An artificial intelligence-based automobile repair information processing method and system

Abstract

The present application relates to the technical field of data processing, and more particularly to a kind of automobile repair information processing method and system based on artificial intelligence, comprising: the use length of the target part of collection recovery and the gray value of target part surface, obtain the residual life representation value of target part;According to residual life representation value, determine the grade of target part and corresponding target part processing strategy;The target part of same grade after processing is respectively assembled to several to be repaired automobile, the oscillation frequency of target part is collected within the preset length of time of automobile operation, and the stable characteristic value of part is obtained;When determining that the repair of automobile does not meet the standard according to stable characteristic value, whether the repair of automobile meets preset standard is determined again according to the frequency energy proportion of target part, or, the reason why the repair of automobile does not meet the standard is determined according to the gap evaluation value of target part;The grade of target part assembled on the automobile of repair not meeting the standard is corrected, and the repair efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a vehicle repair information processing method and system based on artificial intelligence. BACKGROUND

[0002] Vehicle repair refers to the process of repairing and restoring the original function, appearance and safety of damaged vehicles.

[0003] During vehicle repair, damaged parts often need to be replaced. These replaced parts can be recycled and reused if they still have value, and recycled parts can also provide more options for vehicle repair and reduce repair costs.

[0004] Traditional vehicle repair methods often rely on human experience and intuitive judgment, which has great subjectivity and uncertainty in aspects such as life assessment of vehicle parts, formulation of repair strategies, and verification of repair effects, which not only affects the efficiency and quality of vehicle repair, but also may pose a potential threat to driving safety. In the life assessment of vehicle parts, traditional assessment methods usually only consider the use time of the parts, ignoring the actual use environment and wear degree of the parts, resulting in inaccurate assessment results. In addition, for recycled parts, there is a lack of scientific classification and processing strategies, resulting in the waste of some parts that still have value, and the misuse of some parts that pose a safety hazard.

[0005] Chinese patent publication number CN119150082A discloses a vehicle ECU repair instrument data processing method and device, which obtains ECU repair instrument data, transmits the ECU repair instrument data into a fault detection algorithm for fault detection, and obtains a fault detection result. The fault detection algorithm is obtained by optimizing a preset AI algorithm combined with a first algorithm cost and a second algorithm cost. The first algorithm cost is not less than one of a data implicit representation cost and a defect detection cost. The data implicit representation cost represents the difference between the corresponding fault feature information in the sample implicit representation of the same vehicle fault in the ECU repair instrument data sample library. The defect detection cost represents the difference between the corresponding fault classification estimation information in the sample classification estimation information of the same vehicle fault in the ECU repair instrument data sample library.

[0006] It can be seen that the above technical solution only relies on ECU electronic fault data and lacks multi-dimensional state fusion, does not collect the surface gray value and use time of the parts, cannot identify part wear, and has the risk of misjudgment. At the same time, the influence of the oscillation frequency of the parts on the vehicle repair effect is not considered, resulting in low vehicle repair efficiency. SUMMARY

[0007] To this end, the application provides an artificial intelligence-based automobile repair information processing method and system to overcome the problem of low automobile repair efficiency caused by the fact that the prior art only relies on ECU electronic fault data and lacks multi-dimensional state fusion, does not collect the surface gray value and use time of the parts, cannot identify part wear, and has the risk of misjudgment, and does not consider the influence of the oscillation frequency of the parts on the automobile repair effect.

[0008] To achieve the above-mentioned purpose, in one aspect, the application provides an artificial intelligence-based automobile repair information processing method, comprising:

[0009] Recycling the target parts, collecting the use time of the target parts and the gray value of the surface of the target parts, and obtaining the residual life representation value of the target parts;

[0010] Determining the grade of the target parts and the corresponding target part processing strategy according to the residual life representation value;

[0011] Assembling the target parts of the same grade after processing to a plurality of automobiles to be repaired, collecting the oscillation frequency of the target parts within a predetermined time of automobile operation, and obtaining the stable characteristic value of the parts;

[0012] When the stable characteristic value determines that the repair of the automobile does not meet the predetermined standard, the second determination of whether the repair of the automobile meets the predetermined standard is made according to the main frequency energy proportion of the target parts, or the reason why the repair of the automobile does not meet the predetermined standard is determined according to the gap evaluation value of the target parts;

[0013] Correcting the grade of the target parts assembled on the automobile whose repair does not meet the predetermined standard.

