Control method and system for new energy inverter

Through real-time monitoring and identification of missing probability of new energy inverters, and the control parameters are optimized using the adaptive control decision model, the problems of low energy conversion efficiency and poor energy recovery effect in the existing technology are solved, and more efficient energy conversion is achieved and energy recovery.

CN118337033BActive Publication Date: 2024-11-05SUZHOU AIPLE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410763598.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-14
Publication Date
2024-11-05
Estimated Expiration
2044-06-14

AI Technical Summary

Technical Problem

The existing new energy inverter control methods lack real-time monitoring and missing probability identification, resulting in reduced energy conversion efficiency and weakened energy recovery effect.

Method used

By obtaining the conversion monitoring data of the power motor and power battery, identifying the probability of operation missing, and optimizing the control parameters using the adaptive control decision model, real-time monitoring and analysis of new energy inverters are achieved.

Benefits of technology

It improves energy conversion efficiency and energy recovery effect, ensures the best balance between the power motor and the power battery, and improves system operation efficiency and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118337033B_ABST
    Figure CN118337033B_ABST
Patent Text Reader

Abstract

The present application provides a control method and system for a new energy inverter, which relates to the field of direct current and alternating current conversion technology. The method includes: obtaining a power motor and a power battery connected to the new energy inverter for monitoring, obtaining conversion monitoring data of a first conversion mode and a second conversion mode; identifying the operation missing probability of the conversion monitoring data of the first conversion mode and the second conversion mode, and outputting a first missing probability and a second missing probability; training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, and connecting the adaptive control decision model to the new energy inverter; and performing conversion control on the new energy inverter with the control parameter solution output by the adaptive control decision model. The present application can solve the technical problems in the prior art due to low energy conversion efficiency and poor energy recovery effect, and achieve the technical effect of improving energy conversion efficiency and energy recovery effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of direct current and alternating current conversion, and in particular to a control method and system for a new energy inverter. Background Art

[0002] The control of new energy inverter refers to the process of converting direct current into alternating current.

[0003] At present, most of the existing control methods for new energy inverters lack real-time monitoring of the conversion process and missing probability identification, which may lead to reduced energy conversion efficiency of new energy inverters during the conversion process. For example, when converting DC power to AC power, if the new energy inverter fails to optimize the conversion efficiency according to the current working conditions, the waste of energy will increase. During the energy recovery process, if the AC power emitted by the motor cannot be effectively rectified into DC power and recharged to the power battery, the effect of energy recovery will be weakened, which will not only reduce the cruising range of the electric vehicle, but may also have a negative impact on the health of the battery. Therefore, a method is needed to solve the above problems.

[0004] In summary, the existing technologies have technical problems in that most of them lack monitoring and identification of new energy inverters, resulting in low accuracy of real-time monitoring and analysis of conversion process data, further affecting energy conversion efficiency and energy recovery effect. Summary of the invention

[0005] The purpose of this application is to provide a control method and system for a new energy inverter, so as to solve the technical problem in the prior art that most of the new energy inverters are lacking in monitoring and identification, resulting in low accuracy in real-time monitoring and analysis of conversion process data, further affecting energy conversion efficiency and energy recovery effect.

[0006] In view of the above problems, the present application provides a control method and system for a new energy inverter.

[0007] In a first aspect, the present application provides a control method for a new energy inverter, which is implemented by a control system for a new energy inverter, wherein the method includes: obtaining a power motor and a power battery connected to the new energy inverter; monitoring the power motor and the power battery respectively, and obtaining conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts an output signal of the power battery into a signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts an output signal of the power motor into a signal required by the power battery; performing operation missing probability identification on the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and outputting a first missing probability and a second missing probability; training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter; and performing conversion control on the new energy inverter with the control parameter solution output by the adaptive control decision model.

