Energy-saving optimization method and system of high-voltage frequency converter

Abstract

The application discloses an energy-saving optimization method and system of a high-voltage frequency converter, and the method comprises the following steps: determining historical characteristic operation data and historical characteristic control data of different motor working condition requirements according to historical operation logs; analyzing the historical characteristic operation data of the same motor working condition requirement, determining optimal characteristic operation data according to an analysis result, and generating an application evaluation value; judging whether the historical characteristic control data needs to be optimized according to the application evaluation value and an energy-saving principle, determining the historical characteristic control data needing to be optimized and an optimization strategy if the historical characteristic control data needs to be optimized, obtaining energy-saving optimization data, constructing an energy-saving optimization control model according to the motor working condition requirement and the energy-saving optimization data; and obtaining optimal control data of an actual motor working condition requirement based on the energy-saving optimization control model, accurately and efficiently controlling the high-voltage frequency converter according to a demand instruction, improving equipment operation efficiency and energy-saving efficiency, and realizing safe and efficient operation of the system.

Description

Technical Field

[0001] The present application relates to the technical field of energy-saving of high-voltage inverters, and in particular to an energy-saving optimization method and system for high-voltage inverters. Background Art

[0002] A high-voltage inverter is a power regulation device used to control and regulate the operation of high-voltage motors. It adjusts the motor's speed and torque by varying the power supply frequency and voltage, thereby achieving speed control of the motor. However, existing high-voltage inverter control methods use a fixed approach and cannot achieve optimal and precise control of motor requirements. This not only reduces equipment operating efficiency but also affects system stability and reliability. Summary of the Invention

[0003] In order to solve the above technical problems, the present application provides an energy-saving optimization method and system for a high-voltage inverter, which determines the optimization characteristic operation data of different motor working conditions, calculates the application evaluation value of the optimization characteristic operation data corresponding to the historical characteristic control data, determines the energy-saving optimization data according to the application evaluation value and the energy-saving principle, constructs an energy-saving optimization control model according to the different motor working conditions and the corresponding energy-saving optimization data, determines the optimal control data of the actual motor working conditions based on the energy-saving optimization control model, and performs precise and efficient control of the high-voltage inverter according to the demand instructions, thereby improving the equipment operation efficiency and energy-saving efficiency, and realizing safe and efficient operation of the system.

[0004] In some embodiments of the present application, a method for optimizing energy saving of a high-voltage inverter is provided, comprising:

[0005] Obtain the historical operation log of the high-voltage inverter and determine the historical characteristic operation data and historical characteristic control data required for different motor working conditions based on the historical operation log;

[0006] Analyze the historical characteristic operation data of the same motor working condition demand, determine the preferred characteristic operation data of each motor working condition demand based on the analysis results, and generate the application evaluation value of the corresponding historical characteristic control data based on the preferred characteristic operation data;

[0007] Based on the application evaluation value and energy-saving principles, determine whether the historical feature control data needs to be optimized. If so, determine the historical feature control data to be optimized and the optimization strategy;

[0008] Optimize historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and build an energy-saving optimization control model based on different motor working conditions and energy-saving optimization data;

[0009] Obtain the actual motor working condition requirements, obtain the optimal control data of the actual motor working condition requirements based on the energy-saving optimization control model, and generate control instructions for the high-voltage inverter according to the optimal control data.

[0010] In some embodiments of the present application, determining historical characteristic operation data and historical characteristic control data for different motor operating conditions based on historical operation logs includes:

[0011] Obtain the historical operation logs of the high-voltage inverter, extract the historical demand instructions corresponding to each historical operation log, analyze and classify the historical demand instructions, and obtain multiple different motor operating condition requirements;

[0012] Use the historical running time in each historical running log as the time reference line and set the collection nodes based on the preset time interval;

[0013] According to the collection nodes in each time reference line, the completion degree of the corresponding motor working condition requirements, the historical operation data of the motor, and the historical control data of the high-voltage inverter are collected and mapped to the corresponding time reference line to generate a change relationship curve;

[0014] Determine a linear correlation based on the change relationship curve, and determine the degree of correlation between the historical operating data of the motor and the historical control data of the high-voltage inverter and the completion degree of the corresponding motor working condition requirements based on the linear correlation;

[0015] The historical operation data and the historical control data having a correlation greater than a preset correlation threshold are respectively set as the historical characteristic operation data and the historical characteristic control data of the motor working condition demand corresponding to the time reference line;

[0016] Compare historical characteristic operation data and historical characteristic control data according to the same motor working condition requirements, and determine the credibility of the historical characteristic operation data and historical characteristic control data based on the comparison results;

[0017] The historical feature operation data and historical feature control data whose credibility is less than the preset credibility threshold are eliminated.

