Error acquisition method and device for interference test of electric power metering equipment based on machine vision, and medium

Abstract

The invention belongs to the technical field of machine vision, and particularly relates to an error acquisition method and device for an interference test of electric power metering equipment based on machine vision, and a medium. The method comprises the following steps: S1, acquiring error image information displayed by an error collection and display device in real time; s2, acquiring an error change curve and a maximum error real-time reading according to the error image information, and judging whether the error jumps or not according to the error change curve and the maximum error real-time reading; and S3, when the error jumps, recording the jump information and the corresponding test condition. According to the invention, through automatic error capture and parameter acquisition, a manual recording link is eliminated, and the matching accuracy of error data and test conditions is improved; manual real-time monitoring and recording are not needed, the error recording time of single-batch testing is shortened, the working intensity of operators is reduced, and parallel testing of multiple devices is supported. The technical problems of high error risk and low efficiency caused by manual error recording in the prior art are solved.

Description

Technical Field

[0001] This invention belongs to the field of machine vision technology, specifically relating to an error acquisition method, device, and medium for interference testing of power metering equipment based on machine vision. Background Technology

[0002] The current error recording process for interference tests on electric energy meters, terminals, and other motor metering products is primarily manual, with the following steps: Test personnel prepare an external interference source (hardware), an error collection and display device (hardware and software), and the test product. They set up the test environment and preset the initial test conditions for the interference source. The interference test is initiated, and the external interference source applies electromagnetic fast transient pulses (EFT) and other interferences to the product according to the preset conditions. The error collection and display device calculates the error between the product's metering and the standard meter in real time and displays the error data (including a curve interface or out-of-tolerance prompts) on the computer screen. When the test personnel visually observe an error jump or out-of-tolerance prompt on the computer screen, they manually record the current time point and immediately check the test parameters (such as voltage, frequency, pulse width, etc.) on the external interference source's display screen, manually entering the data into the "Error-Test Condition Record Table."

[0003] After the test, the "Error-Test Condition Record Sheet" is manually compiled, and the error data is matched and verified with the corresponding test conditions to ensure that no records are missing or mismatched. The recorded data undergoes a second manual review to confirm the correlation between the error jump time and the test conditions, and finally, a test report is generated.

[0004] The above error recording process has the following drawbacks: First, the risk of human error is high. Error jump identification, time recording, and parameter copying all rely on manual operation, which can easily lead to timestamp deviations or parameter recording errors due to reaction delays and visual fatigue. Second, the synchronization is poor. There is no linkage between the external interference source and the error collection device, and the timing of error jumps and test conditions depends on manual memory, making it difficult to guarantee the accuracy of data correlation. Third, the efficiency is low. The process of manual real-time monitoring, recording, and verification is time-consuming and labor-intensive, especially in long-term, multi-batch tests, where the workload is high and the efficiency is low. Summary of the Invention

[0005] The purpose of this invention is to provide an error acquisition method, device, and medium for interference testing of power metering equipment based on machine vision, so as to solve the technical problems of high error risk and low efficiency caused by manual recording in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides a technical solution for an error acquisition method for interference testing of power metering equipment based on machine vision: an error acquisition method for interference testing of power metering equipment based on machine vision, the method comprising: S1. Obtain error image information displayed in real time by the error collection and display device; S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error; S3. When an error jump occurs, record the jump information and the corresponding test conditions.

[0007] The beneficial effects of the above technical solution are as follows: This invention eliminates the manual recording step through automated error capture and parameter acquisition, greatly improving the accuracy of matching error data with test conditions; it eliminates the need for real-time manual monitoring and recording, significantly reducing the error recording time for a single batch of tests, reducing the workload of operators, and supporting parallel testing of multiple devices. This invention solves the technical problems of high error risk and low efficiency caused by manual error recording in existing technologies.

[0008] Furthermore, the process of determining whether the error has jumped based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, determining the error limit range on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, then it is determined that the error has jumped.

[0009] Furthermore, the process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

[0010] Furthermore, the process of obtaining the maximum real-time error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the maximum real-time error reading from the error reading region.

[0011] Furthermore, the test conditions are obtained by: acquiring a test condition image of the interference source display screen; determining the key parameter area in the interference source display screen used to display the test conditions; and extracting the parameter values ​​of the key parameter area as test conditions.

