Automobile sheet metal part maintenance man-hour estimation method

Abstract

The invention discloses an automobile sheet metal part maintenance man-hour estimation method, and relates to the technical field of automobile sheet metal parts, the method uses an image acquisition device and a convolutional neural network technology, can accurately analyze and calculate the damage condition of the automobile sheet metal part, provides a working basis for later man-hour estimation, and improves the working efficiency. Errors caused by subjective factors in a traditional method are avoided; through deep analysis of the image data set, the maintenance requirement of the sheet metal part can be further accurately identified, the loss assessment coefficient Dsxs is obtained, whether the automobile sheet metal part needs to be replaced or maintained is determined according to the loss assessment coefficient Dsxs, meanwhile, whether an extra maintenance range exists is judged again according to inspection of a sheet metal worker, and the maintenance efficiency of the sheet metal part is improved. Potential problems can be found as soon as possible, appropriate maintenance measures can be taken, comprehensiveness and transparency of maintenance work are facilitated, and missing of maintenance requirements is prevented. And on the basis of multi-dimensional data and calculation, a man-hour evaluation index Pgzs is comprehensively obtained, and a man-hour estimation report is objectively obtained.

Description

Technical Field

[0001] The invention relates to the technical field of automobile sheet metal parts, and in particular to a method for estimating the maintenance man-hours of automobile sheet metal parts. Background Art

[0002] Automotive sheet metal is a technology used to repair and reshape the outer shell of a car. Sheet metal technicians need to use a variety of tools and materials to repair and improve the appearance of the car. During the body repair process, it is usually necessary to deal with various damages, including collisions, scratches, dents, etc. Therefore, effective labor time estimation is crucial to providing customers with accurate service cost estimates and repair schedules.

[0003] At present, in the traditional automobile maintenance process, labor time estimation is usually based on experience and manual inspection. This method can often quickly estimate the duration of maintenance, but it is often affected by human subjectivity, resulting in inaccurate estimates, excessive labor time or shortage. Secondly, this method usually cannot take into account hidden damage or additional maintenance work outside the maintenance scope, which may lead to an underestimation of maintenance time. These problems make the traditional automobile sheet metal parts maintenance labor time estimation method have certain limitations in meeting customer needs and ensuring the efficiency of the maintenance process. Summary of the invention

[0004] A technical problem solved In view of the deficiencies in the prior art, the present invention provides a method for estimating the maintenance man-hours for automobile sheet metal parts, which solves the problems in the background technology.

[0005] Second technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for estimating the maintenance time of automobile sheet metal parts, comprising the following steps: S1. Data collection: Use image acquisition equipment to capture and obtain continuous electronic images of the automobile sheet metal parts to be estimated in advance, and combine them with the historical data of automobile maintenance to collect and record the damage data of relevant sheet metal parts and the information of the sheet metal technicians assigned to the corresponding parts; S2, data analysis: pre-process the continuous images of automobile sheet metal parts, remove noise and smooth the images, identify and extract features in the continuous images, and improve the image quality based on image enhancement technology to generate image data sets; S3. Damage assessment: using convolutional neural network learning technology to deeply analyze and calculate the internal data information of the image data set, obtain: the proportion of damaged area Pszb, the crack depth Lfsd, the number of maintenance personnel Wxrs, the professional years Zznx and the number of damaged surfaces Pms; by associating the proportion of damaged area Pszb and the crack depth Lfsd, obtain the wear state factor Hsyz, and generate the damage assessment coefficient Dsxs in combination with the number of damaged surfaces Pms, compare and analyze the damage assessment coefficient Dsxs with the preset damage assessment threshold Q, and determine whether the automobile sheet metal parts are in the process of replacement or repair; S4, data analysis: according to the inspection of the sheet metal technician during maintenance, the maintenance scope value is locked, and combined with the damage assessment coefficient Dsxs, the time consumption index Xhzs is obtained, and the additional maintenance scope value is distinguished according to the maintenance scope value, and the additional working time index Egzs is generated in combination with the image data set; The time consumption index Xhzs and the extra working time index Egzs are associated with each other by machine learning calculation to obtain the working time evaluation index Pgzs. After dimensionless processing, the working time evaluation index Pgzs is obtained by the following formula:

