Image-assisted testing method and system based on HIL test bench

By collecting and analyzing image and signal data on the HIL test bench, combining image feature recognition and signal data for dual verification, the problem of inability to detect non-electrical properties in the prior art is solved, and more efficient and accurate verification is achieved Testing meets automation needs.

CN118736474BActive Publication Date: 2024-11-05JIANGLING MOTORS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411203867.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-05
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

The existing verification methods based on HIL test benches cannot promptly detect non-electrical problems and cannot intuitively obtain the physical status of the equipment, resulting in low verification test efficiency and accuracy, and cannot meet the requirements of full automation.

Method used

By collecting images of the test operation area and signal control area on the HIL test bench, and using image feature recognition for supervision and judgment, combining signal data for dual verification, realizing self-test function, avoiding non-electrical faults and detection system failures, resulting in failures in non-electrical properties and detection system failures. Error.

Benefits of technology

It improves the efficiency and accuracy of verification tests, reduces operating costs, realizes automated supervision, avoids errors and failures, and enhances the stability of tests.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118736474B_ABST
    Figure CN118736474B_ABST
Patent Text Reader

Abstract

The invention relates to the field of image recognition processing, and proposes an image-assisted testing method and system based on a HIL test bench. By acquiring signal data of the HIL test bench, images of a test operation area and a signal control area are also collected, and visual supervision and judgment are performed through image feature recognition, thereby avoiding the need for a tester to perform patrol supervision, greatly improving the efficiency of the verification test and reducing the operating cost. Double verification is performed based on image and signal data, thereby avoiding test errors or mistakes caused by non-electrical faults, greatly improving the accuracy of the verification test, and realizing a self-checking function through comparative inspection of image and signal data, thereby avoiding experimental data errors caused by faults of the detection system itself, and further improving the stability of the verification test. The invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image recognition processing, and in particular to an image-assisted testing method and system based on a HIL test bench. Background Art

[0002] With the rapid development of the automotive industry, automation has become an indispensable part of it. The use of HIL test benches for verification, as an important verification method in the product development stage, has naturally become an important upgrade goal for the automation of the automotive industry.

[0003] In the prior art, the verification of product development based on the HIL test bench usually involves collecting signal data of the device in the simulation through an integrated circuit, and then judging or detecting the state or change of the signal data to achieve the evaluation of the device performance. However, only detecting and judging through signal data to evaluate the performance cannot timely discover non-electrical problems, and cannot intuitively obtain the physical state of the device under test, such as looseness / shaking of fixed parts, deviation of the force line direction and movement direction of movable parts, and abnormal connection between parts. As a result, the experimenter or operator is still required to record and report, which cannot meet the requirements of full automation, greatly reducing the efficiency and accuracy of the verification test.

[0004] Therefore, how to design an auxiliary test method based on the HIL test bench to meet the automation requirements and improve the efficiency and accuracy of the verification test has become an urgent problem to be solved. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide an image-assisted testing method and system based on a HIL test bench. While acquiring signal data of the HIL test bench, images of the test operation area and the signal control area are also collected, and visual supervision and judgment are performed through image feature recognition, thereby avoiding the need for patrol supervision by testers, greatly improving the efficiency of verification tests and reducing operating costs. Double verification is performed based on image and signal data, thereby avoiding test errors or mistakes caused by non-electrical faults, greatly improving the accuracy of verification tests, and realizing a self-checking function through comparative inspection of image and signal data, thereby avoiding experimental data errors caused by faults of the detection system itself, and further improving the stability of verification tests. The present invention greatly improves the efficiency and accuracy of verification tests based on HIL test benches.

[0006] The present invention proposes an image-assisted testing method based on a HIL test bench, which is implemented by a HIL test bench system. The HIL test bench system includes an acquisition module, an analysis and judgment module, and a recording and early warning module. The analysis and judgment module is electrically connected to the acquisition module and the recording and early warning module respectively. The method includes the following steps:

[0007] The acquisition module obtains the test operation area image, the signal control area image and the working signal data, and pre-processes them respectively, inputs the pre-processed test operation area image and the working signal data into the analysis and judgment module, and inputs the pre-processed signal control area image into the recording and early warning module;

[0008] The analysis and judgment module obtains the operating state of the test operation area according to the image feature extraction network, determines the operating state of the test operation area according to the operating state and the working signal data, and sends the detection signal data corresponding to the working state of the test operation area to the recording and early warning module;

[0009] The recording and warning module determines the detection result according to the signal control area image and the detection signal data and records it in a database. If the detection result is determined to be a fault, a fault warning report is issued.