[0018] In some embodiments of the present application, determining the preferred characteristic operating data required for each motor operating condition based on the analysis results includes:

[0019] Analyze the historical characteristic operation data of different historical operating times of the same motor working condition requirements and the completion degree of the corresponding motor working condition requirements;

[0020] Generate the change efficiency based on the change value of the completion degree within the corresponding historical operation time, and the comparison result between the final completion degree and the preset completion degree threshold. Remove the historical operation time and historical characteristic operation data with a change efficiency less than the preset change efficiency threshold and a final completion degree less than the preset completion degree threshold;

[0021] Calculate the fluctuation degree of the remaining multiple historical characteristic operation data within the same historical operation time, and generate the fluctuation evaluation value of the historical characteristic operation data within the corresponding historical operation time according to the fluctuation degree of the multiple historical characteristic operation data and the corresponding weight coefficient;

[0022] A completion evaluation value is generated for the final completion degree and change efficiency of the motor operating condition requirements corresponding to the historical characteristic operating data of the remaining historical operating time, the completion evaluation values ​​are sorted, and the fluctuation evaluation values ​​are judged in turn according to the sorting results, and the historical characteristic operating data with a fluctuation evaluation value less than the preset fluctuation evaluation value threshold is set as the preferred characteristic operating data corresponding to the motor operating condition requirements.

[0023] In some embodiments of the present application, generating an application evaluation value corresponding to historical feature control data based on the preferred feature operation data includes:

[0024] Comparing the preferred characteristic operation data with a preset standard characteristic operation data interval corresponding to the motor operating condition requirement, obtaining the number of preferred characteristic operation data that are not within the preset standard characteristic operation data interval and the characteristic operation data deviation amount of the preferred characteristic operation data that are not within the preset standard characteristic operation data interval;

[0025] Generate an operation evaluation coefficient based on the number and deviation of characteristic operation data;

[0026] Generate a fluctuation evaluation coefficient based on the degree of fluctuation of the historical characteristic control data corresponding to the preferred characteristic operation data within the historical operation period;

[0027] The preferred characteristic operation data and the corresponding historical characteristic control data are converted into energy consumption to obtain the energy consumption array within the corresponding historical operation time. The energy consumption array at the same collection node is time-aligned and the energy consumption value of the aligned energy consumption array is calculated. The energy consumption evaluation coefficient is generated based on the energy consumption values ​​at multiple collection nodes in the historical operation time.

[0028] Calculate the comprehensive usage cost of the historical feature control data corresponding to the preferred feature operation data within the historical operation time, and subtract the comprehensive usage cost from the preset usage cost threshold to obtain the usage cost difference, and set the compensation coefficient according to the usage cost difference;

[0029] An application evaluation value corresponding to the historical characteristic control data is generated according to the operation evaluation coefficient, the fluctuation evaluation coefficient, the energy consumption evaluation coefficient and the compensation coefficient.

[0030] In some embodiments of the present application, the calculation formula of the application evaluation value is:

[0031]

[0032] Among them, Y is the application evaluation value, a1 is the operation evaluation conversion coefficient, y1 is the weight coefficient of the operation evaluation coefficient, m is the number of preferred feature operation data that are not in the preset standard feature operation data interval, n is the total number of preferred feature operation data, △Ps is the deviation of the sth feature operation data, B0 is the fluctuation degree threshold, B is the fluctuation degree of the historical feature control data within the historical operation time, y2 is the weight coefficient of the fluctuation evaluation coefficient, a2 is the fluctuation evaluation conversion coefficient, w is the number of collection nodes within the corresponding historical application time, Ni is the energy consumption value of the energy consumption array at the i-th collection node, y3 is the weight coefficient of the energy consumption evaluation coefficient, a3 is the energy consumption evaluation conversion coefficient, and c is the compensation coefficient.

[0033] In some embodiments of the present application, judging whether historical control data needs to be optimized based on the application evaluation value and the energy-saving principle includes:

[0034] Presetting a preset application evaluation value threshold;

[0035] When the application evaluation value is less than the preset application evaluation value threshold, the optimized feature operation data to be optimized is screened out according to the feature operation data deviation amount and the optimization coefficient is calculated;

[0036] When the application evaluation value is greater than the preset application evaluation value threshold, the standard data interval of each energy consumption indicator is determined based on the energy-saving principle. According to the degree of correlation between the preferred characteristic operation data and the energy consumption indicator, the optimized characteristic operation data to be optimized for each energy consumption indicator is determined and the optimization coefficient is calculated.

[0037] In some embodiments of the present application, determining the historical feature control data to be optimized and the optimization strategy includes:

[0038] Determine the degree of correlation between the optimization feature operation data to be optimized and the historical feature control data according to the synchronous change time nodes and synchronous change degrees of the optimization feature operation data to be optimized and the historical feature control data within the historical operation time;

[0039] The historical feature control data with a correlation degree greater than a preset correlation degree is set as the historical feature control data to be optimized, and an optimization strategy for the corresponding historical feature control data is generated according to the optimization coefficient. The corresponding historical feature control data is optimized according to the optimization strategy to obtain energy-saving optimization data.

[0040] In some embodiments of the present application, an energy-saving optimization control model is constructed according to different motor operating conditions and energy-saving optimization data, including:

[0041] Obtain characteristic operating condition data for different motor operating conditions, and construct training and test data sets based on the characteristic operating condition data and energy-saving optimization data corresponding to the motor operating condition requirements;

[0042] The characteristic operating condition data in the training data set is set as input data, and the energy-saving optimization data corresponding to the characteristic operating condition data in the training data set is set as output data, and a neural network training is performed to obtain an initial energy-saving optimization control model;

[0043] The accuracy of the initial energy-saving optimization control model generated based on the test data set;

[0044] If the accuracy is less than the preset accuracy threshold, the training data set is iteratively trained to rebuild the initial energy-saving optimization control model until the accuracy is greater than the preset accuracy threshold, and the energy-saving optimization control model is generated;

[0045] If the accuracy is greater than the preset accuracy threshold, the initial energy-saving optimization control model is set as the energy-saving optimization control model.