[0008] In the second aspect, the present application also provides a control system for a new energy inverter, which is used to execute the control method for the new energy inverter as described in the first aspect, wherein the system includes: a power motor connection module, which is used to obtain the power motor and power battery connected to the new energy inverter; a conversion monitoring data acquisition module, which is used to monitor the power motor and the power battery respectively, and obtain conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into the signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into the signal required by the power motor. The output signal is converted into the signal required by the power battery; a first missing probability output module, the first missing probability output module is used to identify the operation missing probability of the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and output the first missing probability and the second missing probability; an adaptive control decision model training module, the adaptive control decision model training module is used to train the adaptive control decision model, the first missing probability and the second missing probability are input into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter; a conversion control module, the conversion control module is used to perform conversion control on the new energy inverter with the control parameter solution output by the adaptive control decision model.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By acquiring the power motor and the power battery connected to the new energy inverter; monitoring the power motor and the power battery respectively, acquiring the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, wherein the first conversion mode is the mode in which the new energy inverter converts the output signal of the power battery into the signal required by the power motor, and the second conversion mode is the mode in which the new energy inverter converts the output signal of the power motor into the signal required by the power battery; performing operation missing probability identification on the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and outputting the first missing probability and the second missing probability; training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter; performing conversion control on the new energy inverter with the control parameter solution output by the adaptive control decision model, realizing the technical goal of real-time monitoring and analysis of conversion process data, and achieving the technical effect of improving energy conversion efficiency and energy recovery effect.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of a control method for a new energy inverter in this application;

[0014] Figure 2 This is a schematic diagram of the structure of the control system used for the new energy inverter in this application.

[0015] Description of reference numerals:

[0016] A power motor connection module 11 , a conversion monitoring data acquisition module 12 , a first missing probability output module 13 , an adaptive control decision model training module 14 , and a conversion control module 15 . DETAILED DESCRIPTION

[0017] This application provides a control method and system for a new energy inverter, which solves the technical problem that most of the existing technologies lack monitoring and identification of new energy inverters, resulting in low accuracy of real-time monitoring and analysis of conversion process data, further affecting energy conversion efficiency and energy recovery effect. The technical goal of real-time monitoring and analysis of conversion process data is achieved, and the technical effect of improving energy conversion efficiency and energy recovery effect is achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them. Example 1

[0019] Please see attached Figure 1 The present application provides a control method for a new energy inverter, wherein the method is applied to a control system for a new energy inverter, and the method specifically comprises the following steps:

[0020] Step 1: Get the power motor and power battery connected to the new energy inverter.

[0021] Specifically, the inverter is used to convert direct current into alternating current, and the inverter of a new energy vehicle is a motor controller. Ensure that the new energy inverter is correctly connected to the power motor and power battery, including physical connection and possible software configuration. For example, the physical connection includes cables, interfaces, etc. Software configuration includes ensuring that the communication protocol is compatible.

[0022] Step 2: Monitor the power motor and the power battery respectively, and obtain conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into a signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts the output signal of the power motor into a signal required by the power battery.

[0023] Specifically, the high-voltage direct current of the power battery is converted into three-phase alternating current with variable frequency and current through a new energy inverter to obtain a first conversion mode. When the energy is recovered through the new energy inverter, the three-phase alternating current emitted by the power motor is rectified into direct current to charge the power battery to obtain a second conversion mode. The power motor and the power battery are monitored separately to obtain the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode. For example, by installing current sensors, voltage sensors, temperature sensors, etc. on the power motor, the monitoring data of the power motor can be collected.

[0024] Step three: performing operation missing probability identification on the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and outputting a first missing probability and a second missing probability.

[0025] Specifically, the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode are obtained to reflect the operating status of the power motor and the energy storage status of the power battery, respectively. The conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode are analyzed in detail to identify parameters related to operation loss, such as load change, energy storage change, efficiency reduction, etc. According to the parameters related to operation loss, the first loss probability and the second loss probability are calculated and output to characterize the load loss probability of the power motor and the energy storage loss probability of the power battery, which are used to view the real-time energy loss situation.

[0026] Step 4: training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, and connecting the adaptive control decision model to the new energy inverter.