[0010] In summary, according to the above-mentioned image-assisted testing method based on the HIL test bench, while acquiring the signal data of the HIL test bench, images of the test operation area and the signal control area are also collected, and visual supervision and judgment are performed through image feature recognition, which avoids the need for patrol supervision by testers, greatly improves the efficiency of the verification test and reduces the operating cost, and performs double verification based on image and signal data, thereby avoiding test errors or mistakes caused by non-electrical faults, greatly improving the accuracy of the verification test, and through the comparison and inspection of image and signal data, a self-checking function is realized, thereby avoiding experimental data errors caused by faults of the detection system itself, and further improving the stability of the verification test. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench. Specifically, the acquisition module obtains the test operation area image, the signal control area image and the working signal data, and preprocesses them respectively, and inputs the preprocessed test operation area image and the working signal data into the analysis and judgment module, and inputs the preprocessed signal control area image into the recording and early warning module, so as to improve the quality of the image and signal data, avoid the detection error caused by misidentification, and further improve the accuracy of the verification test. The analysis and judgment module obtains the operating status of the test operation area according to the image feature extraction network, so as to determine the working status of the test operation area according to the operating status and the working signal data, and sends the detection signal data corresponding to the working status of the test operation area to the recording and early warning module, and performs double verification according to the image and signal data to improve the accuracy of the verification test. The recording and early warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, a fault early warning report is performed. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench.

[0011] Furthermore, the acquisition module acquires the test operation area image, the signal control area image and the working signal data, and performs preprocessing steps respectively, specifically including:

[0012] The acquisition module acquires the test operation area image, the signal control area image and the working signal data;

[0013] Performing color correction processing on the test operation area image, extracting pixel values ​​of a single central pixel point of all non-image edges in the test operation area image and eight adjacent pixel points around the central pixel point, and obtaining a color correction value of the central pixel point according to a weighted average algorithm, so as to use the color correction value as the pixel value of the corresponding pixel point after color correction;

[0014] Grayscale the signal control area image, extract the red, green and blue three-channel pixel values ​​of all single pixels in the signal control area image, obtain the weighted grayscale values ​​of all pixels according to the weighted grayscale algorithm, and use the weighted grayscale values ​​as the grayscale pixel values ​​of the corresponding pixels;

[0015] Then, the grayscaled signal control area image is subjected to illumination correction processing, the brightness values ​​of all individual pixels in the signal control area image are extracted, the brightness values ​​of the pixels whose brightness values ​​are higher than a preset high brightness value are adjusted to the preset high brightness value, and the brightness values ​​of the pixels whose brightness values ​​are lower than a preset low brightness value are adjusted to the preset low brightness value;

[0016] A data missing judgment is performed on the working signal data. If it is determined that the working signal data has data missing, a linear interpolation process is performed based on adjacent signal data to fill the data missing.

[0017] Furthermore, the step of the analysis and judgment module obtaining the operating status of the test operation area according to the image feature extraction network specifically includes:

[0018] After receiving the test operation area image and the working signal data, the analysis and judgment module extracts the key target features and target-related area features of the test operation area image according to the image feature extraction network;

[0019] Calculating the motion trajectory of the key target according to the key target feature to determine the motion state of the key target;

[0020] Calculating an area change value of the target-related region according to the target-related region feature, so as to determine a deformation state of the target-related region according to the area change value;

[0021] The operating state of the test operation area is obtained according to the motion state of the key target and the deformation state of the target-related area.

