Automobile brake pad wear resistance detection method and system based on knowledge graph

Abstract

The invention provides a knowledge graph-based automobile brake pad wear resistance detection method, which comprises the following steps of: firstly, constructing a brake pad wear resistance knowledge graph according to a brake pad wear resistance knowledge base; the multiple key indexes influencing the wear resistance of the brake pad and the importance association relation among the key indexes can be effectively obtained through the brake pad wear resistance knowledge graph, and the knowledge extraction efficiency is greatly improved; secondly, a cylinder detection result view model is constructed based on multiple groups of brake pad wear resistance detection results of multiple key indexes, visual display of detection result data is realized, and visual and effective screening of the brake pad wear resistance detection result data is realized through calculation of the cylindricity of the view model. In combination with the editing operation on the cylinder detection result view model on the user interface, the intuition and operability of data screening are improved, and the high-standard requirements on the empirical and technical properties of testers are greatly reduced.

Description

Technical Field

[0001] The present application relates to the technical field of the present invention related to the detection of wear resistance of automobile brake pads, and in particular to a method for detecting wear resistance of automobile brake pads based on a knowledge graph. Background Art

[0002] Knowledge graph is a modern theory that combines the theories and methods of applied mathematics, graphics, information visualization technology, information science and other disciplines with methods such as citation analysis and co-occurrence analysis in metrology, and uses visual graphs to vividly display the core structure, development history, frontier fields and overall knowledge architecture of disciplines to achieve the purpose of multidisciplinary integration. It displays complex knowledge fields through data mining, information processing, knowledge metrology and graph drawing, reveals the dynamic development laws of knowledge fields, and provides practical and valuable references for disciplinary research.

[0003] Wear resistance is one of the important indicators to measure the quality of brake pads. High-quality brake pads usually use advanced friction materials and manufacturing processes, which can maintain stable friction performance and reduce wear in long-term use. The wear resistance of brake pads is affected by many factors such as material and usage conditions.

[0004] In the prior art, the wear resistance test of brake pads mainly focuses on the improvement of wear resistance test devices. For example, document CN118858323A discloses a wear resistance test device for electric vehicle brake pads, which can realize simultaneous detection of multiple samples, facilitate installation and disassembly, and improve detection efficiency. This hardware structure improvement is relatively mature, while improvements to the wear resistance test method of brake pads based on wear resistance test devices are relatively rare, especially the visualization and intelligent screening of test results of the wear resistance test method of brake pads during the test process, which results in high standards for the experience and technical skills of test personnel during the wear resistance test of brake pads. Therefore, it is necessary to propose a wear resistance test method for automobile brake pads based on knowledge graphs to solve the above problems. Summary of the invention

[0005] In order to solve the technical problem that the wear resistance performance testing process of brake pads in the prior art requires high standards of experience and technical skills of test personnel and cannot realize visual and intelligent screening of test results, the present invention provides a wear resistance performance testing method for automobile brake pads based on a knowledge graph, and the method comprises the following steps: Step S1, constructing a brake pad wear resistance performance knowledge base according to the brake pad wear resistance performance detection data file, and performing information extraction, knowledge fusion and knowledge processing on the brake pad wear resistance performance knowledge base to construct a brake pad wear resistance performance knowledge graph; Step S2, extracting multiple key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performing a brake pad wear resistance test based on the multiple key indicators, and obtaining multiple groups of brake pad wear resistance test results; Step S3, constructing a cylinder test result view model according to the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, wherein the cylinder test result view model takes the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylinder test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result; Step S4, calculating the cylindricity of the cylinder detection result view model, and determining whether the cylindricity is greater than a first threshold value, if yes, executing step S5, otherwise, saving multiple groups of brake pad wear resistance performance test results of the multiple key indicators; Step S5, delete a set of test results that have the greatest impact on the cylindricity, update the cylinder test result view model, and calculate the cylindricity of the updated cylinder test result view model; re-judge whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, save multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder test result view model after the last update.

[0006] As a preferred implementation, the multiple key indicators include any two or more of the following: Material, friction coefficient, wear rate, hardness, thermal decay, noise level, life span, and running-in period.

[0007] As a preferred implementation, the cylindrical test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, and further includes: Obtain the projection circle of the cylinder detection result view model on the xoy coordinate plane and the multiple key indicators, and evenly mark the multiple key indicators at the corresponding marking positions of the projection circle; Standardize the values ​​of each group of the brake pad wear resistance test results, mark the values ​​of the standardized test results at the corresponding marked positions of the projected circle, the size of the values ​​is proportional to the radius of the projected circle at the corresponding marked position, and draw the projected circle of the current group of test results with the radius of the projected circle and the radii of all the marked positions; The projected circles of all groups of detection results are arranged in sequence at unit distances along the Z-axis direction, and the cylinder detection result view model is constructed based on all the projected circles.

[0008] As a preferred implementation, the multiple key indicators are evenly marked on the corresponding marking positions of the projected circle, specifically including: Acquire indicator attributes and indicator quantities of the multiple key indicators, cluster the multiple key indicators according to the indicator attributes, and arrange the key indicators according to the clustering results; The arranged key indicators are evenly marked on the corresponding marking positions of the projected circle according to the number of indicators.

[0009] As a preferred implementation, clustering the multiple key indicators according to the indicator attributes and arranging the key indicators according to the clustering results specifically includes: Based on the brake pad wear resistance knowledge graph, cluster analysis is performed on the multiple key indicators according to the indicator attributes to obtain a classification result of each key indicator and an indicator weight of each key indicator in the classification result; All key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is, and all the sorted key indicators of the same type are combined to obtain the arrangement result of the key indicators.

[0010] As a preferred implementation, a cylinder test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, further comprising: Obtaining the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results; calculating the ratio of the number of groups to the number of indicators, and if the ratio is greater than a second threshold, distributing each group of brake pad wear resistance test results on the same horizontal plane of the side surface of the cylinder, and each of the key indicators is distributed on the side surface of the cylinder along the z-axis direction; If the ratio is not greater than the second threshold, each set of brake pad wear resistance test results are distributed on the side surface of the cylinder along the z-axis direction, and each of the key indicators is distributed on the same horizontal plane of the side surface of the cylinder.

[0011] As a preferred embodiment, it also includes: Obtaining a user's editing trigger operation on the cylinder detection result view model to perform rotation, scaling, and stretching operations on the cylinder detection result view model; The user's editing trigger operation on the identification position corresponding to the detection result in the cylinder detection result view model is obtained to drag, add or delete the identification position.

[0012] As another embodiment, the present invention provides a knowledge graph-based automobile brake pad wear resistance detection system, the system comprising the following modules: A knowledge graph construction module constructs a brake pad wear resistance performance knowledge base based on the brake pad wear resistance performance test data file, and performs information extraction, knowledge fusion and knowledge processing on the brake pad wear resistance performance knowledge base to construct a brake pad wear resistance performance knowledge graph; A test result acquisition module extracts a plurality of key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performs a brake pad wear resistance test based on the plurality of key indicators, and obtains a plurality of groups of brake pad wear resistance test results; A test result view model construction module is used to construct a cylinder test result view model according to the standardized test results of multiple groups of brake pad wear resistance of the multiple key indicators. The cylinder test result view model takes the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylinder test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result; A view model cylindricity calculation module is used to calculate the cylindricity of the cylinder detection result view model, and determine whether the cylindricity is greater than a first threshold value. If so, the detection result update module is executed; otherwise, multiple groups of brake pad wear resistance test results of the multiple key indicators are saved; A detection result updating module deletes a set of detection results that have the greatest impact on the cylindricity, updates the cylinder detection result view model, and calculates the cylindricity of the updated cylinder detection result view model; re-determines whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, saves multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder detection result view model after the last update.