[0027] Specifically, an adaptive control decision model is constructed based on a neural network, and the first missing probability and the second missing probability are input into the adaptive control decision model as input samples, and the control strategies adopted under different missing probabilities are used as output samples. The input samples and the output samples are integrated and divided into training data and verification data. The adaptive control decision model is trained by the training data. When the output of the adaptive control decision model tends to be stable, the adaptive control decision model is verified by the verification data to obtain the output accuracy of the adaptive control decision model. If the output accuracy of the adaptive control decision model meets the output accuracy threshold of the adaptive control decision model, the training of the adaptive control decision model is completed. For example, the division ratio of the training data and the verification data and the output accuracy threshold of the adaptive control decision model are obtained by a technician in this field according to the actual situation. The adaptive control decision model is connected to the new energy inverter to receive the output signal of the adaptive control decision model, so that the new energy inverter can dynamically adjust the working state and control parameters according to the output signal of the adaptive control decision model.

[0028] Step 5: Perform conversion control on the new energy inverter using the control parameter solution output by the adaptive control decision model.

[0029] Specifically, the new energy inverter is converted and controlled through the control parameter solution output by the adaptive control decision model, thereby achieving the optimal balance between the power motor and the power battery, thereby improving the operating efficiency and stability of the entire system.

[0030] The control method for a new energy inverter is applied to a control system for a new energy inverter, which can achieve the technical goal of real-time monitoring and analysis of conversion process data, and achieve the technical effect of improving energy conversion efficiency and energy recovery effect.

[0031] Furthermore, the present application also includes the following steps:

[0032] Acquire a historical operation data set of the power motor, wherein the historical operation data set includes motor balanced load operation samples; perform load operation status analysis on the motor balanced load operation samples to obtain a first balanced load index; identify conversion monitoring data of the first conversion mode to obtain a real-time load index of the power motor; calculate a first missing probability based on the real-time load index and the first balanced load index, wherein the first missing probability represents a load missing probability of the power motor.

[0033] Specifically, data storage records are obtained through a database, file system or cloud storage, and a historical operation data set of the power motor is retrieved. The historical operation data set includes operation records of the power motor under various load conditions, and a motor balanced load operation sample is obtained. For example, it includes load current, voltage, power, etc.

[0034] Then, a detailed load operation status analysis is performed on the motor balanced load operation sample. For example, it includes calculating parameters such as average load, load fluctuation range, operating temperature, efficiency, etc. Based on the load operation status, the first balanced load index is randomly extracted. For example, it includes average load rate, load fluctuation coefficient, operating efficiency, etc.

[0035] Next, real-time data related to the load of the power motor is identified from the conversion monitoring data of the first conversion mode, for example, including the real-time load current, voltage, power, etc. of the power motor. The real-time load index of the power motor is calculated using the conversion monitoring data to indicate the current operating state of the power motor.

[0036] Next, the real-time load index is compared with the first balanced load index by calculating the difference, ratio or other statistics between the real-time load index and the first balanced load index. According to the comparison result, the first missing probability is calculated. The first missing probability reflects the degree to which the real-time load index deviates from the balanced load index. For example, if the real-time load index is significantly lower than the balanced load index, then the load missing probability is high, otherwise, it is low.

[0037] The possibility of load loss is predicted through historical data and real-time data, further improving the accuracy of identifying the probability of operation loss.

[0038] Furthermore, the present application also includes the following steps:

[0039] Collect the motor fault load operation samples of the power motor and store them in the historical operation data set; analyze the load change state of the motor fault load operation samples to obtain a first variation probability; perform conditional probability calculation on the first missing probability according to the first variation probability, and output an optimized first missing probability.

[0040] Specifically, when a power motor fails, the motor fault load operation sample is recorded and stored in the historical operation data set. The historical operation data set includes parameters such as load change, temperature, current, voltage, etc. of the power motor in the fault state.

[0041] Then, a detailed load change state analysis is performed on the motor fault load operation samples, including calculating the load change rate, amplitude, frequency and other parameters, and extracting the first variation probability to characterize the possibility of abnormal load changes in the power motor under similar fault conditions.