[0022] Furthermore, the step of extracting key target features and target-related area features of the test operation area image according to the image feature extraction network specifically includes:

[0023] The image of the test operation area is input into an image feature extraction network, wherein the image feature extraction network includes a basic feature extraction layer, a local feature enhancement layer, a context feature enhancement layer, a key target feature extraction layer, and a target-related area feature extraction layer;

[0024] The basic feature extraction layer obtains the basic feature image of the test operation area image;

[0025] The local feature enhancement layer includes a bottleneck structure branch, an incremental structure branch and a residual branch, the bottleneck structure branch includes two 2x2 convolution blocks and one 1x1 convolution block, the incremental structure branch includes a 1x1 convolution block, a 3x3 convolution block and a 5x5 convolution block, and the local feature enhancement layer performs local feature enhancement on the basic feature image to obtain a local feature enhanced image;

[0026] The context feature enhancement layer includes a plurality of 5×5 convolution blocks and an attention block, the attention block includes a plurality of relationship units, the relationship unit includes a one-dimensional depth-separable convolution kernel and a global average pooling layer, and the context feature enhancement layer performs context feature enhancement on the basic feature image to obtain a context feature enhanced image;

[0027] The key target feature extraction layer performs key target segmentation on the local feature enhanced image to obtain key target features;

[0028] The target-related region feature extraction layer performs target-related region segmentation on the context feature enhanced image to obtain target-related region features.

[0029] Further, the step of determining the working state of the test operation area according to the running state and the working signal data, and sending the detection signal data corresponding to the working state of the test operation area to the recording and early warning module specifically includes:

[0030] Performing trajectory detection on key targets in the test operation area according to the working signal data and the motion state of the key targets in the running state, judging whether the running trajectory of the key targets meets the preset running trajectory standard, and generating normal running trajectory data if the running trajectory of the key targets meets the preset running trajectory standard, and generating abnormal running trajectory data if the running trajectory of the key targets does not meet the preset running trajectory standard;

[0031] Performing change detection on the target-related area in the test operation area according to the working signal data and the deformation state of the target-related area in the running state, judging whether the area change of the target-related area meets the preset area change standard, and generating normal area change data if the area change of the target-related area meets the preset area change standard, and generating abnormal area change data if the area change of the target-related area does not meet the preset area change standard;

[0032] The working state of the test operation area is judged based on the acquired running trajectory data and area change data. If there is no abnormality in the running trajectory data and the area change data, the detection signal data of the normal working state is sent to the recording and early warning module. If there is one abnormality in the running trajectory data and the area change data, the detection signal data of the error working state is sent to the recording and early warning module. If there are two abnormalities in the running trajectory data and the area change data, the detection signal data of the fault working state is sent to the recording and early warning module.

[0033] Furthermore, the recording and warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, the step of performing a fault warning report specifically includes:

[0034] Acquire test status reference data based on the signal control area image;

[0035] The test state reference data is compared with the detection signal data. When both the test state reference data and the detection signal data determine that the test operation area is in a fault state, the detection result is written as a fault, the test state reference data and the detection signal data are stored and recorded in the detection database, and a fault warning report is made.

[0036] Furthermore, the step of comparing the test state reference data with the detection signal data specifically includes:

[0037] When the state of the test operation area determined by the test state reference data is the same as the state of the test operation area determined by the detection signal data, the current state of the test operation area is written into the detection result;

[0038] When the test state reference data determines the state of the test operation area and the test signal data determines the state of the test operation area, the test result is not written and the maintenance request report is not sent.

[0039] The present invention proposes an image-assisted test system based on a HIL test bench, which is implemented by a HIL test bench system. The HIL test bench system includes an acquisition module, an analysis and judgment module, and a recording and early warning module. The analysis and judgment module is electrically connected to the acquisition module and the recording and early warning module respectively. The system includes:

[0040] The acquisition module is used to obtain the test operation area image, the signal control area image and the working signal data, and pre-process them respectively, input the pre-processed test operation area image and the working signal data into the analysis and judgment module, and input the pre-processed signal control area image into the recording and early warning module;

[0041] An analysis and judgment module, used for obtaining the operating state of the test operation area according to the image feature extraction network, determining the operating state of the test operation area according to the operating state and the working signal data, and sending the detection signal data corresponding to the working state of the test operation area to the recording and early warning module;

[0042] The recording and warning module is used to determine the detection result based on the signal control area image and the detection signal data and record it in the database. If the detection result is determined to be a fault, a fault warning report is issued.

[0043] The present invention also provides a storage medium, wherein the storage medium stores one or more programs, and when the programs are executed by a processor, the image-assisted testing method based on the HIL test bench as described above is implemented.

[0044] The present invention also provides a computer device, the computer device comprising a memory and a processor, wherein:

[0045] The memory is used to store computer programs;

[0046] When the processor is used to execute the computer program stored in the memory, the image-assisted testing method based on the HIL test bench as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of an image-assisted testing method based on a HIL test bench proposed in the first embodiment of the present invention;

[0048] Figure 2 A flow chart of an image-assisted testing method based on a HIL test bench proposed in a second embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of an image-assisted testing system based on a HIL test bench proposed in the third embodiment of the present invention.

