demand prediction data corresponding to the subsystem.

[0193] According to the embodiment of the present application, the real-time energy supply data of the comprehensive industrial energy monitoring system subsystem is obtained, the real-time energy supply data and the energy consumption demand prediction data are processed to obtain the supply-demand deviation rate of the subsystem, the supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold to obtain the energy supply-demand state of the subsystem, and the setting running parameter data is adjusted according to the energy supply state, including:

[0194] The real-time energy supply data of the comprehensive industrial energy monitoring system subsystem is obtained;

[0195] The real-time energy supply data and the energy consumption demand prediction data are processed to obtain the supply-demand deviation rate of the subsystem;

[0196] The supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold to obtain the energy supply-demand state of the subsystem, including the supply-demand balance state or the supply-demand imbalance state;

[0197] If the supply-demand deviation rate is less than or equal to the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is the supply-demand balance state;

[0198] If the supply-demand deviation rate is greater than the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is the supply-demand imbalance state, and the setting running parameter data is adjusted.

[0199] It should be noted that in order to evaluate the energy supply-demand situation of the subsystem, the real-time energy supply data of the subsystem is first obtained, and the obtained energy consumption demand prediction data is processed to obtain the supply-demand deviation rate of the subsystem. The supply-demand deviation rate refers to the ratio of the absolute value of the difference between the real-time energy supply data and the energy consumption demand prediction data to the real-time energy supply data. For example, the real-time energy supply data is 10, the energy consumption demand prediction data is 8, The obtained supply-demand deviation rate is compared with the preset supply-demand deviation rate threshold to obtain the energy supply-demand state of the subsystem. In this embodiment, the supply-demand deviation rate threshold is set to (0, 0.25], (0.25, 1], which respectively corresponds to the supply-demand balance state and the supply-demand imbalance state. For example, the obtained supply-demand deviation rate is 0.2, which is less than the preset supply-demand deviation rate threshold, so it is determined that the energy supply-demand state of the subsystem is the supply-demand balance state. If the obtained supply-demand deviation rate is 0.3, which is greater than the preset supply-demand deviation rate threshold, it is determined that the energy supply-demand state of the subsystem is the supply-demand imbalance state, and the setting running parameter data is adjusted according to the supply-demand deviation rate to balance the energy supply-demand of the subsystem.

[0200] According to the embodiment of the present application, the real-time energy consumption data and energy price data of the multiple energy sources in the preset time period of the subsystem of the comprehensive industrial energy monitoring system are acquired, the real-time energy consumption data and the energy price data are processed in combination with the preset expected energy cost data to obtain the energy cost deviation rate of the subsystem, and the energy cost deviation rate of the subsystem is obtained, including:

[0201] The real-time energy consumption data and energy price data of the multiple energy sources in the preset time period of the subsystem of the comprehensive industrial energy monitoring system are acquired.

[0202] The real-time energy consumption data is multiplied by the energy price data and summed to obtain the energy consumption cost data of the subsystem.

[0203] The energy consumption cost data and the preset expected energy cost data are processed to obtain the energy cost deviation rate of the subsystem.

[0204] It should be noted that, in order to understand the energy consumption cost, the real-time energy consumption data and energy price data of the multiple energy sources in the preset time period of the subsystem are first acquired, the real-time energy consumption data is multiplied by the energy price data and summed to obtain the energy consumption cost data of the subsystem.

[0205] The energy consumption cost data calculation formula is:

[0206]

[0207] Among them, is the energy consumption cost data, , The real-time energy consumption data and energy price data of the i-th energy source are respectively;

[0208] The energy consumption cost data and the preset expected energy cost data are processed to obtain the energy cost deviation rate of the subsystem.

[0209] The energy cost deviation rate calculation formula is:

[0210]

[0211] Among them, is the energy cost deviation rate, , The energy consumption cost data and the preset expected energy cost data are respectively.