[0042] Next, the conditional probability calculation is performed using the first variation probability and the first missing probability. Preferably, the first missing probability is multiplied by the first variation probability. After the conditional probability calculation, the optimized first missing probability is obtained, which not only considers the possibility of load missing of the power motor under normal operating conditions, but also considers the abnormal load change of the power motor under a fault state.

[0043] The first missing probability is obtained by calculating the first missing probability after obtaining it, thereby improving the accuracy of obtaining the possibility of missing power motor load.

[0044] Furthermore, the present application also includes the following steps:

[0045] Acquire a battery energy storage module of the power battery; identify the configuration information of the battery energy storage module to acquire a first effective energy storage index, wherein the first effective energy storage index is an index that meets an energy storage safety threshold; identify the conversion monitoring data of the second conversion mode to acquire a real-time energy storage index of the power motor; calculate a second missing probability based on the real-time energy storage index and the first effective energy storage index, wherein the second missing probability represents the energy storage missing probability of the power battery.

[0046] Specifically, access the management system of the power battery or obtain it directly from the battery module to identify and obtain the battery energy storage module in the power battery.

[0047] Then, the configuration information of the battery energy storage module is identified in detail. For example, including battery power and energy density, capacity, etc. If the battery power density and energy density are low, it may lead to insufficient energy supply when the system is running at high load, increasing the risk of energy loss. Based on the configuration information, the first effective energy storage index is determined. The first effective energy storage index is based on factors such as the battery's safe operating range, optimal operating point, and energy storage efficiency to ensure that the battery can effectively power the power motor while meeting the energy storage safety threshold.

[0048] Next, the conversion monitoring data of the second conversion mode is analyzed to identify real-time data directly related to the power battery energy storage, such as the battery charging status, charging / discharging current, voltage, etc., and the real-time energy storage index of the power battery is calculated to reflect the current energy storage status of the power motor, such as remaining power, available energy, etc.

[0049] Next, the real-time energy storage index is compared with the first effective energy storage index. If the real-time energy storage index is lower than the first effective energy storage index, it indicates that there is a lack of energy storage in the power battery. Based on the comparison result, a second lack probability is calculated.

[0050] By calculating the second missing probability, the accuracy of obtaining the power battery energy storage missing probability is improved.

[0051] Furthermore, the present application also includes the following steps: obtaining a battery charge and discharge management system of the power battery, obtaining the historical number of charge and discharge cycles and the historical charge and discharge environment information; analyzing the energy storage loss change state of the historical number of charge and discharge cycles and the historical charge and discharge environment information to obtain a second variation probability; performing conditional probability calculation on the second missing probability based on the second variation probability, and outputting an optimized second missing probability.

[0052] Specifically, the charge and discharge management system of the power battery is accessed to obtain the historical charge and discharge cycle count and historical charge and discharge environment information of the power battery. The historical charge and discharge cycle count reflects the use frequency and aging degree of the power battery. The influence of the environment and life span variation. Frequent charge and discharge cycles may shorten the life of the power battery and increase the possibility of energy loss. The historical charge and discharge environment information includes the charge and discharge performance of the power battery under different environmental conditions.

[0053] Then, the historical number of charge and discharge cycles is analyzed to obtain the charge and discharge cycle life and aging trend of the power battery. As the number of cycles increases, the energy storage capacity of the battery may gradually decrease. The historical charge and discharge environment information is analyzed to obtain the impact of factors such as temperature, humidity, and charging rate on the energy storage loss of the power battery. Different charge and discharge environments may lead to different degrees of energy storage loss. Combining the number of cycles and environmental information, the changing trend and pattern of energy storage loss are identified, and the second variation probability is calculated, which reflects the possibility of changes in the energy storage capacity of the power battery.

[0054] Next, the second variation probability is used to perform conditional probability calculation on the calculated second missing probability, the second missing probability is combined with the second variation probability, and the optimized second missing probability is output, which represents the influence of the historical charge and discharge cycle number and environmental information on the energy storage missing probability.

