Visual measurement and control system and method for maintenance and debugging

Abstract

The invention discloses a visual measurement and control system and method for maintenance and debugging, and relates to the technical field of data processing, and the system comprises a performance test module which is used for executing a hydraulic adjustment test for a tested piece; the data acquisition module is used for performing multivariate data acquisition; the edge processing module is used for extracting a multivariate diagnosis index set; the fault diagnosis module is used for performing multivariate data fusion and fault diagnosis positioning; the maintenance debugging module is used for carrying out virtual regulation and control test and generating an optimal debugging scheme; and the visual maintenance regulation and control module is used for executing visual maintenance regulation and control of the tested piece. The technical problems that fault diagnosis of a shift valve assembly in the prior art possibly involves hydraulic, electronic and mechanical aspects at the same time, accurate positioning is difficult in single-aspect diagnosis, and the maintenance and debugging effect is affected are solved, comprehensive fault diagnosis based on multivariate monitoring data is achieved, and the maintenance and debugging efficiency is improved. And the fault positioning accuracy and the test piece regulation and control precision are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a visual measurement and control system and method for maintenance and debugging. Background Art

[0002] The CH400 and CH300 series shift valve assemblies are important components of modern vehicle transmission systems and are mainly used to achieve vehicle shifting operations. These shift valve assemblies adjust the meshing of gears in the transmission by controlling the flow of hydraulic oil, thereby achieving smooth vehicle shifting. The shift valve assembly involves multi-channel hydraulic control, and the pressure and flow of each channel need to be precisely adjusted and controlled. Therefore, performance testing, fault repair and debugging are required regularly to ensure the hydraulic control performance of the equipment.

[0003] However, the shift valve assembly includes multiple functional units such as the hydraulic control unit, electronic control unit, and mechanical control unit. Its fault diagnosis may involve hydraulics, electronics, and mechanics at the same time. Diagnosis of a single aspect is often difficult to accurately locate the problem, affecting the debugging effect. Summary of the invention

[0004] The present application provides a visual measurement and control system and method for maintenance and debugging, which is used to solve the technical problem that the fault diagnosis of the shift valve assembly in the prior art may involve three aspects: hydraulics, electronics and mechanics at the same time, and the diagnosis of a single aspect is difficult to accurately locate the problem, thus affecting the maintenance and debugging effect.

[0005] The first aspect of the present application provides a visual measurement and control method for maintenance and debugging, the method comprising: performing hydraulic adjustment tests under various temperature conditions on a test piece, and performing dynamic demonstrations through a dynamic demonstration interface; performing multivariate data acquisition during the hydraulic adjustment test, including acquiring a hydraulic sensor data set, an electronic sensor data set, and a mechanical sensor data set, to obtain a multivariate monitoring data set of the test piece under various temperature conditions, and performing visual display through a data monitoring interface; performing key indicator extraction on the multivariate monitoring data set based on multiple edge computing units to obtain a multivariate diagnostic indicator set; performing multivariate data fusion and fault diagnosis and location based on the multivariate diagnostic indicator set to obtain a fault diagnosis result of the test piece, and performing display through a fault diagnosis interface; performing a virtual control test based on the fault diagnosis result of the test piece to generate an optimal debugging plan; and performing visual maintenance and control of the test piece based on the optimal debugging plan.

[0006] The second aspect of the present application provides a visual measurement and control system for maintenance and debugging, the system comprising: a performance testing module, used to perform hydraulic adjustment tests on a test piece under various temperature conditions, and perform dynamic demonstrations through a dynamic demonstration interface; a data acquisition module, used to perform multivariate data acquisition during the hydraulic adjustment test, including acquiring a hydraulic sensor data set, an electronic sensor data set, and a mechanical sensor data set, to obtain a multivariate monitoring data set of the test piece under various temperature conditions, and perform visual display through a data monitoring interface; an edge processing module, used to extract key indicators for the multivariate monitoring data set based on multiple edge computing units, and obtain a multivariate diagnostic indicator set; a fault diagnosis module, used to perform multivariate data fusion and fault diagnosis positioning based on the multivariate diagnostic indicator set, obtain a fault diagnosis result of the test piece, and display it through a fault diagnosis interface; a maintenance and debugging module, used to perform a virtual control test based on the fault diagnosis result of the test piece, and generate an optimal debugging plan; a visual maintenance and control module, used to perform visual maintenance and control of the test piece based on the optimal debugging plan.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The visual measurement and control system and method for maintenance and debugging provided in the present application relate to the field of data processing technology. By executing a hydraulic adjustment test and performing multivariate data collection, a multivariate monitoring data set of a test piece under various temperature conditions is obtained. According to multiple edge computing units, key indicators are extracted to obtain a multivariate diagnostic indicator set, and multivariate data fusion and fault diagnosis and positioning are performed. According to the fault diagnosis result of the test piece, a virtual control test is performed, an optimal debugging plan is generated, and visual maintenance and control of the test piece is performed. The technical problem that the fault diagnosis of the shift valve assembly in the prior art may involve the three aspects of hydraulics, electronics and mechanics at the same time, and the diagnosis of a single aspect is difficult to accurately locate the problem, which affects the maintenance and debugging effect, is solved. The technical effect of performing comprehensive fault diagnosis based on multivariate monitoring data and improving the accuracy of fault location and the control accuracy of the test piece is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flow chart of a visual measurement and control method for maintenance and debugging provided in an embodiment of the present application;

