Storage battery on-line monitoring device monomer voltage measurement precision intelligent inspection method and system

Abstract

The invention belongs to the technical field of electrical equipment inspection, and relates to an intelligent inspection method and system for the monomer voltage measurement precision of a storage battery online monitoring device, and the method comprises the steps: inputting the monomer voltage measurement precision range standard of the storage battery online monitoring device and the parameters of the detected storage battery online monitoring device, and importing the standard and the parameters into an inspection rule base; adjusting the output voltage of the programmable direct-current power supply and the output voltage of the programmable battery simulator, judging whether the output voltage of the programmable battery simulator is within a preset range or not, if so, acquiring an image of a single voltage display value of the detected storage battery online monitoring device, performing intelligent identification, performing abnormality filtering operation on the identified voltage value, and performing the abnormality filtering operation on the detected storage battery online monitoring device. And then calculating the monomer voltage measurement accuracy of the detected storage battery on-line monitoring device, and comparing the monomer voltage measurement accuracy with the monomer voltage measurement accuracy range standard of the storage battery on-line monitoring device to judge whether the measurement accuracy reaches the standard or not. According to the invention, intelligent and accurate detection of the measurement precision of the single voltage of the storage battery on-line monitoring device is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of electrical equipment inspection, and particularly relates to an intelligent inspection method and system for the measurement accuracy of the individual voltage of a battery online monitoring device. Background Art

[0002] As a key device for real-time monitoring of the operation status of batteries in the power system, the performance stability of the substation battery online monitoring device is directly related to the overall operation quality of the power system. During the equipment inspection process, the measurement accuracy of the individual voltage of the battery online monitoring device is one of the important indicators for evaluating the performance of the battery online monitoring device. However, traditional inspection methods often rely on manual observation and manual recording, with problems such as high inspection errors, cumbersome inspection processes, and slow inspection speeds, making it difficult to meet the high requirements for the inspection of battery online monitoring devices in modern substations.

[0003] To ensure the stable operation of the battery online monitoring device in the substation, the quality inspection personnel of the substation network access equipment need to strictly inspect the battery online monitoring device according to the power industry standards to ensure that it can meet the technical parameter requirements of the substation for the operating equipment. As a key inspection item among them, the inspection accuracy of the measurement accuracy of the individual voltage of the battery online monitoring device is particularly important.

[0004] Chinese Patent Document CN117269871A discloses an inspection device for a battery online monitor, including: a temperature source output module for outputting simulated battery temperature data to the battery online monitor; a voltage source output module for outputting simulated battery voltage data to the battery online monitor; the voltage source output module further includes a super capacitor, and the simulated battery voltage data is the output voltage of the super capacitor; an equivalent internal resistance output module connected in series with the voltage source output module for outputting simulated battery equivalent internal resistance data to the battery online monitor; a microcontroller electrically connected to the temperature source output module, the voltage source output module, and the equivalent internal resistance output module respectively, for adjusting the resistance value of the equivalent internal resistance output module, and receiving the detection data transmitted back by the battery online monitor and performing accuracy detection.

[0005] The above solution provides an inspection device for inspecting a battery online monitor.

[0006] If the artificial method is used to inspect this detection item, it will consume a lot of time and energy of the quality inspection personnel of the substation network access equipment. Not only is the inspection speed slow, the inspection efficiency is low, but also problems such as human misinspection and false inspection are extremely likely to occur.

[0007] To solve the above problems and effectively assist in improving the inspection efficiency of the single-cell voltage measurement accuracy of the battery online monitoring device by the quality inspection personnel of the substation access equipment, it is very necessary to design an intelligent inspection method for the single-cell voltage measurement accuracy of the battery online monitoring device. Summary of the Invention

[0008] The present invention aims to overcome at least one defect of the above-mentioned prior art and provides an intelligent inspection method for the single-cell voltage measurement accuracy of a battery online monitoring device.

[0009] The present invention also discloses a system loaded with the intelligent inspection method for the single-cell voltage measurement accuracy of the battery online monitoring device.