[0050] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0051] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0054] See also Figure 1 , which is a flow chart of an image-assisted testing method based on a HIL test bench according to a first embodiment of the present invention. The image-assisted testing method based on a HIL test bench comprises steps S01 to S03, wherein:

[0055] Step S01: the acquisition module acquires the test operation area image, the signal control area image and the working signal data, and pre-processes them respectively, inputs the pre-processed test operation area image and the working signal data into the analysis and judgment module, and inputs the pre-processed signal control area image into the recording and early warning module;

[0056] It should be noted that in this embodiment, the acquisition module acquires the test operation area image, the signal control area image and the working signal data;

[0057] Performing color correction processing on the test operation area image, extracting pixel values ​​of a single central pixel point of all non-image edges in the test operation area image and eight adjacent pixel points around the central pixel point, and obtaining a color correction value of the central pixel point according to a weighted average algorithm, so as to use the color correction value as the pixel value of the corresponding pixel point after color correction;

[0058] Grayscale the signal control area image, extract the red, green and blue three-channel pixel values ​​of all single pixels in the signal control area image, obtain the weighted grayscale values ​​of all pixels according to the weighted grayscale algorithm, and use the weighted grayscale values ​​as the grayscale pixel values ​​of the corresponding pixels;

[0059] Then, the grayscaled signal control area image is subjected to illumination correction processing, the brightness values ​​of all individual pixels in the signal control area image are extracted, the brightness values ​​of the pixels whose brightness values ​​are higher than a preset high brightness value are adjusted to the preset high brightness value, and the brightness values ​​of the pixels whose brightness values ​​are lower than a preset low brightness value are adjusted to the preset low brightness value;

[0060] A data missing judgment is performed on the working signal data. If it is determined that the working signal data has data missing, a linear interpolation process is performed based on adjacent signal data to fill the data missing.

[0061] Step S02: the analysis and judgment module obtains the operating state of the test operation area according to the image feature extraction network, determines the operating state of the test operation area according to the operating state and the working signal data, and sends the detection signal data corresponding to the working state of the test operation area to the recording and early warning module;

[0062] It should be noted that, in this embodiment, after the analysis and judgment module receives the test operation area image and the working signal data, it extracts the key target features and target-related area features of the test operation area image according to the image feature extraction network;

[0063] Calculating the motion trajectory of the key target according to the key target feature to determine the motion state of the key target;

[0064] Calculating an area change value of the target-related region according to the target-related region feature, so as to determine a deformation state of the target-related region according to the area change value;

[0065] The operating state of the test operation area is obtained according to the motion state of the key target and the deformation state of the target-related area.

[0066] It should be noted that in this embodiment, the test operation area image is input into an image feature extraction network, and the image feature extraction network includes a basic feature extraction layer, a local feature enhancement layer, a context feature enhancement layer, a key target feature extraction layer, and a target-related area feature extraction layer;

[0067] The basic feature extraction layer obtains the basic feature image of the test operation area image;

[0068] The local feature enhancement layer includes a bottleneck structure branch, an incremental structure branch and a residual branch, the bottleneck structure branch includes two 2x2 convolution blocks and one 1x1 convolution block, the incremental structure branch includes a 1x1 convolution block, a 3x3 convolution block and a 5x5 convolution block, and the local feature enhancement layer performs local feature enhancement on the basic feature image to obtain a local feature enhanced image;

[0069] The context feature enhancement layer includes a plurality of 5×5 convolution blocks and an attention block, the attention block includes a plurality of relationship units, the relationship unit includes a one-dimensional depth-separable convolution kernel and a global average pooling layer, and the context feature enhancement layer performs context feature enhancement on the basic feature image to obtain a context feature enhanced image;

[0070] The key target feature extraction layer performs key target segmentation on the local feature enhanced image to obtain key target features;

[0071] The target-related region feature extraction layer performs target-related region segmentation on the context feature enhanced image to obtain target-related region features.