[0012] Furthermore, when an error jump is detected, the frame rate of the camera used to acquire the test condition image is increased.

[0013] Furthermore, the error image information is obtained through the system interface of the error collection and display device.

[0014] This invention also provides a technical solution for an error acquisition device for interference testing of power metering equipment based on machine vision: an error acquisition device for interference testing of power metering equipment based on machine vision, comprising a processor, the processor being used to execute a computer program to implement the steps of the error acquisition method for interference testing of power metering equipment based on machine vision as described below: S1. Obtain error image information displayed in real time by the error collection and display device; S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error; S3. When an error jump occurs, record the jump information and the corresponding test conditions.

[0015] The beneficial effects of the above technical solution are as follows: This invention eliminates the manual recording step through automated error capture and parameter acquisition, greatly improving the accuracy of matching error data with test conditions; it eliminates the need for real-time manual monitoring and recording, significantly reducing the error recording time for a single batch of tests, reducing the workload of operators, and supporting parallel testing of multiple devices. This invention solves the technical problems of high error risk and low efficiency caused by manual error recording in existing technologies.

[0016] Furthermore, the process of determining whether the error has jumped based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, determining the error limit range on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, then it is determined that the error has jumped.

[0017] Furthermore, the process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

[0018] Furthermore, the process of obtaining the maximum real-time error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the maximum real-time error reading from the error reading region.

[0019] Furthermore, the test conditions are obtained by: acquiring a test condition image of the interference source display screen; determining the key parameter area in the interference source display screen used to display the test conditions; and extracting the parameter values ​​of the key parameter area as test conditions.

[0020] Furthermore, when an error jump is detected, the frame rate of the camera used to acquire the test condition image is increased.

[0021] Furthermore, the error image information is obtained through the system interface of the error collection and display device.

[0022] The present invention also provides a technical solution for a computer-readable storage medium: a computer-readable storage medium having a computer program stored internally, the computer program being processed by a processor to execute the steps of the following error acquisition method for interference testing of power metering equipment based on machine vision: S1. Obtain error image information displayed in real time by the error collection and display device; S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error; S3. When an error jump occurs, record the jump information and the corresponding test conditions.

[0023] The beneficial effects of the above technical solution are as follows: This invention eliminates the manual recording step through automated error capture and parameter acquisition, greatly improving the accuracy of matching error data with test conditions; it eliminates the need for real-time manual monitoring and recording, significantly reducing the error recording time for a single batch of tests, reducing the workload of operators, and supporting parallel testing of multiple devices. This invention solves the technical problems of high error risk and low efficiency caused by manual error recording in existing technologies.

[0024] Furthermore, the process of determining whether the error has jumped based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, determining the error limit range on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, then it is determined that the error has jumped.

[0025] Furthermore, the process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

[0026] Furthermore, the process of obtaining the maximum real-time error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the maximum real-time error reading from the error reading region.

[0027] Furthermore, the test conditions are obtained by: acquiring a test condition image of the interference source display screen; determining the key parameter area in the interference source display screen used to display the test conditions; and extracting the parameter values ​​of the key parameter area as test conditions.

[0028] Furthermore, when an error jump is detected, the frame rate of the camera used to acquire the test condition image is increased.

[0029] Furthermore, the error image information is obtained through the system interface of the error collection and display device. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the device connection for an error acquisition device for interference testing of power metering equipment based on machine vision, according to an embodiment of the present invention. Detailed Implementation

[0031] This invention eliminates manual recording by automating error capture and parameter acquisition, significantly improving the accuracy of matching error data with test conditions. It also eliminates the need for real-time manual monitoring and recording, significantly reducing error recording time for single-batch tests, lowering operator workload, and supporting parallel testing across multiple devices. This invention solves the technical problems of high error risk and low efficiency caused by manual error recording in existing technologies.

[0032] Implementation method of error acquisition device for interference testing of power metering equipment based on machine vision: An error acquisition device for interference testing of power metering equipment based on machine vision is disclosed. This device automatically captures error jumps and collects test conditions (mainly interference information of interference sources) through machine vision, and realizes synchronous data transmission and storage, effectively solving the problems of high human error rate, poor synchronization and low efficiency in the existing technology.