[0010] The detailed technical solution of the present invention is as follows: An intelligent inspection method for the single-cell voltage measurement accuracy of a battery online monitoring device, which is applied to the inspection system for the single-cell voltage measurement accuracy of the battery online monitoring device. The method includes: S1. In the inspection system for the single-cell voltage measurement accuracy of the battery online monitoring device, according to the inspection requirements, input the standard of the single-cell voltage measurement accuracy range of the battery online monitoring device and the parameters of the battery online monitoring device to be inspected, and import the pre-constructed inspection rule library; wherein, the standard of the single-cell voltage measurement accuracy range of the battery online monitoring device is determined according to the electric power industry standard; S2. Adjust the output voltage of the programmable DC power supply to 100% , adjust the output voltage of the programmable battery simulator to X% , and read whether the value of the output voltage of the programmable battery simulator is within the preset range. If the reading results of n consecutive times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; wherein, is the nominal battery pack voltage of the battery online monitoring device, is the single-cell voltage of the battery monitored by the battery online monitoring device, X is a positive number, and n is a positive integer; S3. If the value of the output voltage of the programmable battery simulator in S2 is within the preset range, obtain an image of the single-cell voltage display value of the current battery online monitoring device to be inspected, and use the YOLOv8 model for target detection to obtain an image of the voltage numerical area; S4. Preprocess the image of the voltage numerical area to separate the voltage digital part and the background part in the image of the voltage numerical area, use the PaddleOCR digital special model to identify the voltage digital part, and then perform post-processing of rule verification for voltage value range constraint on the identified voltage numerical result to complete the intelligent identification of the single-cell voltage display value; S5. Filter the single - cell voltage display value of the currently detected battery online monitoring device to eliminate abnormal values in the collected voltage data, and calculate the measurement accuracy of the single - cell voltage of the battery online monitoring device according to the constructed inspection rule library to obtain the measurement accuracy of the single - cell voltage of the detected battery online monitoring device in this scenario; S6. Adjust the proportion X in the output voltage of the programmable battery simulator to different values, and repeat S2 - S5 to obtain the measurement accuracy of the single - cell voltage of the detected battery online monitoring device in multiple scenarios. Then compare it with the standard of the measurement accuracy range of the single - cell voltage of the battery online monitoring device entered. If it is within this range value, it is determined that the measurement accuracy of the single - cell voltage of the detected battery online monitoring device meets the standard; otherwise, it is determined that it does not meet the standard.

[0011] Preferably according to the present invention, in S3, the YOLOv8 model is used for numerical target detection, and the input resolution of the model is adjusted to 1280x1280 to obtain an image of the voltage numerical area for target detection.

[0012] Preferably according to the present invention, in S4, pre - process the voltage numerical area image, including: Successively extract the region of interest from the voltage numerical area image and crop the voltage numerical area obtained by target detection; Use the non - local means method for denoising and filtering; Adopt the CLAHE method for image enhancement processing, and complete the separation of voltage digits and the background through adaptive threshold processing.

[0013] Preferably according to the present invention, in S4, use the PaddleOCR digital - specific model to identify voltage digits, and add an optimization strategy design in this model, that is, only train and identify voltage display value characters, including digits 0 - 9, decimal points, V, kV, mV.

[0014] Preferably according to the present invention, in S5, filtering the single - cell voltage display value of the currently detected battery online monitoring device includes: adopting the 3σ criterion and the Grubbs test model. In the 3σ criterion, a sliding window mechanism is adopted to calculate the mean μ and standard deviation σ of the data within the window; in the Grubbs test model, iterative detection is performed to automatically execute multiple rounds of detection until there are no outliers; and the modified T - distribution look - up table method is used for critical value optimization; further, a fusion rule is constructed for the improved 3σ criterion and the Grubbs test model by means of weighted voting of the weighted sum of the output abnormal probabilities to screen out the abnormal values in the collected voltage data and perform noise reduction and filtering processing on them.

[0015] Preferably according to the present invention, in S5, the calculation formula for the measurement accuracy of the single-cell voltage of the battery on-line monitoring device: (4); In formula (4): represents the voltage measurement accuracy; represents the standard single-cell voltage value of the battery monitored by the battery on-line monitoring device; represents the displayed value of the single-cell voltage of the battery on-line monitoring device.

[0016] Preferably according to the present invention, the preset range of the output voltage of the programmable battery simulator is X% ± 0.2V, where X% sequentially takes 50% 、70% 、90% 、110% 、130% .

[0017] In another aspect of the present invention, a system for realizing the intelligent inspection method for the single-cell voltage measurement accuracy of the battery on-line monitoring device is provided. The system includes: An input module, used to input the standard of the single-cell voltage measurement accuracy range of the battery on-line monitoring device and the parameters of the battery on-line monitoring device to be inspected, and import the pre-constructed inspection rule library; A voltage adjustment module, used to adjust the output voltage of the programmable DC power supply and the output voltage of the programmable battery simulator respectively. Among them, the output voltage of the programmable battery simulator is adjusted to X% , is the single-cell voltage of the battery monitored by the battery on-line monitoring device, and read whether X% is within the preset range. If the reading results of consecutive n times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; n is a positive integer; A voltage detection module, used to perform target detection on the image of the displayed value of the single-cell voltage of the currently inspected battery on-line monitoring device obtained by using the YOLOv8 model to obtain the voltage numerical area image; A voltage value recognition module, used to preprocess the voltage numerical area image to separate the voltage digital part and the background part in the voltage numerical area image, and use the PaddleOCR digital special model to recognize the voltage digital part, and then perform rule verification post-processing on the recognized voltage numerical result for voltage value range constraint to obtain the finally recognized displayed value of the single-cell voltage of the battery on-line monitoring device to be inspected; An intelligent analysis module, configured to filter the displayed value of the single-cell voltage of the currently inspected on-line monitoring device for storage batteries, and calculate the measurement accuracy of the single-cell voltage of the currently inspected on-line monitoring device for storage batteries; An inspection result determination module, configured to adjust the ratio X in the output voltage of the programmable battery simulator to different values, so as to obtain the measurement accuracy of the single-cell voltage of the inspected on-line monitoring device for storage batteries in multiple scenarios, and compare it with the standard of the input range of the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries, so as to determine whether the measurement accuracy of the single-cell voltage of the currently inspected on-line monitoring device for storage batteries meets the standard.