[0072] It should be noted that in this embodiment, the trajectory detection is performed on the key target in the test operation area according to the working signal data and the motion state of the key target in the running state, and it is determined whether the running trajectory of the key target meets the preset running trajectory standard. If the running trajectory of the key target meets the preset running trajectory standard, normal running trajectory data is generated; if the running trajectory of the key target does not meet the preset running trajectory standard, abnormal running trajectory data is generated;

[0073] Performing change detection on the target-related area in the test operation area according to the working signal data and the deformation state of the target-related area in the running state, judging whether the area change of the target-related area meets the preset area change standard, and generating normal area change data if the area change of the target-related area meets the preset area change standard, and generating abnormal area change data if the area change of the target-related area does not meet the preset area change standard;

[0074] The working state of the test operation area is judged based on the acquired running trajectory data and area change data. If there is no abnormality in the running trajectory data and the area change data, the detection signal data of the normal working state is sent to the recording and early warning module. If there is one abnormality in the running trajectory data and the area change data, the detection signal data of the error working state is sent to the recording and early warning module. If there are two abnormalities in the running trajectory data and the area change data, the detection signal data of the fault working state is sent to the recording and early warning module.

[0075] Step S03: the recording and warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, a fault warning report is issued;

[0076] It should be noted that in this embodiment, the test state reference data is obtained according to the signal control area image;

[0077] Compare the test state reference data with the detection signal data. When both the test state reference data and the detection signal data determine that the test operation area is in a fault state, write the detection result as a fault, store and record the test state reference data and the detection signal data in a detection database, and make a fault warning report;

[0078] When the state of the test operation area determined by the test state reference data is the same as the state of the test operation area determined by the detection signal data, the current state of the test operation area is written into the detection result;

[0079] When the test state reference data determines the state of the test operation area and the test signal data determines the state of the test operation area, the test result is not written and the maintenance request report is not sent.

[0080] In summary, according to the above-mentioned image-assisted testing method based on the HIL test bench, while acquiring the signal data of the HIL test bench, images of the test operation area and the signal control area are also collected, and visual supervision and judgment are performed through image feature recognition, which avoids the need for patrol supervision by testers, greatly improves the efficiency of the verification test and reduces the operating cost, and performs double verification based on image and signal data, thereby avoiding test errors or mistakes caused by non-electrical faults, greatly improving the accuracy of the verification test, and through the comparison and inspection of image and signal data, a self-checking function is realized, thereby avoiding experimental data errors caused by faults of the detection system itself, and further improving the stability of the verification test. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench. Specifically, the acquisition module obtains the test operation area image, the signal control area image and the working signal data, and preprocesses them respectively, and inputs the preprocessed test operation area image and the working signal data into the analysis and judgment module, and inputs the preprocessed signal control area image into the recording and early warning module, so as to improve the quality of the image and signal data, avoid the detection error caused by misidentification, and further improve the accuracy of the verification test. The analysis and judgment module obtains the operating status of the test operation area according to the image feature extraction network, so as to determine the working status of the test operation area according to the operating status and the working signal data, and sends the detection signal data corresponding to the working status of the test operation area to the recording and early warning module, and performs double verification according to the image and signal data to improve the accuracy of the verification test. The recording and early warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, a fault early warning report is performed. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench.

[0081] See also Figure 2, which is a flow chart of an image-assisted testing method based on a HIL test bench according to a second embodiment of the present invention, wherein the image-assisted testing method based on a HIL test bench comprises steps S11 to S16, wherein:

[0082] Step S11: the acquisition module acquires the test operation area image, the signal control area image and the working signal data, performs color correction processing on the test operation area image, performs grayscale processing on the signal control area image, performs illumination correction processing on the grayscale signal control area image, and performs data missing judgment on the working signal data. If it is determined that the working signal data has data missing, linear interpolation processing is performed according to adjacent signal data to fill the data missing;

[0083] Step S12: After the analysis and judgment module receives the test operation area image and the working signal data, the key target features and target-related area features of the test operation area image are extracted according to the image feature extraction network, the motion trajectory of the key target is calculated according to the key target features to determine the motion state of the key target, the area change value of the target-related area is calculated according to the target-related area features, the deformation state of the target-related area is determined according to the area change value, and the operation state of the test operation area is obtained according to the motion state of the key target and the deformation state of the target-related area;