[0033] like Figure 1 As shown, the device (i.e. Figure 1 The “error image recognition based on machine vision” is connected to the industrial camera, power supply and error inspection device respectively; the meter under test (or terminal) is connected to the interference source and the power supply and error inspection device respectively.

[0034] The processor of this device implements an error acquisition method for interference testing of power metering equipment based on machine vision through the following software modules: error capture module, test condition visual acquisition module, and signal and data transmission module.

[0035] Error capture module: The error capture module is connected to the error collection and display device in the interference test (i.e., Figure 1The computer system of the power supply and error testing device acquires the real-time display content of the error collection and display device screen through its video interface, including the error curve display area or the error reading area. Here, error refers to the difference between the actual measured value of the meter under test (or terminal) and the theoretical measured value of the standard meter. In this embodiment, the error curve display area is used to display the real-time changes in relative error (error percentage) in the form of an error curve. The error reading area is used to display the maximum absolute error that occurs during the test.

[0036] For the error curve display area, the error capture module processes it according to the following steps: 1) Curve region localization and extraction: Using template matching or edge detection algorithms, the region where the error curve is located on the screen is located, and the ROI (Region of Interest) is defined as the display area of ​​the error curve, while filtering out irrelevant background interference.

[0037] 2) Curve image preprocessing: Denoising, grayscale conversion, and contrast enhancement are performed on the ROI region. Then, the error curve contour of the ROI region is extracted by Hough transform, and the endpoints of the curve are filled in and the spikes are smoothed.

[0038] For the error reading range, the error capture module processes the data according to the following steps: 1) Display area positioning and ROI locking: Based on screen coordinate preset or template matching, lock the fixed area (such as dashboard numbers, text boxes) to display error values, and generate fixed ROI coordinates as the coordinates of the error display area.

[0039] 2) Display Recognition and Numerical Conversion: The error display area is segmented into characters (projection method to separate numbers and symbols), and OCR (Optical Character Recognition) algorithms such as Tesseract are used to recognize the characters and convert the recognized characters into floating-point numerical values ​​(including positive and negative signs and decimal points).

[0040] Based on the above-mentioned identification content, the error capture module performs error anomaly identification according to the following steps: First, obtain the maximum error displayed in real time (take the absolute value) and compare it with the preset error limit. When the maximum error does not exceed the preset error limit, there is obviously no abnormality. When the maximum error exceeds the preset error limit, calculate the ratio of the error limit to the maximum error, and according to the ratio, define the error limit range above and below the error curve where the error is 0 (i.e., the 0 mark on the vertical axis). When the newly appearing error point falls outside the error limit range or on the boundary of the error limit range, it indicates that an error abnormality has occurred.

[0041] Unified anomaly response and logging: When the error capture module determines that an error triggers an anomaly (i.e., a jump occurs), it immediately calls the system's high-precision clock interface to record a millisecond-level timestamp. Simultaneously, it stores the anomaly type (curve jump / numerical deviation), corresponding numerical / slope characteristics, and timestamp in the log system, triggering an external capture signal.

[0042] Test conditions visual acquisition module: by deploying industrial-grade high-definition cameras (i.e. Figure 1 An industrial camera is used to capture real-time images of the interference source display screen to collect test conditions for common interference sources. The camera is fixed in the optimal shooting position using a bracket to ensure that the parameter area of ​​the interference source display screen is complete and clear. Image recognition algorithms are used to locate key parameter areas (voltage, frequency, pulse width, etc.) on the display screen, extract parameter values, and convert them into structured data.

[0043] Obtaining test conditions through image recognition has the following advantages: Multi-scene adaptation: It supports adaptive recognition of interference source displays of different brands and models. By using a preset display template library (including character styles and layout features) combined with dynamic image correction technology (such as distortion correction and brightness compensation), it solves the recognition difficulties caused by differences in displays. Real-time calibration mechanism: Standard parameter images are periodically captured for calibration, automatically correcting recognition deviations caused by changes in lighting and camera movement, ensuring parameter extraction accuracy (numerical error ≤ 0.1%).