[0018] In another aspect of the present invention, there is also provided an electronic device, including: At least one processor; and A memory, the memory stores instructions, when the instructions are executed by the at least one processor, the at least one processor is caused to execute the intelligent inspection method for the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries as described above.

[0019] In another aspect of the present invention, there is also provided a machine-readable storage medium, which stores executable instructions, and when the instructions are executed, the machine is caused to execute the intelligent inspection method for the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries as described above.

[0020] Compared with the prior art, the beneficial effects of the present invention are: (1) An intelligent inspection method for the measurement accuracy of the single-cell voltage of an on-line monitoring device for storage batteries provided by the present invention designs a data intelligent acquisition method and a data intelligent analysis and processing strategy for the functional characteristics of the on-line monitoring device for storage batteries, ensures the accuracy of value selection in the inspection process, and at the same time ensures the comprehensiveness of the inspection of the measurement accuracy of the single-cell voltage of the storage battery; at the same time, an inspection method in multiple scenarios is proposed, and an inspection rule library is constructed based on this, which can realize the intelligent acquisition, multi-scenario inspection, intelligent analysis, result visualization display and intelligent storage of the detection data of the on-line monitoring device for storage batteries, and finally realizes the intelligent and accurate inspection of the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries.

[0021] (2) The present invention effectively solves the problem of single-scenario and inefficient inspection carried out by the traditional method of manual observation and recording, improves the inspection efficiency and accuracy of the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries by the quality inspection personnel of the substation access network equipment, and greatly reduces the work pressure of the inspection personnel. Description of the Drawings

[0022] Figure 1 It is a flowchart of the intelligent inspection method for the measurement accuracy of the single-cell voltage of the on-line monitoring device for storage batteries described in the present invention.

[0023] Figure 2 It is the architecture diagram of the intelligent detection platform for the on-line monitoring device of the storage battery in Embodiment 1 of the present invention.

[0024] Figure 3 It is an example diagram of the single-cell voltage measurement and inspection process of the on-line monitoring device of the storage battery in Embodiment 1 of the present invention. Specific implementation manners

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0027] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0028] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0029] Aiming at the deficiencies of the prior art, the present invention provides an intelligent inspection method for the single-cell voltage measurement accuracy of an on-line monitoring device of a storage battery. This method designs a data intelligent acquisition method and a data intelligent analysis and processing strategy for the functional characteristics of the on-line monitoring device of the storage battery to ensure the accuracy of the selected values in the inspection process. At the same time, to ensure the comprehensiveness of the inspection of the single-cell voltage measurement accuracy of the storage battery, this method proposes inspection methods in multiple scenarios and constructs an inspection rule library. By integrating the inspection rule library with intelligent analysis technology, it effectively realizes the intelligent acquisition, analysis, filtering, and calculation processing of data in the entire inspection process, and further realizes the purpose of intelligent and accurate inspection. In addition, this method uses chart visualization technology to give the single-cell voltage measurement accuracy of the on-line monitoring device of the storage battery to be inspected, providing an accurate judgment basis for the inspection personnel to inspect the single-cell voltage measurement accuracy of the on-line monitoring device of the storage battery.

[0030] Through the design of the above method, the problems of single - scenario and inefficient inspection by traditional manual observation and recording methods are effectively solved, and it realizes the intelligent inspection of the single - cell voltage measurement accuracy of the battery online monitoring device for substation incoming equipment in multiple scenarios, improving the efficiency and accuracy of the substation incoming equipment quality inspection personnel for the inspection of the single - cell voltage measurement accuracy of the battery online monitoring device. At the same time, it improves the safety and reliability of the operation of the substation battery online monitoring device.

[0031] The following further describes the intelligent inspection method and system for the single - cell voltage measurement accuracy of the battery online monitoring device of the present invention in combination with specific embodiments.

[0032] Embodiment 1 Refer Figure 1 , this embodiment provides an intelligent inspection method for the single - cell voltage measurement accuracy of a battery online monitoring device, designs a data intelligent acquisition method and a data intelligent analysis and processing strategy for the functional characteristics of the battery online monitoring device, and ensures the accuracy of value selection during the inspection process.

[0033] The specific design is to use a programmable DC power supply to automatically regulate the battery pack voltage and current of the battery online monitoring device; use a programmable battery simulator to automatically regulate multiple scenarios of the change of the single - cell voltage data of different channels of the battery online monitoring device; use an image intelligent recognition device to intelligently recognize the single - cell voltage value of the battery online monitoring device in real - time for intelligent acquisition.