[0084] Step S13: the test operation area image is input into the image feature extraction network, the basic feature extraction layer obtains the basic feature image of the test operation area image, the local feature enhancement layer performs local feature enhancement on the basic feature image to obtain a local feature enhanced image, the context feature enhancement layer performs context feature enhancement on the basic feature image to obtain a context feature enhanced image, the key target feature extraction layer performs key target segmentation on the local feature enhanced image to obtain key target features, and the target-related region feature extraction layer performs target-related region segmentation on the context feature enhanced image to obtain target-related region features;

[0085] Step S14: performing trajectory detection on key targets in the test operation area according to the working signal data and the motion state of key targets in the running state, performing change detection on target-related areas in the test operation area according to the working signal data and the deformation state of target-related areas in the running state, and judging the working state of the test operation area according to the obtained running trajectory data and area change data, so as to send detection signal data to the recording and early warning module;

[0086] Step S15: Acquire test state reference data according to the signal control area image, compare the test state reference data with the detection signal data, and when both the test state reference data and the detection signal data determine that the test operation area is in a fault state, write the detection result as a fault, store and record the test state reference data and the detection signal data in the detection database, and make a fault warning report;

[0087] Step S16: When the state of the test operation area determined by the test state reference data is different from the state of the test operation area determined by the detection signal data, the detection result is not written and the maintenance request report is not sent.

[0088] In summary, according to the above-mentioned image-assisted testing method based on the HIL test bench, while acquiring the signal data of the HIL test bench, images of the test operation area and the signal control area are also collected, and visual supervision and judgment are performed through image feature recognition, which avoids the need for patrol supervision by testers, greatly improves the efficiency of the verification test and reduces the operating cost, and performs double verification based on image and signal data, thereby avoiding test errors or mistakes caused by non-electrical faults, greatly improving the accuracy of the verification test, and through the comparison and inspection of image and signal data, a self-checking function is realized, thereby avoiding experimental data errors caused by faults of the detection system itself, and further improving the stability of the verification test. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench. Specifically, the acquisition module obtains the test operation area image, the signal control area image and the working signal data, and preprocesses them respectively, and inputs the preprocessed test operation area image and the working signal data into the analysis and judgment module, and inputs the preprocessed signal control area image into the recording and early warning module, so as to improve the quality of the image and signal data, avoid the detection error caused by misidentification, and further improve the accuracy of the verification test. The analysis and judgment module obtains the operating status of the test operation area according to the image feature extraction network, so as to determine the working status of the test operation area according to the operating status and the working signal data, and sends the detection signal data corresponding to the working status of the test operation area to the recording and early warning module, and performs double verification according to the image and signal data to improve the accuracy of the verification test. The recording and early warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, a fault early warning report is performed. The present invention greatly improves the efficiency and accuracy of the verification test based on the HIL test bench.

[0089] See also Figure 3 , which is a schematic diagram of the structure of an image-assisted testing system based on a HIL test bench according to a third embodiment of the present invention, the system comprises:

[0090] The acquisition module 10 is used to obtain the test operation area image, the signal control area image and the working signal data, and pre-process them respectively, input the pre-processed test operation area image and the working signal data into the analysis and judgment module, and input the pre-processed signal control area image into the recording and early warning module;

[0091] The analysis and judgment module 20 is used to obtain the operating state of the test operation area according to the image feature extraction network, to determine the operating state of the test operation area according to the operating state and the working signal data, and to send the detection signal data corresponding to the working state of the test operation area to the recording and early warning module;

[0092] The recording and warning module 30 is used to determine the detection result based on the signal control area image and the detection signal data and record it in the database. If the detection result is determined to be a fault, a fault warning report is issued.

[0093] The present invention also provides a computer storage medium on which one or more programs are stored. When the programs are executed by a processor, the above-mentioned image-assisted testing method based on the HIL test bench is implemented.

[0094] The present invention also proposes a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the above-mentioned image-assisted testing method based on the HIL test bench.