[0011] Figure 2A schematic diagram of a process for obtaining a fault diagnosis result of a tested component in a visual measurement and control method for maintenance and debugging provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of the structure of a visual measurement and control system for maintenance and debugging provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: performance testing module 11, data acquisition module 12, edge processing module 13, fault diagnosis module 14, maintenance and debugging module 15, visual maintenance and control module 16. DETAILED DESCRIPTION

[0014] The present application provides a visual measurement and control system and method for maintenance and debugging, which is used to solve the technical problem that the fault diagnosis of the shift valve assembly in the prior art may involve three aspects: hydraulics, electronics and mechanics at the same time, and the diagnosis of a single aspect is difficult to accurately locate the problem, thus affecting the maintenance and debugging effect.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides a visual measurement and control method for maintenance and debugging, the method comprising:

[0019] P10: Perform hydraulic adjustment tests under various temperature conditions on the test piece and perform dynamic demonstrations through the dynamic demonstration interface.

[0020] Specifically, a series of hydraulic adjustment tests under various temperature conditions are designed and performed for the DUT. Various temperature changes that the DUT may encounter in the actual working environment are simulated to comprehensively evaluate the performance stability and adjustment ability of its hydraulic system. To achieve this goal, advanced temperature control technology and high-precision hydraulic testing equipment are used. First, through a sophisticated temperature control system, different test temperatures are accurately set and maintained, including low temperature, normal temperature and high temperature environments, to ensure that the test conditions are close to actual working conditions.

[0021] During the test, the hydraulic adjustment system dynamically adjusts the tested part according to the preset parameters and procedures, simulating the hydraulic pressure changes, flow distribution and other scenarios in actual work. At the same time, a dynamic demonstration interface is introduced as a real-time display tool. The interface integrates graphical display technology and real-time data processing capabilities, and can intuitively display the changes in key parameters in the hydraulic adjustment process, such as pressure curves, flow fluctuations, etc. It not only provides intuitive visual feedback for operators, but also simplifies the complex hydraulic adjustment process into easy-to-understand visual information through dynamic charts, animation effects and other means. This real-time interactive method greatly enhances the transparency and comprehensibility of the test, allowing operators to quickly capture the key points in the test and discover potential problems or abnormalities in a timely manner.

[0022] P20: Perform multivariate data collection during the hydraulic adjustment test process, including collecting hydraulic sensor data sets, electronic sensor data sets, and mechanical sensor data sets, obtaining multivariate monitoring data sets of the test piece under various temperature conditions, and visually displaying them through the data monitoring interface.

[0023] Furthermore, step P20 of the embodiment of the present application further includes:

[0024] P21: Based on the multiple temperature conditions, multiple test conditions are generated; P22: The data acquisition module includes a hydraulic sensor module, an electronic sensor module and a mechanical sensor module; P23: For the multiple test conditions, multi-channel synchronous data acquisition is performed based on the hydraulic sensor module, the electronic sensor module and the mechanical sensor module respectively to obtain the hydraulic sensor data set, electronic sensor data set and mechanical sensor data set under different test conditions.

[0025] It should be understood that in order to collect multivariate data during the hydraulic regulation test process, multiple test conditions are first carefully designed based on different temperature conditions to simulate various working environments that the test piece may encounter in actual applications. Furthermore, multivariate data collection is performed based on a data acquisition module, and the data acquisition module includes a hydraulic sensor module, an electronic sensor module, and a mechanical sensor module. For the multiple test conditions, multi-channel synchronous data collection is performed based on the hydraulic sensor module, the electronic sensor module, and the mechanical sensor module, respectively. For example, through a high-precision time synchronization mechanism, such as GPS time synchronization or network time protocol (NTP), the data of hydraulic, electronic, and mechanical sensors are collected simultaneously to ensure the synchronization and consistency of the data, and to obtain a hydraulic sensor data set, an electronic sensor data set, and a mechanical sensor data set.