[0014] Further, the grade of the target parts and the corresponding target part processing strategy are determined according to the residual life representation value of the target parts, the grade of the target parts includes any one of A grade, B grade and C grade, and the residual life grades corresponding to the A grade, the B grade and the C grade decrease in turn.

[0015] Further, the residual life representation value is determined by the use time of the target parts and the gray value of the surface of the target parts.

[0016] Further, when the stable characteristic value of the target parts is greater than or equal to a first predetermined driving stability threshold, it is determined that the repair of the automobile does not meet the predetermined standard, wherein the stable characteristic value is determined by the oscillation frequency collected during the driving process of the automobile.

[0017] Further, when the stable characteristic value is greater than or equal to the first predetermined driving stability threshold and less than the second predetermined driving stability threshold, the second determination of whether the repair of the automobile meets the predetermined standard is made according to the main frequency energy proportion;

[0018] and, under the condition that the stability characteristic value is greater than or equal to the second preset driving stability threshold value, determining the reason why the repair of the automobile does not meet the preset standard according to the gap evaluation value;

[0019] Further, determining whether the repair of the automobile meets the preset standard according to the main frequency energy proportion of the target part, wherein,

[0020] if the main frequency energy proportion is less than a preset main frequency energy proportion, it is determined that the repair of the automobile meets the preset standard;

[0021] if the main frequency energy proportion is greater than or equal to the preset main frequency energy proportion, it is determined that the repair of the automobile does not meet the preset standard, and the grade of the target part is corrected;

[0022] the main frequency energy proportion is a ratio between the main frequency band energy and the total frequency band energy.

[0023] Further, determining that the repair of the automobile does not meet the preset standard according to the gap evaluation value of the target part, wherein,

[0024] if the gap evaluation value is less than a preset gap evaluation value, it is determined that the reason why the repair of the automobile does not meet the preset standard is that the grading of the target part is wrong, and the grade of the target part is corrected;

[0025] if the gap evaluation value is greater than or equal to the preset gap evaluation value, it is determined that the reason why the repair of the automobile does not meet the preset standard is that the assembly is too loose, and a warning is issued.

[0026] Further, the gap evaluation value is a ratio between the gap of the target part and the contact part of the automobile and a preset gap.

[0027] Further, the correction process of the grade of the target part comprises:

[0028] obtaining the grade of the target part assembled on the automobile, denoted as a target grade;

[0029] if the stability characteristic value of the automobile assembled with the target part of the target grade is greater than or equal to the first preset driving stability threshold value and less than the second preset driving stability threshold value, the target grade is lowered by one level;

[0030] if the stability characteristic value of the automobile assembled with the target part of the target grade is greater than or equal to the second preset driving stability threshold value, the target grade is lowered by two levels;

[0031] if the grade of the target part after the target grade is lowered exceeds C level, the target part is scrapped.

[0032] On the other hand, the present application provides a system suitable for an automobile repair information processing method based on artificial intelligence, comprising:

[0033] a data collection module comprising a service time collection unit configured to collect service time of the target part, a surface grayscale value collection unit configured to collect surface grayscale value of the target part, an oscillation frequency collection unit configured to collect oscillation frequency of the target part, and an energy collection unit configured to collect frequency band energy;

[0034] a part rating module connected with the data collection module and configured to determine the grade of the target part and a corresponding target part processing strategy according to the residual life representation value of the target part;

[0035] a running detection module connected with the data collection module and configured to determine whether the repair of the automobile meets the preset standard according to the target part main frequency energy proportion, or determine the reason why the repair of the automobile does not meet the preset standard according to the target part gap evaluation value, when the stable characteristic value determines that the repair of the automobile does not meet the preset standard;

[0036] an optimization adjustment module connected with the part rating module and the running detection module respectively, and configured to correct the grade of the target part assembled on the automobile whose repair does not meet the preset standard.