[0013] As a preferred implementation, the multiple key indicators include any two or more of the following: Material, friction coefficient, wear rate, hardness, thermal decay, noise level, life span, and running-in period.

[0014] As a preferred implementation, the cylindrical test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, and further includes: Obtain the projection circle of the cylinder detection result view model on the xoy coordinate plane and the multiple key indicators, and evenly mark the multiple key indicators at the corresponding marking positions of the projection circle; Standardize the values ​​of each group of the brake pad wear resistance test results, mark the values ​​of the standardized test results at the corresponding marked positions of the projected circle, the size of the values ​​is proportional to the radius of the projected circle at the corresponding marked position, and draw the projected circle of the current group of test results with the radius of the projected circle and the radii of all the marked positions; The projected circles of all groups of detection results are arranged in sequence at unit distances along the Z-axis direction, and the cylinder detection result view model is constructed based on all the projected circles.

[0015] As a preferred implementation, the multiple key indicators are evenly marked on the corresponding marking positions of the projected circle, specifically including: Acquire indicator attributes and indicator quantities of the multiple key indicators, cluster the multiple key indicators according to the indicator attributes, and arrange the key indicators according to the clustering results; The arranged key indicators are evenly marked on the corresponding marking positions of the projected circle according to the number of indicators.

[0016] As a preferred implementation, clustering the multiple key indicators according to the indicator attributes and arranging the key indicators according to the clustering results specifically includes: Based on the brake pad wear resistance knowledge graph, cluster analysis is performed on the multiple key indicators according to the indicator attributes to obtain a classification result of each key indicator and an indicator weight of each key indicator in the classification result; All key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is, and all the sorted key indicators of the same type are combined to obtain the arrangement result of the key indicators.

[0017] As a preferred implementation, a cylinder test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, further comprising: Obtaining the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results; calculating the ratio of the number of groups to the number of indicators, and if the ratio is greater than a second threshold, distributing each group of brake pad wear resistance test results on the same horizontal plane of the side surface of the cylinder, and each of the key indicators is distributed on the side surface of the cylinder along the z-axis direction; If the ratio is not greater than the second threshold, each set of brake pad wear resistance test results are distributed on the side surface of the cylinder along the z-axis direction, and each of the key indicators is distributed on the same horizontal plane of the side surface of the cylinder.

[0018] As a preferred embodiment, it also includes: Obtaining a user's editing trigger operation on the cylinder detection result view model to perform rotation, scaling, and stretching operations on the cylinder detection result view model; The user's editing trigger operation on the identification position corresponding to the detection result in the cylinder detection result view model is obtained to drag, add or delete the identification position.

[0019] As another embodiment, the present invention provides a device for detecting the wear resistance of automobile brake pads based on a knowledge graph, and the system executes the method for detecting the wear resistance of automobile brake pads based on a knowledge graph.

[0020] As another embodiment, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program executes the knowledge graph-based automobile brake pad wear resistance detection method.

[0021] It can be seen that the present invention provides a method and system for detecting the wear resistance of automobile brake pads based on a knowledge graph. Firstly, a knowledge graph of the wear resistance of brake pads is constructed according to a knowledge base of the wear resistance of brake pads. Through the knowledge graph of the wear resistance of brake pads, multiple key indicators affecting the wear resistance of brake pads and the importance correlation relationship between the key indicators can be effectively obtained, which greatly improves the efficiency of knowledge extraction; secondly, a cylindrical detection result view model can be quickly and conveniently constructed based on multiple groups of brake pad wear resistance test results of multiple key indicators, which realizes the three-dimensional visualization display of the test result data and improves the intuitiveness of the display of the test result data; and the visualization and intelligent screening of the brake pad wear resistance test result data are realized through the calculation of the cylindricality of the view model, which greatly reduces the high standards of experience and technical requirements for test personnel in the detection process; combined with the editing operation of the cylindrical detection result view model on the user interface, the flexibility of data screening is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments and the description of the prior art will be briefly introduced below. 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 paying creative work.

[0023] Figure 1 It is a schematic diagram of the cylinder detection result view model display effect of the present invention; Figure 2 It is a structural schematic diagram of the automobile brake pad wear resistance detection system based on the knowledge graph of the present invention; Figure 3It is a schematic diagram of the display effect of projecting a circle in the cylinder detection result view model of the present invention. DETAILED DESCRIPTION

[0024] The embodiments of the present invention are further described below with reference to the accompanying drawings.

[0025] Embodiment 1: The present invention provides a method for detecting the wear resistance of automobile brake pads based on a knowledge graph, and the method comprises the following steps: Step S1, construct a brake pad wear resistance knowledge base based on the brake pad wear resistance test data file, extract information, fuse knowledge and process knowledge on the brake pad wear resistance knowledge base to construct a brake pad wear resistance knowledge graph; it should be noted that the brake pad wear resistance test data file can be a collection of historical test data files, or a file resource related to the brake pad wear resistance test data extracted from an online resource library or paper library such as the Internet, which is not limited here; and construct a brake pad wear resistance knowledge base through a large number of brake pad wear resistance test data files. On this basis, extract information, fuse knowledge and process knowledge on the brake pad wear resistance knowledge base to construct a brake pad wear resistance knowledge graph. The knowledge graph of the present invention consists of three components, namely, entity, relationship and attribute; wherein, entity refers to the relevant documents, paragraphs or sentences that record the impact on the wear resistance of the brake pad; relationship is the interaction or connection between the above entities. For example, the association, dependency, subordination or other types of relationships between two entities; attributes refer to indicators that affect the wear resistance of brake pads, such as material, friction coefficient, wear rate, hardness, thermal decay, noise level, life, and running-in period. The entities, relationships and attributes in the knowledge graph of the present invention can also be constructed in the following way: entities refer to indicators that affect the wear resistance of brake pads, relationships are the interactions or connections between the above indicators, and attributes refer to the correlation weights between the above indicators.

[0026] Step S2, extracting multiple key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performing brake pad wear resistance testing based on the multiple key indicators, and obtaining multiple groups of brake pad wear resistance testing results; it should be noted that, since the knowledge graph records several indicators that affect the wear resistance of the brake pad, these indicators have different effects on the wear resistance of the brake pad, or some indicators have an erroneous effect on the wear resistance of the brake pad, that is, irrelevant indicators are also recorded in the knowledge graph, and therefore it is necessary to screen key indicators to reduce the impact of irrelevant or weakly correlated indicators on the detection test. Specifically, multiple key indicators that affect the wear resistance of the brake pad can be extracted from the brake pad wear resistance knowledge graph. For example, from the attributes of the indicators that affect the wear resistance of the brake pads in the knowledge graph, the indicators with a large number of occurrences or record strength are extracted as key indicators, or from the attributes of the entities that identify the indicators that affect the wear resistance of the brake pads and the association weights between the entities, the indicators with large weights are extracted as key indicators; it can also be other multiple key indicators that affect the wear resistance of the brake pads extracted from the knowledge graph, which can be adjusted during use or for specific projects, and are not limited here. Then, the wear resistance of the brake pads is tested on the existing brake pad wear resistance testing device according to the multiple key indicators, so as to obtain multiple groups of brake pad wear resistance test results; it should be emphasized that the above-mentioned brake pad wear resistance testing device has a sensor component that can detect the above-mentioned key indicators, and the sensor component that detects the above-mentioned key indicators is a sensor device in the prior art, which will not be described in detail here.