[0026] The hydraulic data set includes hydraulic parameters such as pressure, flow, and temperature, which are collected in real time by the hydraulic sensor module. The electronic data set includes electronic parameters such as current, voltage, and signal delay, which are collected in real time by the electronic sensor module. The mechanical data set includes mechanical parameters such as vibration, displacement, and wear, which are collected in real time by the mechanical sensor module.

[0027] At the same time, the data monitoring interface displays the data of hydraulic, electronic and mechanical sensors in real time. Using a variety of visualization methods such as charts, trend charts and dashboards, the data display is more intuitive and easy to understand. The data monitoring interface has an abnormality detection function, which can monitor the abnormality of the data in real time (such as exceeding the set threshold) and remind the operator to deal with it in time through visual and sound alarms.

[0028] P30: Based on the multiple edge computing units, key indicators are extracted for the multivariate monitoring data set to obtain a multivariate diagnostic indicator set.

[0029] Furthermore, step P30 of the embodiment of the present application further includes:

[0030] P31: Build an edge computing unit architecture, which includes multiple edge computing units corresponding to the hydraulic system, electronic system and mechanical system respectively; P32: According to the multiple edge computing units, perform data preprocessing on the multivariate monitoring data set to obtain a multivariate calibration data set; P33: Perform feature extraction based on the multivariate calibration data set to obtain time domain features, frequency domain features and time-frequency domain features; P34: Comprehensively analyze the time domain features, frequency domain features and time-frequency domain features to extract key indicators of the hydraulic system, key indicators of the electronic system and key indicators of the mechanical system; P35: Based on the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system, a multivariate diagnostic indicator set is constructed.

[0031] Optionally, the multivariate monitoring data set is deeply analyzed and processed by taking advantage of the efficiency and real-time performance of edge computing to extract key indicators that are essential for fault diagnosis. Specifically, the edge computing unit architecture is first built, which consists of multiple specially designed edge computing units, each of which is optimized for a specific system (such as hydraulic system, electronic system, and mechanical system) to ensure the accuracy and efficiency of data processing.

[0032] Furthermore, the multiple edge computing units are used to perform data preprocessing on the multivariate monitoring data set. Data preprocessing is a key step before data analysis, including a series of operations such as data cleaning, denoising, and calibration, which aims to improve data quality and reduce errors in subsequent analysis. Through this step, a more accurate and reliable multivariate calibration data set can be obtained. Subsequently, feature extraction is performed based on the multivariate calibration data set to extract feature information useful for subsequent analysis from the original data. A variety of feature extraction techniques are used, including time domain analysis, frequency domain analysis, and time-frequency domain analysis, to fully capture the time changes, frequency components, and correlation information between them in the data. Through these analyses, time domain features, frequency domain features, and time-frequency domain features are obtained to provide rich feature vectors for subsequent fault diagnosis.

[0033] Furthermore, the time domain features, frequency domain features and time-frequency domain features are comprehensively analyzed, and the features of different fields (hydraulic system, electronic system and mechanical system) are integrated and compared to reveal the intrinsic connection and mutual influence between them. Through comprehensive analysis, the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system are extracted, which are directly related to the performance and health of the system. Among them, the key indicators of the hydraulic system include pressure fluctuation range, flow rate change rate, hydraulic response time, etc. The key indicators of the electronic system include current waveform characteristics, signal delay, voltage fluctuation, etc. The key indicators of the mechanical system include vibration amplitude, displacement speed, mechanical wear, etc.

[0034] Finally, the key indicators of the hydraulic system, the electronic system and the mechanical system are integrated to form a multivariate diagnostic indicator set, which not only contains the key information within each system, but also reflects the interaction and influence between the systems, providing a comprehensive basis for subsequent fault diagnosis and performance evaluation.

[0035] P40: Based on the multivariate diagnostic indicator set, multivariate data fusion and fault diagnosis positioning are performed to obtain the fault diagnosis result of the tested device, and the result is displayed through the fault diagnosis interface.

[0036] Further, such as Figure 2 As shown, step P40 of the embodiment of the present application also includes:

[0037] P41: Based on the multi-element diagnostic indicator set, the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system are extracted; P42: Using the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system, fault identification is performed separately through the pre-trained fault identification sub-network to obtain the corresponding multiple single diagnostic results; P43: Based on the multiple single diagnostic results, fault fusion positioning is performed through the comprehensive fault judgment unit to obtain the fault diagnosis result of the test component.