[0055] The optimized second missing probability combines multiple information such as the real-time operating status of the power battery, historical charge and discharge data, and environmental conditions, making it more comprehensive and reliable.

[0056] Furthermore, the present application also includes the following steps:

[0057] The adaptive control decision model judges the first missing probability and the second missing probability, and outputs a first conversion mode if the first missing probability is greater than or equal to the second missing probability; and outputs a second conversion mode if the first missing probability is less than the second missing probability; based on the first conversion mode / the second conversion mode, with the first missing probability being equal to the second missing probability as the goal, the conversion control parameters of the new energy inverter are optimized, and a control parameter solution is output.

[0058] Specifically, the adaptive control decision model receives the first missing probability and the second missing probability, and compares the first missing probability and the second missing probability. If the first missing probability is greater than or equal to the second missing probability, indicating that the load missing probability of the power motor is greater than or equal to the energy storage missing probability of the power battery, it is judged that the current power motor may face a greater load pressure or potential failure, so the stable operation of the power motor should be prioritized, and the first conversion method is output, that is, a conversion strategy that focuses more on ensuring the stable operation of the power motor is selected. On the contrary, if the first missing probability is less than the second missing probability, it is judged that the current power battery may face a greater energy storage pressure or potential failure, so the stable operation and energy storage efficiency of the power battery should be prioritized, and the second conversion method is output, that is, a conversion strategy that focuses more on ensuring the energy storage efficiency of the power battery is selected.

[0059] Then, after determining the conversion mode to be adopted currently, that is, the first conversion mode or the second conversion mode, the control parameters of the first conversion mode or the second conversion mode are optimized through the adaptive control decision model, so that under the selected conversion mode, the first missing probability and the second missing probability are as equal or close as possible to achieve the best balance between the power motor and the power battery. For example, by adjusting multiple control parameters, such as voltage, current, frequency, phase, etc., searching in the parameter space through the gradient descent method, genetic algorithm, particle swarm optimization algorithm, etc., to find the optimal parameter combination and output the control parameter solution.

[0060] The control parameter solution output by the adaptive control decision model is used to control the conversion of the new energy inverter, thereby achieving the optimal balance between the power motor and the power battery, thereby improving the operating efficiency and stability of the entire system.

[0061] Furthermore, the present application also includes the following steps:

[0062] The first loss data of the first conversion mode is calculated by the loss feedback network in the adaptive control decision model; the control parameter solution output by the adaptive control decision model is fed back based on the first loss data, and an optimized control parameter solution is output.

[0063] Specifically, the adaptive control decision model also includes a loss feedback network, through which real-time operation data of the first conversion mode is received. For example, parameters such as voltage, current, temperature, and frequency are included. The loss feedback network calculates the first loss data under the first conversion mode based on these real-time operation data in combination with a preset loss calculation model or algorithm. For example, the first loss data is a loss in various forms such as energy loss, efficiency loss, and equipment wear.

[0064] Then, the first loss data is passed to the adaptive control decision model through the loss feedback network. The adaptive control decision model evaluates whether the currently output control parameter solution is effective based on the received first loss data, and determines whether the currently output control parameter solution needs to be adjusted. If it is determined that adjustment is required, the adaptive control decision model re-optimizes the parameters based on the loss data to find a new control parameter solution that can reduce loss or improve efficiency.

[0065] The loss feedback network provides a dynamic feedback mechanism for the adaptive control decision model, which can continuously optimize the control parameter solution according to the real-time operating data and loss conditions, thereby achieving more efficient and stable new energy inverter control.

[0066] Furthermore, the present application also includes the following steps:

[0067] Collect first connection information between the new energy inverter and the power motor, and second connection information between the new energy inverter and the power battery, wherein the connection information includes connection wire information, connection interface information and switch device information; collect conversion samples of the new energy inverter according to the first connection information and the second connection information, and output a conversion sample data set; introduce a loss function to perform loss analysis on the conversion sample data set, and output a switch loss index, a line loss index and an interface loss index; train the loss feedback network with the switch loss index, the line loss index and the interface loss index.

