Driving power supply operation state monitoring and adjusting method, equipment and medium

Abstract

The invention relates to a driving power supply operation state monitoring and adjusting method and device and a medium, and relates to the technical field of driving power supplies. Acquiring a running state real-time data set of each monitoring point in the running process of the driving power supply collected by the monitoring equipment, wherein the running state real-time data set at least comprises a power factor, power loss, load, output ripple and temperature; judging whether the running state of the current driving power supply is abnormal or not according to the running state real-time data set and the running state standard data set; when the running state of the driving power supply is abnormal, acquiring a first monitoring point; obtaining a first adjustment parameter according to the running state real-time data set and the running state standard data set of the first monitoring point; and adjusting the operation state of the first monitoring point according to the first adjustment parameter. The LED driving power supply has the effect of improving the reliability of the LED driving power supply.

Description

Technical Field

[0001] The present application relates to the technical field of driving power supply, and in particular to a method, device and medium for monitoring and adjusting the operating status of a driving power supply. Background Art

[0002] LED driver power supply is a power converter that converts power supply into a specific voltage and current to drive LED to emit light. Usually, the input of LED driver power supply includes high-voltage industrial frequency AC (i.e. mains), low-voltage DC, high-voltage DC, low-voltage high-frequency AC (such as the output of electronic transformer), etc. During use, when the LED driver power supply fails or operates unstably, it will cause the LED lamps and LED display screens driven by it to fail. In order to ensure the normal operation of LED lamps and LED display screens, it is necessary to ensure that the operating status of the LED driver power supply remains normal. Therefore, it is necessary to monitor the operating status of the LED driver power supply in real time during its operation.

[0003] The common LED driver power supply monitoring in the prior art usually simply determines whether the voltage, current or temperature and other performances meet the standards by setting thresholds, and issues alarms or stops operation when they do not meet the standards to ensure that LED lamps and LED displays are not affected. This monitoring method cannot comprehensively judge the actual operation of the LED driver power supply, nor can it make adaptive adjustments based on the monitoring results, resulting in poor reliability of the LED driver power supply, which may affect the normal operation of LED lamps and LED displays. Summary of the invention

[0004] The purpose of this application is to provide a method, device and medium for monitoring and adjusting the operating status of a driving power supply to improve the reliability of the driving power supply.

[0005] In the first aspect, a method for monitoring and adjusting the operating status of a driving power supply provided by the present application adopts the following technical solution: A method for monitoring and adjusting the operating status of a driving power supply, comprising: Acquire basic information of the driving power supply, wherein the basic information of the driving power supply includes a circuit connection relationship and a standard data set of an operating state; Obtaining a number of monitoring points according to the circuit connection relationship; Acquire a real-time data set of the operating status of each monitoring point during the operation of the driving power source collected by the monitoring device, wherein the real-time data set of the operating status includes at least power factor, power loss, load, output ripple and temperature; Judging whether the current driving power supply operation state is abnormal according to the operation state real-time data set and the operation state standard data set; When the operating state of the driving power supply is abnormal, obtaining a first monitoring point; Obtaining a first adjustment parameter according to a real-time data set of operating status and a standard data set of operating status of a first monitoring point; The operating state of the first monitoring point is adjusted according to the first adjustment parameter.

[0006] By adopting the above-mentioned technical scheme, the present application can make a comprehensive judgment on the actual operation status of the driving power supply by real-time monitoring the operation status of multiple monitoring points of the driving power supply. At the same time, it can obtain adjustment parameters according to the monitoring results and adaptively adjust the corresponding monitoring points, thereby effectively improving the reliability of the LED driving power supply and ensuring that the LED lamps and LED display screens driven by the driving power supply can maintain normal operation.

[0007] Furthermore, judging whether the current driving power supply operation state is abnormal according to the operation state real-time data set and the operation state standard data set includes: Preset the abnormal range threshold for each operating status data; Compare the real-time data set of the operating status with the standard data set of the operating status, and select the operating status data that exceeds the abnormal range threshold; Record the number of running status data whose difference between real-time running status data and standard running status data exceeds the abnormal range threshold; When the number of operating status data exceeding the abnormal range threshold is greater than 0, it is determined that the current operating status of the driving power supply is abnormal.