[0046] In some embodiments of the present application, generating a control instruction for a high-voltage inverter according to optimal control data includes:

[0047] Obtain the actual motor working condition requirements and obtain the actual characteristic working condition data of the actual motor working condition requirements;

[0048] The actual characteristic operating condition data is input into the energy-saving optimization control model to obtain the optimal control data required by the actual motor operating condition, and control instructions are generated for the high-voltage inverter according to the optimal control data.

[0049] In some embodiments of the present application, an energy-saving optimization system for a high-voltage inverter is also included:

[0050] An acquisition module is used to obtain the historical operation log of the high-voltage inverter and determine the historical characteristic operation data and historical characteristic control data required by different motor working conditions based on the historical operation log;

[0051] A generation module is used to analyze the historical characteristic operation data of the same motor working condition requirement, determine the preferred characteristic operation data of each motor working condition requirement based on the analysis results, and generate an application evaluation value of the corresponding historical characteristic control data based on the preferred characteristic operation data;

[0052] A judgment module is used to judge whether the historical characteristic control data needs to be optimized based on the application evaluation value and the energy-saving principle. If so, it determines the historical characteristic control data to be optimized and the optimization strategy;

[0053] A construction module is used to optimize historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and to build an energy-saving optimization control model based on different motor working conditions and energy-saving optimization data;

[0054] The control module obtains the actual motor working condition requirements, obtains the optimal control data of the actual motor working condition requirements based on the energy-saving optimization control model, and generates control instructions for the high-voltage inverter according to the optimal control data.

[0055] Compared with the prior art, the energy-saving optimization method and system for a high-voltage inverter according to the embodiments of the present application have the following advantages:

[0056] By determining the optimized characteristic operation data of different motor working conditions, calculating the optimized characteristic operation data to generate the application evaluation value of the corresponding historical characteristic control data, determining the energy-saving optimization data based on the application evaluation value and energy-saving principles, and constructing an energy-saving optimization control model based on different motor working conditions and the corresponding energy-saving optimization data, the optimal control data of the actual motor working condition requirements is determined based on the energy-saving optimization control model, and the high-voltage inverter is accurately and efficiently controlled according to the demand instructions, thereby improving the equipment operation efficiency and energy-saving efficiency, and achieving safe and efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of a method for energy-saving optimization of a high-voltage inverter in a preferred embodiment of the present application;

[0058] Figure 2 This is a schematic diagram of an energy-saving optimization system for a high-voltage inverter in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0059] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0060] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0061] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0062] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0063] like Figure 1 As shown, a method for energy-saving optimization of a high-voltage inverter according to a preferred embodiment of the present application includes:

[0064] Step S101: Obtain historical operation logs of the high-voltage inverter, and determine historical characteristic operation data and historical characteristic control data of different motor working conditions based on the historical operation logs;

[0065] Step S102: Analyze historical characteristic operation data of the same motor working condition requirement, determine preferred characteristic operation data for each motor working condition requirement based on the analysis results, and generate an application evaluation value corresponding to the historical characteristic control data based on the preferred characteristic operation data;

[0066] Step S103: judging whether the historical characteristic control data needs to be optimized based on the application evaluation value and the energy-saving principle; if so, determining the historical characteristic control data to be optimized and the optimization strategy;

[0067] Step S104: Optimizing the historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and constructing an energy-saving optimization control model according to different motor operating conditions and the energy-saving optimization data;

[0068] Step S105: Acquire actual motor operating condition requirements, obtain optimal control data of the actual motor operating condition requirements based on the energy-saving optimization control model, and generate control instructions for the high-voltage inverter according to the optimal control data.

[0069] In this embodiment, the historical demand instructions include the adjustment range of the motor's operating parameters such as speed and torque. The historical demand instructions are classified according to different working conditions and the size of the adjustment range to obtain multiple different motor working conditions. The historical characteristic operating data refers to the historical operating data of the motor that changes according to different motor working conditions. The historical characteristic control data refers to the historical control data of the high-voltage inverter that changes according to different motor working conditions.

[0070] In some embodiments of the present application, determining historical characteristic operation data and historical characteristic control data for different motor operating conditions based on historical operation logs includes:

[0071] Obtain the historical operation logs of the high-voltage inverter, extract the historical demand instructions corresponding to each historical operation log, analyze and classify the historical demand instructions, and obtain multiple different motor operating condition requirements;

[0072] Use the historical running time in each historical running log as the time reference line and set the collection nodes based on the preset time interval;

[0073] According to the collection nodes in each time reference line, the completion degree of the corresponding motor working condition requirements, the historical operation data of the motor, and the historical control data of the high-voltage inverter are collected and mapped to the corresponding time reference line to generate a change relationship curve;

[0074] Determine a linear correlation based on the change relationship curve, and determine the degree of correlation between the historical operating data of the motor and the historical control data of the high-voltage inverter and the completion degree of the corresponding motor working condition requirements based on the linear correlation;

[0075] The historical operation data and the historical control data having a correlation greater than a preset correlation threshold are respectively set as the historical characteristic operation data and the historical characteristic control data of the motor working condition demand corresponding to the time reference line;

[0076] Compare historical characteristic operation data and historical characteristic control data according to the same motor working condition requirements, and determine the credibility of the historical characteristic operation data and historical characteristic control data based on the comparison results;

[0077] The historical feature operation data and historical feature control data whose credibility is less than the preset credibility threshold are eliminated.