[0038] In a possible embodiment of the present application, the fault of the tested part is accurately located by in-depth analysis and fusion of the multivariate diagnostic indicator set, and the results are displayed through an intuitive fault diagnosis interface. Specifically, the key indicators of the hydraulic system, electronic system and mechanical system are first accurately extracted from the multivariate diagnostic indicator set. These indicators not only represent the core operating status of each system, but also imply potential clues to system failures. Subsequently, these key indicators are used to perform fault identification through a pre-trained fault identification subnetwork. The fault identification subnetwork is constructed based on deep learning or machine learning algorithms, and is specially trained for different types of systems (such as hydraulic systems, electronic systems, and mechanical systems), including hydraulic system fault identification subnetworks, electronic system fault identification subnetworks, and mechanical system fault identification subnetworks, which can accurately identify common fault modes in their respective systems. Each subnetwork works independently and outputs a single diagnostic result of the corresponding system, that is, the fault identification result generated by each subnetwork, including the fault type, severity, and possible cause, which can provide a preliminary fault judgment.

[0039] Furthermore, as a whole system, the failure of the DUT is often not isolated, but the result of the interaction between multiple systems. Therefore, a comprehensive fault judgment unit is introduced to fuse and locate multiple single diagnostic results. The comprehensive fault judgment unit can use advanced fusion algorithms, such as Bayesian networks, fuzzy logic or deep learning, to comprehensively analyze the diagnostic results from different systems to reveal the inherent connections and mutual influences between them. In this way, the overall fault of the DUT can be located more accurately, and a comprehensive DUT fault diagnosis result can be given.

[0040] Finally, the fault diagnosis results of the tested device are intuitively displayed through the fault diagnosis interface. The fault diagnosis interface can intuitively display the fault diagnosis results through various visualization methods such as charts, heat maps, fault location maps, etc., providing powerful decision support for operators. At the same time, the diagnostic data is updated in real time to provide the latest fault information and diagnostic results.

[0041] Furthermore, step P43 of the embodiment of the present application also includes:

[0042] P43-1: Perform fault impact analysis based on the hydraulic system, electronic system and mechanical system, construct a multi-system fault propagation map and embed it in the comprehensive fault judgment unit; P43-2: According to the multi-system fault propagation map, perform conflict analysis on the multiple single diagnosis results to obtain a fault conflict analysis result; P43-3: Based on a preset priority sorting, fuse and resolve the fault conflict analysis results to obtain a fault fusion weight; P43-4: Through the fault fusion weight, fuse and locate the multiple single diagnosis results to obtain the fault diagnosis result of the test piece.

[0043] Specifically, the specific process of fault fusion positioning through the comprehensive fault judgment unit can be: first, based on the hydraulic system, electronic system, and mechanical system, the fault impact analysis is performed to analyze the mutual influence between the hydraulic system, electronic system, and mechanical system, and to deeply understand the interaction mechanism between the systems and their potential fault propagation paths. Through advanced methods such as failure mode and effects analysis (FMEA) and fault tree analysis (FTA), it is systematically identified how each single fault propagates across the system, and then a comprehensive multi-system fault propagation map is formed. This map not only reveals the inherent connection between faults, but also clarifies the direction and possibility of fault propagation. It is then embedded in the comprehensive fault judgment unit as the basic framework for subsequent diagnostic analysis.

[0044] Furthermore, based on the constructed multi-system fault propagation mapping, the results from each single diagnostic module (such as independent diagnosis for hydraulic system, electronic system, and mechanical system) are received. These results may conflict due to differences in diagnostic angles, methods, or data sources. Therefore, through conflict analysis algorithms, such as Bayesian networks, fuzzy logic, etc., multiple diagnostic results are compared and evaluated, potential conflict points are identified, and the types and severity of conflicts are classified and recorded to form fault conflict analysis results. This process helps to clarify the uncertainty in diagnosis and lays the foundation for subsequent fusion solutions.

[0045] In order to effectively handle conflicts, a preset priority sorting mechanism is introduced. According to different fault types and system importance, the preset priority sorting is used to determine which type of fault should be given priority. This mechanism comprehensively considers multiple factors such as fault type, system importance, historical data support, and current operating status, and assigns corresponding weights to different fault diagnosis results. Through this priority sorting, the system can intelligently select more reliable and critical diagnosis results, fuse and resolve conflicts, and finally calculate the fault fusion weight. This weight not only reflects the reliability of each individual diagnosis result, but also reflects the overall fault judgment tendency of the system.

[0046] Furthermore, the fault fusion weights are used to perform weighted fusion positioning on multiple individual diagnostic results. This process essentially integrates diagnostic information from different sources and dimensions to form a more comprehensive and accurate fault diagnosis result. By comprehensively evaluating the contribution of each individual diagnosis, the system can more accurately locate the source of the fault and provide corresponding maintenance suggestions or warning information.

[0047] P50: According to the fault diagnosis result of the tested device, a virtual control test is performed to generate an optimal debugging solution.