[0008] By adopting the above technical solution, the present application determines whether there is an abnormality in the current driving power supply by calculating the difference between the real-time operating status data and the standard operating status data and comparing it with the preset abnormal range threshold, thereby improving the comprehensiveness of the driving power supply operating status monitoring.

[0009] Furthermore, when the operating state of the driving power supply is abnormal, obtaining the first monitoring point includes: Sort the real-time data set of operating status according to the number of operating status data exceeding the abnormal range threshold; The monitoring point corresponding to the real-time running status data set with the largest number of running status data exceeding the abnormal range threshold is selected as the first monitoring point.

[0010] By adopting the above technical solution, when there are multiple abnormal monitoring points, the present application can determine the monitoring point with the most serious abnormality based on the number of real-time data of abnormal operating status, and adjust it first to ensure the reliability of the adjustment of the driving power supply operating status.

[0011] Furthermore, obtaining the first adjustment parameter according to the real-time data set of the operating status of the first monitoring point and the standard data set of the operating status includes: Construct an initial model for adjusting parameter prediction; Acquire operation status real-time data set samples, operation status standard data set samples and corresponding adjustment parameter samples in several operation status adjustment processes in the adjustment parameter prediction database; The samples of the real-time data set of the running status and the samples of the standard data set of the running status are used as input features, and the samples of the adjustment parameters are used as output features to construct a sample set; The initial model for adjusting parameter prediction is trained according to the sample set to obtain a trained adjusting parameter prediction model; The real-time data set of the operating status and the standard data set of the operating status of the first monitoring point are input into the trained adjustment parameter prediction model to obtain the first adjustment parameter.

[0012] By adopting the above technical solution, the present application constructs and trains an adjustment parameter prediction model, uses a neural network to predict the first adjustment parameter, improves the intelligence and accuracy of the prediction of the first adjustment parameter, and thus ensures the accuracy of automatic adjustment of the driving power supply operating state.

[0013] Furthermore, the adjusting parameter prediction initial model is trained according to the sample set to obtain a trained adjusting parameter prediction model, including: Divide the sample set into a training set and a test set, and preset the number of training rounds; Input the training set into the adjusted parameter prediction initial model and train according to the preset number of training rounds; When the adjustment parameter prediction initial model reaches a preset number of training rounds, a trained adjustment parameter prediction model is obtained; Inputting the running status real-time data set samples and the running status standard data set samples in the test set into the trained adjustment parameter prediction model to obtain adjustment parameter prediction samples; The adjustment parameter prediction mean square error is obtained based on the adjustment parameter samples in the test set and the corresponding adjustment parameter prediction samples; The model parameters of the adjustment parameter prediction model are adjusted according to the adjustment parameter pre-mean square error, and the trained adjustment parameter prediction model is obtained according to the adjusted model parameters.

[0014] By adopting the above-mentioned technical solution, the present application trains the model through the real-time data set samples of the operating status, the standard data set samples of the operating status and the corresponding adjustment parameter samples, so that it can learn the characteristic relationship between the real-time data set samples of the operating status, the standard data set samples of the operating status and the corresponding adjustment parameter samples. After the training is completed, the model needs to be tested to determine its accuracy. When the accuracy does not meet the standard, the model parameters are adjusted accordingly to ensure that the final adjustment parameter prediction model meets the requirements.

[0015] Furthermore, it also includes: Obtain several sets of real-time data sets of operating status of each monitoring point changing over time; Build a real-time data set of running status change trends; Determine whether there is potential abnormality in the current driving power supply operation state according to the change trend of the real-time operation state data set and the standard operation state data set; When there is a potential abnormality in the operation state of the driving power supply, a second monitoring point is obtained; Obtaining a second adjustment parameter according to a change trend of a real-time data set of an operating status of a second monitoring point; The operating state of the second monitoring point is adjusted according to the second adjustment parameter.