[0212] According to the embodiment of the present application, the supply-demand deviation rate and the energy cost deviation rate are processed to obtain the corresponding subsystem operation evaluation index of the subsystem, the subsystem operation evaluation index is processed to obtain the system operation evaluation index of the comprehensive industrial energy monitoring system, and the system operation evaluation index of the comprehensive industrial energy monitoring system is obtained, including:

[0213] ​​According to the supply-demand deviation rate and the energy cost deviation rate, a sub-operation evaluation index corresponding to the subsystem is obtained;

[0214] Type characteristic data of the subsystem is acquired, a preset weight coefficient list is queried according to the type characteristic data, and a weight coefficient corresponding to the subsystem is obtained;

[0215] According to the multiple sub-operation evaluation indexes and the corresponding weight coefficients, a system operation evaluation index of the comprehensive industrial energy monitoring system is obtained.

[0216] It should be noted that the operation of the subsystem is comprehensively evaluated according to the energy supply and demand and the cost use of the subsystem. First, according to the obtained supply-demand deviation rate and energy cost deviation rate, a sub-operation evaluation index corresponding to the subsystem is obtained;

[0217] The sub-operation evaluation index calculation formula is:

[0218] ;

[0219] Among them, is the sub-operation evaluation index, , respectively, the supply-demand deviation rate and the energy cost deviation rate, is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset comprehensive industrial energy monitoring platform);

[0220] Further, type characteristic data of the subsystem is acquired, a preset weight coefficient list is queried according to the type characteristic data, and a weight coefficient corresponding to the subsystem is obtained, wherein the preset weight coefficient list is obtained by querying the preset comprehensive industrial energy monitoring platform, and according to the multiple sub-operation evaluation indexes and the corresponding weight coefficients, a system operation evaluation index of the comprehensive industrial energy monitoring system is obtained.

[0221] The system operation evaluation index calculation formula is:

[0222] ;

[0223] Among them, is the system operation evaluation index, , respectively, the sub-operation evaluation index of the jth subsystem and the weight coefficient, is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset comprehensive industrial energy monitoring platform).

[0224] According to the embodiment of the present application, the system operation evaluation index is compared with a preset system operation evaluation threshold value, the running state of the comprehensive industrial energy monitoring system is determined according to the threshold comparison result, and the energy supply between the subsystems is optimized according to the running state.

[0225] processing the system operation evaluation index with a preset system operation evaluation benchmark index to obtain an operation evaluation relative value;

[0226] comparing the operation evaluation relative value with a preset system operation evaluation threshold value to obtain an operation state of the comprehensive industrial energy monitoring system, including a normal operation state or an abnormal operation state;

[0227] if the operation evaluation relative value is less than or equal to the preset system operation evaluation threshold value, determining that the operation state of the comprehensive industrial energy monitoring system is an abnormal operation state, and optimizing energy supply between subsystems according to the operation state;

[0228] if the operation evaluation relative value is greater than the preset system operation evaluation threshold value, determining that the operation state of the comprehensive industrial energy monitoring system is a normal operation state.

[0229] It should be noted that the obtained system operation evaluation index is processed with a preset system operation evaluation benchmark index to obtain an operation evaluation relative value, for example, the system operation evaluation index is 7, the preset system operation evaluation benchmark index is 10, and 7 / 10=0.7 is the operation evaluation relative value, and the operation evaluation relative value is compared with the preset system operation evaluation threshold value to obtain the operation state of the comprehensive industrial energy monitoring system, in the embodiment, the preset system operation evaluation threshold value is set to (0, 0.75], (0.75, 1], corresponding to the normal operation state and the abnormal operation state, respectively, for example, the obtained operation evaluation relative value is 0.7, which is less than the preset system operation evaluation threshold value, so that the operation state of the comprehensive industrial energy monitoring system is determined to be an abnormal operation state, and energy supply between subsystems is optimized according to the operation state; if the obtained operation evaluation relative value is 0.9, which is greater than the preset system operation evaluation threshold value, it is determined that the operation state of the comprehensive industrial energy monitoring system is a normal operation state.

[0230] It is worth mentioning that, according to the embodiment of the application, further comprising:

[0231] obtaining energy use time data, self-energy total data and total energy demand data of the comprehensive industrial energy monitoring system;

[0232] comparing the self-energy total data with the total energy demand data;

[0233] if the self-energy total data is greater than the total energy demand data, processing the self-energy total data and the total energy demand data to obtain excess energy supply data;

[0234] querying a preset energy price list according to the energy use time data to obtain a real-time energy price;

[0235] According to the excess energy supply data and a real-time energy price, excess energy value data is obtained by calculation;

[0236] The excess energy value data is compared with a preset energy value threshold, and an excess energy disposal scheme is determined according to a comparison result of the threshold comparison;

[0237] If greater than the preset energy value threshold, the excess energy is sold on the grid;

[0238] If less than or equal to the preset energy value threshold, a storage energy device is started to store energy.