[0068] Specifically, during the training of the loss feedback network, the first connection information between the new energy inverter and the power motor is collected, including the connection wire information, the connection interface information and the switch device information. For example, the connection wire information includes the wire length, diameter, material, etc., the connection interface information includes the interface type, interface quality, contact resistance, etc., and the switch device information includes the switch type, switch state, switch loss, etc.

[0069] Similarly, the second connection information between the new energy inverter and the power battery is collected, and the connection method of the second connection information is the same as that of the first connection information.

[0070] Then, according to the collected first connection information and second connection information, conversion samples of the new energy inverter are collected, that is, the working state and performance data of the inverter are converted under different connection conditions such as different wires, interfaces, switch combinations, etc. The collected conversion samples are sorted into a data set, namely, a conversion sample data set.

[0071] Next, the loss function is introduced to perform loss analysis on the conversion sample data set. The loss function can reflect the performance loss of the inverter under different connection conditions. According to the loss function, the conversion sample data set is calculated to output the switch loss index, line loss index and interface loss index. These indicators respectively represent the loss of the switch device, connecting wire and connection interface during the inverter conversion process, namely the conduction and cutoff losses.

[0072] Next, the switch loss index, line loss index and interface loss index are used as training data of the loss feedback network and input into the loss feedback network. The loss feedback network learns and predicts the inverter loss, and learns and predicts the inverter loss under different connection conditions based on the input loss index.

[0073] By training the loss feedback network, the loss of the inverter under different connection conditions can be accurately predicted, providing a decision-making basis for subsequent inverter optimization control.

[0074] In summary, the control method for a new energy inverter provided in this application has the following technical effects:

[0075] By acquiring the power motor and the power battery connected to the new energy inverter; monitoring the power motor and the power battery respectively, acquiring the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, wherein the first conversion mode is the mode in which the new energy inverter converts the output signal of the power battery into the signal required by the power motor, and the second conversion mode is the mode in which the new energy inverter converts the output signal of the power motor into the signal required by the power battery; performing operation missing probability identification on the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and outputting the first missing probability and the second missing probability; training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter; performing conversion control on the new energy inverter with the control parameter solution output by the adaptive control decision model, realizing the technical goal of real-time monitoring and analysis of conversion process data, and achieving the technical effect of improving energy conversion efficiency and energy recovery effect. Example 2

[0076] Based on the control method for the new energy inverter in the aforementioned embodiment, the present application also provides a control system for the new energy inverter, see the attached Figure 2 , the system comprising:

[0077] The power motor connection module 11 is used to obtain the power motor and power battery connected to the new energy inverter.

[0078] A conversion monitoring data acquisition module 12 is used to monitor the power motor and the power battery respectively, and obtain conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into a signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts the output signal of the power motor into a signal required by the power battery.

[0079] The first missing probability output module 13 is used to identify the running missing probabilities of the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, and output a first missing probability and a second missing probability.

[0080] The adaptive control decision model training module 14 is used to train the adaptive control decision model, input the first missing probability and the second missing probability into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter.

[0081] The conversion control module 15 is used to perform conversion control on the new energy inverter according to the control parameter solution output by the adaptive control decision model.

[0082] Furthermore, the first missing probability output module 13 in the system is also used for:

[0083] Acquire a historical operation data set of the power motor, wherein the historical operation data set includes a motor balanced load operation sample;

[0084] Performing load operation status analysis on the motor balanced load operation sample to obtain a first balanced load index;

[0085] Identifying the conversion monitoring data of the first conversion mode to obtain a real-time load index of the power motor;

[0086] A first missing probability is calculated according to the real-time load index and the first balanced load index, wherein the first missing probability represents a load missing probability of the power motor.

[0087] Furthermore, the first missing probability output module 13 in the system is also used for:

[0088] Collecting motor fault load operation samples of the power motor and storing them in the historical operation data set;

[0089] Analyze the load change state of the motor fault load operation sample to obtain a first variation probability;

[0090] A conditional probability calculation is performed on the first missing probability according to the first mutation probability, and an optimized first missing probability is output.