[0016] By adopting the above-mentioned technical solution, in addition to being able to make adjustments based on the real-time data of the monitored operating status, the present application can also detect whether there are potential abnormalities at present by analyzing the changing trends of the real-time data. If there are potential abnormalities, it indicates that there may be hidden dangers and corresponding adjustments need to be made, which can further ensure the reliability of the monitoring and adjustment of the driving power supply operating status.

[0017] Furthermore, judging whether there is a potential abnormality in the current driving power supply operation state according to the change trend of the operation state real-time data set and the operation state standard data set includes: The time series analysis model is used to predict the change trend of the real-time data set of the operating status, and the operating status prediction data set is obtained; Preset the abnormal range threshold for each operating status data; Compare the operation status prediction data set with the operation status standard data set; When there is operating status data exceeding the abnormal range threshold, it is determined that there is a potential abnormality in the current operating status of the driving power supply.

[0018] By adopting the above technical solution, the present application predicts the operating status within a certain period of time in the future by predicting the changing trend of the real-time data set of the operating status, which can effectively discover potential anomalies and ensure the reliability of the driving power supply operating status monitoring.

[0019] Further, obtaining a second adjustment parameter according to a change trend of a real-time data set of an operating state of the second monitoring point; and adjusting the operating state of the second monitoring point according to the second adjustment parameter include: A compensation function is performed on the difference between the real-time data set of the running status and the standard data set of the running status according to the change trend of the real-time data set of the running status to obtain a second adjustment parameter. The compensation function is a function built with the goal of minimizing the difference between the real-time data set of the running status and the standard data set of the running status.

[0020] By adopting the above technical solution, the present application obtains the second adjustment parameter through the compensation function response to adjust the monitoring point where potential abnormal conditions may exist, thereby ensuring the reliability and accuracy of the adjustment of the operating state of the driving power supply.

[0021] In a second aspect, the present application provides a computer device that adopts the following technical solution: A computer device comprises a memory and a processor, wherein the memory stores a method for monitoring and adjusting the operating status of a driving power supply as described in the first aspect and which can be loaded and executed by the processor.

[0022] By adopting the above technical solution, the present application automatically monitors and adjusts the operating status of the driving power supply through a computer program, thereby improving the reliability of the driving power supply operation and the intelligence of the status adjustment.

[0023] In a third aspect, the present application provides a computer-readable storage medium that adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and executes a method for monitoring and adjusting the operating status of a driving power supply as described in the first aspect.

[0024] By adopting the above technical solution, the present application automatically monitors and adjusts the operating status of the driving power supply through a computer program, thereby improving the reliability of the driving power supply operation and the intelligence of the status adjustment.

[0025] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application can make a comprehensive judgment on the actual operation of the driving power supply by real-time monitoring the operating status of multiple monitoring points of the driving power supply. At the same time, it can obtain adjustment parameters according to the monitoring results and adaptively adjust the corresponding monitoring points, effectively improving the reliability of the LED driving power supply and ensuring that the LED lamps and LED display screens driven by the driving power supply can maintain normal operation; 2. This application constructs and trains an adjustment parameter prediction model, uses a neural network to predict the first adjustment parameter, improves the intelligence and accuracy of the first adjustment parameter prediction, and thus ensures the accuracy of automatic adjustment of the driving power supply operating state; 3. In addition to being able to make adjustments based on real-time data of monitored operating status, this application can also detect whether there are potential abnormalities at present by analyzing the changing trends of real-time data. If there are potential abnormalities, it indicates that there may be hidden dangers and corresponding adjustments need to be made, which can further ensure the reliability of the monitoring and adjustment of the driving power supply operating status. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a flow chart of a method for monitoring and adjusting real-time data of operating status according to an embodiment of the present application; Figure 2 It is a flow chart of the operating status change trend monitoring and adjustment method of an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following is combined with Figure 1 -Attached Figure 2 , further details of this application are given.