[0034] Construct a rule library based on different industry standards, different types of devices to be inspected, and different inspection single - cell voltage ranges as factors. In the software system for inspecting the single - cell voltage measurement accuracy of the battery online monitoring device, design an intelligent analysis module to filter and analyze and calculate the single - cell voltage data, and complete the intelligent detection of the single - cell voltage measurement accuracy of the battery online monitoring device in multiple scenarios according to the constructed inspection rule library. When the system inspection is completed, it intelligently generates a conclusion on whether the single - cell voltage measurement accuracy of the battery online monitoring device meets the standard and a detection report.

[0035] The specific implementation process of this method is as follows: S1. Enter the standard of the single - cell voltage measurement accuracy range of the battery online monitoring device and the parameters of the battery online monitoring device to be inspected, and import the pre - constructed inspection rule library.

[0036] Specifically, in the inspection system for the single - cell voltage measurement accuracy of the battery online monitoring device, according to the inspection requirements, enter the standard of the single - cell voltage measurement accuracy range of the battery online monitoring device and the relevant parameters of the battery online monitoring device to be inspected, and import the pre - constructed inspection rule library; among them, the standard of the single - cell voltage measurement accuracy range of the battery online monitoring device is determined according to the electric power industry standard.

[0037] The described inspection rule library refers to the construction of a rule library based on different industry standards, different types of devices to be inspected, and different ranges of individual inspection voltages as factors.

[0038] This step completes the preliminary configuration of intelligent inspection.

[0039] S2. Adjust the output voltage of the programmable DC power supply and the output voltage of the programmable battery simulator respectively. Among them, adjust the output voltage of the programmable battery simulator to X%. , For the on-line monitoring device of the storage battery to monitor the individual voltage of the storage battery, and read whether X% is within the preset range. If the read results of n consecutive times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; n is a positive integer.

[0040] In this embodiment, adjust the output voltage of the programmable DC power supply to 100% , adjust the output voltage of the programmable battery simulator to X% , and read whether the value of the output voltage of the programmable battery simulator is within the preset range. If the read results of n consecutive times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; among them, is the nominal battery pack voltage of the on-line monitoring device of the storage battery, is the standard individual voltage value of the storage battery monitored by the on-line monitoring device of the storage battery, X is a positive number, and n is a positive integer.

[0041] Furthermore, the preset range is X% ±0.2V. For example, in this embodiment, first adjust the output voltage of the programmable battery simulator to 50% , then in this scenario, the preset range of the output voltage of the programmable battery simulator is 50% ±0.2V. The number of read times n is set to 3.

[0042] Based on the above, that is: read whether the value of the output voltage of the programmable battery simulator is within the range of 50%UB±0.2V. If the measured value is not within the above range, read the second time after 5S. If the measured value is still not within the above range, read the third time after 5S. If the third measured value is still not within the above range, the detection system gives a prompt "The output voltage adjustment of the programmable battery simulator is abnormal".

[0043] S3. When the value of the output voltage of the programmable battery simulator read is within the preset range, obtain an image of the individual voltage display value of the current storage battery on-line monitoring device to be inspected and perform object detection using the YOLOv8 model to obtain an image of the voltage numerical value area.

[0044] When the output voltage of the programmable battery simulator is adjusted to reach 50% of the preset value ±0.2V, the single-cell voltage display value of the battery online monitoring device is intelligently recognized by the AI image intelligent recognition device. The intelligent recognition technology of the single-cell voltage display value is specifically designed as follows: The YOLOv8 algorithm model is used for numerical small target detection, and the input resolution of the model is adjusted to 1280x1280 to achieve higher-precision capture and positioning of the digital area of the voltage display value, so as to obtain the voltage numerical area image of the target detection.

[0045] It should be understood that in this embodiment, there is no improvement to the YOLOv8 algorithm model, so the YOLOv8 algorithm model will not be elaborated in detail here.

[0046] S4. Preprocess the voltage numerical area image to separate the voltage digital part and the background part in the voltage numerical area image, and use the PaddleOCR digital special model to recognize the voltage digital part. Then, after the rule verification post-processing of the recognized voltage numerical result for the voltage value range constraint, the single-cell voltage display value of the battery online monitoring device to be detected finally recognized is obtained.

[0047] Specifically, preprocessing the voltage numerical area image includes: sequentially extracting the ROI (Region of Interest), cropping the voltage numerical area obtained by target detection; using the non-local mean method for denoising filtering; using the CLAHE method for image enhancement; and further separating the voltage digital and the background through the adaptive threshold processing technology.