[0044] Signal and data transmission module: 1) Signal transmission: When the error capture module triggers the jump signal, it transmits the control signal to the camera of the test condition vision acquisition module through the low-latency bus, so that the camera increases the shooting frame rate (up to 50 frames / second) at the corresponding time point to ensure clear acquisition of test condition images.

[0045] 2) Data transmission: The camera compresses the collected parameter images and timestamp data and transmits them to the computer storage unit via Ethernet.

[0046] 3) Anti-interference transmission: Shielded cables and data encryption technology are used to reduce the impact of electromagnetic interference on signal transmission and ensure that the control signal delay is ≤30ms; the image data transmission adopts a verification and retransmission mechanism to avoid data loss or damage.

[0047] 4) Dynamic bandwidth adaptation: Automatically adjusts the data transmission rate according to the test scenario requirements, prioritizing the transmission bandwidth during error transition periods and reducing the rate to save resources during non-transition periods.

[0048] Automatic synchronization and storage module: 1) The timestamps and error data recorded by the error capture module are matched with the parameter data extracted by the test condition acquisition module to generate a related data table.

[0049] 2) Establish a database to store related data, supporting data query, export, and automatic generation of test reports.

[0050] 3) Redundant storage mechanism: It adopts a dual storage method of local cache + cloud backup to prevent data loss. The local cache supports offline storage and is automatically synchronized to the cloud after the network is restored.

[0051] 4) Data correlation verification: The error data and test conditions are verified again by using a timestamp alignment algorithm. If a time deviation is found (more than 50ms), it will be automatically marked and the user will be notified to ensure the accuracy of data correlation.

[0052] Implementation method of error acquisition method for interference test of power metering equipment based on machine vision: An error acquisition method for interference testing of power metering equipment based on machine vision, the method comprising: S1. Obtain error image information displayed in real time by the error collection and display device.

[0053] Furthermore, the error image information is obtained through the system interface of the error collection and display device.

[0054] Error collection and display device in access interference test (i.e. Figure 1 The computer system of the power supply and error testing device (in the device) acquires the real-time display content of the error collection and display device screen through its video interface, including the error curve display area or the error reading area. Here, error refers to the difference between the actual measured value of the meter under test (or terminal) and the theoretical measured value of the standard meter.

[0055] S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error.

[0056] Furthermore, the process of determining whether the error has jumped based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, determining the error limit range on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, then it is determined that the error has jumped.

[0057] Furthermore, the process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

[0058] Furthermore, the process of obtaining the maximum real-time error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the maximum real-time error reading from the error reading region.

[0059] Furthermore, when an error jump is detected, the frame rate of the camera used to acquire the test condition image is increased.

[0060] For the error curve display area, the error capture module processes it according to the following steps: 1) Curve region localization and extraction: Using template matching or edge detection algorithms, the region where the error curve is located on the screen is located, and the ROI (Region of Interest) is defined as the display area of ​​the error curve, while filtering out irrelevant background interference.

[0061] 2) Curve image preprocessing: Denoising, grayscale conversion, and contrast enhancement are performed on the ROI region. Then, the error curve contour of the ROI region is extracted by Hough transform, and the endpoints of the curve are filled in and the spikes are smoothed.

[0062] For the error reading range, the error capture module processes the data according to the following steps: 1) Display area positioning and ROI locking: Based on screen coordinate preset or template matching, lock the fixed area (such as dashboard numbers, text boxes) to display error values, and generate fixed ROI coordinates as the coordinates of the error display area.

[0063] 2) Display Recognition and Numerical Conversion: The error display area is segmented into characters (projection method to separate numbers and symbols), and OCR (Optical Character Recognition) algorithms such as Tesseract are used to recognize the characters and convert the recognized characters into floating-point numerical values ​​(including positive and negative signs and decimal points).

[0064] Based on the above-mentioned identification content, the error capture module performs error anomaly identification according to the following steps: First, obtain the maximum error displayed in real time (take the absolute value) and compare it with the preset error limit. When the maximum error does not exceed the preset error limit, there is obviously no abnormality. When the maximum error exceeds the preset error limit, calculate the ratio of the error limit to the maximum error, and according to the ratio, define the error limit range above and below the error curve where the error is 0 (i.e., the 0 mark on the vertical axis). When the newly appearing error point falls outside the error limit range or on the boundary of the error limit range, it indicates that an error abnormality has occurred.