[0239] It should be noted that, in order to reduce the energy operation cost and maximize the advantages of enterprise self-supply energy, the energy use time data, the total self-supply energy data and the total energy demand data of the comprehensive industrial energy monitoring system are obtained, the total self-supply energy data and the total energy demand data are compared first, if the total self-supply energy data is greater than the total energy demand data, the difference between the total self-supply energy data and the total energy demand data is the excess energy supply data, which indicates that there is a surplus in the self-supply energy of the enterprise, which needs to be reasonably arranged, the preset energy price list is queried according to the energy use time data to obtain a real-time energy price, then the excess energy value data is obtained by calculation according to the excess energy supply data and the real-time energy price, for example, the excess energy supply data is 100, the real-time energy price is 0.55, and 100*0.55=55 is the excess energy value data; finally, the excess energy value data is compared with a preset energy value threshold, and an excess energy disposal scheme is determined according to a comparison result of the threshold comparison, in the embodiment, the energy value threshold is set to 100, for example, the obtained excess energy value data is 55, which is less than the preset energy value threshold, so the storage energy device is started to store energy, if the obtained excess energy value data is 101, the excess energy is sold on the grid to improve the profitability.

[0240] It is worth mentioning that, according to the embodiment of the application, further comprising:

[0241] If the total self-supply energy data is less than the total energy demand data, the excess energy supply data is obtained by processing the total self-supply energy data and the total energy demand data;

[0242] The excess energy supply data is compared with a preset difference threshold, and an energy supply adjustment scheme is determined according to a comparison result of the threshold comparison;

[0243] According to the preset difference threshold, a first preset difference threshold and a second preset difference threshold are extracted, and the first preset difference threshold is less than the second preset difference threshold;

[0244] If the excess energy supply data is less than or equal to the first preset difference threshold, the set parameters of the self-supply energy device are adjusted;

[0245] if the energy supply difference data is greater than the first preset difference threshold and less than or equal to the second preset difference threshold, activating an external network energy supply response;

[0246] if the energy supply difference data is greater than the second preset difference threshold, adjusting the setting parameters of the self-energy supply device and activating the external network energy supply response.

[0247] It should be noted that if the total self-energy supply data is less than the total energy demand data, it indicates that the current self-energy supply is insufficient, and the energy supply capacity needs to be improved. In order to reduce the energy cost, the energy supply needs to be adjusted according to the specific situation. First, the total energy demand data is subtracted from the total self-energy supply data to obtain the energy supply difference data. For example, the total energy demand data is 100, the total self-energy supply data is 80, and 100-80=20 is the energy supply difference data. Then, the energy supply difference data is compared with the preset difference threshold, and the energy supply adjustment scheme is determined according to the comparison result. The preset difference threshold includes the first preset difference threshold and the second preset difference threshold. In the embodiment, the first preset difference threshold is set to 25, and the second preset difference threshold is set to 30. For example, the obtained energy supply difference data is 20, which is less than the first preset difference threshold, so the setting parameters of the self-energy supply device are adjusted. If the obtained energy supply difference data is 28, which is greater than the first preset difference threshold and less than the second preset difference threshold, the external network energy supply response is activated. If the obtained energy supply difference data is 35, which is greater than the second preset difference threshold, the setting parameters of the self-energy supply device are adjusted and the external network energy supply response is activated.

[0248] It is worth mentioning that according to the embodiment of the present application, if the energy supply difference data is greater than the second preset difference threshold, the setting parameters of the self-energy supply device are adjusted and the external network energy supply response is activated, which further includes:

[0249] obtaining energy use information of a subsystem of the comprehensive industrial energy monitoring system;

[0250] querying a preset energy use priority list according to the energy use information to obtain an energy use priority corresponding to the subsystem;

[0251] sorting the energy use priority from high to low to obtain a subsystem energy use order table;

[0252] adjusting an energy distribution scheme according to the energy use order table.