[0078] In this embodiment, the completion degree of the motor operating condition requirement refers to the evaluation result of the completion of the corresponding demand instruction, the linear correlation means that the completion degree of the motor operating condition requirement changes with the change of historical operating data and historical control data, and the credibility refers to the number of times the historical characteristic operating data (or historical characteristic control data) in the same motor operating condition requirement appears in the corresponding time reference line and the total number of corresponding time references of the same motor operating condition requirement. The accuracy of the historical characteristic operating data and the historical characteristic control data is judged based on the credibility, laying a data foundation for the subsequent determination of the preferred characteristic operating data, ensuring the accuracy of the subsequent energy-saving optimization data, and accurately and efficiently controlling the high-voltage inverter according to the demand instruction, improving the equipment operation efficiency and energy-saving efficiency, and realizing safe and efficient operation of the system.

[0079] In some embodiments of the present application, determining the preferred characteristic operating data required for each motor operating condition based on the analysis results includes:

[0080] Analyze the historical characteristic operation data of different historical operating times of the same motor working condition requirements and the completion degree of the corresponding motor working condition requirements;

[0081] Generate the change efficiency based on the change value of the completion degree within the corresponding historical operation time, and the comparison result between the final completion degree and the preset completion degree threshold. Remove the historical operation time and historical characteristic operation data with a change efficiency less than the preset change efficiency threshold and a final completion degree less than the preset completion degree threshold;

[0082] Calculate the fluctuation degree of the remaining multiple historical characteristic operation data within the same historical operation time, and generate the fluctuation evaluation value of the historical characteristic operation data within the corresponding historical operation time according to the fluctuation degree of the multiple historical characteristic operation data and the corresponding weight coefficient;

[0083] A completion evaluation value is generated for the final completion degree and change efficiency of the motor operating condition requirements corresponding to the historical characteristic operating data of the remaining historical operating time, the completion evaluation values ​​are sorted, and the fluctuation evaluation values ​​are judged in turn according to the sorting results, and the historical characteristic operating data with a fluctuation evaluation value less than the preset fluctuation evaluation value threshold is set as the preferred characteristic operating data corresponding to the motor operating condition requirements.

[0084] In this embodiment, the change value = the change value / the corresponding historical operating time, the change value refers to the final completion degree within the historical operating time - the initial completion degree, the preset completion threshold is set according to the minimum completion status of the demand instruction, and the historical characteristic operating data within the historical operating time of the same motor working condition requirement is screened according to the change efficiency and the final completion degree, so as to eliminate the historical characteristic operating data that is less than the preset change efficiency threshold and the preset completion threshold.

[0085] In this embodiment, the fluctuation evaluation value of the historical characteristic operation data corresponding to the historical operation time is calculated based on the fluctuation degree of multiple historical characteristic operation data within the remaining historical operation time. The smaller the fluctuation evaluation value, the higher the stability of the historical characteristic operation data, that is, the higher the safety stability of the system. The corresponding fluctuation evaluation value is judged according to the completion evaluation value sorting result, and the first historical characteristic operation data that is less than the preset fluctuation evaluation value threshold is set as the preferred characteristic operation data for the corresponding motor working condition requirement.

[0086] In this embodiment, the preferred characteristic operation data of the motor operating condition requirement refers to the historical characteristic operation data that can meet the maximum completion degree of the demand instructions and maintain stable operation of the system in the historical operation log. The application evaluation value of the historical characteristic control data within the same historical operation time is obtained according to the preferred characteristic operation data of each motor operating condition requirement, which lays the foundation for the subsequent construction of the energy-saving optimization control model and improves the accuracy of the energy-saving optimization control model, so as to accurately and efficiently control the high-voltage inverter according to the demand instructions, improve the equipment operation efficiency and energy-saving efficiency, and realize safe and efficient operation of the system.

[0087] In some embodiments of the present application, generating an application evaluation value corresponding to historical feature control data based on the preferred feature operation data includes:

[0088] Comparing the preferred characteristic operation data with a preset standard characteristic operation data interval corresponding to the motor operating condition requirement, obtaining the number of preferred characteristic operation data that are not within the preset standard characteristic operation data interval and the characteristic operation data deviation amount of the preferred characteristic operation data that are not within the preset standard characteristic operation data interval;

[0089] Generate an operation evaluation coefficient based on the number and deviation of characteristic operation data;

[0090] Generate a fluctuation evaluation coefficient based on the degree of fluctuation of the historical characteristic control data corresponding to the preferred characteristic operation data within the historical operation period;

[0091] The preferred characteristic operation data and the corresponding historical characteristic control data are converted into energy consumption to obtain the energy consumption array within the corresponding historical operation time. The energy consumption array at the same collection node is time-aligned and the energy consumption value of the aligned energy consumption array is calculated. The energy consumption evaluation coefficient is generated based on the energy consumption values ​​at multiple collection nodes in the historical operation time.

[0092] Calculate the comprehensive usage cost of the historical feature control data corresponding to the preferred feature operation data within the historical operation time, and subtract the comprehensive usage cost from the preset usage cost threshold to obtain the usage cost difference, and set the compensation coefficient according to the usage cost difference;

[0093] An application evaluation value corresponding to the historical characteristic control data is generated according to the operation evaluation coefficient, the fluctuation evaluation coefficient, the energy consumption evaluation coefficient and the compensation coefficient.