[0028] The common LED driver power supply monitoring in the prior art is usually to simply determine whether the voltage, current or temperature and other performances meet the standards by setting thresholds, and to alarm or stop the operation when they do not meet the standards to ensure that the LED lamps and LED displays are not affected. This monitoring method cannot make a comprehensive judgment on the actual operation of the LED driver power supply, nor can it make adaptive adjustments based on the monitoring results, resulting in poor reliability of the LED driver power supply, which may affect the normal operation of the LED lamps and LED displays. Therefore, the embodiments of the present application provide a driver power supply operation status monitoring and adjustment method, device and medium, with reference to Figure 1 ,include: S1. Obtain basic information of the driving power supply.

[0029] Specifically, the basic information of the driving power supply includes the circuit connection relationship and the standard operating status data set. The circuit connection relationship may include the main components in the driving power supply and the distribution and connection of the components. The standard operating status data set includes the standard value of the driving power supply power factor, power loss standard value, load standard value, output ripple standard value and temperature standard value.

[0030] S2. Obtain several monitoring points according to the circuit connection relationship.

[0031] Specifically, the driver power supply can be analyzed according to factors such as circuit connection relationship, importance of circuit components, LED driver requirements and environmental impact, and several monitoring points that can fully reflect the operating status of the driver power supply can be obtained for monitoring the driver power supply. Specifically, it can include different circuit connections, high-temperature parts, important circuit components, key LED power supply output positions, etc. Among them, the different circuit connections are because the driver power supply is usually composed of multiple circuits, which may affect each other, thus causing power fluctuations; high-temperature parts refer to parts that affect the temperature rise of the circuit due to the high temperature of the installation environment. Monitoring can timely discover problems and repair them; important circuit components refer to important parts where failures may cause the entire driver power supply to fail to operate.

[0032] S3. Obtain a real-time data set of the operating status of each monitoring point during the operation of the driving power source collected by the monitoring device.

[0033] Specifically, the real-time data set of the operating status includes at least power factor, power loss, load, output ripple and temperature. In order to ensure the stable operation of the driving power supply and the flexibility of detection, the data collection of the monitoring points adopts a detection method that combines contact and non-contact methods. Among them, contact measurement includes building a detection circuit in the circuit, installing a detection device, etc.; non-contact measurement includes thermal imaging measurement, sound wave detection, magnetic field detection, etc. The monitoring points are determined according to the circuit's use environment, installation location, etc., including different circuit connections, high-temperature parts, key LED lamp bead locations, driving power supplies, etc.

[0034] S4. Determine whether the current driving power supply operating state is abnormal based on the operating state real-time data set and the operating state standard data set.

[0035] Specifically, by comparing the real-time data set of the operating status with the standard data set of the operating status, it is possible to intuitively determine whether the operating status of the current driving power supply is abnormal.

[0036] S5. When the operating state of the driving power supply is abnormal, obtain a first monitoring point.

[0037] Specifically, when there is only one abnormal monitoring point, the monitoring point is the first monitoring point.

[0038] S6. Obtain a first adjustment parameter according to the real-time data set of the operating status of the first monitoring point and the standard data set of the operating status.

[0039] Specifically, the first adjustment parameter is predicted by adjusting the parameter prediction model according to the real-time data set of the operating status and the standard data set of the operating status of the first monitoring point.

[0040] S7. Adjust the operating state of the first monitoring point according to the first adjustment parameter.

[0041] Specifically, after the operation status adjustment of the first monitoring point is completed, the process returns to step S3 to re-collect the real-time data sets of the operation status of each monitoring point, and then continues to make the next adjustment according to the real-time data sets of the operation status.

[0042] The implementation principle of the embodiment of the present application is: by constructing and training an adjustment parameter prediction model, a neural network is used to predict the first adjustment parameter, thereby improving the intelligence and accuracy of the prediction of the first adjustment parameter, thereby ensuring the accuracy of automatic adjustment of the driving power supply operating state.

[0043] Since there may be a certain correlation between the operating states of each monitoring point, when adjusting the operating state, the monitoring point with the most abnormal data is selected for adjustment first, which may cause other monitoring points with partial abnormalities to be adjusted synchronously, without the need to adjust each monitoring point separately. Therefore, step S4 of the embodiment of the present application specifically includes: S41. Preset an abnormal range threshold for each operating status data.