[0037] Compared with the prior art, the beneficial effects of the present application are that the present application classifies the parts according to the service time and surface state of the parts, reduces the false scrapping of parts and the misuse of low-life parts, reduces the material cost, monitors the repair quality according to the automobile running data, and introduces a multi-level judgment mechanism to ensure the accuracy of the repair standard. At the same time, it also has an intelligent grade correction function, which can quickly feedback and adjust for substandard conditions, thereby improving the automobile repair efficiency.

[0038] Further, the present application determines the grade of the target part and the corresponding target part processing strategy according to the residual life representation value of the target part, divides the target part into A level or B level or C level, reduces the repair process and misuse of low-life parts through the grading strategy, thereby improving the resource utilization efficiency.

[0039] Further, the present application fuses the service time and surface grayscale value of the target part, the service time reflects the historical load accumulation of the part, the surface grayscale value detects the material wear condition through image analysis technology, accurately identifies defects, quantifies the residual life representation value, thereby improving the reliability of the evaluation.

[0040] Further, the present application verifies the performance of the repaired automobile by using dynamic parameters such as oscillation frequency and main frequency energy proportion, thereby improving the repair efficiency.

[0041] Further, the application preliminarily determines that the repair of the automobile does not meet the preset standard when the stable characteristic value is greater than or equal to the first preset driving stability threshold value. Then, secondary determination is performed by using the frequency energy proportion, or the reason why the repair does not meet the standard is determined according to the gap evaluation value, so that the reliability of the repair quality is ensured.

[0042] Further, the application adjusts the part grade dynamically, so that the system can reflect the state change of the part in a timely manner according to the actual performance of the part, and the flexibility and accuracy of part management are improved. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 A flowchart of the method for processing automobile repair information based on artificial intelligence according to an embodiment of the application is shown in FIG. 1.

[0044] Figure 2 A schematic diagram of module connection of the system suitable for the method for processing automobile repair information based on artificial intelligence according to an embodiment of the application is shown in FIG. 2.

[0045] Figure 3 A flowchart of determining the grade of the target part and the corresponding target part processing strategy according to the residual life representation value of the target part according to an embodiment of the application is shown in FIG. 3.

[0046] Figure 4 A flowchart of secondary determining whether the repair of the automobile meets the preset standard according to the frequency energy proportion of the target part according to an embodiment of the application is shown in FIG. 4. DETAILED DESCRIPTION

[0047] In order to make the objectives and advantages of the application clearer and more apparent, the application will be further described below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and do not limit the protection scope of the application.

[0048] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the application, and do not limit the protection scope of the application.

[0049] It should be pointed out that the data in the embodiments are obtained by comprehensive analysis and evaluation of the historical detection data and the corresponding historical detection results of the application in the three months before the detection. Those skilled in the art can understand that the determination method of the application for a single parameter can be to select the value with the highest proportion as the preset standard parameter according to the data distribution, to use weighted summation to obtain the value as the preset standard parameter, to substitute each historical data into a specific formula and to obtain the value by using the formula as the preset standard parameter, or other selection methods, as long as the application can clearly define different specific situations in the single determination process by using the obtained value.

[0050] Referring to Figure 1 , Figure 2 , Figure 3 and Figure 4 , which are respectively a flowchart of an embodiment of the application based on an artificial intelligence automobile repair information processing method; a module connection diagram of an embodiment of the application based on an artificial intelligence automobile repair information processing method system; a flowchart of an embodiment of the application for determining the grade of a target part and the corresponding target part processing strategy according to the residual life representation value of the target part; and a flowchart of an embodiment of the application for determining whether the repair of an automobile meets the preset standard according to the main frequency energy proportion of the target part.