[0253] It should be noted that if self-supplied energy is insufficient, the energy supply of important equipment should be guaranteed first. First, the energy consumption information of the subsystem should be obtained, and the preset energy consumption priority list should be queried based on the energy consumption information to obtain the energy consumption priority corresponding to the subsystem. The preset energy consumption priority list is obtained by querying the preset comprehensive industrial energy monitoring platform, and then the energy consumption priorities are sorted from high to low to obtain the subsystem energy consumption sequence table. Finally, the energy allocation plan is adjusted according to the energy consumption sequence table to give priority to ensuring the energy consumption of subsystems with high energy consumption priorities.

[0254] The third aspect of the present invention provides a readable storage medium, which stores a control optimization method program based on an integrated industrial energy monitoring system. When the control optimization method program based on an integrated industrial energy monitoring system is executed by a processor, the steps of the control optimization method based on an integrated industrial energy monitoring system as described in any one of the above items are implemented.

[0255] The control optimization method and system based on the comprehensive industrial energy monitoring system disclosed in the present invention obtains historical weather data and historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system for a preset time period and processes them to obtain the historical energy consumption impact coefficient, combines the historical operating parameter data and the corresponding historical energy consumption data for training, obtains the energy demand forecasting model corresponding to the subsystem, obtains the set operating parameter data, predicted weather data and planned production capacity data of the subsystem for a preset time period, combines them with the energy demand forecasting model for processing, obtains the energy demand forecasting data corresponding to the subsystem, obtains the real-time energy supply data of the subsystem, combines them with the energy demand forecasting data for processing, and obtains the energy demand forecasting data of the subsystem. The supply and demand deviation rate is used to obtain the energy supply and demand status of the subsystem through threshold comparison, and the operating parameter data is adjusted according to the energy supply status. The real-time energy consumption data and energy price data of multiple energy sources in the preset time period of the subsystem are obtained and combined with the preset expected energy cost data for processing to obtain the energy cost deviation rate of the subsystem. Combined with the supply and demand deviation rate, the sub-operation evaluation index of the subsystem is obtained for further processing to obtain the system operation evaluation index of the comprehensive industrial energy monitoring system. Finally, the operating status of the comprehensive industrial energy monitoring system is determined through the threshold comparison results, and the energy supply between subsystems is optimized according to the operating status, thereby realizing the control optimization of energy within and between subsystems.

[0256] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely exemplary. For example, the division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices, or units, and can be electrical, mechanical, or in other forms.

[0257] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected as needed to achieve the purposes of the embodiments.

[0258] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; and the integrated unit can be implemented in the form of hardware or hardware plus software functional units.

[0259] Those of ordinary skill in the art can understand that all or part of the steps of the above-described method embodiments can be completed by a program instructing related hardware, and the aforementioned program can be stored in a readable storage medium, and when the program is executed, the steps of the method embodiments are executed; and the aforementioned storage medium includes mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks or optical disks, and various media that can store program codes.

[0260] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes mobile storage devices, ROMs, RAMs, magnetic disks or optical disks, and various media that can store program codes.