[0065] Unified anomaly response and logging: When the error capture module determines that an error triggers an anomaly (i.e., a jump occurs), it immediately calls the system's high-precision clock interface to record a millisecond-level timestamp. Simultaneously, it stores the anomaly type (curve jump / numerical deviation), corresponding numerical / slope characteristics, and timestamp in the log system, triggering an external capture signal.

[0066] S3. When an error jump occurs, record the jump information and the corresponding test conditions.

[0067] Furthermore, the test conditions are obtained by: acquiring a test condition image of the interference source display screen; determining the key parameter area in the interference source display screen used to display the test conditions; and extracting the parameter values ​​of the key parameter area as test conditions.

[0068] By deploying industrial-grade high-definition cameras (i.e. Figure 1 An industrial camera is used to capture real-time images of the interference source display screen to collect test conditions for common interference sources. The camera is fixed in the optimal shooting position using a bracket to ensure that the parameter area of ​​the interference source display screen is complete and clear. Image recognition algorithms are used to locate key parameter areas (voltage, frequency, pulse width, etc.) on the display screen, extract parameter values, and convert them into structured data.

[0069] Obtaining test conditions through image recognition has the following advantages: Multi-scene adaptation: It supports adaptive recognition of interference source displays of different brands and models. By using a preset display template library (including character styles and layout features) combined with dynamic image correction technology (such as distortion correction and brightness compensation), it solves the recognition difficulties caused by differences in displays. Real-time calibration mechanism: Standard parameter images are periodically captured for calibration, automatically correcting recognition deviations caused by changes in lighting and camera movement, ensuring parameter extraction accuracy (numerical error ≤ 0.1%).

[0070] Signal Transmission: When the error capture module triggers a transition signal, it transmits the control signal to the camera of the test condition vision acquisition module via a low-latency bus, enabling the camera to increase the shooting frame rate (up to 50 frames / second) at the corresponding time point, ensuring clear acquisition of test condition images. Data Transmission: The camera compresses the acquired parameter images and timestamp data and transmits them to the computer storage unit via Ethernet. Anti-interference Transmission: Shielded cables and data encryption technology are used to reduce the impact of electromagnetic interference on signal transmission, ensuring that the control signal delay is ≤30ms. Image data transmission employs a verification and retransmission mechanism to avoid data loss or corruption. Dynamic Bandwidth Adaptation: The data transmission rate is automatically adjusted according to the test scenario requirements, prioritizing transmission bandwidth during error transition periods and reducing the rate to conserve resources during non-transition periods.

[0071] The error capture module records timestamps and error data, which are then synchronized with the parameter data extracted by the test condition acquisition module to generate a related data table. A database is established to store the related data, supporting data querying, export, and automatic generation of test reports. A redundant storage mechanism is employed: a dual storage method of local caching and cloud backup is used to prevent data loss. The local cache supports offline storage and automatically synchronizes to the cloud after network recovery. Data correlation verification: a timestamp alignment algorithm is used to perform secondary verification between error data and test conditions. If a time deviation (exceeding 50ms) is found, it is automatically marked and the user is notified to ensure accurate data correlation.

[0072] Implementation of computer-readable storage media: A computer-readable storage medium storing a computer program internally, the computer program being processed to perform the steps of an error acquisition method for interference testing of a machine vision-based power metering device, as described below: S1. Obtain error image information displayed in real time by the error collection and display device.

[0073] Furthermore, the error image information is obtained through the system interface of the error collection and display device.

[0074] Error collection and display device in access interference test (i.e. Figure 1 The computer system of the power supply and error testing device (in the device) acquires the real-time display content of the error collection and display device screen through its video interface, including the error curve display area or the error reading area. Here, error refers to the difference between the actual measured value of the meter under test (or terminal) and the theoretical measured value of the standard meter.

[0075] S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error.

[0076] Furthermore, the process of determining whether the error has jumped based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, determining the error limit range on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, then it is determined that the error has jumped.

[0077] Furthermore, the process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

[0078] Furthermore, the process of obtaining the maximum real-time error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the maximum real-time error reading from the error reading region.

[0079] Furthermore, when an error jump is detected, the frame rate of the camera used to acquire the test condition image is increased.