[0048] Furthermore, the key point of the adaptive threshold processing is to dynamically adjust the threshold parameter to adapt to the local feature change of the image. The specific steps are as follows: 1) Local area statistical analysis design: For each pixel point in the voltage numerical area image, a local window of 5×5 pixels is established with this point as the center, and the statistical quantity of the gray value in this window is calculated, that is: (1); In formula (1): represents the statistical quantity of the gray value in the local area; represents the gray mean value of the local window; is an empirical offset constant, which is designed as 10 gray levels in the present invention and is used to adjust the segmentation sensitivity.

[0049] 2) Dynamic threshold mapping generation design: Generate a pixel-level threshold matrix based on the above statistics, and perform binary decision for each pixel. Specific decision rule design: If the current pixel grayscale value I(x,y) > T(x,y), it is determined as the digital area and set to high level; if I(x,y) ≤ T(x,y), it is determined as the background and set to low level.

[0050] 3) Illumination compensation optimization design: In the image enhanced by CLAHE, adjust the threshold formula by introducing a weighting factor α to compensate for local overexposure or underexposure areas caused by the enhancement process: (2); In formula (2): represents the statistical quantity of grayscale values in the compensated local area; Gglobal is the global image grayscale mean; α takes a value of 0.8 to achieve the balance of local and global features.

[0051] 4) Edge sharpening enhancement design: Combining the image structure features after non-local means denoising, apply weight correction to the edge area through Sobel operator detection during threshold calculation to strengthen the continuity of the digital contour: (3); In formula (3): represents the statistical quantity of grayscale values in the corrected local area; E(x,y) is the edge intensity coefficient; β is used to adjust the edge sharpening degree, and in this invention, this value is designed to be 0.2.

[0052] Through the above steps, dynamic adaptation to local brightness changes in the image is achieved, and the separation of voltage digits and the background is effectively completed.

[0053] Then use the PaddleOCR digital special model to recognize the voltage digits. To improve the intelligent recognition effect, an optimization strategy design is added to this model. Specifically, only train and recognize characters related to voltage display values such as digits 0-9, decimal points, V, kV, mV, etc.

[0054] Finally, perform post-processing of rule verification for the recognized voltage numerical results again for voltage value range constraints to complete the intelligent recognition of the single-cell voltage display value.

[0055] That is, since the collected data is affected by voltage fluctuations, if the single-cell voltage display value on the battery online monitoring device taken only once is used as the final single-cell voltage display value, there may be collection deviation. Therefore, to further improve the accuracy of voltage data collection, design to continuously collect the single-cell voltage display value of the battery online monitoring device 20 times, and take the average value of these 20 numerical values as the final single-cell voltage display value of the battery online monitoring device. , through the TCP reliable transmission mechanism, the sampled data is timely transmitted back to the single-cell voltage measurement accuracy inspection system of the battery online monitoring device. Meanwhile, the inspection system continuously reads the DC voltage values of each channel output by the programmable battery simulator within 60S at a frequency of 1s / time through programmable remote communication technology. , and take its average value as the standard single-cell voltage value of the battery monitored by the battery online monitoring device. , and sequentially complete the intelligent acquisition of the measured value and the standard value of the battery online monitoring device.

[0056] S5. Filter the single-cell voltage display value of the currently detected battery online monitoring device identified, and calculate the single-cell voltage measurement accuracy of the currently detected battery online monitoring device.

[0057] That is, filter the single-cell voltage display value of the currently detected battery online monitoring device identified to eliminate abnormal values in the collected voltage data, and calculate the single-cell voltage measurement accuracy of the battery online monitoring device according to the constructed inspection rule library, so as to obtain the single-cell voltage measurement accuracy of the detected battery online monitoring device in this scenario.

[0058] Perform intelligent filtering analysis and processing on the collected voltage data through the intelligent analysis module. The specific design is to construct a voltage value anomaly detection engine in the intelligent analysis module, adopt the 3σ criterion and the Grubbs test model, and improve them.

[0059] The further design is to adopt a sliding window mechanism, that is, window size adaptive adjustment technology, in the 3σ criterion to calculate the mean μ and standard deviation σ of the data within the window, perform iterative detection in the Grubbs test model, automatically execute multiple rounds of detection until there are no abnormal values, and adopt the modified T-distribution look-up table method for critical value optimization. Further, for the improved 3σ criterion and Grubbs test model, design a fusion rule construction through a weighted voting method of outputting the weighted sum of abnormal probabilities to achieve a multi-model fusion detection strategy, and then quickly screen out the obviously abnormal values in the collected voltage data for noise reduction filtering processing. Calculate the single-cell voltage measurement accuracy of the battery online monitoring device according to the constructed rule library.

[0060] Among them, the calculation formula for the single-cell voltage measurement accuracy of the battery online monitoring device: (4); In formula (4): represents the voltage measurement accuracy; represents the standard single-cell voltage value of the battery monitored by the battery online monitoring device; represents the single-cell voltage display value of the battery online monitoring device.

[0061] Calculate the measurement accuracy of the single - cell voltage of the battery online monitoring device to be detected under the above scenario based on the above formula.