[0044] Specifically, affected by environmental factors or driving requirements, normal operating status data may not be completely consistent with standard operating status data. Therefore, an abnormal range threshold is set for each operating status data according to actual requirements and the difference of each operating status data.

[0045] S42, comparing the real-time data set of the operating status with the standard data set of the operating status, and selecting the operating status data that exceeds the abnormal range threshold; Specifically, the real-time running status data set and the standard running status data set are first compared, and then the difference between the same running status data in the real-time running status data set and the standard running status data set is compared with the abnormal range threshold, and the running status data exceeding the abnormal range threshold is regarded as abnormal running status data.

[0046] S43, recording the number of running status data for which the difference between the real-time running status data and the standard running status data exceeds the abnormal range threshold.

[0047] Specifically, the number of abnormal operating status data included in each operating status real-time data having abnormal operating status data is recorded.

[0048] S44: When the number of operating status data exceeding the abnormal range threshold is greater than 0, it is determined that the current operating status of the driving power supply is abnormal.

[0049] Specifically, the existence of operating status data exceeding the abnormal range threshold indicates that the current operating status of the driving power supply is abnormal.

[0050] Step S5 of the embodiment of the present application includes: S51. Sort the real-time operating status data set according to the number of operating status data exceeding the abnormal range threshold.

[0051] S52: Select the monitoring point corresponding to the real-time running status data set with the largest number of running status data exceeding the abnormal range threshold as the first monitoring point.

[0052] Specifically, when there are multiple abnormal monitoring points, the monitoring point with the most serious abnormality is determined according to the amount of real-time data of abnormal operation status, and is adjusted first.

[0053] In order to improve the intelligence and accuracy of the prediction of the first adjustment parameter, step S6 of the embodiment of the present application includes: S61, construct an initial model for adjusting parameter detection.

[0054] Specifically, an adjustment parameter detection initial model is constructed based on LSTM, and model parameters of the adjustment parameter detection initial model are configured. The model parameters include but are not limited to the number of LSTM units, activation function, and input sequence length.

[0055] S62, obtaining operation status real-time data set samples, operation status standard data set samples and corresponding adjustment parameter samples in the drive power supply operation status monitoring and adjustment database, and constructing the operation status real-time data set samples, operation status standard data set samples and corresponding adjustment parameter samples into a sample set.

[0056] Specifically, the driving power supply operating status monitoring and adjustment database stores operating status real-time data set samples, operating status standard data set samples and corresponding adjustment parameter samples acquired and stored during previous driving power supply operating status monitoring and adjustment. The operating status real-time data set samples and operating status standard data set samples are used as input, and the adjustment parameter samples are used as output to construct a sample set.

[0057] S63. Train the initial model for adjusting parameter detection according to the sample set to obtain a trained adjusting parameter detection model.

[0058] Specifically, a sample set is used to train an initial model for adjusting parameter detection, wherein samples of the real-time data set of operating status and samples of the standard data set of operating status are used as input data, and samples of adjustment parameters are used as output data, so that the model can learn the characteristic relationship between samples of the real-time data set of operating status, samples of the standard data set of operating status and samples of adjustment parameters.

[0059] S64: Input the real-time data set of the operating status and the standard data set of the operating status of the first monitoring point into the trained adjustment parameter prediction model to obtain a first adjustment parameter.

[0060] Specifically, the adjustment parameter detection model predicts the corresponding adjustment parameter detection result according to the learned feature relationship and the input adjustment parameter detection data set, and outputs the adjustment parameter detection result.

[0061] In the process of model construction, in addition to training the model, it is also necessary to determine whether the accuracy of the model meets the standard through testing. Therefore, step S63 of this embodiment specifically includes: S631, dividing the sample set into a training set and a test set, and presetting the number of training rounds.

[0062] Specifically, 70% of the sample set is usually used as a training set and 30% as a test set.

[0063] S632: Input the training set into the initial model to adjust the parameters and perform training according to the preset number of training rounds.

[0064] Specifically, during training, the running status real-time data set samples and the running status standard data set samples of the training set are used as input data, and the adjustment parameter samples are used as output data to train the adjustment parameter detection initial model.