[0048] Furthermore, step P50 of the embodiment of the present application also includes:

[0049] P51: Extract key influencing factors based on the fault diagnosis results of the tested device; P52: Build a control optimization space based on the key influencing factors, and adjust the control parameters in the control optimization space to generate multiple alternative control schemes; P53: Obtain multiple performance indicators, perform balanced optimization on the multiple alternative control schemes, and obtain multiple preferred debugging schemes; P54: Build a virtual model of the tested device, perform virtual control tests on the multiple preferred debugging schemes, obtain multiple control performance indicators, and obtain the optimal debugging scheme based on the multiple control performance indicators.

[0050] It should be understood that the virtual control test is carried out according to the fault diagnosis results of the tested device, aiming to generate a set of optimal debugging solutions through intelligent methods to restore or optimize the performance of the tested device. First, the fault diagnosis results of the tested device are deeply analyzed to extract the key factors affecting the performance of the tested device. These factors may involve pressure fluctuations in the hydraulic system, signal interference in the electronic system, or the degree of wear of the mechanical system, which are directly related to the operating efficiency and stability of the equipment.

[0051] Next, a multi-dimensional control optimization space is established based on the extracted key influencing factors. This space contains all possible combinations of control parameters for finding the optimal control solution. It also includes multiple dimensions such as pressure, flow, current, signal delay, vibration, etc., each dimension represents a control parameter. In the control optimization space, multiple alternative control solutions are generated by adjusting different control parameters. These solutions cover different parameter combinations and represent potential performance improvement paths under different strategies.

[0052] However, a single performance indicator is often difficult to fully reflect the comprehensive performance of the equipment. Therefore, according to the control requirements, multiple performance indicators such as efficiency, stability, life, etc. are introduced to balance and optimize multiple alternative control schemes to obtain multiple preferred debugging schemes. This process can use optimization algorithms such as genetic algorithms and particle swarm optimization to find the optimal solution between multiple objectives and ensure that the generated preferred debugging scheme can achieve a good balance in all aspects.

[0053] Furthermore, in order to verify the effectiveness of these preferred debugging schemes, a virtual model of the device under test is established to perform virtual control tests on the multiple preferred debugging schemes. This virtual model is based on high-precision physical simulation and machine learning technology, and can simulate the operating status and performance of the equipment under different control schemes. By performing virtual control tests on multiple preferred debugging schemes, the control performance indicators of each scheme are recorded and analyzed, including response speed, stability, and energy consumption. Based on the results of the virtual control test, the scheme with the best control performance is selected as the final optimal debugging scheme. This method not only improves the efficiency and accuracy of equipment debugging, but also reduces the risks and costs in the actual debugging process.

[0054] Furthermore, step P54 of the embodiment of the present application also includes:

[0055] P54-1: Based on debugging requirements, multiple performance indicators are obtained, and the multiple performance indicators include but are not limited to response speed, stability, and energy consumption; P54-2: For the multiple performance indicators, performance weights are configured, and a balance function is constructed; P54-3: According to the balance function, the multiple alternative control schemes are balanced and optimized to obtain a performance balance sequence, and multiple preferred debugging schemes are extracted through the performance balance sequence.

[0056] Specifically, based on the multiple control performance indicators, the specific process of obtaining the optimal debugging solution can be, first, according to the specific application and working environment of the system, determine the multiple key performance indicators that need to be optimized, which directly affect the overall performance and efficiency of the system. The multiple performance indicators not only cover the basic operating characteristics of the equipment, such as response speed (measurement of the speed of the equipment's response to external instructions or changes), stability (assessment of the equipment's ability to keep its performance parameters unchanged during operation), but also consider energy consumption (representing the amount of energy consumed by the equipment during operation, which is of great significance for energy conservation and emission reduction).

[0057] Furthermore, according to the debugging requirements and actual application scenarios, weights are assigned to each performance indicator. The configuration of weights reflects the importance of each performance indicator. Exemplarily, the weight ratio of response speed, stability, and energy consumption is 0.4:0.3:0.3. Using the configured performance weights, a comprehensive balance function is constructed, which is used to comprehensively evaluate the performance of different control schemes. The formula is: F=w1·S1+w2·S2+w3·S3; where F is the comprehensive balance score, w1, w2, w3 are the weights of response speed, stability, and energy consumption, respectively, and S1, S2, S3 are the scores of response speed, stability, and energy consumption, respectively.

[0058] Furthermore, all the alternative control schemes are evaluated and ranked using a balance function, and the comprehensive balance score of each scheme is calculated. Multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) are applied to weigh and optimize multiple performance indicators to find the optimal control scheme. For example, the biological evolution process is simulated by a genetic algorithm, and the optimal solution is found among the candidate schemes through operations such as selection, crossover and mutation.