[0027] Step S3, construct a cylinder test result view model based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, the cylinder test result view model uses the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylinder test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result. It should be noted that in order to realize the intuitive display and intuitive and efficient screening of the multiple groups of test results of the above-mentioned multiple key indicators, it is first necessary to perform standardized operations on the multiple groups of test results of the multiple key indicators to be displayed, for example, perform data preprocessing such as error correction, completion, and normalization to ensure the accuracy and displayability of the data to be displayed. It should be emphasized that the above-mentioned normalization operation of the present invention can be a normalization operation performed once for each identical key indicator in all groups of detection result data; and in order to avoid the adverse effects of jump data on subsequent model construction, preferably, a group of detection result data corresponding to the jump data is deleted to prevent the adverse visual effects caused by excessive surface deformation of the cylindrical detection result view model.

[0028] Then, the present invention innovatively presents and filters the multiple groups of brake pad wear resistance test results of the multiple key indicators by constructing a cylindrical test result view model, such as Figure 1 As shown, the cylinder detection result view model is in the shape of a cylinder. The cylinder detection result view model can be implemented based on three-dimensional view software such as AutoCAD, 3Dmax, UG, etc. and combined with data import and editing plug-ins / components that come with the view software or are developed by a third party, which will not be described in detail here; and the xoy coordinate plane is used as the bottom surface, the origin o is used as the bottom surface circle center, and the z-axis direction is used as the cylinder axis center. Among them, each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface. The figure shows three horizontal sections of the cylinder, which are marked in green, pink and light yellow respectively; the intersection circle of the three horizontal sections and the cylinder is parallel to the xoy coordinate plane, and the intersection circle is called the projection circle, and one group of brake pad wear resistance test results is evenly arranged on the edge of the projection circle; at this time, in the three-dimensional coordinate system, the key indicators marked at the marking position of the same z coordinate value belong to the same group of test results.

[0029] Furthermore, in order to improve the intuitiveness of the inspection personnel's observation of the inspection results, and more importantly, to reduce the impact of the inspection result values ​​on the degree of concavity of the side surface of the cylinder after the corresponding positions are marked (the distance between the above-mentioned projected circles is the unit distance), preferably, the present invention distributes each of the key indicators along the z-axis direction on the side surface of the cylinder, that is, in the three-dimensional coordinate system, the key indicators marked at the marking positions with (approximately) the same xy coordinate values ​​on the side surface of the cylinder are the same.

[0030] In addition, since it is necessary to identify the size of the value of the detection result at the corresponding identification position by the coordinate value, in this embodiment, the z coordinate of the identification position in the three-dimensional coordinate system is used to identify the group to which the key indicator belongs, and the xy coordinate of the identification position in the three-dimensional coordinate system is used to identify the value of the key indicator; since the value is a normalized value, its size is often not equal to 1, therefore, assuming that the radius of the projected circle is a unit length R=1, the actual identification position of the key indicator is the coordinate of the actual length position in the direction of the radius on the initial position of the projected circle where the key indicator is located, wherein the initial position is the position of the identification corresponding to the current key indicator in a plurality of positions uniformly distributed on the projected circle in advance; thus, the visual effect presented is that the movement (i.e. stretching or compression) of the above-mentioned actual identification position relative to the initial position will cause the concave-convex deformation of the side surface of the cylinder; obviously, the cylinder detection result view model presents a concave-convex arc on the side surface of the cylinder according to the value of the detection result. In addition, the radius of the projected circle can also be set to other set values ​​according to actual needs, which are not limited here.

[0031] Step S4, calculate the cylindricity of the cylinder detection result view model, determine whether the cylindricity is greater than the first threshold value, if yes, execute step S5, otherwise, save the multiple groups of brake pad wear resistance test results of the multiple key indicators; it should be noted that in order to achieve the screening of the test results based on the cylinder detection result view model, thereby improving the intuitiveness and efficiency of the screening of the test results. The present invention innovatively adopts a method for screening test results based on cylindricity on the basis of the cylinder detection result view model. Since all groups of test results and their indicators have been marked on the surface of the cylinder detection result view model, and the size of the test value is marked by the concave and convex deformation of the side of the cylinder, the screening of the test result data can be achieved by calculating the cylindricity of the cylinder detection result view model. Specifically, the cylindricity of the cylinder test result view model is calculated, that is, the ratio of the difference between the maximum coaxial inscribed cylindrical radius and the minimum coaxial circumscribed cylindrical radius to the radius R of the projected circle. The closer the ratio is to 0, the smaller the cylindricity and the smaller the difference in the test results; the larger the ratio is, the larger the cylindricity and the larger the difference in the test results. Then, in order to measure it, a first threshold value can be set, for example, the first threshold value is 0.2 or 0.4, so as to determine whether the cylindricity is greater than the first threshold value. If so, the difference in the test results is greater, so that the further screening process of the subsequent test results is performed; otherwise, it indicates that the difference in the test results is small and meets the requirements, so that the multiple groups of brake pad wear resistance test results of the multiple key indicators are saved.

[0032] Step S5, delete a set of test results that have the greatest impact on the cylindricity, update the cylinder test result view model, and calculate the cylindricity of the updated cylinder test result view model; re-judge whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, save multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder test result view model after the last update. It should be noted that, when it is judged that the cylindricity is greater than the first threshold, the difference in the test results is too large, and the test results with larger deviations need to be deleted. Specifically, a group of test results that have the greatest impact on the cylindricity are deleted, for example, the test results corresponding to the projected circle in contact with the maximum coaxial inscribed cylinder and / or the minimum coaxial circumscribed cylinder are deleted; after deleting the test results and their corresponding projected circles, the cylinder test result view model can be updated, that is, the above-mentioned projected circle and the test results marked at the corresponding positions are deleted from the cylinder test result view model; then, the cylindricity of the updated cylinder test result view model is calculated, and the method for calculating the cylindricity is the same as the aforementioned step S4, which will not be repeated here. Finally, re-determine whether the cylindricity is greater than the first threshold; repeat the aforementioned deletion, update, and judgment process in sequence until the cylindricity is not greater than the first threshold, at which time the remaining groups of test results marked on the cylinder test result view model updated for the last time have small errors / differences, thereby meeting the test result screening requirements. Therefore, multiple groups of brake pad wear resistance test results of the multiple key indicators identified by the cylinder test result view model after the last update are saved, thereby realizing visual identification and screening of the test results, providing intuitiveness and efficiency in the screening of the test results, and reducing the experience and technical requirements for testers.