[0051] Referring to Figure 1 , in one aspect, an embodiment of the application provides an artificial intelligence-based automobile repair information processing method, which comprises:

[0052] Step S1, recycling the target part, collecting the use time of the target part and the gray value of the surface of the target part, and obtaining the residual life representation value of the target part;

[0053] Step S2, determining the grade of the target part and the corresponding target part processing strategy according to the residual life representation value;

[0054] Step S3, assembling the target parts of the same grade after processing to a plurality of automobiles to be repaired, collecting the oscillation frequency of the target part within a preset time period of 30 minutes of automobile operation, and obtaining the stable characteristic value of the part;

[0055] Step S4, when the stable characteristic value determines that the repair of the automobile does not meet the preset standard, determining whether the repair of the automobile meets the preset standard according to the main frequency energy proportion of the target part, or determining the reason why the repair of the automobile does not meet the preset standard according to the gap evaluation value of the target part;

[0056] Step S5, correcting the grade of the target part assembled on the automobile whose repair does not meet the preset standard.

[0057] In this embodiment, the target part is selected as an axle part.

[0058] Referring to Figure 3 , specifically, the grade of the target part and the corresponding target part processing strategy are determined according to the residual life representation value of the target part, the grade of the target part comprises any one of A, B and C, and the residual life grades corresponding to the A, B and C grades are sequentially decreasing, wherein,

[0059] If the residual life representation value is less than the first preset residual life representation value 0.4, the grade of the target part is determined to be C, and the target part is subjected to repair welding.

[0060] If the remaining life representation value is greater than or equal to the first preset remaining life representation value and less than the second preset remaining life representation value 0.8, it is determined that the grade of the target part is B grade, and the target part is surface cleaned;

[0061] If the remaining life representation value is greater than or equal to the second preset remaining life representation value, it is determined that the grade of the target part is A grade, and the target part is not processed.

[0062] Specifically, the remaining life representation value is determined by the use time of the target part and the gray value of the surface of the target part.

[0063] The remaining life representation value is calculated by the following formula:

[0064]

[0065] In the formula, P represents the remaining life representation value; a represents the first weight, and a is set to 0.56; T represents the use time of the target part; T0 represents the design life of the target part; β represents the second weight, and β is set to 0.44; G represents the gray value of the surface of the target part; G0 represents the preset gray value of the surface of the target part, and G0 is set to 180.

[0066] In practice, the first preset remaining life representation value is generally selected in the range of [0.2, 0.5], and the second preset remaining life representation value is generally selected in the range of [0.6, 0.9]. Preferably, the first preset remaining life representation value is selected as 0.4, and the second preset remaining life representation value is selected as 0.8.

[0067] Specifically, whether the repair of the automobile meets the preset standard is determined according to the stable characteristic value of the target part, wherein,

[0068] If the stable characteristic value is less than the first preset driving stability threshold 50Hz, it is determined that the repair of the automobile meets the preset standard;

[0069] If the stable characteristic value is greater than or equal to the first preset driving stability threshold and less than the second preset driving stability threshold 70Hz, it is determined that the repair of the automobile does not meet the preset standard, and whether the repair of the automobile meets the preset standard is determined again according to the main frequency energy proportion;

[0070] If the stable characteristic value is greater than or equal to the second preset driving stability threshold, it is determined that the repair of the automobile does not meet the preset standard, and the reason why the repair of the automobile does not meet the preset standard is determined according to the gap evaluation value.

[0071] The stable characteristic value is determined by the oscillation frequency collected during driving of the automobile;

[0072] The stable characteristic value is calculated by the following formula:

[0073]

[0074] In the formula, F represents the stable characteristic value; f i represents the oscillation frequency of the target part recorded for the i-th time; i = 1, 2, 3 … n; n represents the total number of records.