[0091] Furthermore, the first missing probability output module 13 in the system is also used for:

[0092] Obtaining a battery energy storage module of the power battery;

[0093] Identify the configuration information of the battery energy storage module to obtain a first effective energy storage index, wherein the first effective energy storage index is an index that meets an energy storage safety threshold;

[0094] Identifying the conversion monitoring data of the second conversion mode to obtain a real-time energy storage index of the power motor;

[0095] A second missing probability is calculated according to the real-time energy storage index and the first effective energy storage index, wherein the second missing probability represents the energy storage missing probability of the power battery.

[0096] Furthermore, the first missing probability output module 13 in the system is also used for:

[0097] Obtaining a battery charge and discharge management system of the power battery, and obtaining historical charge and discharge cycle numbers and historical charge and discharge environment information;

[0098] Analyze the energy storage loss change state of the historical charge and discharge cycle number and the historical charge and discharge environment information to obtain a second variation probability;

[0099] Perform conditional probability calculation on the second missing probability according to the second mutation probability, and output an optimized second missing probability.

[0100] Furthermore, the conversion control module 15 in the system is also used for:

[0101] The adaptive control decision model judges the first missing probability and the second missing probability, and outputs a first conversion mode if the first missing probability is greater than or equal to the second missing probability;

[0102] If the first missing probability is less than the second missing probability, outputting a second conversion mode;

[0103] Based on the first conversion mode / the second conversion mode, with the first missing probability equal to the second missing probability as the goal, the conversion control parameters of the new energy inverter are optimized and the control parameter solution is output.

[0104] Furthermore, the conversion control module 15 in the system is also used for:

[0105] Calculating first loss data of the first conversion mode by using a loss feedback network in the adaptive control decision model;

[0106] Feedback is performed on the control parameter solution output by the adaptive control decision model based on the first loss data, and an optimized control parameter solution is output.

[0107] Furthermore, the conversion control module 15 in the system is also used for:

[0108] Collecting first connection information between the new energy inverter and the power motor, and second connection information between the new energy inverter and the power battery, wherein the connection information includes connection wire information, connection interface information, and switch device information;

[0109] collecting conversion samples of the new energy inverter according to the first connection information and the second connection information, and outputting a conversion sample data set,

[0110] Introducing a loss function to perform loss analysis on the conversion sample data set, and outputting a switch loss index, a line loss index, and an interface loss index;

[0111] The loss feedback network is trained with the switch loss index, the line loss index and the interface loss index.

[0112] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The control method and specific examples for the new energy inverter in the aforementioned embodiment 1 are also applicable to the control system for the new energy inverter in this embodiment. Through the aforementioned detailed description of the control method for the new energy inverter, those skilled in the art can clearly know the control system for the new energy inverter in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0113] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A control method for a new energy inverter, characterized in that: The method comprises: Obtain the power motor and power battery connected to the new energy inverter; The power motor and the power battery are monitored respectively to obtain conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into a signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts the output signal of the power motor into a signal required by the power battery; Performing operation missing probability identification on the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, wherein the missing probability reflects the degree to which the real-time load index deviates from the balanced load index, and outputting a first missing probability and a second missing probability; Training an adaptive control decision model, inputting the first missing probability and the second missing probability into the adaptive control decision model, wherein the adaptive control decision model is connected to the new energy inverter; Performing conversion control on the new energy inverter using the control parameter solution output by the adaptive control decision model; The step of identifying the operation missing probability of the conversion monitoring data of the first conversion mode includes: Acquire a historical operation data set of the power motor, wherein the historical operation data set includes a motor balanced load operation sample; Performing load operation status analysis on the motor balanced load operation sample to obtain a first balanced load index; Identifying the conversion monitoring data of the first conversion mode to obtain a real-time load index of the power motor; A first missing probability is calculated according to the real-time load index and the first balanced load index, wherein the first missing probability represents a load missing probability of the power motor.