[0033] As a preferred embodiment, the multiple key indicators include any two or more of the following: material, friction coefficient, wear rate, hardness, thermal decay, noise level, life, and running-in period; the above-mentioned technical parameters affecting the wear resistance of brake pads are common technical parameters in the field and no further explanation is required.

[0034] As a preferred implementation, the cylindrical test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, and further includes: Obtain the projection circle of the cylinder detection result view model on the xoy coordinate plane and the multiple key indicators, and evenly mark the multiple key indicators on the corresponding identification positions of the projection circle; it should be noted that each group of detection results corresponds to a projection circle, and all the key indicators of this group of detection results are evenly distributed on the circumference of the projection circle according to the number of key indicators and the circumference of the projection circle. The purpose of even distribution is not only the aesthetics of the even distribution, but more importantly, the movement (i.e. stretching or compression) of the actual identification position relative to the initial position after the corresponding numerical value of the key indicator is assigned to the corresponding identification position of the key indicator under the even distribution will cause the concave-convex deformation of the side of the cylinder. Under the even distribution, this concave-convex deformation will be more stable, and the position of the tangent point under the stable change will also be more accurate, so that the calculation accuracy is higher when determining the above-mentioned maximum coaxial inscribed cylinder and the minimum coaxial circumscribed cylinder, thereby ensuring the accuracy of the detection result screening.

[0035] Standardize the values ​​of each group of brake pad wear resistance test results, mark the standardized test results at the corresponding marked position of the projection circle, the size of the value is proportional to the radius of the projection circle at the corresponding marked position, and draw the projection circle of the current group of test results with the radius of the projection circle and the radii of all the marked positions. It should be noted that it is necessary to standardize the multiple groups of test results of multiple key indicators to be displayed, for example, perform data preprocessing such as error correction, completion, and normalization to ensure the accuracy and displayability of the data to be displayed. Figure 3 As shown, the numerical value of the normalized test result is marked on the corresponding marking position (8 marking positions corresponding to the blue dots) of the projected circle (the circle with a radius of R in the figure), and the size of the numerical value is proportional to the radius of the projected circle at the corresponding marking position. For example, at the marking position directly above the center of the circle, the corresponding value of the key indicator of the marking position is 1.2, then the final position of the marking position is the position directly above the center of the circle with a distance of 1.2R, as shown in FIG. Figure 3 The black dot marks the position. Then, the black mark position and the projected circle are used as tangents to mark the final mark position of the protruding component; in a similar manner, the projected circle of the current group of detection results is drawn with the radius of the projected circle and the radius of all the mark positions, and finally a projection circle with concave and convex deformation is formed.

[0036] The projected circles of all groups of detection results are arranged in sequence at a unit distance along the Z-axis direction, and the cylindrical detection result view model is constructed based on all the projected circles. It should be noted that a similar method to the above is used to form the projection circles of concave and convex deformations corresponding to all detection results, and the projection circles of all groups of detection results are arranged in sequence at a unit distance along the Z-axis direction. After all the projection circles of concave and convex deformations are arranged, a cylindrical detection result view model is constructed based on these projection circles, wherein the upper and lower bottom surfaces of the cylindrical detection result view model are the original projection circles, and all the projection circles of concave and convex deformations are surrounded by a side cylinder, and a method similar to the projection circle concave and convex method is used to construct the concave and convex cross-section of the cylindrical side where the final identification position of each concave and convex is located, which will not be elaborated here; thereby, a cylindrical detection result view model with a cylindrical side with concave and convex deformations is realized, Figure 1 Not shown.

[0037] As a preferred implementation, the multiple key indicators are evenly marked on the corresponding marking positions of the projected circle, specifically including: Acquire indicator attributes and indicator quantities of the multiple key indicators, cluster the multiple key indicators according to the indicator attributes, and arrange the key indicators according to the clustering results; The key indicators after arrangement are evenly marked on the corresponding marking positions of the projected circle according to the number of indicators. It should be noted that in order to facilitate the inspection personnel to observe the concave and convex shapes presented by each key indicator and its value, and to facilitate the more accurate calculation and positioning of the position of the tangent point under the condition of steady changes, preferably, the present invention clusters the multiple key indicators according to the indicator attributes, and specifically, obtains the indicator attributes and indicator quantity of the multiple key indicators, wherein the indicator attribute is the type of indicator to which the indicator belongs. For example, the time-related indicators life and running-in period, the friction-related indicators friction coefficient and wear rate, so that the key indicators are arranged according to the clustering results, that is, the marking positions corresponding to the above-mentioned similar indicators are arranged adjacently; such an arrangement can facilitate the inspection personnel to observe the concave and convex shapes presented by each key indicator and its value, and to facilitate the more accurate calculation and positioning of the position of the tangent point under the condition of steady changes.

[0038] As a preferred implementation, clustering the multiple key indicators according to the indicator attributes and arranging the key indicators according to the clustering results specifically includes: Based on the knowledge graph of the wear resistance of the brake pad, cluster analysis is performed on the multiple key indicators according to the indicator attributes to obtain the classification result of each key indicator and the indicator weight of each key indicator in the classification result; it should be noted that in order to further ensure the smooth change of the final identification position, the present invention performs cluster analysis on the multiple key indicators based on the knowledge graph of the wear resistance of the brake pad according to the indicator attributes to obtain the classification result of each key indicator and the indicator weight of each key indicator in the classification result. For example, the indicator weight of the friction coefficient related to the friction indicator is set to 0.4, the indicator weight of the wear rate is set to 0.3, the indicator weight of the wear amount is set to 0.2, and the indicator weight of the wear index is set to 0.1; the indicator weight is used to set the relative position of the corresponding indicator in the same category of indicators.

[0039] All key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is, and all key indicators of the same type after sorting are combined to obtain the arrangement result of the key indicators. It should be noted that all key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is. For example, the friction-related indexes are sorted as follows: wear index, wear rate, friction coefficient, wear amount; that is, the index with the largest weight is the most central and the index with the smallest weight is the most side. All indicators of the same type are sorted in a similar way, and then all key indicators of the same type after sorting are combined (i.e., arranged together) to obtain the arrangement result of the key indicators; thereby, the smooth change of the final identification position can be guaranteed.

[0040] As a preferred implementation, a cylinder test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, further comprising: Obtain the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results; calculate the ratio of the number of groups to the number of indicators, and if the ratio is greater than a second threshold, distribute each group of brake pad wear resistance test results on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; it should be noted that since the number of test result groups and the number of key indicators are not fixed, the simultaneous change of the two will have a greater impact on the view effect of the constructed cylinder detection result view model, in order to avoid a single view parameter configuration method resulting in the cylinder detection result view model being too tall or too flat, which is not conducive to observation by detection personnel and lacks aesthetics. To this end, the present invention adaptively adjusts the size of the cylinder test result view model according to the number of test result groups and the number of key indicators; specifically, the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results are obtained; the ratio of the number of groups to the number of indicators is calculated. If the ratio is greater than the second threshold, it indicates that the number of key indicators is relatively large relative to the number of indicators. At this time, each group of brake pad wear resistance test results is distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction. On the contrary, if the ratio is not greater than the second threshold, it indicates that the number of key indicators is relatively large relative to the number of key indicators. At this time, each group of brake pad wear resistance test results is distributed on the cylinder side surface along the z-axis direction, and each of the key indicators is distributed on the same horizontal plane of the cylinder side surface; thereby achieving flexible adjustment of the distribution of indicators on the cylinder, increasing aesthetics, facilitating observation by test personnel, and the construction of concave and convex sides.