[0075] Referring to Figure 4 , specifically, according to the proportion of the main frequency energy of the target part, it is determined whether the repair of the automobile meets the preset standard, wherein,

[0076] If the proportion of the main frequency energy is less than the preset proportion of the main frequency energy 0.65, it is determined that the repair of the automobile meets the preset standard;

[0077] If the proportion of the main frequency energy is greater than or equal to the preset proportion of the main frequency energy, it is determined that the repair of the automobile does not meet the preset standard, and the grade of the target part is corrected;

[0078] The proportion of the main frequency energy is the ratio between the energy of the main frequency band and the total frequency band.

[0079] In this embodiment, the main frequency band is set to 80-120Hz, but the above value is not limited thereto, and those skilled in the art can adjust the value according to actual needs.

[0080] Specifically, according to the gap evaluation value of the target part, it is determined that the repair of the automobile does not meet the preset standard, wherein,

[0081] If the gap evaluation value is less than the preset gap evaluation value 1.2, it is determined that the reason why the repair of the automobile does not meet the preset standard is that the classification of the target part is wrong, and the grade of the target part is corrected;

[0082] If the gap evaluation value is greater than or equal to the preset gap evaluation value, it is determined that the reason why the repair of the automobile does not meet the preset standard is that the assembly is too loose, and a warning is issued.

[0083] Specifically, the gap evaluation value is the ratio between the gap of the target part and the contact part of the automobile and the preset gap 0.78mm.

[0084] The gap of the target part and the contact part of the automobile is obtained by a laser displacement sensor.

[0085] Specifically, the correction process of the grade of the target part includes:

[0086] Obtaining the grade of the target part assembled on the automobile, denoted as the target grade;

[0087] If the stability characteristic value of the automobile equipped with the target part of the grade is greater than or equal to the first preset driving stability threshold value and less than the second preset driving stability threshold value, the target grade is lowered by one level;

[0088] If the stability characteristic value of the automobile equipped with the target part of the grade is greater than or equal to the second preset driving stability threshold value, the target grade is lowered by two levels.

[0089] If the grade after the target grade is lowered exceeds the C level, the target part is scrapped.

[0090] Referring to Figure 2 In another aspect, the present application provides a system suitable for an artificial intelligence-based automobile repair information processing method, comprising:

[0091] A data acquisition module, comprising a time length acquisition unit for acquiring the use time length of the target part, a gray value acquisition unit for acquiring the gray value of the surface of the target part, an oscillation acquisition unit for acquiring the oscillation frequency of the target part, and an energy acquisition unit for acquiring the frequency band energy;

[0092] A part rating module connected to the data acquisition module, for determining the grade of the target part and the corresponding target part processing strategy according to the residual life representation value of the target part;

[0093] A running detection module connected to the data acquisition module, for determining whether the repair of the automobile does not meet the preset standard according to the stability characteristic value, or determining whether the repair of the automobile meets the preset standard according to the main frequency energy proportion of the target part, or determining the reason why the repair of the automobile does not meet the preset standard according to the gap evaluation value of the target part;

[0094] An optimization adjustment module connected to the part rating module and the running detection module, for correcting the grade of the target part equipped in the automobile whose repair does not meet the preset standard.

[0095] Specifically, the specific structure of the part rating module, the running detection module, and the optimization adjustment module is not limited, and each unit thereof can be composed of a logic component, which includes a field programmable component, a computer, or a microprocessor in a computer.

[0096] Specifically, the gray value acquisition unit is composed of an industrial camera and an image processing software OpenCV; the oscillation acquisition unit is an acceleration sensor installed on the surface of the target part; and the energy acquisition unit is a spectrum analyzer.