[0080] For the error curve display area, the error capture module identifies anomalies through the following steps: 1) Curve region localization and extraction: Using template matching or edge detection algorithms, the region where the error curve is located on the screen is located, and the ROI (Region of Interest) is defined as the display area of ​​the error curve, while filtering out irrelevant background interference.

[0081] 2) Curve image preprocessing: Denoising, grayscale conversion, and contrast enhancement are performed on the ROI region. Then, the error curve contour of the ROI region is extracted by Hough transform, and the endpoints of the curve are filled in and the spikes are smoothed.

[0082] For the error reading range, the error capture module processes the data according to the following steps: 1) Display area positioning and ROI locking: Based on screen coordinate preset or template matching, lock the fixed area (such as dashboard numbers, text boxes) to display error values, and generate fixed ROI coordinates as the coordinates of the error display area.

[0083] 2) Display Recognition and Numerical Conversion: The error display area is segmented into characters (projection method to separate numbers and symbols), and OCR (Optical Character Recognition) algorithms such as Tesseract are used to recognize the characters and convert the recognized characters into floating-point numerical values ​​(including positive and negative signs and decimal points).

[0084] Based on the above-mentioned identification content, the error capture module performs error anomaly identification according to the following steps: First, obtain the maximum error displayed in real time (take the absolute value) and compare it with the preset error limit. When the maximum error does not exceed the preset error limit, there is obviously no abnormality. When the maximum error exceeds the preset error limit, calculate the ratio of the error limit to the maximum error, and according to the ratio, define the error limit range above and below the error curve where the error is 0 (i.e., the 0 mark on the vertical axis). When the newly appearing error point falls outside the error limit range or on the boundary of the error limit range, it indicates that an error abnormality has occurred.

[0085] Unified anomaly response and logging: When the error capture module determines that an error triggers an anomaly (i.e., a jump occurs), it immediately calls the system's high-precision clock interface to record a millisecond-level timestamp. Simultaneously, it stores the anomaly type (curve jump / numerical deviation), corresponding numerical / slope characteristics, and timestamp in the log system, triggering an external capture signal.

[0086] S3. When an error jump occurs, record the jump information and the corresponding test conditions.

[0087] Furthermore, the test conditions are obtained by: acquiring a test condition image of the interference source display screen; determining the key parameter area in the interference source display screen used to display the test conditions; and extracting the parameter values ​​of the key parameter area as test conditions.

[0088] By deploying industrial-grade high-definition cameras (i.e. Figure 1 An industrial camera is used to capture real-time images of the interference source display screen to collect test conditions for common interference sources. The camera is fixed in the optimal shooting position using a bracket to ensure that the parameter area of ​​the interference source display screen is complete and clear. Image recognition algorithms are used to locate key parameter areas (voltage, frequency, pulse width, etc.) on the display screen, extract parameter values, and convert them into structured data.

[0089] Obtaining test conditions through image recognition has the following advantages: Multi-scene adaptation: It supports adaptive recognition of interference source displays of different brands and models. By using a preset display template library (including character styles and layout features) combined with dynamic image correction technology (such as distortion correction and brightness compensation), it solves the recognition difficulties caused by differences in displays. Real-time calibration mechanism: Standard parameter images are periodically captured for calibration, automatically correcting recognition deviations caused by changes in lighting and camera movement, ensuring parameter extraction accuracy (numerical error ≤ 0.1%).

[0090] Signal Transmission: When the error capture module triggers a transition signal, it transmits the control signal to the camera of the test condition vision acquisition module via a low-latency bus, enabling the camera to increase the shooting frame rate (up to 50 frames / second) at the corresponding time point, ensuring clear acquisition of test condition images. Data Transmission: The camera compresses the acquired parameter images and timestamp data and transmits them to the computer storage unit via Ethernet. Anti-interference Transmission: Shielded cables and data encryption technology are used to reduce the impact of electromagnetic interference on signal transmission, ensuring that the control signal delay is ≤30ms. Image data transmission employs a verification and retransmission mechanism to avoid data loss or corruption. Dynamic Bandwidth Adaptation: The data transmission rate is automatically adjusted according to the test scenario requirements, prioritizing transmission bandwidth during error transition periods and reducing the rate to conserve resources during non-transition periods.