[0041] As a preferred embodiment, it also includes: The user's editing trigger operation on the cylinder detection result view model is obtained to rotate, scale, and stretch the cylinder detection result view model; it should be noted that in addition to being able to realize the automatic import of detection data to generate the above-mentioned cylinder detection result view model, the present invention can also set corresponding operation trigger controls for detection personnel to realize rotation, scaling, and stretching operations on the cylinder detection result view model; specifically, the user's editing trigger operation on the identification position corresponding to the detection result in the cylinder detection result view model is obtained to drag, add and delete the identification position; these operations can facilitate the detection personnel to manually modify the attribute information such as the value of the key identification corresponding to the identification position, so as to realize the manual adjustment of the detection result, thereby realizing the modification of the convexity of the concave and convex side; the projection circle and its identification position corresponding values ​​can also be manually added, deleted, checked and modified, and the cylinder detection result view model can also be rotated, scaled, stretched and other operations, which are not limited here.

[0042] It can be seen that the present invention provides a method for detecting the wear resistance of automobile brake pads based on a knowledge graph. Firstly, a knowledge graph of the wear resistance of brake pads is constructed according to a knowledge base of the wear resistance of brake pads. The knowledge graph of the wear resistance of brake pads can effectively obtain multiple key indicators affecting the wear resistance of brake pads and the importance correlation relationship between the key indicators, thereby greatly improving the efficiency of knowledge extraction. Secondly, a cylindrical detection result view model is constructed based on multiple groups of brake pad wear resistance test results of multiple key indicators, thereby realizing a visual display of the test result data. Intuitive and effective screening of the brake pad wear resistance test result data is realized through the calculation of the cylindricality of the view model. Combined with the editing operation of the cylindrical detection result view model on the user interface, the intuitiveness and operability of data screening are improved, thereby greatly reducing the high standard requirements on the experience and technical skills of the test personnel.

[0043] As another example, Figure 2 As shown, the present invention provides a system for detecting the wear resistance of automobile brake pads based on a knowledge graph, and the system includes the following modules: The knowledge graph construction module constructs a brake pad wear resistance performance knowledge base based on the brake pad wear resistance performance test data file, and extracts information, fuses knowledge and processes knowledge on the brake pad wear resistance performance knowledge base to construct a brake pad wear resistance performance knowledge graph; it should be noted that the brake pad wear resistance performance test data file can be a collection of historical test data files, or a file resource related to brake pad wear resistance performance test data extracted from online resource libraries and paper libraries such as the Internet, and there is no restriction here; and a brake pad wear resistance performance knowledge base is constructed through a large number of brake pad wear resistance performance test data files. On this basis, the brake pad wear resistance knowledge base is subjected to information extraction, knowledge fusion and knowledge processing to construct a knowledge graph of brake pad wear resistance. The knowledge graph of the present invention is composed of three components, namely entities, relationships and attributes; wherein entities refer to relevant documents, paragraphs or sentences that record the impact on the wear resistance of brake pads; relationships are the interactions or connections between the above entities, for example, the correlation, dependency, subordination or other types of relationships between two entities; attributes refer to indicators that affect the wear resistance of brake pads, for example, material, friction coefficient, wear rate, hardness, thermal decay, noise level, life, and running-in period. The entities, relationships and attributes in the knowledge graph of the present invention can also be constructed in the following manner: entities refer to indicators that affect the wear resistance of brake pads, relationships are the interactions or connections between the above indicators, and attributes refer to the correlation weights between the above indicators.

[0044] The test result acquisition module extracts multiple key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performs brake pad wear resistance testing based on the multiple key indicators, and obtains multiple groups of brake pad wear resistance testing results; it should be noted that since the knowledge graph records several indicators that affect the wear resistance of the brake pad, these indicators have different effects on the wear resistance of the brake pad, or the effects of some indicators on the wear resistance of the brake pad are even incorrect, that is, irrelevant indicators are also recorded in the knowledge graph, and therefore it is necessary to screen key indicators to reduce the impact of irrelevant indicators or weakly correlated indicators on the detection test. Specifically, multiple key indicators that affect the wear resistance of brake pads can be extracted from the knowledge graph of wear resistance of brake pads. For example, indicators with a large number of occurrences or record strengths can be extracted as key indicators based on the attributes of the indicators that affect the wear resistance of brake pads in the knowledge graph, or indicators with large weights can be extracted as key indicators based on the attributes of the entities that identify the indicators that affect the wear resistance of brake pads and the association weights between the entities. It can also be other multiple key indicators that affect the wear resistance of brake pads extracted from the knowledge graph, which are not limited here. Then, the wear resistance of brake pads is tested on the existing brake pad wear resistance testing device based on the multiple key indicators, so as to obtain multiple groups of brake pad wear resistance test results. It should be emphasized that the above-mentioned brake pad wear resistance testing device has a sensor component that can detect the above-mentioned key indicators, and the sensor component that detects the above-mentioned key indicators is a sensor device in the prior art, which will not be described in detail here.

[0045] The test result view model construction module constructs a cylindrical test result view model according to the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators. The cylindrical test result view model takes the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylindrical test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result. It should be noted that in order to realize the intuitive display and intuitive and efficient screening of multiple groups of test results of the above-mentioned multiple key indicators, it is first necessary to perform standardization operations on the multiple groups of test results of the multiple key indicators to be displayed, for example, perform data preprocessing such as error correction, completion, and normalization to ensure the accuracy and presentability of the data to be displayed; it should be emphasized that the above-mentioned normalization operation of the present invention can be a normalization operation for each identical key indicator in all groups of test result data; and in order to avoid the adverse effects of jump data on subsequent model construction, preferably, a group of test result data corresponding to the jump data is deleted to prevent adverse visual effects caused by excessive surface deformation of the cylindrical test result view model. Then, the present invention innovatively presents and screens the multiple groups of brake pad wear resistance test results of the multiple key indicators by constructing a cylindrical test result view model, such as Figure 1As shown, the cylinder detection result view model is in the shape of a cylinder. The cylinder detection result view model can be implemented based on three-dimensional view software such as AutoCAD, 3Dmax, UG, etc. and combined with data import and editing plug-ins / components that come with the view software or are developed by a third party, which will not be described in detail here; and the xoy coordinate plane is used as the bottom surface, the origin o is used as the bottom surface circle center, and the z-axis direction is used as the cylinder axis center. Among them, each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface. The figure shows three horizontal sections of the cylinder, which are marked in green, pink and light yellow respectively; the intersection circle of the three horizontal sections and the cylinder is parallel to the xoy coordinate plane, and the intersection circle is called the projection circle, and one group of brake pad wear resistance test results is evenly arranged on the edge of the projection circle; at this time, in the three-dimensional coordinate system, the key indicators marked at the marking position of the same z coordinate value belong to the same group of test results. Furthermore, in order to improve the intuitiveness of the inspection personnel's observation of the inspection results, and more importantly, to reduce the impact of the inspection result values ​​on the degree of concavity of the side surface of the cylinder after the corresponding positions are marked (the distance between the above-mentioned projected circles is the unit distance), preferably, the present invention distributes each of the key indicators along the z-axis direction on the side surface of the cylinder, that is, in the three-dimensional coordinate system, the key indicators marked at the marking positions with (approximately) the same xy coordinate values ​​on the side surface of the cylinder are the same. In addition, since it is necessary to identify the size of the value of the detection result at the corresponding identification position by the coordinate value, in this embodiment, the z coordinate of the identification position in the three-dimensional coordinate system is used to identify the group to which the key indicator belongs, and the xy coordinate of the identification position in the three-dimensional coordinate system is used to identify the value of the key indicator; since the value is a normalized value, its size is often not equal to 1, therefore, assuming that the radius of the projected circle is a unit length R=1, the actual identification position of the key indicator is the coordinate of the actual length position in the direction of the radius on the initial position of the projected circle where the key indicator is located, wherein the initial position is the position of the identification corresponding to the current key indicator in a plurality of positions uniformly distributed on the projected circle in advance; thus, the visual effect presented is that the movement (i.e. stretching or compression) of the above-mentioned actual identification position relative to the initial position will cause the concave-convex deformation of the side surface of the cylinder; obviously, the cylinder detection result view model presents a concave-convex arc on the side surface of the cylinder according to the value of the detection result. In addition, the radius of the projected circle can also be set to other set values ​​according to actual needs, which are not limited here.