[0097] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

[0098] The above only describes the preferred embodiments of the present application and is not intended to limit the present application; the present application can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based automobile repair information processing method, characterized by, The method comprises the following steps: collecting the service time and the gray value of the target part surface to obtain the residual life characteristic value of the target part; determining the grade of the target part and the corresponding target part processing strategy according to the residual life characteristic value; assembling the target parts of the same grade after processing into several vehicles to be repaired, collecting the oscillation frequency of the target part within a preset service time, and obtaining the stable characteristic value of the part; when the stable characteristic value of the target part is greater than or equal to the first preset driving stability threshold value, it is determined that the repair of the vehicle does not meet the preset standard, wherein the stable characteristic value is determined by the oscillation frequency collected during the driving of the vehicle. when the stable characteristic value is greater than or equal to the first preset driving stability threshold value and less than the second preset driving stability threshold value, the secondary determination of whether the repair of the vehicle meets the preset standard is made according to the main frequency energy proportion; 2. The artificial intelligence-based automobile repair information processing method of claim 1, characterized by, when the stable characteristic value is greater than or equal to the second preset driving stability threshold value, the reason why the repair of the vehicle does not meet the preset standard is determined according to the gap evaluation value.

3. The artificial intelligence-based automobile repair information processing method of claim 2, characterized by, The secondary determination of whether the repair of the vehicle meets the preset standard is made according to the main frequency energy proportion of the target part, wherein 4. The artificial intelligence-based automobile repair information processing method of claim 3, characterized by, if the main frequency energy proportion is less than the preset main frequency energy proportion, it is determined that the repair of the vehicle meets the preset standard; 5. The artificial intelligence-based automobile repair information processing method of claim 4, characterized by, if the main frequency energy proportion is greater than or equal to the preset main frequency energy proportion, it is determined that the repair of the vehicle does not meet the preset standard, and the grade of the target part is corrected; The main frequency energy proportion is the ratio of the energy of the main frequency band to the total frequency band.

6. The artificial intelligence-based automobile repair information processing method of claim 5, characterized by, The reason why the repair of the vehicle does not meet the preset standard is determined according to the gap evaluation value of the target part, wherein if the gap evaluation value is less than the preset gap evaluation value, it is determined that the reason why the repair of the vehicle does not meet the preset standard is the error in the classification of the target part, and the grade of the target part is corrected; if the gap evaluation value is greater than or equal to the preset gap evaluation value, it is determined that the reason why the repair of the vehicle does not meet the preset standard is that the assembly is too loose, and a warning is issued. The gap evaluation value is the ratio of the gap between the target part and the contact part of the vehicle to the preset gap.

7. The artificial intelligence-based automobile repair information processing method of claim 6, characterized by, The correction process of the grade of the target part comprises the following steps: obtaining the grade of the target part assembled on the vehicle, denoted as the target grade; ​ 8. The artificial intelligence-based automobile repair information processing method of claim 7, characterized by, ​ 9. The artificial intelligence-based automobile repair information processing method of claim 8, characterized by, ​ ​ If the stability characteristic value of the automobile equipped with the target part of the grade is greater than or equal to the first preset driving stability threshold and less than the second preset driving stability threshold, the target grade is lowered by one level; If the stability characteristic value of the automobile equipped with the target part of the grade is greater than or equal to the second preset driving stability threshold, the target grade is lowered by two levels; If the grade of the target part after the target grade is lowered exceeds the C level, the target part is scrapped.

10. A system suitable for use in the artificial intelligence-based automobile repair information processing method according to any one of claims 1 to 9, characterized by, The method comprises the following steps: a data acquisition module comprising a time length acquisition unit for acquiring the use time length of the target part, a gray value acquisition unit for acquiring the gray value of the surface of the target part, an oscillation acquisition unit for acquiring the oscillation frequency of the target part, and an energy acquisition unit for acquiring the frequency band energy; a part rating module connected to the data acquisition module, for determining the grade of the target part and the corresponding target part processing strategy according to the residual life representation value of the target part; a running detection module connected to the data acquisition module, for determining whether the repair of the automobile does not meet the preset standard according to the stability characteristic value, determining whether the repair of the automobile meets the preset standard according to the main frequency energy proportion of the target part, or determining the reason why the repair of the automobile does not meet the preset standard according to the gap evaluation value of the target part; an optimization adjustment module connected to the part rating module and the running detection module, for correcting the grade of the target part equipped in the automobile whose repair does not meet the preset standard.

Images