[0094] In this embodiment, the degree of fluctuation refers to the average value of the fluctuation change values ​​of multiple historical feature control data at adjacent collection nodes during the historical operation time. The energy consumption conversion is to match and convert the preferred feature operation data and historical feature control data associated with energy consumption, and is obtained based on the data-energy consumption mapping table. The data-energy consumption mapping table is the energy consumption value matched according to the feature operation data and the feature control data.

[0095] In this embodiment, the operation evaluation coefficient is used to evaluate the operating status of the preferred characteristic operation data for the motor operating condition requirements. The smaller the number and the deviation of the characteristic operation data, the larger the operation evaluation coefficient, that is, the better the operating status. The fluctuation evaluation coefficient is used to evaluate the stability of the historical characteristic control data. The smaller the fluctuation degree, the smaller the fluctuation evaluation coefficient, which means that the historical characteristic control data is more stable, that is, the system operates stably. The energy consumption evaluation coefficient is used to evaluate the energy consumption status of the preferred characteristic operation data and the historical characteristic control data. The smaller the energy consumption value, the smaller the energy consumption evaluation coefficient, that is, the less comprehensive energy consumption of the high-voltage inverter and the motor. The compensation coefficient is used to be set according to the difference between the maximum usage cost and the comprehensive usage cost. The larger the difference, the larger the compensation coefficient, and the smaller the difference, the smaller the compensation coefficient.

[0096] In this embodiment, a comprehensive analysis is performed based on the operating status of the optimized characteristic operating data under each motor working condition requirement, the stability status of the historical characteristic control data, the energy consumption status of the high-voltage inverter and the motor, and the usage cost status to obtain an application evaluation value of the corresponding historical characteristic control data. Based on the application evaluation value, it is determined whether the corresponding historical characteristic control data is optimized, so that the high-voltage inverter is accurately and efficiently controlled according to the demand instructions, thereby improving the equipment operating efficiency and energy-saving efficiency, and realizing safe and efficient operation of the system.

[0097] In some embodiments of the present application, the calculation formula of the application evaluation value is:

[0098]

[0099] Among them, Y is the application evaluation value, a1 is the operation evaluation conversion coefficient, y1 is the weight coefficient of the operation evaluation coefficient, m is the number of preferred feature operation data that are not in the preset standard feature operation data interval, n is the total number of preferred feature operation data, △Ps is the deviation of the sth feature operation data, B0 is the fluctuation degree threshold, B is the fluctuation degree of the historical feature control data within the historical operation time, y2 is the weight coefficient of the fluctuation evaluation coefficient, a2 is the fluctuation evaluation conversion coefficient, w is the number of collection nodes within the corresponding historical application time, Ni is the energy consumption value of the energy consumption array at the i-th collection node, y3 is the weight coefficient of the energy consumption evaluation coefficient, a3 is the energy consumption evaluation conversion coefficient, and c is the compensation coefficient.

[0100] In this embodiment, the value range of c is (0.75, 1.25), y1 is 0.6, y2 is 0.1, and y3 is 0.3. The smaller the preset usage cost difference range in which the usage cost difference lies, the larger the compensation coefficient.

[0101] In some embodiments of the present application, judging whether historical control data needs to be optimized based on the application evaluation value and the energy-saving principle includes:

[0102] Presetting a preset application evaluation value threshold;

[0103] When the application evaluation value is less than the preset application evaluation value threshold, the optimized feature operation data to be optimized is screened out according to the feature operation data deviation amount and the optimization coefficient is calculated;

[0104] When the application evaluation value is greater than the preset application evaluation value threshold, the standard data interval of each energy consumption indicator is determined based on the energy-saving principle. According to the degree of correlation between the preferred characteristic operation data and the energy consumption indicator, the optimized characteristic operation data to be optimized for each energy consumption indicator is determined and the optimization coefficient is calculated.

[0105] In this embodiment, the energy-saving principle refers to achieving minimum energy consumption under the premise of ensuring the normal operation of the motor and the high-voltage inverter. According to the category of the energy consumption array after the energy consumption conversion of the optimized characteristic operation data and the historical characteristic control data, multiple energy consumption indicators are determined, and the standard data interval corresponding to the lowest energy consumption of the energy consumption indicator is set in advance. According to the degree of correlation between the preferred characteristic operation data and the corresponding energy consumption indicator, if the correlation degree is greater than 80%, it is set as the optimized characteristic operation data that is strongly correlated with the corresponding energy consumption indicator. If the strongly correlated optimized characteristic operation data of each energy consumption indicator is not in the corresponding standard data interval, it is the optimized characteristic operation data to be optimized, and the optimization coefficient is set according to the data difference amount that is not in the standard data interval.

[0106] In this embodiment, the corresponding optimization feature operation data to be optimized and the corresponding optimization coefficient are determined based on the comparison result between the application evaluation value and the preset application evaluation value threshold, laying the foundation for the subsequent determination of the historical feature control data to be optimized, thereby determining accurate energy-saving optimization data and improving the energy-saving optimization efficiency of the high-voltage inverter.