[0065] S633: When the initial model for adjusting parameter detection reaches a preset number of training rounds, a trained adjustment parameter detection model is obtained.

[0066] S634: Input the running status real-time data set samples and the running status standard data set samples in the test set into the trained adjustment parameter detection model to obtain adjustment parameter detection result prediction samples.

[0067] Specifically, after the model is trained, the output results of the model are tested using input data in a sample set of known output data.

[0068] S635. Obtain a mean square error of the adjustment parameter detection result according to the adjustment parameter samples in the test set and the corresponding adjustment parameter detection result prediction samples.

[0069] Specifically, mean-square error (MSE) is a measure of the difference between the estimator and the estimated quantity, that is, the adjustment parameter sample and the corresponding adjustment parameter detection result prediction sample. The difference between the adjustment parameter sample and the corresponding adjustment parameter detection result prediction sample is judged based on the mean-square error, so as to judge whether the trained adjustment parameter detection model meets the requirements.

[0070] S636: When the mean square error of the adjusted parameter detection result is greater than the preset error value, the model parameters of the parameter detection model are adjusted repeatedly until the mean square error of the adjusted parameter detection result is less than the preset error value.

[0071] Specifically, if the mean square error of the adjustment parameter detection result is greater than the preset error value, the accuracy of the adjusted parameter detection model after training is low and does not meet the requirements, and the model parameters need to be adjusted.

[0072] S637. When the mean square error of the adjustment parameter detection result is less than the preset error value, a trained adjustment parameter detection model is obtained according to the current model parameters.

[0073] Specifically, the model parameters of the adjustment parameter detection model are adjusted according to the adjustment parameter samples in the test set and the corresponding adjustment parameter detection result prediction samples, and the trained adjustment parameter detection model is obtained according to the adjusted model parameters.

[0074] The implementation principle of the embodiment of the present application is: the initial model for adjustment parameter detection is trained through the constructed sample set, so that it can learn the characteristic relationship between the real-time data set samples of the operating status, the standard data set samples of the operating status and the adjustment parameter samples. After the training is completed, the model needs to be tested to determine its accuracy. When the accuracy does not meet the standard, the model parameters are adjusted accordingly to ensure that the final adjustment parameter detection model meets the requirements, thereby improving the intelligence and reliability of the drive power supply operating status monitoring and adjustment.

[0075] The monitoring method in the prior art cannot timely predict the change of the operating state when there are potential influencing factors on the operating state of the driving power supply, resulting in limitations in the monitoring of the operating state of the LED driving power supply. Figure 2 The driving power supply operation status monitoring and adjustment method of the present application can also adjust the driving power supply operation status in advance according to the change trend of the real-time data set of the operation status, specifically including: A1. Obtain several sets of real-time data sets of operating status of each monitoring point that change over time.

[0076] Specifically, a fixed time period may be preset, and several groups of real-time data sets of operating status within the time period are collected.

[0077] A2. Build a real-time data set of running status change trends.

[0078] Specifically, with the real-time data of the operating status as the dependent variable and time as the independent variable, a curve showing the change of the real-time data of the operating status over time can be constructed, which is the change trend of the real-time data set of the operating status.

[0079] A3. Determine whether there is potential abnormality in the current driving power supply operation state according to the change trend of the real-time operation state data set and the standard operation state data set.

[0080] Specifically, the changing trend of the real-time data set of the operating status is predicted through the time series analysis model to obtain the operating status prediction data set, the abnormal range threshold of each operating status data is preset, the operating status prediction data set is compared with the operating status standard data set, and when there is operating status data exceeding the abnormal range threshold, it is judged that there is potential abnormality in the current driving power supply operating state.

[0081] A4. When there is a potential abnormality in the operating state of the driving power supply, a second monitoring point is obtained.

[0082] Specifically, the second monitoring point may be acquired in the same manner as the first monitoring point.

[0083] A5. Obtain a second adjustment parameter according to a change trend of the real-time data set of the operating status of the second monitoring point.

[0084] Specifically, a compensation function is performed on the difference between the real-time data set of the running status and the standard data set of the running status according to the change trend of the real-time data set of the running status to obtain the second adjustment parameter. The compensation function is a function built with the goal of minimizing the difference between the real-time data set of the running status and the standard data set of the running status.