[0046] The view model cylindricity calculation module calculates the cylindricity of the cylinder detection result view model and determines whether the cylindricity is greater than a first threshold value. If so, the detection result update module is executed; otherwise, multiple groups of brake pad wear resistance test results of the multiple key indicators are saved. It should be noted that in order to realize the screening of the test results based on the cylinder detection result view model, thereby improving the intuitiveness and efficiency of the screening of the test results, the present invention innovatively adopts a method for screening the test results based on cylindricity on the basis of the cylinder detection result view model. Since all groups of test results and their indicators have been marked on the surface of the cylinder detection result view model, and the size of the test value is marked by the concave and convex deformation of the side of the cylinder, the cylinder detection result can be calculated. The cylindricity of the view model is used to realize the screening of the test result data; specifically, the cylindricity of the cylindrical test result view model is calculated, that is, the ratio of the difference between the maximum coaxial inscribed cylindrical radius and the minimum coaxial circumscribed cylindrical radius to the radius R of the projected circle. The closer the ratio is to 0, the smaller the cylindricity is, and the smaller the difference in the test results is; the larger the ratio is, the larger the cylindricity is, and the larger the difference in the test results is; then, in order to measure it, a first threshold value can be set, for example, the first threshold value is 0.2 or 0.4, so as to determine whether the cylindricity is greater than the first threshold value. If so, the greater the difference in the test results is, the further screening process of the subsequent test results is performed; otherwise, it indicates that the difference in the test results is small and meets the requirements, thereby saving multiple groups of brake pad wear resistance test results of the multiple key indicators.

[0047] A detection result updating module deletes a set of detection results that have the greatest impact on the cylindricity, updates the cylinder detection result view model, and calculates the cylindricity of the updated cylinder detection result view model; re-determines whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, saves multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder detection result view model after the last update. It should be noted that, when it is judged that the cylindricity is greater than the first threshold, the difference in the detection results is too large, and the detection results with larger deviations need to be deleted. Specifically, a group of detection results that have the greatest impact on the cylindricity are deleted, for example, the detection results corresponding to the projected circle in contact with the maximum coaxial inscribed cylinder and / or the minimum coaxial circumscribed cylinder are deleted; after deleting the detection results and their corresponding projected circles, the cylinder detection result view model can be updated, that is, the above-mentioned projected circle and the detection results marked at the corresponding positions are deleted from the cylinder detection result view model; then, the cylindricity of the updated cylinder detection result view model is calculated, and the method for calculating the cylindricity is the same as the aforementioned step S4, which will not be repeated here. Finally, re-judge whether the cylindricity is greater than the first threshold value; repeat the aforementioned deletion, update, and judgment process in sequence until the cylindricity is no greater than the first threshold value. At this time, the remaining several groups of test results marked on the cylinder test result view model updated last time have relatively small errors / gaps, thereby satisfying the test result screening requirements. Therefore, multiple groups of brake pad wear resistance test results of the multiple key indicators identified by the cylinder test result view model updated last time are saved, thereby realizing visual identification and screening of test results, providing intuitiveness and efficiency in test result screening, and reducing the experience and technical requirements for testers.

[0048] As a preferred embodiment, the multiple key indicators include any two or more of the following: material, friction coefficient, wear rate, hardness, thermal decay, noise level, life, and running-in period; the above-mentioned technical parameters affecting the wear resistance of brake pads are common technical parameters in the field and no further explanation is required.

[0049] As a preferred implementation, the cylindrical test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, and further includes: Obtain the projection circle of the cylinder detection result view model on the xoy coordinate plane and the multiple key indicators, and evenly mark the multiple key indicators on the corresponding identification positions of the projection circle; it should be noted that each group of detection results corresponds to a projection circle, and all the key indicators of this group of detection results are evenly distributed on the circumference of the projection circle according to the number of key indicators and the circumference of the projection circle. The purpose of even distribution is not only the aesthetics of the even distribution, but more importantly, the movement (i.e. stretching or compression) of the actual identification position relative to the initial position after the corresponding numerical value of the key indicator is assigned to the corresponding identification position of the key indicator under the even distribution will cause the concave-convex deformation of the side of the cylinder. Under the even distribution, this concave-convex deformation will be more stable, and the position of the tangent point under the stable change will also be more accurate, so that the calculation accuracy is higher when determining the above-mentioned maximum coaxial inscribed cylinder and the minimum coaxial circumscribed cylinder, thereby ensuring the accuracy of the detection result screening.

[0050] The values ​​of each group of the brake pad wear resistance test results are standardized, and the values ​​of the standardized test results are marked on the corresponding marked positions of the projected circle. The size of the values ​​is proportional to the radius of the projected circle at the corresponding marked positions, and the projection circle of the current group of test results is drawn with the radius of the projected circle and the radii of all the marked positions. It should be noted that it is necessary to perform standardized operations on multiple groups of test results of multiple key indicators to be displayed, for example, perform data preprocessing such as error correction, completion, and normalization to ensure the accuracy and displayability of the data to be displayed; such as Figure 3 As shown, the numerical value of the standardized test result is marked on the corresponding marking position (8 marking positions corresponding to the blue dots) of the projected circle (the circle with a radius of R in the figure), and the size of the numerical value is proportional to the radius of the projected circle at the corresponding marking position. For example, at the marking position directly above the center of the circle, the corresponding value of the key indicator of the marking position is 1.2, then the final position of the marking position is the position directly above the center of the circle with a distance of 1.2R, as shown in FIG. Figure 3 The black dot marks the position as shown; then the black mark position and the projected circle are used as tangents to mark the final protruding position of the component; in a similar manner, the projection circle of the current group of detection results is drawn with the radius of the projection circle and the radius of all the mark positions, and finally a projection circle with concave and convex deformation is formed.