[0006] In the formula, Cgsl represents the purchase quantity, and They are respectively expressed as the weight values ​​of the time consumption index Xhzs, the extra working hours index Egzs and the purchase quantity Cgsl, where: , , ,and , R represents the constant correction coefficient; S5. Man-hour evaluation: Compare and analyze the man-hour evaluation index Pgzs with the preset evaluation threshold K, obtain a man-hour estimation report, and adopt a corresponding work plan based on the corresponding man-hour estimation report.

[0007] Preferably, an image acquisition device is used to capture continuous electronic images of the automobile sheet metal parts to be estimated, and the relevant image frames are continuously recorded to ensure that the entire automobile sheet metal parts are completely recorded, and the relevant sheet metal parts damage data in the image are identified, including the automobile sheet metal parts type, size, curvature, material type, degree of cracks, damage, and location and coordinates of the damage; the continuous image frames are sorted in a corresponding order according to the data information in the image and the shooting order; and the sheet metal technician information assigned to the corresponding parts is determined in combination with the automobile maintenance history data information.

[0008] Preferably, wavelet denoising technology is used to decompose the data information in a plurality of image frames by wavelet transform, and remove the noise component in the wavelet domain, and reconstruct the plurality of image frames back to the original domain by inverse transform, and histogram equalization is used to adjust the brightness, stretch the image range value, and adjust the image contrast; Image enhancement technology is used to extract key feature information from image frames, identify and analyze defective areas in the image, and select and adjust the degree of difference between different areas in the image frame based on their characteristics.

[0009] Preferably, the damaged area ratio Pszb is associated with the crack depth Lfsd, and after dimensionless processing, the wear state factor Hsyz is obtained by the following formula:

[0010] Where Wxcs is the number of maintenance times, and They are respectively represented by the weight values ​​of the damaged area proportion Pszb, crack depth Lfsd and repair times Wxcs, where: , , ,and , C represents the constant correction coefficient; The damage assessment coefficient Dsxs is obtained by the following formula:

[0011] Where Pms is the number of damaged surfaces.

[0012] Preferably, the damage assessment coefficient Dsxs is compared and analyzed with a preset damage assessment threshold Q to determine whether the automobile sheet metal parts are in the process of replacement or repair: If the damage assessment coefficient Dsxs is greater than or equal to the preset damage assessment threshold Q, that is, Dsxs ≥ Q, it means that the current automobile sheet metal parts need to be directly replaced; If the damage assessment coefficient Dsxs is lower than the preset damage assessment threshold Q, that is, Dsxs<Q, it means that the current automobile sheet metal parts need to continue to be repaired.

[0013] Preferably, the maintenance personnel Wxrs and the full-time years Zznx are associated to obtain the labor generation coefficient Llxs, and after dimensionless processing, the labor generation coefficient Llxs is obtained by the following formula:

[0014] In the formula, It is expressed as the weight value of the number of maintenance personnel Wxrs. It is expressed as the weight value of full-time years Zznx, where: , ,and , P represents the constant correction coefficient.

[0015] Preferably, the time consumption index Xhzs is obtained by associating the labor generation coefficient Llxs with the damage assessment coefficient Dsxs, and after dimensionless processing, the time consumption index Xhzs is obtained by the following formula:

[0016] In the formula, Expressed as the weight value of the labor generation coefficient Llxs, It is expressed as the weight value of the damage assessment coefficient Dsxs, and B is expressed as the constant correction coefficient. , ,and .

[0017] Preferably, when inspecting a vehicle, the bodyworker locks in the determined repair range value, including known problems or damaged parts, and analyzes the image data set to determine the additional repair range value, and compares the additional repair range value with the determined repair range value to generate a ratio value Blz.

[0018] Preferably, the extra working hours index Egzs is obtained by the following formula:

[0019] The significance of this formula is to determine the range of the extra working hours index Egzs based on the proportional relationship between the determined maintenance range value and the extra maintenance range value.