[0062] S6. Adjust the proportion X in the output voltage of the programmable battery simulator to different values, and repeat S2 - S5 to obtain the measurement accuracy of the single - cell voltage of the battery online monitoring device to be detected under multiple scenarios. Then compare it with the standard range of the measurement accuracy of the single - cell voltage of the battery online monitoring device entered to determine whether the measurement accuracy of the single - cell voltage of the current battery online monitoring device to be detected meets the standard.

[0063] If it is within the corresponding range value, it is determined that the measurement accuracy of the single - cell voltage of the battery online monitoring device to be detected meets the standard; otherwise, it is determined not to meet the standard.

[0064] That is, repeat the above S2 - S5. The system sequentially adjusts the output voltage of the programmable battery simulator to 70% , 90% , 110% , 130% according to the multi - scenario inspection rule library, intelligently collect and record the display value of the single - cell voltage of the battery online monitoring device under the corresponding scenario, and intelligently calculate the measurement accuracy of the single - cell voltage through the intelligent analysis module.

[0065] Then, conduct an intelligent analysis on the measurement accuracy of the single - cell voltage of the battery online monitoring device to be detected under multiple scenarios. When all reach the range value specified by the corresponding industry standard of the inspection rule library, it is determined that the measurement accuracy of the single - cell voltage of the battery online monitoring device to be detected meets the standard; otherwise, it is determined not to meet the standard.

[0066] The effectiveness of this method is verified below with specific application examples.

[0067] Demonstratively, according to the electric power industry standard, combined with the inspection requirements for the measurement accuracy of the single - cell voltage of the battery online monitoring device and the attached drawings of the specification, a detailed description is made, but not limited to this.

[0068] According to the requirements of the electric power industry standard of "DL / T 2226 - 2021 Technical Conditions for On - line Monitoring System of Vented Lead - Acid Batteries for Electric Power Use" for the measurement accuracy of the single - cell voltage of the battery online monitoring device, conduct the inspection of the measurement accuracy of the single - cell voltage of the battery: the measurement accuracy error does not exceed ±0.2%.

[0069] S1: First, according to the Figure 1 design of the inspection process for the measurement accuracy of the single - cell voltage of the battery online monitoring device as shown, construct an intelligent inspection platform for the battery online monitoring device using a programmable DC power supply, a programmable battery simulator, and an AI image recognition device. The platform architecture diagram is as shown in Figure 2 .

[0070] S2: According to the requirements of the row standard, design a test process rule library for the inspection item of the single-cell voltage measurement accuracy of the battery online monitoring device. Simulate the scenario according to the rule library, construct the battery pack voltage environment by controlling and adjusting the output voltage of the programmable DC power supply, and control and adjust the output voltage of the programmable battery simulator to automatically switch the detection scenarios from 50%→70%→90%→110%→130% of the standard single-cell voltage value.

[0071] S3: In each scenario, use the AI image intelligent recognition device to intelligently recognize the displayed value of the single-cell voltage of the battery online monitoring device, continuously collect the displayed value 20 times, and take its average value as , and transmit the data back to the software system for inspecting the single-cell voltage measurement accuracy of the battery online monitoring device in a timely manner; at the same time, the detection system continuously reads the DC voltage values of each channel output by the programmable battery simulator within 60S at a frequency of 1s / time , and take its average value as , and sequentially complete the automatic acquisition of the measured value and the standard value of the battery online monitoring device.

[0072] S4: Use the intelligent analysis module system to perform intelligent filtering analysis and processing on the collected voltage data, and calculate the measurement accuracy of the single-cell voltage of the battery online monitoring device. The calculation formula is the above formula (4).

[0073] S5: Finally, record, analyze, and store the inspection results of the single-cell voltage measurement accuracy in each scenario.

[0074] S6: In this system, 4 channels are enabled by the programmable battery simulator to simulate 4 battery single cells, and the battery online monitoring device to be inspected is connected to these 4 batteries for measurement. The inspection system inspects the accuracy of the single-cell voltage measurement accuracy of the battery online monitoring device, and presents and statistically analyzes the inspection results in tabular form. The results of this inspection are intelligently stored in the inspection report for storage and reference. The specific implementation effect is as Figure 3 shown.

[0075] In summary, for the intelligent inspection method of the single-cell voltage measurement accuracy of the battery online monitoring device of the present invention, a data intelligent acquisition method and a data intelligent analysis and processing strategy are designed according to the functional characteristics of the battery online monitoring device, ensuring the accuracy of the value selection in the inspection process. At the same time, to ensure the comprehensiveness of the inspection of the single-cell voltage measurement accuracy of the battery, the present invention proposes an inspection method in multiple scenarios and constructs an inspection rule library, which can realize the intelligent acquisition, multi-scenario inspection, intelligent analysis, result visualization display, and intelligent storage of the detection data of the battery online monitoring device, and finally realizes the intelligent and accurate inspection of the single-cell voltage measurement accuracy of the battery online monitoring device.