[0091] The error capture module records timestamps and error data, which are then synchronized with the parameter data extracted by the test condition acquisition module to generate a related data table. A database is established to store the related data, supporting data querying, export, and automatic generation of test reports. A redundant storage mechanism is employed: a dual storage method of local caching and cloud backup is used to prevent data loss. The local cache supports offline storage and automatically synchronizes to the cloud after network recovery. Data correlation verification: a timestamp alignment algorithm is used to perform secondary verification between error data and test conditions. If a time deviation (exceeding 50ms) is found, it is automatically marked and the user is notified to ensure accurate data correlation.

[0092] Specifically, the computer-readable storage medium can be volatile memory or non-volatile memory, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which serves as an external cache. For example, Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), SynchLink DRAM (SLDRAM), or Direct Rambus RAM (DRRAM).

[0093] This invention has the following characteristics: 1. Improve testing efficiency: Through automated error capture and parameter acquisition, the interference conditions causing errors are directly located, eliminating the need for manual recording and avoiding the problem of having to completely repeat experiments to locate interference conditions due to missing manual records. This reduces the workload of operators and supports parallel testing of multiple devices.

[0094] 2. Enhanced versatility: Through machine vision and adaptive algorithms, it can be adapted to different brands and models of testing equipment without the need to modify existing interference sources and error collection devices, reducing equipment replacement costs.

[0095] 3. Data traceability: Complete storage of error jumps, test conditions, and timestamp data, supporting historical data queries and test replays, providing a reliable basis for product failure analysis and optimization.

[0096] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still make modifications to the technical solutions described in the foregoing embodiments without creative effort, or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An error acquisition method for interference testing of power metering equipment based on machine vision, characterized in that, The method includes: S1. Obtain error image information displayed in real time by the error collection and display device; S2. Obtain the error change curve and the real-time reading of the maximum error based on the error image information, and determine whether the error has jumped based on the error change curve and the real-time reading of the maximum error; S3. When an error jump occurs, record the jump information and the corresponding test conditions.

2. The error acquisition method for interference testing of power metering equipment based on machine vision according to claim 1, characterized in that, The process of determining whether an error jump has occurred based on the error change curve and the real-time reading of the maximum error includes: when the real-time reading of the maximum error exceeds the preset error limit, the error limit range is determined on the error change curve based on the real-time reading of the maximum error and the preset error limit; if the latest error point after the error change curve falls outside or on the boundary of the error limit range, it is determined that an error jump has occurred.

3. The error acquisition method for interference testing of power metering equipment based on machine vision according to claim 1, characterized in that, The process of obtaining the error change curve based on the error image information includes: determining the error curve display area in the error image for displaying the error curve based on the error image information, and obtaining the error curve from the error curve display area.

4. The error acquisition method for interference testing of power metering equipment based on machine vision according to claim 1, characterized in that, The process of obtaining the real-time maximum error reading based on the error image information includes: determining the error reading region in the error image for displaying the error reading based on the error image information, and obtaining the real-time maximum error reading from the error reading region.

5. The error acquisition method for interference testing of power metering equipment based on machine vision according to any one of claims 1 to 4, characterized in that, The test conditions are obtained as follows: acquire the test condition image of the interference source display screen; determine the key parameter area in the interference source display screen used to display the test conditions; extract the parameter values ​​of the key parameter area as the test conditions.

6. The error acquisition method for interference testing of power metering equipment based on machine vision according to claim 5, characterized in that, When a jump in error is detected, the frame rate of the camera used to acquire the test condition image is increased.

7. The error acquisition method for interference testing of power metering equipment based on machine vision according to claim 1, characterized in that, The error image information is obtained through the system interface of the error collection and display device.

8. An error acquisition device for interference testing of power metering equipment based on machine vision, comprising a processor, characterized in that, The processor is used to execute a computer program to implement the steps of the error acquisition method for interference testing of power metering equipment based on machine vision as described in any one of claims 1 to 7.

9. A computer-readable storage medium, wherein a computer program is stored internally, characterized in that, The computer program is used to be processed to execute the steps of the error acquisition method for interference testing of power metering equipment based on machine vision as described in any one of claims 1 to 7.

Images