Claims

1. A control optimization method based on an integrated industrial energy monitoring system, characterized in that: The following steps are involved: Obtain historical operating parameter data, historical energy consumption data, historical weather data, and historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system for a preset historical period, and process the historical weather data and historical production capacity data to obtain a historical energy consumption impact coefficient; Training is performed based on the historical operating parameter data, the historical energy consumption impact coefficient, and the corresponding historical energy consumption data to obtain an energy demand prediction model corresponding to the subsystem; Obtaining the set operating parameter data, forecast weather data, and planned production capacity data for the subsystem of the integrated industrial energy monitoring system for a preset time period, and processing them in combination with the energy demand forecasting model to obtain energy demand forecast data corresponding to the subsystem; Acquire real-time energy supply data of a subsystem of the integrated industrial energy monitoring system, process the real-time energy supply data and the energy demand forecast data to obtain a supply-demand deviation rate of the subsystem, compare the supply-demand deviation rate with a preset supply-demand deviation rate threshold, obtain an energy supply and demand status of the subsystem, and adjust the set operating parameter data according to the energy supply status; Obtain real-time energy consumption data and energy price data of multiple energy sources in a preset time period of the integrated industrial energy monitoring system subsystem, process the real-time energy consumption data and energy price data in combination with preset expected energy cost data, and obtain the energy cost deviation rate of the subsystem; Processing is performed based on the supply-demand deviation rate and the energy cost deviation rate to obtain a sub-operation evaluation index corresponding to the subsystem, and processing is performed based on the sub-operation evaluation index to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system; Comparing the system operation evaluation index with a preset system operation evaluation threshold, determining the operation status of the comprehensive industrial energy monitoring system according to the threshold comparison result, and optimizing the energy supply between subsystems according to the operation status; The historical operating parameter data includes equipment historical operating parameter data and energy historical operating parameter data; The historical weather data includes historical temperature difference mean data and historical sunshine duration data; The historical production capacity data includes historical production data and historical single-unit energy consumption data; Inputting the historical temperature difference mean data and the historical sunshine duration data, as well as the historical output data and the historical single-unit energy consumption data into a preset energy consumption impact coefficient evaluation model for processing to obtain a historical energy consumption impact coefficient; Processing is performed based on the supply-demand deviation rate and the energy cost deviation rate to obtain a sub-operation evaluation index corresponding to the subsystem; Obtain the type characteristic data of the subsystem, query the preset weight coefficient list according to the type characteristic data, and obtain the weight coefficient corresponding to the subsystem; Processing the plurality of sub-operation evaluation indices and corresponding weight coefficients to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system; Obtain energy consumption time data, total self-supplied energy data and total energy demand data from the integrated industrial energy monitoring system; Comparing the total self-supplied energy data with the total energy demand data; If the total self-supplied energy data is greater than the total energy demand data, processing is performed based on the total self-supplied energy data and the total energy demand data to obtain excess energy supply data; querying a preset energy price list based on the energy consumption time data to obtain real-time energy prices; Calculate excess energy value data based on the excess energy supply data and real-time energy prices; Comparing the excess energy value data with a preset energy value threshold, and determining an excess energy disposal plan based on the threshold comparison result; Obtain real-time energy supply data of the subsystems of the integrated industrial energy monitoring system; Processing the real-time energy supply data and the energy demand forecast data to obtain a supply-demand deviation rate of the subsystem; Comparing the supply-demand deviation rate with a preset supply-demand deviation rate threshold to obtain the energy supply and demand state of the subsystem, including a supply-demand balance state or a supply-demand imbalance state; If the supply-demand deviation rate is less than or equal to a preset supply-demand deviation rate threshold, it is determined that the energy supply and demand state of the subsystem is in a supply-demand balance state; If the supply-demand deviation rate is greater than a preset supply-demand deviation rate threshold, the energy supply-demand state of the subsystem is determined to be in a supply-demand imbalance state, and the set operating parameter data is adjusted; Obtain real-time energy consumption data and energy price data of multiple energy sources during preset time periods in the integrated industrial energy monitoring system subsystem; Multiplying the real-time energy consumption data by the energy price data and summing the results to obtain energy consumption cost data of the subsystem; Processing the energy cost data and the preset expected energy cost data to obtain the energy cost deviation rate of the subsystem; If the total self-supplied energy data is less than the total energy demand data, the energy supply difference data is obtained by processing the total self-supplied energy data and the total energy demand data; Comparing the energy supply difference data with a preset difference threshold, and determining an energy supply adjustment plan based on the threshold comparison result; Extracting a first preset difference threshold and a second preset difference threshold according to the preset difference threshold, wherein the first preset difference threshold is smaller than the second preset difference threshold; If the energy supply difference data is less than or equal to a first preset difference threshold, adjusting the setting parameters of the self-powered device; If the energy supply difference data is greater than a first preset difference threshold and less than or equal to a second preset difference threshold, activating an external network energy supply response; If the energy supply difference data is greater than a second preset difference threshold, the setting parameters of the self-powered device are adjusted, and the external network energy supply response is activated.