[0107] In some embodiments of the present application, determining the historical feature control data to be optimized and the optimization strategy includes:

[0108] Determine the degree of correlation between the optimization feature operation data to be optimized and the historical feature control data according to the synchronous change time nodes and synchronous change degrees of the optimization feature operation data to be optimized and the historical feature control data within the historical operation time;

[0109] The historical feature control data with a correlation degree greater than a preset correlation degree is set as the historical feature control data to be optimized, and an optimization strategy for the corresponding historical feature control data is generated according to the optimization coefficient. The corresponding historical feature control data is optimized according to the optimization strategy to obtain energy-saving optimization data.

[0110] In this embodiment, optimized optimization feature operation data is obtained according to the optimization coefficient, and corresponding prediction feature control data is obtained according to the optimized optimization feature operation data. The prediction feature control data is the historical control data corresponding to the optimized optimization feature operation data under the same motor working condition requirement. The optimization strategy with the shortest time and lowest usage cost is generated according to the degree of deviation between multiple prediction feature control data and the corresponding historical feature control data.

[0111] In this embodiment, the historical characteristic control data to be optimized and the optimization strategy are determined based on the degree of correlation between the optimization characteristic operation data to be optimized and the historical characteristic control data, thereby improving the energy-saving optimization efficiency of the high-voltage inverter, reducing the data processing volume, and quickly determining the energy-saving optimization data required for each motor working condition, so as to accurately and efficiently control the high-voltage inverter according to the demand instructions, improve the equipment operation efficiency and energy-saving efficiency, and realize safe and efficient operation of the system.

[0112] In some embodiments of the present application, an energy-saving optimization control model is constructed according to different motor operating conditions and energy-saving optimization data, including:

[0113] Obtain characteristic operating condition data for different motor operating conditions, and construct training and test data sets based on the characteristic operating condition data and energy-saving optimization data corresponding to the motor operating condition requirements;

[0114] The characteristic operating condition data in the training data set is set as input data, and the energy-saving optimization data corresponding to the characteristic operating condition data in the training data set is set as output data, and a neural network training is performed to obtain an initial energy-saving optimization control model;

[0115] The accuracy of the initial energy-saving optimization control model generated based on the test data set;

[0116] If the accuracy is less than the preset accuracy threshold, the training data set is iteratively trained to rebuild the initial energy-saving optimization control model until the accuracy is greater than the preset accuracy threshold, and the energy-saving optimization control model is generated;

[0117] If the accuracy is greater than the preset accuracy threshold, the initial energy-saving optimization control model is set as the energy-saving optimization control model.

[0118] In some embodiments of the present application, generating a control instruction for a high-voltage inverter according to optimal control data includes:

[0119] Obtain the actual motor working condition requirements and obtain the actual characteristic working condition data of the actual motor working condition requirements;

[0120] The actual characteristic operating condition data is input into the energy-saving optimization control model to obtain the optimal control data required by the actual motor operating condition, and control instructions are generated for the high-voltage inverter according to the optimal control data.

[0121] In some embodiments of the present application, Figure 2 As shown, it also includes an energy-saving optimization system for high-voltage inverters:

[0122] An acquisition module is used to obtain the historical operation log of the high-voltage inverter and determine the historical characteristic operation data and historical characteristic control data required by different motor working conditions based on the historical operation log;

[0123] A generation module is used to analyze the historical characteristic operation data of the same motor working condition requirement, determine the preferred characteristic operation data of each motor working condition requirement based on the analysis results, and generate an application evaluation value of the corresponding historical characteristic control data based on the preferred characteristic operation data;

[0124] A judgment module is used to judge whether the historical characteristic control data needs to be optimized based on the application evaluation value and the energy-saving principle. If so, it determines the historical characteristic control data to be optimized and the optimization strategy;

[0125] A construction module is used to optimize historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and to build an energy-saving optimization control model based on different motor working conditions and energy-saving optimization data;

[0126] The control module obtains the actual motor working condition requirements, obtains the optimal control data of the actual motor working condition requirements based on the energy-saving optimization control model, and generates control instructions for the high-voltage inverter according to the optimal control data.