[0095] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain storage, communication, propagation or transmission of a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0096] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0097] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0098] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0099] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An image-assisted testing method based on a HIL test bench, characterized in that: The method is implemented by a HIL test bench system, wherein the HIL test bench system includes a collection module, an analysis and judgment module, and a recording and early warning module, wherein the analysis and judgment module is electrically connected to the collection module and the recording and early warning module respectively, and the method includes the following steps: The acquisition module obtains the test operation area image, the signal control area image and the working signal data, and pre-processes them respectively, inputs the pre-processed test operation area image and the working signal data into the analysis and judgment module, and inputs the pre-processed signal control area image into the recording and early warning module; The analysis and judgment module obtains the operating state of the test operation area according to the image feature extraction network, determines the operating state of the test operation area according to the operating state and the working signal data, and sends the detection signal data corresponding to the working state of the test operation area to the recording and early warning module; The step of determining the working state of the test operation area according to the running state and the working signal data, and sending the detection signal data corresponding to the working state of the test operation area to the recording and early warning module specifically includes: Performing trajectory detection on key targets in the test operation area according to the working signal data and the motion state of the key targets in the running state, judging whether the running trajectory of the key targets meets the preset running trajectory standard, and generating normal running trajectory data if the running trajectory of the key targets meets the preset running trajectory standard, and generating abnormal running trajectory data if the running trajectory of the key targets does not meet the preset running trajectory standard; Performing change detection on the target-related area in the test operation area according to the working signal data and the deformation state of the target-related area in the running state, judging whether the area change of the target-related area meets the preset area change standard, and generating normal area change data if the area change of the target-related area meets the preset area change standard, and generating abnormal area change data if the area change of the target-related area does not meet the preset area change standard; The working state of the test operation area is judged according to the operation trajectory data and area change data obtained by judgment. If there is no abnormality in the operation trajectory data and the area change data, the detection signal data of the normal working state is sent to the recording and early warning module. If there is one abnormality in the operation trajectory data and the area change data, the detection signal data of the error working state is sent to the recording and early warning module. If there are two abnormalities in the operation trajectory data and the area change data, the detection signal data of the fault working state is sent to the recording and early warning module. The recording and warning module determines the detection result according to the signal control area image and the detection signal data and records it in a database. If the detection result is determined to be a fault, a fault warning report is issued.

2. The image-assisted testing method based on the HIL test bench according to claim 1, characterized in that: The acquisition module acquires the test operation area image, the signal control area image and the working signal data, and performs preprocessing steps respectively, specifically including: The acquisition module acquires the test operation area image, the signal control area image and the working signal data; Performing color correction processing on the test operation area image, extracting pixel values ​​of a single central pixel point of all non-image edges in the test operation area image and eight adjacent pixel points around the central pixel point, and obtaining a color correction value of the central pixel point according to a weighted average algorithm, so as to use the color correction value as the pixel value of the corresponding pixel point after color correction; Grayscale the signal control area image, extract the red, green and blue three-channel pixel values ​​of all single pixels in the signal control area image, obtain the weighted grayscale values ​​of all pixels according to the weighted grayscale algorithm, and use the weighted grayscale values ​​as the grayscale pixel values ​​of the corresponding pixels; Then, the grayscaled signal control area image is subjected to illumination correction processing, the brightness values ​​of all individual pixels in the signal control area image are extracted, the brightness values ​​of the pixels whose brightness values ​​are higher than a preset high brightness value are adjusted to the preset high brightness value, and the brightness values ​​of the pixels whose brightness values ​​are lower than a preset low brightness value are adjusted to the preset low brightness value; A data missing judgment is performed on the working signal data. If it is determined that the working signal data has data missing, a linear interpolation process is performed based on adjacent signal data to fill the data missing.

3. The image-assisted testing method based on the HIL test bench according to claim 1, characterized in that: The step of the analysis and judgment module obtaining the operating status of the test operation area according to the image feature extraction network specifically includes: After receiving the test operation area image and the working signal data, the analysis and judgment module extracts the key target features and target-related area features of the test operation area image according to the image feature extraction network; Calculating the motion trajectory of the key target according to the key target feature to determine the motion state of the key target; Calculating an area change value of the target-related region according to the target-related region feature, so as to determine a deformation state of the target-related region according to the area change value; The operating state of the test operation area is obtained according to the motion state of the key target and the deformation state of the target-related area.