2. The control optimization method based on the integrated industrial energy monitoring system according to claim 1 is characterized in that: The step of obtaining the set operating parameter data, forecast weather data, and planned production capacity data for the subsystem of the integrated industrial energy monitoring system during a preset time period, and processing the data in combination with the energy demand forecasting model to obtain the energy demand forecasting data corresponding to the subsystem includes: Obtaining the set operating parameter data, forecast weather data and planned production capacity data for the pre-set time period of the integrated industrial energy monitoring system subsystem; The set operating parameter data includes equipment set operating parameter data and energy set operating parameter data; The predicted weather data includes predicted temperature difference mean data and predicted sunshine duration data; The planned production capacity data includes planned output data and calibrated single-unit energy consumption data; Inputting the predicted temperature difference mean data, the predicted sunshine duration data, the planned output data, and the calibrated single-unit energy consumption data into a preset energy consumption impact coefficient evaluation model for processing to obtain a predicted energy consumption impact coefficient; The equipment setting operation parameter data, energy setting operation parameter data and predicted energy consumption impact coefficient are input into the energy consumption demand prediction model for processing to obtain energy consumption demand prediction data corresponding to the subsystem.

3. The control optimization method based on the integrated industrial energy monitoring system according to claim 2 is characterized in that: Comparing the system operation evaluation index with a preset system operation evaluation threshold, determining the operation status of the comprehensive industrial energy monitoring system according to the threshold comparison result, and optimizing the energy supply between subsystems according to the operation status includes: Processing the system operation evaluation index with a preset system operation evaluation benchmark index to obtain an operation evaluation relative value; Comparing the operation evaluation relative value with a preset system operation evaluation threshold to obtain the operation status of the comprehensive industrial energy monitoring system, including a normal operation status or an abnormal operation status; If the operation evaluation relative value is less than or equal to a preset system operation evaluation threshold, the operation state of the integrated industrial energy monitoring system is determined to be an abnormal operation state, and the energy supply between subsystems is optimized according to the operation state; If the operation evaluation relative value is greater than a preset system operation evaluation threshold, it is determined that the operation state of the comprehensive industrial energy monitoring system is a normal operation state.