[0020] Preferably, the man-hour evaluation index Pgzs is compared and analyzed with a preset evaluation threshold K to obtain a man-hour estimation report; wherein the evaluation threshold K includes a first threshold K1 and a second threshold K2, and the first threshold K1 is greater than the evaluation threshold K, and the second threshold K2 is less than the evaluation threshold K. The contents of the man-hour estimation report are as follows: If the man-hour evaluation index Pgzs ≤ the second threshold value K2, it indicates that the current maintenance complexity of the automobile sheet metal parts is within 20%; If the second threshold value K2 < the man-hour evaluation index Pgzs ≤ the evaluation threshold value K, it indicates that the maintenance complexity of the current automobile sheet metal parts is within 20%-30%; If the evaluation threshold K < the working time evaluation index Pgzs ≤ the first threshold K1, it means that the maintenance complexity of the current automobile sheet metal parts has exceeded 30%; The corresponding estimate report will be assigned to the sheet metal technician of the corresponding level through the data information recorded in the personnel file and combined with the sheet metal technician's duty roster.

[0021] Three beneficial effects The present invention provides a method for estimating the man-hours for repairing automobile sheet metal parts, which has the following beneficial effects: 1. A method for estimating the maintenance man-hours of automobile sheet metal parts. The method uses image acquisition equipment and convolutional neural network technology to accurately analyze and calculate the damage of automobile sheet metal parts, providing a working basis for the later estimation of man-hours and avoiding the errors caused by subjective factors in traditional methods. Through in-depth analysis of image data sets, the maintenance needs of sheet metal parts can be further accurately identified, and the damage coefficient Dsxs can be obtained. According to the damage coefficient Dsxs, it is determined whether the automobile sheet metal parts need to be replaced or repaired. At the same time, according to the inspection of the sheet metal technician, it is judged again whether there is an additional maintenance scope, so as to find potential problems early and take appropriate maintenance measures, which is conducive to the comprehensiveness and transparency of maintenance work and prevents the omission of maintenance needs. Based on multi-dimensional data and calculations, the man-hour evaluation index Pgzs is comprehensively obtained, and an objective man-hour estimation report is obtained, which is convenient for further accurate evaluation of the maintenance man-hours of sheet metal parts, so that decision makers can better understand the nature and cost of maintenance work and mobilize sheet metal technicians of corresponding levels in a targeted manner. Compared with relying on experience or manual inspection to evaluate man-hours, this method is relatively scientific.

[0022] 2. This method for estimating the working hours for repairing automobile sheet metal parts collects multi-dimensional data through infrared camera equipment, provides accurate damage assessment for repair projects, and further understands the repair history of the damaged location of the automobile based on the record information of historical repairs, further providing a basis for the evaluation of repair needs, and further reflects the repair history and current damage status of automobile parts through the wear state factor Hsyz, providing a basis for subsequent decision-making. The damage coefficient Dsxs can be used for further decision-making to determine whether the automobile sheet metal parts need to be replaced or continued to be repaired, which helps to further improve the accuracy of working hours estimation and reduce subjective estimates and errors in traditional methods. Comparing and analyzing the damage coefficient Dsxs with the pre-set damage threshold Q can provide objective decision-making basis for car owners, repair shops and insurance companies.

[0023] 3. A method for estimating the maintenance man-hours of automobile sheet metal parts. This method provides more transparency and objectivity for maintenance decisions through clear maintenance complexity assessment and man-hour estimation report grading, which helps to further optimize the allocation of personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The present invention is a flowchart of a method for estimating the maintenance man-hours of automobile sheet metal parts. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Automotive sheet metal is a technology used to repair and reshape the outer shell of a car. Sheet metal technicians need to use a variety of tools and materials to repair and improve the appearance of the car. During the body repair process, it is usually necessary to deal with various damages, including collisions, scratches, dents, etc. Therefore, effective labor time estimation is crucial to providing customers with accurate service cost estimates and repair schedules.