[0076] The detection method described in the present invention effectively solves the problems of single - scenario and inefficient inspection by traditional manual observation and recording methods, improves the inspection efficiency and accuracy of the quality inspection personnel of substation incoming - network equipment for the measurement accuracy of the single - cell voltage of the battery on - line monitoring device, and greatly reduces the work pressure of the inspection personnel.

[0077] Embodiment 2 This embodiment provides a system for realizing an intelligent inspection method for the measurement accuracy of the single - cell voltage of a battery on - line monitoring device. The system includes: An input module, which is used to input the standard of the measurement accuracy range of the single - cell voltage of the battery on - line monitoring device and the parameters of the battery on - line monitoring device to be inspected, and import a pre - constructed inspection rule library; A voltage adjustment module, which is used to adjust the output voltage of the programmable DC power supply and the output voltage of the programmable battery simulator respectively. Among them, the output voltage of the programmable battery simulator is adjusted to X% , to monitor the single - cell voltage of the battery by the battery on - line monitoring device, and read whether X% is within a preset range. If the reading results of consecutive n times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; n is a positive integer; A voltage detection module, which is used to perform target detection on the image of the single - cell voltage display value of the currently inspected battery on - line monitoring device obtained by using the YOLOv8 model to obtain a voltage value region image; A voltage value recognition module, which is used to pre - process the voltage value region image to separate the voltage digital part and the background part in the voltage value region image, and use the PaddleOCR digital - specific model to recognize the voltage digital part, and then perform post - processing of rule verification on the voltage value range constraint for the recognized voltage value result to obtain the finally recognized single - cell voltage display value of the battery on - line monitoring device to be inspected; An intelligent analysis module, which is used to filter the recognized single - cell voltage display value of the currently inspected battery on - line monitoring device and calculate the measurement accuracy of the single - cell voltage of the currently inspected battery on - line monitoring device; An inspection result determination module, which is used to adjust the ratio X in the output voltage of the programmable battery simulator to different values to obtain the measurement accuracy of the single - cell voltage of the battery on - line monitoring device to be inspected in multiple scenarios, and compare it with the input standard of the measurement accuracy range of the single - cell voltage of the battery on - line monitoring device to determine whether the measurement accuracy of the single - cell voltage of the currently inspected battery on - line monitoring device meets the standard.

[0078] Embodiment 3 This embodiment also provides an electronic device, including: At least one processor; and a memory that stores instructions which, when executed by the at least one processor, cause the at least one processor to execute the intelligent inspection method for the individual cell voltage measurement accuracy of the battery online monitoring device as described above.

[0079] In this embodiment, the electronic device may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronic devices, and the like.

[0080] Embodiment 4 This embodiment also provides a machine-readable storage medium that stores executable instructions which, when executed, cause the machine to execute the intelligent inspection method for the individual cell voltage measurement accuracy of the battery online monitoring device as described above.

[0081] Specifically, a system or device equipped with a readable storage medium may be provided, on which software program code for implementing the functions of any one of the above embodiments is stored, and the computer or processor of the system or device reads and executes the instructions stored in the readable storage medium.

[0082] In this case, the program code read from the readable medium itself can implement the functions of any one of the above embodiments, so the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of this specification.

[0083] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network. B Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in one block or multiple blocks.

[0085] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in one block or multiple blocks.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in one block or multiple blocks.

[0087] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solutions of the present invention, rather than limitations on the specific implementation manners of the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the claims of the present invention shall be included within the protection scope of the claims of the present invention.

Claims

1. An intelligent inspection method for the measurement accuracy of the single - cell voltage of an on - line battery monitoring device, characterized in that, The method includes: S1. Enter the standard of the single-cell voltage measurement accuracy range of the battery on-line monitoring device and the parameters of the battery on-line monitoring device to be tested, and import them into the pre-constructed inspection rule library; S2. Adjust the output voltage of the programmable DC power supply and the output voltage of the programmable battery simulator respectively. Among them, adjust the output voltage of the programmable battery simulator to X%. , The battery cell voltage of the storage battery is monitored by the on-line monitoring device for storage batteries, and X% is read whether it is within the preset range. If the reading results of consecutive n times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; n is a positive integer; S3. When the value of the output voltage of the programmable battery simulator is read within the preset range, obtain the image of the single-cell voltage display value of the current battery on-line monitoring device to be tested and perform object detection using the YOLOv8 model to obtain the voltage numerical area image; S4. Preprocess the voltage numerical area image to separate the voltage digital part and the background part in the voltage numerical area image, use the PaddleOCR digital special model to identify the voltage digital part, and then perform post-processing of rule verification on the identified voltage numerical result for voltage value range constraint to obtain the finally identified single-cell voltage display value of the battery on-line monitoring device to be tested; S5. Filter the identified single-cell voltage display value of the current battery on-line monitoring device to be tested, and calculate the single-cell voltage measurement accuracy of the current battery on-line monitoring device to be tested; S6. Adjust the proportion X in the output voltage of the programmable battery simulator to different values, and repeat S2 - S5 to obtain the single-cell voltage measurement accuracy of the battery on-line monitoring device to be tested in multiple scenarios, and compare it with the standard of the single-cell voltage measurement accuracy range of the battery on-line monitoring device entered to determine whether the single-cell voltage measurement accuracy of the current battery on-line monitoring device to be tested meets the standard.