4. A control optimization system based on an integrated industrial energy monitoring system, characterized in that: The system comprises a memory and a processor, wherein the memory comprises a program of a control optimization method based on an integrated industrial energy monitoring system, and when the program of the control optimization method based on the integrated industrial energy monitoring system is executed by the processor, the following steps are implemented: Obtain historical operating parameter data, historical energy consumption data, historical weather data, and historical production capacity data of the subsystem of the comprehensive industrial energy monitoring system for a preset historical period, and process the historical weather data and historical production capacity data to obtain a historical energy consumption impact coefficient; Training is performed based on the historical operating parameter data, the historical energy consumption impact coefficient, and the corresponding historical energy consumption data to obtain an energy demand prediction model corresponding to the subsystem; Obtaining the set operating parameter data, forecast weather data, and planned production capacity data for the subsystem of the integrated industrial energy monitoring system for a preset time period, and processing them in combination with the energy demand forecasting model to obtain energy demand forecast data corresponding to the subsystem; Acquire real-time energy supply data of a subsystem of the integrated industrial energy monitoring system, process the real-time energy supply data and the energy demand forecast data to obtain a supply-demand deviation rate of the subsystem, compare the supply-demand deviation rate with a preset supply-demand deviation rate threshold, obtain an energy supply and demand status of the subsystem, and adjust the set operating parameter data according to the energy supply status; Obtain real-time energy consumption data and energy price data of multiple energy sources in a preset time period of the integrated industrial energy monitoring system subsystem, process the real-time energy consumption data and energy price data in combination with preset expected energy cost data, and obtain the energy cost deviation rate of the subsystem; Processing is performed based on the supply-demand deviation rate and the energy cost deviation rate to obtain a sub-operation evaluation index corresponding to the subsystem, and processing is performed based on the sub-operation evaluation index to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system; Comparing the system operation evaluation index with a preset system operation evaluation threshold, determining the operation status of the comprehensive industrial energy monitoring system according to the threshold comparison result, and optimizing the energy supply between subsystems according to the operation status; The historical operating parameter data includes equipment historical operating parameter data and energy historical operating parameter data; The historical weather data includes historical temperature difference mean data and historical sunshine duration data; The historical production capacity data includes historical production data and historical single-unit energy consumption data; Inputting the historical temperature difference mean data and the historical sunshine duration data, as well as the historical output data and the historical single-unit energy consumption data into a preset energy consumption impact coefficient evaluation model for processing to obtain a historical energy consumption impact coefficient; Processing is performed based on the supply-demand deviation rate and the energy cost deviation rate to obtain a sub-operation evaluation index corresponding to the subsystem; Obtain the type characteristic data of the subsystem, query the preset weight coefficient list according to the type characteristic data, and obtain the weight coefficient corresponding to the subsystem; Processing the plurality of sub-operation evaluation indices and corresponding weight coefficients to obtain a system operation evaluation index of the comprehensive industrial energy monitoring system; Obtain energy consumption time data, total self-supplied energy data and total energy demand data from the integrated industrial energy monitoring system; Comparing the total self-supplied energy data with the total energy demand data; If the total self-supplied energy data is greater than the total energy demand data, processing is performed based on the total self-supplied energy data and the total energy demand data to obtain excess energy supply data; querying a preset energy price list based on the energy consumption time data to obtain real-time energy prices; Calculate excess energy value data based on the excess energy supply data and real-time energy prices; Comparing the excess energy value data with a preset energy value threshold, and determining an excess energy disposal plan based on the threshold comparison result; Obtain real-time energy supply data of the subsystems of the integrated industrial energy monitoring system; Processing the real-time energy supply data and the energy demand forecast data to obtain a supply-demand deviation rate of the subsystem; Comparing the supply-demand deviation rate with a preset supply-demand deviation rate threshold to obtain the energy supply and demand state of the subsystem, including a supply-demand balance state or a supply-demand imbalance state; If the supply-demand deviation rate is less than or equal to a preset supply-demand deviation rate threshold, it is determined that the energy supply and demand state of the subsystem is in a supply-demand balance state; If the supply-demand deviation rate is greater than a preset supply-demand deviation rate threshold, the energy supply-demand state of the subsystem is determined to be in a supply-demand imbalance state, and the set operating parameter data is adjusted; Obtain real-time energy consumption data and energy price data of multiple energy sources during preset time periods in the integrated industrial energy monitoring system subsystem; Multiplying the real-time energy consumption data by the energy price data and summing the results to obtain energy consumption cost data of the subsystem; Processing the energy cost data and the preset expected energy cost data to obtain the energy cost deviation rate of the subsystem; If the total self-supplied energy data is less than the total energy demand data, the energy supply difference data is obtained by processing the total self-supplied energy data and the total energy demand data; Comparing the energy supply difference data with a preset difference threshold, and determining an energy supply adjustment plan based on the threshold comparison result; Extracting a first preset difference threshold and a second preset difference threshold according to the preset difference threshold, wherein the first preset difference threshold is smaller than the second preset difference threshold; If the energy supply difference data is less than or equal to a first preset difference threshold, adjusting the setting parameters of the self-powered device; If the energy supply difference data is greater than a first preset difference threshold and less than or equal to a second preset difference threshold, activating an external network energy supply response; If the energy supply difference data is greater than a second preset difference threshold, the setting parameters of the self-powered device are adjusted, and the external network energy supply response is activated.

5. The control optimization system based on the integrated industrial energy monitoring system according to claim 4 is characterized in that: The step of obtaining the set operating parameter data, forecast weather data, and planned production capacity data for the subsystem of the integrated industrial energy monitoring system during a preset time period, and processing the data in combination with the energy demand forecasting model to obtain the energy demand forecasting data corresponding to the subsystem includes: Obtaining the set operating parameter data, forecast weather data and planned production capacity data for the pre-set time period of the integrated industrial energy monitoring system subsystem; The set operating parameter data includes equipment set operating parameter data and energy set operating parameter data; The predicted weather data includes predicted temperature difference mean data and predicted sunshine duration data; The planned production capacity data includes planned output data and calibrated single-unit energy consumption data; Inputting the predicted temperature difference mean data, the predicted sunshine duration data, the planned output data, and the calibrated single-unit energy consumption data into a preset energy consumption impact coefficient evaluation model for processing to obtain a predicted energy consumption impact coefficient; The equipment setting operation parameter data, energy setting operation parameter data and predicted energy consumption impact coefficient are input into the energy consumption demand prediction model for processing to obtain energy consumption demand prediction data corresponding to the subsystem.

Images