2. The method according to claim 1, characterized in that After obtaining the first missing probability, the following steps are also included: Collecting motor fault load operation samples of the power motor and storing them in the historical operation data set; Analyze the load change state of the motor fault load operation sample to obtain a first variation probability; A conditional probability calculation is performed on the first missing probability according to the first mutation probability, and an optimized first missing probability is output.

3. The method according to claim 1, characterized in that The operation missing probability identification is performed on the conversion monitoring data of the second conversion mode, including: Obtaining a battery energy storage module of the power battery; Identify the configuration information of the battery energy storage module to obtain a first effective energy storage index, wherein the first effective energy storage index is an index that meets an energy storage safety threshold; Identifying the conversion monitoring data of the second conversion mode to obtain a real-time energy storage index of the power motor; A second missing probability is calculated according to the real-time energy storage index and the first effective energy storage index, wherein the second missing probability represents the energy storage missing probability of the power battery.

4. The method according to claim 1, characterized in that The method further comprises: Obtaining a battery charge and discharge management system of the power battery, and obtaining historical charge and discharge cycle numbers and historical charge and discharge environment information; Analyze the energy storage loss change state of the historical charge and discharge cycle number and the historical charge and discharge environment information to obtain a second variation probability; Perform conditional probability calculation on the second missing probability according to the second mutation probability, and output an optimized second missing probability.

5. The method according to claim 1, characterized in that The method of performing conversion control on the new energy inverter using the control parameter solution output by the adaptive control decision model includes: The adaptive control decision model judges the first missing probability and the second missing probability, and outputs a first conversion mode if the first missing probability is greater than or equal to the second missing probability; If the first missing probability is less than the second missing probability, outputting a second conversion mode; Based on the first conversion mode / the second conversion mode, with the first missing probability equal to the second missing probability as the goal, the conversion control parameters of the new energy inverter are optimized and the control parameter solution is output.

6. The method according to claim 5, characterized in that The adaptive control decision model also includes a loss feedback network, including: Calculating first loss data of the first conversion mode by using a loss feedback network in the adaptive control decision model; Feedback is performed on the control parameter solution output by the adaptive control decision model based on the first loss data, and an optimized control parameter solution is output.

7. The method according to claim 6, characterized in that Training the loss feedback network includes: Collecting first connection information between the new energy inverter and the power motor, and second connection information between the new energy inverter and the power battery, wherein the connection information includes connection wire information, connection interface information, and switch device information; Collect conversion samples of the new energy inverter according to the first connection information and the second connection information, and output a conversion sample data set; Introducing a loss function to perform loss analysis on the conversion sample data set, and outputting a switch loss index, a line loss index, and an interface loss index; The loss feedback network is trained with the switch loss index, the line loss index and the interface loss index.

8. A control system for a new energy inverter, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A power motor connection module, which is used to obtain a power motor and a power battery connected to a new energy inverter; A conversion monitoring data acquisition module, the conversion monitoring data acquisition module is used to monitor the power motor and the power battery respectively, and acquire conversion monitoring data of a first conversion mode and conversion monitoring data of a second conversion mode, wherein the first conversion mode is a mode in which the new energy inverter converts the output signal of the power battery into a signal required by the power motor, and the second conversion mode is a mode in which the new energy inverter converts the output signal of the power motor into a signal required by the power battery; A first missing probability output module, the first missing probability output module is used to identify the operation missing probability of the conversion monitoring data of the first conversion mode and the conversion monitoring data of the second conversion mode, the missing probability reflects the degree to which the real-time load index deviates from the balanced load index, and outputs a first missing probability and a second missing probability; An adaptive control decision model training module, wherein the adaptive control decision model training module is used to train an adaptive control decision model, input the first missing probability and the second missing probability into the adaptive control decision model, and the adaptive control decision model is connected to the new energy inverter; A conversion control module is used to perform conversion control on the new energy inverter using the control parameter solution output by the adaptive control decision model.