[0085] A6. Adjust the operating state of the second monitoring point according to the second adjustment parameter.

[0086] The implementation principle of the embodiment of the present application is: in addition to being able to make adjustments based on the real-time data of the monitored operating status, the present application can also detect whether there is a potential abnormality at present by analyzing the changing trend of the real-time data. If there is a potential abnormality, it indicates that there may be hidden dangers and corresponding adjustments need to be made, which can further ensure the reliability of the monitoring and adjustment of the driving power supply operating status.

[0087] The embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a method for monitoring and adjusting the operating state of a driving power supply, specifically including: S1. Obtain basic information of the driving power supply.

[0088] S2. Obtain several monitoring points according to the circuit connection relationship.

[0089] S3. Obtain a real-time data set of the operating status of each monitoring point during the operation of the driving power source collected by the monitoring device.

[0090] S4. Determine whether the current driving power supply operating state is abnormal based on the operating state real-time data set and the operating state standard data set.

[0091] S5. When the operating state of the driving power supply is abnormal, obtaining a first monitoring point; S6. Obtain a first adjustment parameter according to the real-time data set of the operating status of the first monitoring point and the standard data set of the operating status.

[0092] S7. Adjust the operating state of the first monitoring point according to the first adjustment parameter.

[0093] Wherein, the computer is a server, and the computer device includes a processor, a memory, a network interface and a database connected through a system bus. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store basic information of the driving power supply, real-time data sets of operating status, abnormal range thresholds, adjustment parameter prediction models, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery performance test method can be implemented.

[0094] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1. Obtain basic information of the driving power supply.

[0095] S2. Obtain several monitoring points according to the circuit connection relationship.

[0096] S3. Obtain a real-time data set of the operating status of each monitoring point during the operation of the driving power source collected by the monitoring device.

[0097] S4. Determine whether the current driving power supply operating state is abnormal based on the operating state real-time data set and the operating state standard data set.

[0098] S5. When the operating state of the driving power supply is abnormal, obtaining a first monitoring point; S6. Obtain a first adjustment parameter according to the real-time data set of the operating status of the first monitoring point and the standard data set of the operating status.

[0099] S7. Adjust the operating state of the first monitoring point according to the first adjustment parameter.

[0100] In addition, the processor in the computer device executes all the steps of the above-mentioned driving power supply operation status monitoring and adjustment method when executing the computer program.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0102] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0103] The embodiments of this specific implementation are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. The same components are represented by the same figure marks. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for monitoring and adjusting the operating status of a driving power supply, characterized in that: include: Acquire basic information of the driving power supply, wherein the basic information of the driving power supply includes a circuit connection relationship and a standard data set of an operating state; Obtaining a number of monitoring points according to the circuit connection relationship; Acquire a real-time data set of the operating status of each monitoring point during the operation of the driving power source collected by the monitoring device, wherein the real-time data set of the operating status includes at least power factor, power loss, load, output ripple and temperature; Judging whether the current driving power supply operation state is abnormal according to the operation state real-time data set and the operation state standard data set; When the operating state of the driving power supply is abnormal, obtaining a first monitoring point; Obtaining a first adjustment parameter according to a real-time data set of operating status and a standard data set of operating status of a first monitoring point; The operating state of the first monitoring point is adjusted according to the first adjustment parameter.

2. A method for monitoring and adjusting the operating status of a driving power supply according to claim 1, characterized in that: The step of judging whether the current driving power supply operation state is abnormal according to the operation state real-time data set and the operation state standard data set includes: Preset the abnormal range threshold for each operating status data; Compare the real-time data set of the operating status with the standard data set of the operating status, and select the operating status data that exceeds the abnormal range threshold; Record the number of running status data whose difference between real-time running status data and standard running status data exceeds the abnormal range threshold; When the number of operating status data exceeding the abnormal range threshold is greater than 0, it is determined that the current operating status of the driving power supply is abnormal.