[0127] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A method for energy-saving optimization of a high-voltage inverter, characterized in that: include: Obtain the historical operation log of the high-voltage inverter and determine the historical characteristic operation data and historical characteristic control data required for different motor working conditions based on the historical operation log; Analyze the historical characteristic operation data of the same motor working condition demand, determine the preferred characteristic operation data of each motor working condition demand based on the analysis results, and generate the application evaluation value of the corresponding historical characteristic control data based on the preferred characteristic operation data; Based on the application evaluation value and energy-saving principles, determine whether the historical feature control data needs to be optimized. If so, determine the historical feature control data to be optimized and the optimization strategy; Optimize historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and build an energy-saving optimization control model based on different motor working conditions and energy-saving optimization data; Obtain the actual motor operating conditions, obtain the optimal control data based on the energy-saving optimization control model, and generate control instructions for the high-voltage inverter according to the optimal control data; Generate application evaluation values ​​corresponding to historical feature control data based on the selected feature operation data, including: Comparing the preferred characteristic operation data with a preset standard characteristic operation data interval corresponding to the motor operating condition requirement, obtaining the number of preferred characteristic operation data that are not within the preset standard characteristic operation data interval and the characteristic operation data deviation amount of the preferred characteristic operation data that are not within the preset standard characteristic operation data interval; Generate an operation evaluation coefficient based on the number and deviation of characteristic operation data; Generate a fluctuation evaluation coefficient based on the degree of fluctuation of the historical characteristic control data corresponding to the preferred characteristic operation data within the historical operation period; The preferred characteristic operation data and the corresponding historical characteristic control data are converted into energy consumption to obtain the energy consumption array within the corresponding historical operation time. The energy consumption array at the same collection node is time-aligned and the energy consumption value of the aligned energy consumption array is calculated. The energy consumption evaluation coefficient is generated based on the energy consumption values ​​at multiple collection nodes in the historical operation time. Calculate the comprehensive usage cost of the historical feature control data corresponding to the preferred feature operation data within the historical operation time, and subtract the comprehensive usage cost from the preset usage cost threshold to obtain the usage cost difference, and set the compensation coefficient according to the usage cost difference; Generate application evaluation values ​​corresponding to historical characteristic control data based on operation evaluation coefficient, fluctuation evaluation coefficient, energy consumption evaluation coefficient and compensation coefficient; The calculation formula of the application evaluation value is: ； Wherein, Y is the application evaluation value, a1 is the operation evaluation conversion coefficient, y1 is the weight coefficient of the operation evaluation coefficient, m is the number of preferred feature operation data that are not in the preset standard feature operation data interval, and n is the total number of preferred feature operation data. is the deviation of the sth characteristic operation data, B0 is the fluctuation threshold, B is the fluctuation degree of the historical characteristic control data in the historical operation time, y2 is the weight coefficient of the fluctuation evaluation coefficient, a2 is the fluctuation evaluation conversion coefficient, w is the number of acquisition nodes in the corresponding historical application time, Ni is the energy consumption value of the energy consumption array at the i-th acquisition node, y3 is the weight coefficient of the energy consumption evaluation coefficient, a3 is the energy consumption evaluation conversion coefficient, and c is the compensation coefficient.

2. The energy-saving optimization method for a high-voltage inverter according to claim 1, characterized in that: Determine historical characteristic operation data and historical characteristic control data for different motor working conditions based on historical operation logs, including: Obtain the historical operation logs of the high-voltage inverter, extract the historical demand instructions corresponding to each historical operation log, analyze and classify the historical demand instructions, and obtain multiple different motor operating condition requirements; Use the historical running time in each historical running log as the time reference line and set the collection nodes based on the preset time interval; According to the collection nodes in each time reference line, the completion degree of the corresponding motor working condition requirements, the historical operation data of the motor, and the historical control data of the high-voltage inverter are collected and mapped to the corresponding time reference line to generate a change relationship curve; Determine a linear correlation based on the change relationship curve, and determine the degree of correlation between the historical operating data of the motor and the historical control data of the high-voltage inverter and the completion degree of the corresponding motor working condition requirements based on the linear correlation; The historical operation data and the historical control data having a correlation greater than a preset correlation threshold are respectively set as the historical characteristic operation data and the historical characteristic control data of the motor working condition demand corresponding to the time reference line; Compare historical characteristic operation data and historical characteristic control data according to the same motor working condition requirements, and determine the credibility of the historical characteristic operation data and historical characteristic control data based on the comparison results; The historical feature operation data and historical feature control data whose credibility is less than the preset credibility threshold are eliminated.

3. The energy-saving optimization method for a high-voltage inverter according to claim 2, characterized in that: Based on the analysis results, the optimal characteristic operating data required for each motor working condition is determined, including: Analyze the historical characteristic operation data of different historical operating times of the same motor working condition requirements and the completion degree of the corresponding motor working condition requirements; Generate the change efficiency based on the change value of the completion degree within the corresponding historical operation time, and the comparison result between the final completion degree and the preset completion degree threshold. Remove the historical operation time and historical characteristic operation data with a change efficiency less than the preset change efficiency threshold and a final completion degree less than the preset completion degree threshold; Calculate the fluctuation degree of the remaining multiple historical characteristic operation data within the same historical operation time, and generate the fluctuation evaluation value of the historical characteristic operation data within the corresponding historical operation time according to the fluctuation degree of the multiple historical characteristic operation data and the corresponding weight coefficient; A completion evaluation value is generated for the final completion degree and change efficiency of the motor operating condition requirements corresponding to the historical characteristic operating data of the remaining historical operating time, the completion evaluation values ​​are sorted, and the fluctuation evaluation values ​​are judged in turn according to the sorting results, and the historical characteristic operating data with a fluctuation evaluation value less than the preset fluctuation evaluation value threshold is set as the preferred characteristic operating data corresponding to the motor operating condition requirements.

4. The energy-saving optimization method for a high-voltage inverter according to claim 3, characterized in that: Based on the application evaluation value and energy-saving principles, determine whether historical control data needs to be optimized, including: Presetting a preset application evaluation value threshold; When the application evaluation value is less than the preset application evaluation value threshold, the optimized feature operation data to be optimized is screened out according to the feature operation data deviation amount and the optimization coefficient is calculated; When the application evaluation value is greater than the preset application evaluation value threshold, the standard data interval of each energy consumption indicator is determined based on the energy-saving principle. According to the degree of correlation between the preferred characteristic operation data and the energy consumption indicator, the optimized characteristic operation data to be optimized for each energy consumption indicator is determined and the optimization coefficient is calculated.