[0051] The projected circles of all groups of detection results are arranged in sequence at a unit distance along the Z-axis direction, and the cylindrical detection result view model is constructed based on all the projected circles. It should be noted that a similar method to the above is used to form the projection circles of concave and convex deformations corresponding to all detection results, and the projection circles of all groups of detection results are arranged in sequence at a unit distance along the Z-axis direction. After all the projection circles of concave and convex deformations are arranged, a cylindrical detection result view model is constructed based on these projection circles, wherein the upper and lower bottom surfaces of the cylindrical detection result view model are the original projection circles, and all the projection circles of concave and convex deformations are surrounded by a side cylinder, and a method similar to the projection circle concave and convex method is used to construct the concave and convex cross-section of the cylindrical side where the final identification position of each concave and convex is located, which will not be elaborated here; thereby, a cylindrical detection result view model with a cylindrical side with concave and convex deformations is realized, Figure 1 Not shown.

[0052] As a preferred implementation, the multiple key indicators are evenly marked on the corresponding marking positions of the projected circle, specifically including: Acquire indicator attributes and indicator quantities of the multiple key indicators, cluster the multiple key indicators according to the indicator attributes, and arrange the key indicators according to the clustering results; The key indicators after arrangement are evenly marked on the corresponding marking positions of the projected circle according to the number of indicators. It should be noted that in order to facilitate the inspection personnel to observe the concave and convex shapes presented by each key indicator and its value, and to facilitate the more accurate calculation and positioning of the position of the tangent point under the condition of steady change, preferably, the present invention clusters the multiple key indicators according to the indicator attributes, specifically, obtains the indicator attributes and indicator quantity of the multiple key indicators, wherein the indicator attribute is the type of indicator to which the indicator belongs, for example, the time-related indicator life and running-in period, the friction-related indicator friction coefficient and wear rate, so as to arrange the key indicators according to the clustering results, that is, the marking positions corresponding to the above-mentioned similar indicators are arranged adjacently; such an arrangement can facilitate the inspection personnel to observe the concave and convex shapes presented by each key indicator and its value, and to facilitate the more accurate calculation and positioning of the position of the tangent point under the condition of steady change.

[0053] As a preferred implementation, clustering the multiple key indicators according to the indicator attributes and arranging the key indicators according to the clustering results specifically includes: Based on the knowledge graph of the wear resistance performance of the brake pad, a cluster analysis is performed on the multiple key indicators according to the indicator attributes to obtain the classification result of each key indicator and the indicator weight of each key indicator in the classification result; it should be noted that in order to further ensure the smooth change of the final identification position, the present invention is based on the knowledge graph of the wear resistance performance of the brake pad, and the multiple key indicators are clustered and analyzed according to the indicator attributes to obtain the classification result of each key indicator and the indicator weight of each key indicator in the classification result. For example, the indicator weight of the friction-related indicator friction coefficient is set to 0.4, the indicator weight of the wear rate is set to 0.3, the indicator weight of the wear amount is set to 0.2, and the indicator weight of the wear index is set to 0.1; the indicator weight is used to set the relative position of the corresponding indicator in the same category.

[0054] All key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is, and all key indicators of the same type after sorting are combined to obtain the arrangement result of the key indicators. It should be noted that all key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is. For example, the friction-related indexes are sorted as follows: wear index, wear rate, friction coefficient, wear amount; that is, the index with the largest weight is the most central and the index with the smallest weight is the most side. All indicators of the same type are sorted in a similar way, and then all key indicators of the same type after sorting are combined (i.e., arranged together) to obtain the arrangement result of the key indicators; thereby, the smooth change of the final identification position can be guaranteed.

[0055] As a preferred implementation, a cylinder test result view model is constructed based on the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, further comprising: Obtain the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results; calculate the ratio of the number of groups to the number of indicators, and if the ratio is greater than a second threshold, distribute each group of brake pad wear resistance test results on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; it should be noted that since the number of test result groups and the number of key indicators are not fixed, the simultaneous change of the two will have a greater impact on the view effect of the constructed cylinder detection result view model, in order to avoid a single view parameter configuration method causing the cylinder detection result view model to be too tall or thin The effect of being too flat is not conducive to the observation of the inspection personnel, and the aesthetics is also insufficient; for this reason, the present invention adaptively adjusts the size of the cylindrical inspection result view model according to the number of groups of inspection results and the number of key indicators; specifically, the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results are obtained; the ratio of the number of groups to the number of indicators is calculated. If the ratio is greater than the second threshold, it indicates that the number of groups of key indicators is relatively large relative to the number of indicators. At this time, each group of brake pad wear resistance test results is distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction. On the contrary, if the ratio is not greater than the second threshold, it indicates that the number of key indicators is relatively large relative to the number of groups of key indicators. At this time, each group of brake pad wear resistance test results is distributed on the cylinder side surface along the z-axis direction, and each of the key indicators is distributed on the same horizontal plane of the cylinder side surface; thereby realizing the flexible adjustment of the distribution of indicators on the cylinder, increasing the aesthetics, facilitating the observation of the inspection personnel and the construction of the concave and convex side surfaces.

[0056] As a preferred embodiment, it also includes: The user's editing trigger operation on the cylinder detection result view model is obtained to rotate, scale, and stretch the cylinder detection result view model; it should be noted that in addition to being able to realize the automatic import of detection data to generate the above-mentioned cylinder detection result view model, the present invention can also set corresponding operation trigger controls for detection personnel to realize rotation, scaling, and stretching operations on the cylinder detection result view model; specifically, the user's editing trigger operation on the identification position corresponding to the detection result in the cylinder detection result view model is obtained to drag, add and delete the identification position; these operations can facilitate the detection personnel to manually modify the attribute information such as the value of the key identification corresponding to the identification position, so as to realize the manual adjustment of the detection result, thereby realizing the modification of the convexity of the concave and convex side; the projection circle and its identification position corresponding values ​​can also be manually added, deleted, checked and modified, and the cylinder detection result view model can also be rotated, scaled, stretched and other operations, which are not limited here.

[0057] Embodiment 2: The present invention provides a device for detecting the wear resistance of automobile brake pads based on a knowledge graph, and the system executes the method for detecting the wear resistance of automobile brake pads based on a knowledge graph.

[0058] Embodiment 3: The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program executes the knowledge graph-based automobile brake pad wear resistance detection method.

[0059] It will be appreciated by those skilled in the art that the present invention includes devices for performing one or more of the operations described in the present application. These devices may be specially designed and manufactured for the desired purpose, or may include known devices in general-purpose computers. These devices have computer programs stored therein, which are selectively activated or reconfigured. Such computer programs may be stored in a device (e.g., computer) readable medium or in any type of medium suitable for storing electronic instructions and coupled to a bus, respectively, the computer readable medium including but not limited to any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, the readable medium includes any medium that stores or transmits information in a readable form by a device (e.g., computer). Those skilled in the art will appreciate that each block in these structure diagrams and / or block diagrams and / or flow charts and combinations of blocks in these structure diagrams and / or block diagrams and / or flow charts can be implemented using computer program instructions. Those skilled in the art will appreciate that these computer program instructions can be provided to a general-purpose computer, a professional computer, or a processor of other programmable data processing methods to implement, thereby executing the scheme specified in the block or multiple blocks of the structure diagram and / or block diagram and / or flow chart disclosed in the present invention through the processor of the computer or other programmable data processing method.