3. A method for monitoring and adjusting the operating status of a driving power supply according to claim 2, characterized in that: When the operation state of the driving power supply is abnormal, obtaining the first monitoring point includes: Sort the real-time data set of operating status according to the number of operating status data exceeding the abnormal range threshold; The monitoring point corresponding to the real-time running status data set with the largest number of running status data exceeding the abnormal range threshold is selected as the first monitoring point.

4. A driving power supply operation status monitoring and adjustment method according to claim 1, characterized in that: The step of obtaining the first adjustment parameter according to the real-time data set of the operating status of the first monitoring point and the standard data set of the operating status includes: Construct an initial model for adjusting parameter prediction; Acquire operation status real-time data set samples, operation status standard data set samples and corresponding adjustment parameter samples in several operation status adjustment processes in the adjustment parameter prediction database; The samples of the real-time data set of the running status and the samples of the standard data set of the running status are used as input features, and the samples of the adjustment parameters are used as output features to construct a sample set; The initial model for adjusting parameter prediction is trained according to the sample set to obtain a trained adjusting parameter prediction model; The real-time data set of the operating status and the standard data set of the operating status of the first monitoring point are input into the trained adjustment parameter prediction model to obtain the first adjustment parameter.

5. A method for monitoring and adjusting the operating status of a driving power supply according to claim 4, characterized in that: The step of training the initial adjustment parameter prediction model according to the sample set to obtain a trained adjustment parameter prediction model includes: Divide the sample set into a training set and a test set, and preset the number of training rounds; Input the training set into the adjusted parameter prediction initial model and train according to the preset number of training rounds; When the adjustment parameter prediction initial model reaches a preset number of training rounds, a trained adjustment parameter prediction model is obtained; Inputting the running status real-time data set samples and the running status standard data set samples in the test set into the trained adjustment parameter prediction model to obtain adjustment parameter prediction samples; The adjustment parameter prediction mean square error is obtained based on the adjustment parameter samples in the test set and the corresponding adjustment parameter prediction samples; The model parameters of the adjustment parameter prediction model are adjusted according to the adjustment parameter pre-mean square error, and the trained adjustment parameter prediction model is obtained according to the adjusted model parameters.

6. A method for monitoring and adjusting the operating status of a driving power supply according to any one of claims 1 to 5, characterized in that: Also includes: Obtain several sets of real-time data sets of operating status of each monitoring point changing over time; Build a real-time data set of running status change trends; Determine whether there is potential abnormality in the current driving power supply operation state according to the change trend of the real-time operation state data set and the standard operation state data set; When there is a potential abnormality in the operation state of the driving power supply, a second monitoring point is obtained; Obtaining a second adjustment parameter according to a change trend of a real-time data set of an operating status of a second monitoring point; The operating state of the second monitoring point is adjusted according to the second adjustment parameter.

7. A method for monitoring and adjusting the operating status of a driving power supply according to claim 6, characterized in that: The step of judging whether there is a potential abnormality in the current driving power supply operation state according to the change trend of the operation state real-time data set and the operation state standard data set includes: The time series analysis model is used to predict the change trend of the real-time data set of the operating status, and the operating status prediction data set is obtained; Preset the abnormal range threshold for each operating status data; Compare the operation status prediction data set with the operation status standard data set; When there is operating status data exceeding the abnormal range threshold, it is determined that there is a potential abnormality in the current operating status of the driving power supply.

8. A method for monitoring and adjusting the operating status of a driving power supply according to claim 7, characterized in that: The second adjustment parameter is obtained according to the change trend of the real-time data set of the operating status of the second monitoring point; Adjusting the operating state of the second monitoring point according to the second adjustment parameter includes: A compensation function is performed on the difference between the real-time running status data set and the standard running status data set according to the change trend of the real-time running status data set to obtain a second adjustment parameter. The compensation function is a function built with the goal of minimizing the difference between the real-time running status data set and the standard running status data set.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a method for monitoring and adjusting the operating status of a driving power supply as described in any one of claims 1 to 8, which can be loaded and executed by the processor.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes a method for monitoring and adjusting the operating status of a driving power supply as described in any one of claims 1 to 8.

Images