5. The energy-saving optimization method for a high-voltage inverter according to claim 4, characterized in that: Determine the historical characteristic control data that needs to be optimized and the optimization strategy, including: Determine the degree of correlation between the optimization feature operation data to be optimized and the historical feature control data according to the synchronous change time nodes and synchronous change degrees of the optimization feature operation data to be optimized and the historical feature control data within the historical operation time; The historical feature control data with a correlation degree greater than a preset correlation degree is set as the historical feature control data to be optimized, and an optimization strategy for the corresponding historical feature control data is generated according to the optimization coefficient. The corresponding historical feature control data is optimized according to the optimization strategy to obtain energy-saving optimization data.

6. The energy-saving optimization method for a high-voltage inverter according to claim 5, characterized in that: Build an energy-saving optimization control model based on different motor operating conditions and energy-saving optimization data, including: Obtain characteristic operating condition data for different motor operating conditions, and construct training and test data sets based on the characteristic operating condition data and energy-saving optimization data corresponding to the motor operating condition requirements; The characteristic operating condition data in the training data set is set as input data, and the energy-saving optimization data corresponding to the characteristic operating condition data in the training data set is set as output data, and a neural network training is performed to obtain an initial energy-saving optimization control model; The accuracy of the initial energy-saving optimization control model generated based on the test data set; If the accuracy is less than the preset accuracy threshold, the training data set is iteratively trained to rebuild the initial energy-saving optimization control model until the accuracy is greater than the preset accuracy threshold, and the energy-saving optimization control model is generated; If the accuracy is greater than the preset accuracy threshold, the initial energy-saving optimization control model is set as the energy-saving optimization control model.

7. The energy-saving optimization method for a high-voltage inverter according to claim 6, characterized in that: Generate control instructions for the high-voltage inverter according to the optimal control data, including: Obtain the actual motor working condition requirements and obtain the actual characteristic working condition data of the actual motor working condition requirements; The actual characteristic operating condition data is input into the energy-saving optimization control model to obtain the optimal control data required by the actual motor operating condition, and control instructions are generated for the high-voltage inverter according to the optimal control data.

8. An energy-saving optimization system for a high-voltage inverter, characterized in that: include: An acquisition module is used to obtain the historical operation log of the high-voltage inverter and determine the historical characteristic operation data and historical characteristic control data required by different motor working conditions based on the historical operation log; A generation module is used to analyze the historical characteristic operation data of the same motor working condition requirement, determine the preferred characteristic operation data of each motor working condition requirement based on the analysis results, and generate an application evaluation value of the corresponding historical characteristic control data based on the preferred characteristic operation data; A judgment module is used to judge whether the historical characteristic control data needs to be optimized based on the application evaluation value and the energy-saving principle. If so, it determines the historical characteristic control data to be optimized and the optimization strategy; A construction module is used to optimize historical characteristic control data according to the optimization strategy to obtain energy-saving optimization data, and to build an energy-saving optimization control model based on different motor working conditions and energy-saving optimization data; The control module obtains the actual motor working condition requirements, obtains the optimal control data of the actual motor working condition requirements based on the energy-saving optimization control model, and generates control instructions for the high-voltage inverter according to the optimal control data; Generate application evaluation values ​​corresponding to historical feature control data based on the selected feature operation data, including: Comparing the preferred characteristic operation data with a preset standard characteristic operation data interval corresponding to the motor operating condition requirement, obtaining the number of preferred characteristic operation data that are not within the preset standard characteristic operation data interval and the characteristic operation data deviation amount of the preferred characteristic operation data that are not within the preset standard characteristic operation data interval; Generate an operation evaluation coefficient based on the number and deviation of characteristic operation data; Generate a fluctuation evaluation coefficient based on the degree of fluctuation of the historical characteristic control data corresponding to the preferred characteristic operation data within the historical operation period; The preferred characteristic operation data and the corresponding historical characteristic control data are converted into energy consumption to obtain the energy consumption array within the corresponding historical operation time. The energy consumption array at the same collection node is time-aligned and the energy consumption value of the aligned energy consumption array is calculated. The energy consumption evaluation coefficient is generated based on the energy consumption values ​​at multiple collection nodes in the historical operation time. Calculate the comprehensive usage cost of the historical feature control data corresponding to the preferred feature operation data within the historical operation time, and subtract the comprehensive usage cost from the preset usage cost threshold to obtain the usage cost difference, and set the compensation coefficient according to the usage cost difference; Generate application evaluation values ​​corresponding to historical characteristic control data based on operation evaluation coefficient, fluctuation evaluation coefficient, energy consumption evaluation coefficient and compensation coefficient; The calculation formula of the application evaluation value is: ； Wherein, Y is the application evaluation value, a1 is the operation evaluation conversion coefficient, y1 is the weight coefficient of the operation evaluation coefficient, m is the number of preferred feature operation data that are not in the preset standard feature operation data interval, and n is the total number of preferred feature operation data. is the deviation of the sth characteristic operation data, B0 is the fluctuation threshold, B is the fluctuation degree of the historical characteristic control data in the historical operation time, y2 is the weight coefficient of the fluctuation evaluation coefficient, a2 is the fluctuation evaluation conversion coefficient, w is the number of acquisition nodes in the corresponding historical application time, Ni is the energy consumption value of the energy consumption array at the i-th acquisition node, y3 is the weight coefficient of the energy consumption evaluation coefficient, a3 is the energy consumption evaluation conversion coefficient, and c is the compensation coefficient.

Images