[0060] Those skilled in the art will appreciate that the various operations, methods, steps, measures, and schemes discussed in the present invention may be alternated, modified, combined, or deleted. Further, other steps, measures, and schemes in the various operations, methods, and schemes discussed in the present invention may also be alternated, modified, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and schemes in the prior art that are similar to those disclosed in the present invention may also be alternated, modified, rearranged, decomposed, combined, or deleted.

[0061] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting the wear resistance of automobile brake pads based on knowledge graph, characterized in that: The method comprises the following steps: Step S1, constructing a brake pad wear resistance performance knowledge base according to the brake pad wear resistance performance detection data file, and performing information extraction, knowledge fusion and knowledge processing on the brake pad wear resistance performance knowledge base to construct a brake pad wear resistance performance knowledge graph; Step S2, extracting multiple key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performing a brake pad wear resistance test based on the multiple key indicators, and obtaining multiple groups of brake pad wear resistance test results; Step S3, constructing a cylinder test result view model according to the standardized multiple groups of brake pad wear resistance test results of the multiple key indicators, wherein the cylinder test result view model takes the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylinder test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result; Step S4, calculating the cylindricity of the cylinder detection result view model, and determining whether the cylindricity is greater than a first threshold value, if yes, executing step S5, otherwise, saving multiple groups of brake pad wear resistance performance test results of the multiple key indicators; Step S5, delete a set of test results that have the greatest impact on the cylindricity, update the cylinder test result view model, and calculate the cylindricity of the updated cylinder test result view model; re-judge whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, save multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder test result view model after the last update.

2. The brake pad wear resistance testing method according to claim 1, characterized in that: The multiple key indicators include any two or more of the following: Material, friction coefficient, wear rate, hardness, thermal decay, noise level, lifespan, and running-in period.

3. The brake pad wear resistance testing method according to claim 1, characterized in that: The step S3 of constructing a cylinder test result view model according to the standardized test results of multiple groups of brake pad wear resistance performance of the multiple key indicators further includes: Obtain the projection circle of the cylinder detection result view model on the xoy coordinate plane and the multiple key indicators, and evenly mark the multiple key indicators at the corresponding marking positions of the projection circle; Standardize the values ​​of each group of the brake pad wear resistance test results, mark the values ​​of the standardized test results at the corresponding marked positions of the projected circle, the size of the values ​​is proportional to the radius of the projected circle at the corresponding marked position, and draw the projected circle of the current group of test results with the radius of the projected circle and the radii of all the marked positions; The projected circles of all groups of detection results are arranged in sequence at unit distances along the Z-axis direction, and the cylinder detection result view model is constructed based on all the projected circles.

4. The brake pad wear resistance testing method according to claim 3, characterized in that: Evenly marking the multiple key indicators at the corresponding marking positions of the projected circle specifically includes: Acquire indicator attributes and indicator quantities of the multiple key indicators, cluster the multiple key indicators according to the indicator attributes, and arrange the key indicators according to the clustering results; The arranged key indicators are evenly marked on the corresponding marking positions of the projected circle according to the number of indicators.

5. The brake pad wear resistance testing method according to claim 4, characterized in that: Clustering the multiple key indicators according to the indicator attributes and arranging the key indicators according to the clustering results specifically includes: Based on the brake pad wear resistance knowledge graph, cluster analysis is performed on the multiple key indicators according to the indicator attributes to obtain a classification result of each key indicator and an indicator weight of each key indicator in the classification result; All key indicators of the same type are sorted according to the principle that the larger the indicator weight, the more central it is, and all the sorted key indicators of the same type are combined to obtain the arrangement result of the key indicators.

6. The brake pad wear resistance testing method according to claim 1, characterized in that: Step S3 constructs a cylinder test result view model according to the standardized test results of multiple groups of brake pad wear resistance performance of the multiple key indicators, and also includes: Obtaining the number of indicators of the multiple key indicators and the number of groups of the multiple groups of brake pad wear resistance test results; calculating the ratio of the number of groups to the number of indicators, and if the ratio is greater than a second threshold, distributing each group of brake pad wear resistance test results on the same horizontal plane of the side surface of the cylinder, and each of the key indicators is distributed on the side surface of the cylinder along the z-axis direction; If the ratio is not greater than the second threshold, each set of brake pad wear resistance test results are distributed on the side surface of the cylinder along the z-axis direction, and each of the key indicators is distributed on the same horizontal plane of the side surface of the cylinder.

7. The method for testing the wear resistance of brake pads according to any one of claims 1 to 6, characterized in that: Also includes: Obtaining a user's editing trigger operation on the cylinder detection result view model to perform rotation, scaling, and stretching operations on the cylinder detection result view model; The user's editing trigger operation on the identification position corresponding to the detection result in the cylinder detection result view model is obtained to drag, add or delete the identification position.

8. A knowledge graph-based automobile brake pad wear resistance detection system, characterized in that: To implement the brake pad wear resistance detection method according to any one of claims 1 to 7, the system comprises the following modules: A knowledge graph construction module constructs a brake pad wear resistance performance knowledge base based on the brake pad wear resistance performance test data file, and performs information extraction, knowledge fusion and knowledge processing on the brake pad wear resistance performance knowledge base to construct a brake pad wear resistance performance knowledge graph; A test result acquisition module extracts a plurality of key indicators that affect the wear resistance of the brake pad from the brake pad wear resistance knowledge graph, performs a brake pad wear resistance test based on the plurality of key indicators, and obtains a plurality of groups of brake pad wear resistance test results; A test result view model construction module is used to construct a cylinder test result view model according to the standardized test results of multiple groups of brake pad wear resistance of the multiple key indicators. The cylinder test result view model takes the xoy coordinate plane as the bottom surface, the origin o as the bottom circle center, and the z-axis direction as the cylinder axis center; each group of brake pad wear resistance test results are distributed on the same horizontal plane of the cylinder side surface, and each of the key indicators is distributed on the cylinder side surface along the z-axis direction; the cylinder test result view model presents a concave and convex arc on the cylinder side surface according to the numerical value of the test result; A view model cylindricity calculation module is used to calculate the cylindricity of the cylinder detection result view model, and determine whether the cylindricity is greater than a first threshold value. If so, the detection result update module is executed; otherwise, multiple groups of brake pad wear resistance test results of the multiple key indicators are saved; A detection result updating module deletes a set of detection results that have the greatest impact on the cylindricity, updates the cylinder detection result view model, and calculates the cylindricity of the updated cylinder detection result view model; re-determines whether the cylindricity is greater than the first threshold; until the cylindricity is not greater than the first threshold, saves multiple sets of brake pad wear resistance test results of the multiple key indicators identified by the cylinder detection result view model after the last update.

9. A knowledge graph-based automobile brake pad wear resistance testing device, characterized in that: The system executes the knowledge graph-based automobile brake pad wear resistance detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program executes the method for detecting the wear resistance of automobile brake pads based on knowledge graph as described in any one of claims 1 to 7.

Images