[0059] Furthermore, all the alternative control schemes are sorted according to the comprehensive balance score to form a performance balance sequence. The higher the score of the scheme in the sequence, the better its comprehensive performance. Multiple preferred debugging schemes with higher scores are extracted from the performance balance sequence. These schemes achieve the best balance between various performance indicators and have high application value.

[0060] P60: Based on the optimal debugging solution, perform visual maintenance and control of the tested part.

[0061] Optionally, based on the optimal debugging scheme, visual maintenance and control of the tested part is performed. During the execution process, a visual interface is used to intuitively display the control steps and real-time data. Charts, dashboards, dynamic demonstrations and other forms are used to help operators understand and execute the control scheme. First, a detailed maintenance and control plan can be formulated based on the optimal debugging scheme. This plan not only includes repair measures for specific fault points, but also covers the necessary adjustments to optimize the overall performance of the equipment. By clarifying the goals, methods and expected results of each step of the operation, clear guidance is provided for subsequent maintenance and control work.

[0062] Next, advanced visualization technology is used to intuitively present the maintenance and control process. Visualization technology simplifies the complex equipment structure and maintenance and control process into an easy-to-understand and easy-to-operate interface through various forms such as graphics, images, and animations. Operators only need to use interactive devices such as touch screens and mice to complete operations such as monitoring equipment status, adjusting control parameters, and sending maintenance instructions. In the process of performing maintenance and control, with the help of real-time data monitoring and feedback mechanisms. Through various sensors and monitoring devices installed on the tested parts, the operating status and performance parameters of the equipment are obtained in real time. Provide an important reference basis for maintenance and control, and promptly discover and correct possible deviations and errors. Once an abnormal situation is detected, the system will immediately issue an alarm and automatically or assist the operator to take corresponding countermeasures.

[0063] During this process, full utilization of advanced technical means such as visualization technology, real-time data monitoring and feedback mechanism, emergency plan and rapid response mechanism was made to ensure the accuracy, efficiency and safety of maintenance and control.

[0064] In summary, the embodiments of the present application have at least the following technical effects:

[0065] The present application performs hydraulic adjustment tests and conducts multivariate data collection to obtain a multivariate monitoring data set of the test piece under various temperature conditions. Based on multiple edge computing units, key indicators are extracted to obtain a multivariate diagnostic indicator set, and multivariate data fusion and fault diagnosis and location are performed. Based on the fault diagnosis results of the test piece, a virtual control test is performed to generate an optimal debugging plan and perform visual maintenance and control of the test piece.

[0066] The technical effect of conducting comprehensive fault diagnosis based on multivariate monitoring data and improving the accuracy of fault location and test piece control precision has been achieved.

[0067] Embodiment 2

[0068] Based on the same inventive concept as the visual measurement and control method for maintenance and debugging in the aforementioned embodiment, Figure 3 As shown, the present application provides a visual measurement and control system for maintenance and debugging, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0069] The performance test module 11 is used to perform hydraulic adjustment tests under various temperature conditions on the tested part and to perform dynamic demonstrations through a dynamic demonstration interface;

[0070] The data acquisition module 12 is used to collect multivariate data during the hydraulic adjustment test process, including collecting hydraulic sensor data sets, electronic sensor data sets and mechanical sensor data sets, obtaining multivariate monitoring data sets of the tested part under various temperature conditions, and visually displaying them through a data monitoring interface;

[0071] The edge processing module 13 is used to extract key indicators for the multivariate monitoring data set according to the multiple edge computing units to obtain a multivariate diagnostic indicator set;

[0072] A fault diagnosis module 14 is used to perform multivariate data fusion and fault diagnosis positioning based on the multivariate diagnosis indicator set, obtain the fault diagnosis result of the tested device, and display it through a fault diagnosis interface;

[0073] A maintenance and debugging module 15 is used to perform virtual control tests according to the fault diagnosis results of the tested component and generate an optimal debugging solution;

[0074] The visual maintenance control module 16 is used to perform visual maintenance control of the tested device based on the optimal debugging solution.

[0075] Furthermore, the data acquisition module 12 is also used to perform the following steps:

[0076] Based on the multiple temperature conditions, multiple test conditions are generated; the data acquisition module includes a hydraulic sensor module, an electronic sensor module and a mechanical sensor module; for the multiple test conditions, multi-channel synchronous data acquisition is performed based on the hydraulic sensor module, the electronic sensor module and the mechanical sensor module respectively to obtain the hydraulic sensor data set, electronic sensor data set and mechanical sensor data set under different test conditions.