2. The intelligent inspection method for the single cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 1, characterized in that In S3, the YOLOv8 model is used for numerical object detection, and the input resolution of the model is adjusted to 1280x1280 to obtain the voltage numerical area image of object detection.

3. The intelligent inspection method for the single cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 2, characterized in that In S4, the preprocessing of the voltage numerical area image includes: Successively extract the region of interest from the voltage numerical area image, and crop the voltage numerical area obtained by object detection; Use the non-local means method for denoising filtering; Adopt the CLAHE method for image enhancement processing, and complete the separation of the voltage digital and the background through adaptive threshold processing.

4. The intelligent inspection method for the single-cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 3, wherein In S4, the PaddleOCR digital special model is used to identify the voltage digital, and an optimization strategy design is added to the model, that is, only train and identify the voltage display value characters, including the numbers 0 - 9, decimal point, V, kV, mV.

5. The intelligent inspection method for the single-cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 4, characterized in that In S5, the filtering of the identified single-cell voltage display value of the current battery on-line monitoring device to be tested includes: Adopt a sliding window mechanism in the 3σ criterion to calculate the mean μ and standard deviation σ of the data in the window; Perform iterative detection in the Grubbs test model, automatically execute multiple rounds of detection until there are no outliers, and use the modified T-distribution look-up table method for critical value optimization; Construct a fusion rule for the improved 3σ criterion and the Grubbs test model design through a weighted voting method of weighted summation of the output abnormal probabilities to screen out the abnormal numerical values in the collected voltage data and perform noise reduction filtering on them.

6. The intelligent inspection method for the single cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 1, characterized in that In S5, the calculation formula for the single-cell voltage measurement accuracy of the battery on-line monitoring device: （4）； In formula (4): represents the voltage measurement accuracy; represents the standard single-cell voltage value of the storage battery monitored by the on-line monitoring device for storage batteries; represents the single-cell voltage display value of the on-line monitoring device for storage batteries.

7. The intelligent inspection method for the single-cell voltage measurement accuracy of the on-line monitoring device for storage batteries according to claim 1, wherein The preset range of the output voltage of the programmable battery simulator is X% ±0.2V, where X% takes 50% 、70% 、90% 、110% 、130% .

8. A system for implementing an intelligent inspection method for the measurement accuracy of the single-cell voltage of a battery on-line monitoring device, characterized in that, The system includes: An input module for inputting the standard of the single - cell voltage measurement accuracy range of the battery online monitoring device and the parameters of the battery online monitoring device to be tested, and importing them into a pre - constructed inspection rule library; A voltage regulation module is used to regulate the output voltage of a programmable DC power supply and the output voltage of a programmable battery simulator respectively. Among them, the output voltage of the programmable battery simulator is regulated to X%. , The single-cell voltage of the storage battery is monitored by the on-line monitoring device for storage batteries, and X% is read whether it is within the preset range. If the reading results of consecutive n times are not within the preset range, it is determined that the output voltage adjustment of the programmable battery simulator is abnormal and the determination result is output; n is a positive integer; A voltage detection module for using the YOLOv8 model to perform object detection on the image of the single - cell voltage display value of the currently tested battery online monitoring device to obtain a voltage value region image; A voltage value recognition module for pre - processing the voltage value region image to separate the voltage digital part and the background part in the voltage value region image, using the PaddleOCR digital - specific model to recognize the voltage digital part, and then performing post - processing of rule verification for voltage value range constraint on the recognized voltage value result to obtain the finally recognized single - cell voltage display value of the battery online monitoring device to be tested; An intelligent analysis module for filtering the recognized single - cell voltage display value of the currently tested battery online monitoring device and calculating the single - cell voltage measurement accuracy of the currently tested battery online monitoring device; An inspection result determination module for adjusting the proportion X in the output voltage of the programmable battery simulator to different values to obtain the single - cell voltage measurement accuracy of the battery online monitoring device to be tested under multiple scenarios, and comparing it with the standard of the single - cell voltage measurement accuracy range of the battery online monitoring device to be input to determine whether the single - cell voltage measurement accuracy of the currently tested battery online monitoring device meets the standard.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory that stores instructions, and when the instructions are executed by the at least one processor, the at least one processor executes the intelligent inspection method for the single - cell voltage measurement accuracy of the battery online monitoring device according to any one of claims 1 to 7.

10. A machine-readable storage medium, characterized in that, An executable instruction is stored on the machine - readable storage medium, and when the instruction is executed, the machine executes the intelligent inspection method for the single - cell voltage measurement accuracy of the battery online monitoring device according to any one of claims 1 to 7.

Images