4. The image-assisted testing method based on the HIL test bench according to claim 3 is characterized in that: The step of extracting key target features and target-related area features of the test operation area image according to the image feature extraction network specifically includes: The image of the test operation area is input into an image feature extraction network, wherein the image feature extraction network includes a basic feature extraction layer, a local feature enhancement layer, a context feature enhancement layer, a key target feature extraction layer, and a target-related area feature extraction layer; The basic feature extraction layer obtains the basic feature image of the test operation area image; The local feature enhancement layer includes a bottleneck structure branch, an incremental structure branch and a residual branch, the bottleneck structure branch includes two 2x2 convolution blocks and one 1x1 convolution block, the incremental structure branch includes a 1x1 convolution block, a 3x3 convolution block and a 5x5 convolution block, and the local feature enhancement layer performs local feature enhancement on the basic feature image to obtain a local feature enhanced image; The context feature enhancement layer includes a plurality of 5×5 convolution blocks and an attention block, the attention block includes a plurality of relationship units, the relationship unit includes a one-dimensional depth-separable convolution kernel and a global average pooling layer, and the context feature enhancement layer performs context feature enhancement on the basic feature image to obtain a context feature enhanced image; The key target feature extraction layer performs key target segmentation on the local feature enhanced image to obtain key target features; The target-related region feature extraction layer performs target-related region segmentation on the context feature enhanced image to obtain target-related region features.

5. The image-assisted testing method based on the HIL test bench according to claim 1, characterized in that: The recording and warning module determines the detection result according to the signal control area image and the detection signal data and records it in the database. If the detection result is determined to be a fault, the steps of performing a fault warning report specifically include: Acquire test status reference data based on the signal control area image; The test state reference data is compared with the detection signal data. When both the test state reference data and the detection signal data determine that the test operation area is in a fault state, the detection result is written as a fault, the test state reference data and the detection signal data are stored and recorded in the detection database, and a fault warning report is made.

6. The image-assisted testing method based on the HIL test bench according to claim 5, characterized in that: The step of comparing the test state reference data with the detection signal data specifically includes: When the state of the test operation area determined by the test state reference data is the same as the state of the test operation area determined by the detection signal data, the current state of the test operation area is written into the detection result; When the test state reference data determines the state of the test operation area and the test signal data determines the state of the test operation area, the test result is not written and the maintenance request report is not sent.

7. An image-assisted testing system based on a HIL test bench, characterized in that: The method is implemented by a HIL test bench system, wherein the HIL test bench system includes a collection module, an analysis and judgment module, and a recording and early warning module, wherein the analysis and judgment module is electrically connected to the collection module and the recording and early warning module respectively, and the system includes: The acquisition module is used to obtain the test operation area image, the signal control area image and the working signal data, and pre-process them respectively, input the pre-processed test operation area image and the working signal data into the analysis and judgment module, and input the pre-processed signal control area image into the recording and early warning module; An analysis and judgment module, used for obtaining the operating state of the test operation area according to the image feature extraction network, determining the operating state of the test operation area according to the operating state and the working signal data, and sending the detection signal data corresponding to the working state of the test operation area to the recording and early warning module; The step of determining the working state of the test operation area according to the running state and the working signal data, and sending the detection signal data corresponding to the working state of the test operation area to the recording and early warning module specifically includes: Performing trajectory detection on key targets in the test operation area according to the working signal data and the motion state of the key targets in the running state, judging whether the running trajectory of the key targets meets the preset running trajectory standard, and generating normal running trajectory data if the running trajectory of the key targets meets the preset running trajectory standard, and generating abnormal running trajectory data if the running trajectory of the key targets does not meet the preset running trajectory standard; Performing change detection on the target-related area in the test operation area according to the working signal data and the deformation state of the target-related area in the running state, judging whether the area change of the target-related area meets the preset area change standard, and generating normal area change data if the area change of the target-related area meets the preset area change standard, and generating abnormal area change data if the area change of the target-related area does not meet the preset area change standard; The working state of the test operation area is judged according to the operation trajectory data and area change data obtained by judgment. If there is no abnormality in the operation trajectory data and the area change data, the detection signal data of the normal working state is sent to the recording and early warning module. If there is one abnormality in the operation trajectory data and the area change data, the detection signal data of the error working state is sent to the recording and early warning module. If there are two abnormalities in the operation trajectory data and the area change data, the detection signal data of the fault working state is sent to the recording and early warning module. The recording and warning module is used to determine the detection result based on the signal control area image and the detection signal data and record it in the database. If the detection result is determined to be a fault, a fault warning report is issued.

8. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by a processor, implement the image-assisted testing method based on a HIL test bench as described in any one of claims 1 to 6.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, the image-assisted testing method based on the HIL test bench according to any one of claims 1 to 6 is implemented.