[0077] Furthermore, the edge processing module 13 is further configured to perform the following steps:

[0078] An edge computing unit architecture is constructed, wherein the edge computing unit architecture includes multiple edge computing units corresponding to the hydraulic system, the electronic system and the mechanical system respectively; data preprocessing is performed on the multivariate monitoring data set according to the multiple edge computing units to obtain a multivariate calibration data set; feature extraction is performed based on the multivariate calibration data set to obtain time domain features, frequency domain features and time-frequency domain features; the time domain features, frequency domain features and time-frequency domain features are comprehensively analyzed to extract key indicators of the hydraulic system, the electronic system and the mechanical system; a multivariate diagnostic indicator set is constructed based on the key indicators of the hydraulic system, the electronic system and the mechanical system.

[0079] Furthermore, the fault diagnosis module 14 is also used to perform the following steps:

[0080] Based on the multi-element diagnostic indicator set, the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system are extracted; using the key indicators of the hydraulic system, the key indicators of the electronic system and the key indicators of the mechanical system, fault identification is performed separately through a pre-trained fault identification subnetwork to obtain corresponding multiple single diagnostic results; based on the multiple single diagnostic results, fault fusion positioning is performed through a comprehensive fault judgment unit to obtain the fault diagnosis result of the test component.

[0081] Furthermore, the fault diagnosis module 14 is also used to perform the following steps:

[0082] Based on the fault impact analysis of the hydraulic system, the electronic system and the mechanical system, a multi-system fault propagation map is constructed and embedded in the comprehensive fault judgment unit; according to the multi-system fault propagation map, the multiple single diagnosis results are subjected to conflict analysis to obtain a fault conflict analysis result; based on a preset priority sorting, the fault conflict analysis results are fused and resolved to obtain a fault fusion weight; through the fault fusion weight, the multiple single diagnosis results are fused and located to obtain the fault diagnosis result of the tested component.

[0083] Furthermore, the maintenance and debugging module 15 is also used to perform the following steps:

[0084] According to the fault diagnosis result of the device under test, key influencing factors are extracted; based on the key influencing factors, a control optimization space is constructed, and control parameters are adjusted in the control optimization space to generate multiple alternative control schemes; multiple performance indicators are obtained, and the multiple alternative control schemes are balanced and optimized to obtain multiple preferred debugging schemes; a virtual model of the device under test is established, and a virtual control test is performed on the multiple preferred debugging schemes to obtain multiple control performance indicators, and based on the multiple control performance indicators, the optimal debugging scheme is obtained.

[0085] Furthermore, the maintenance and debugging module 15 is also used to perform the following steps:

[0086] Based on debugging requirements, multiple performance indicators are obtained, and the multiple performance indicators include but are not limited to response speed, stability, and energy consumption; for the multiple performance indicators, performance weights are configured, and a balance function is constructed; according to the balance function, the multiple alternative control schemes are balanced and optimized to obtain a performance balance degree sequence, and multiple preferred debugging schemes are extracted through the performance balance degree sequence.

[0087] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0089] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A visual measurement and control system for maintenance and debugging, characterized in that: The system comprises: Performance test module, used to perform hydraulic adjustment tests under various temperature conditions on the tested part, and conduct dynamic demonstration through the dynamic demonstration interface; The data acquisition module is used to collect multivariate data during the hydraulic adjustment test process, including collecting hydraulic sensor data sets, electronic sensor data sets and mechanical sensor data sets, obtaining multivariate monitoring data sets of the tested parts under various temperature conditions, and visually displaying them through the data monitoring interface; An edge processing module, configured to extract key indicators for the multivariate monitoring data set according to a plurality of edge computing units, and obtain a multivariate diagnostic indicator set; A fault diagnosis module, used to perform multivariate data fusion and fault diagnosis positioning based on the multivariate diagnosis indicator set, obtain the fault diagnosis result of the tested device, and display it through a fault diagnosis interface; A maintenance and debugging module, used to perform virtual control tests and generate an optimal debugging solution according to the fault diagnosis results of the tested component; The visual maintenance and control module is used to perform visual maintenance and control of the tested part based on the optimal debugging solution.

2. The visual measurement and control system for maintenance and debugging according to claim 1, characterized in that: Based on the data acquisition module, multi-dimensional data acquisition of the hydraulic adjustment test process is carried out, including: Based on the multiple temperature conditions, generating multiple test conditions; The data acquisition module includes a hydraulic sensor module, an electronic sensor module and a mechanical sensor module; For the multiple test conditions, multi-channel synchronous data acquisition is performed based on the hydraulic sensor module, the electronic sensor module and the mechanical sensor module to obtain hydraulic sensor data sets, electronic sensor data sets and mechanical sensor data sets under different test conditions.

3. The visual measurement and control system for maintenance and debugging according to claim 1, characterized in that: According to the plurality of edge computing units, key indicators are extracted for the multivariate monitoring data set to obtain a multivariate diagnostic indicator set, including: Building an edge computing unit architecture, wherein the edge computing unit architecture includes multiple edge computing units corresponding to the hydraulic system, the electronic system, and the mechanical system respectively; According to the plurality of edge computing units, data preprocessing is performed on the multivariate monitoring data set to obtain a multivariate calibration data set; Perform feature extraction based on the multivariate calibration data set to obtain time domain features, frequency domain features, and time-frequency domain features; Comprehensively analyzing the time domain features, frequency domain features and time-frequency domain features, and extracting key indicators of the hydraulic system, the electronic system and the mechanical system; Based on the hydraulic system key indicators, the electronic system key indicators and the mechanical system key indicators, a multivariate diagnostic indicator set is constructed.

4. The visual measurement and control system for maintenance and debugging as claimed in claim 3, characterized in that: Based on the multivariate diagnostic indicator set, multivariate data fusion and fault diagnosis positioning are performed to obtain the fault diagnosis result of the tested device, including: Based on the multivariate diagnostic indicator set, extracting the hydraulic system key indicators, the electronic system key indicators and the mechanical system key indicators; Using the hydraulic system key indicators, the electronic system key indicators and the mechanical system key indicators, the pre-trained fault identification sub-network is used to perform fault identification respectively to obtain corresponding multiple single diagnosis results; Based on the multiple individual diagnosis results, a comprehensive fault determination unit is used to perform fault fusion positioning to obtain the fault diagnosis result of the device under test.

5. The visual measurement and control system for maintenance and debugging as claimed in claim 4, characterized in that: Based on the multiple single diagnosis results, a comprehensive fault determination unit is used to perform fault fusion location to obtain the fault diagnosis result of the device under test, including: Perform fault impact analysis based on hydraulic system, electronic system and mechanical system, construct multi-system fault propagation mapping and embed it in the comprehensive fault determination unit; According to the multi-system fault propagation mapping, the plurality of single diagnosis results are subjected to conflict analysis to obtain a fault conflict analysis result; Based on a preset priority ranking, the fault conflict analysis results are integrated and resolved to obtain a fault integration weight; The multiple individual diagnosis results are fused and located by using the fault fusion weight to obtain the fault diagnosis result of the device under test.

6. The visual measurement and control system for maintenance and debugging according to claim 1, characterized in that: According to the fault diagnosis result of the tested device, a virtual control test is performed to generate an optimal debugging solution, including: Extracting key influencing factors according to the fault diagnosis result of the tested device; Based on the key influencing factors, a control optimization space is constructed, and control parameters are adjusted in the control optimization space to generate multiple alternative control schemes; Acquire multiple performance indicators, balance and optimize the multiple alternative control schemes, and obtain multiple preferred debugging schemes; A virtual model of the device under test is established, a virtual control test is performed on the multiple preferred debugging schemes, a multiple control performance indicators are obtained, and based on the multiple control performance indicators, the optimal debugging scheme is obtained.

7. The visual measurement and control system for maintenance and debugging according to claim 6, characterized in that: Obtain multiple performance indicators, balance and optimize the multiple alternative control schemes, and obtain multiple preferred debugging schemes, including: Based on the debugging requirements, multiple performance indicators are obtained, including but not limited to response speed, stability, and energy consumption; For the multiple performance indicators, configure performance weights and construct a balancing function; According to the balance function, the multiple alternative control schemes are balanced and optimized to obtain a performance balance degree sequence, and multiple preferred debugging schemes are extracted through the performance balance degree sequence.

8. A visual measurement and control method for maintenance and debugging, characterized in that: The method comprises: Perform hydraulic adjustment tests under various temperature conditions on the tested parts, and conduct dynamic demonstrations through the dynamic demonstration interface; Perform multivariate data collection during the hydraulic adjustment test process, including collecting hydraulic sensor data sets, electronic sensor data sets, and mechanical sensor data sets, obtaining multivariate monitoring data sets of the tested parts under various temperature conditions, and visually displaying them through the data monitoring interface; Extract key indicators from the multivariate monitoring data set according to the plurality of edge computing units to obtain a multivariate diagnostic indicator set; Based on the multivariate diagnostic indicator set, multivariate data fusion and fault diagnosis positioning are performed to obtain the fault diagnosis result of the tested device, and the result is displayed through the fault diagnosis interface; According to the fault diagnosis result of the tested device, a virtual control test is performed to generate an optimal debugging solution; Based on the optimal debugging solution, visual maintenance and regulation of the tested part is performed.

Images