[0027] At present, in the traditional automobile maintenance process, labor time estimation is usually based on experience and manual inspection. This method can often quickly estimate the duration of maintenance, but it is often affected by human subjectivity, resulting in inaccurate estimates, excessive labor time or shortage. Secondly, this method usually cannot take into account hidden damage or additional maintenance work outside the maintenance scope, which may lead to an underestimation of maintenance time. These problems make the traditional automobile sheet metal parts maintenance labor time estimation method have certain limitations in meeting customer needs and ensuring the efficiency of the maintenance process.

[0028] Example 1 See also Figure 1 The present invention provides a method for estimating the maintenance time of automobile sheet metal parts, comprising the following steps: S1. Data collection: Use image acquisition equipment to capture and obtain continuous electronic images of the automobile sheet metal parts to be estimated in advance, and combine them with the historical data of automobile maintenance to collect and record the damage data of relevant sheet metal parts and the information of the sheet metal technicians assigned to the corresponding parts; S2, data analysis: pre-process the continuous images of automobile sheet metal parts, remove noise and smooth the images, identify and extract features in the continuous images, and improve the image quality based on image enhancement technology to generate image data sets; S3. Damage assessment: using convolutional neural network learning technology to deeply analyze and calculate the internal data information of the image data set, obtain: the proportion of damaged area Pszb, the crack depth Lfsd, the number of maintenance personnel Wxrs, the professional years Zznx and the number of damaged surfaces Pms; by associating the proportion of damaged area Pszb and the crack depth Lfsd, obtain the wear state factor Hsyz, and generate the damage assessment coefficient Dsxs in combination with the number of damaged surfaces Pms, compare and analyze the damage assessment coefficient Dsxs with the preset damage assessment threshold Q, and determine whether the automobile sheet metal parts are in the process of replacement or repair; S4, data analysis: according to the inspection of the sheet metal technician during maintenance, the maintenance scope value is locked, and combined with the damage assessment coefficient Dsxs, the time consumption index Xhzs is obtained, and the additional maintenance scope value is distinguished according to the maintenance scope value, and the additional working time index Egzs is generated in combination with the image data set; The time consumption index Xhzs and the extra working time index Egzs are associated with each other by machine learning calculation to obtain the working time evaluation index Pgzs. After dimensionless processing, the working time evaluation index Pgzs is obtained by the following formula:

[0029] In the formula, Cgsl represents the purchase quantity, and They are respectively expressed as the weight values ​​of the time consumption index Xhzs, the extra working hours index Egzs and the purchase quantity Cgsl, where: , , ,and , R represents the constant correction coefficient; The above-mentioned purchase quantity Cgsl refers to the equipment or parts that need to be purchased from other stores or other platforms when repairing automobile sheet metal parts; and it is collected through the accounting manual; S5. Man-hour evaluation: Compare and analyze the man-hour evaluation index Pgzs with the preset evaluation threshold K, obtain a man-hour estimation report, and adopt a corresponding work plan based on the corresponding man-hour estimation report.

[0030] In this embodiment, continuous electronic images are collected and relevant sheet metal parts damage data are extracted from them to prepare for subsequent estimates. Through in-depth analysis of the image data set, the maintenance needs of sheet metal parts can be further accurately identified, including multiple factors such as damage area, crack depth Lfsd and number of maintenance personnel, and the damage assessment coefficient Dsxs is obtained. According to the damage assessment coefficient Dsxs, it is determined whether the automobile sheet metal parts need to be replaced or repaired. At the same time, according to the inspection of the sheet metal technician, it is judged again whether there is additional maintenance scope; and based on multi-dimensional data and calculations, the working time evaluation index Pgzs is comprehensively obtained, and an objective working time estimation report is made, so as to mobilize sheet metal technicians of corresponding levels.

[0031] Example 2 Please refer to Figure 1Specifically: Use image acquisition equipment to capture continuous electronic images of the automobile sheet metal parts to be estimated, and continuously record relevant image frames to ensure that the entire automobile sheet metal parts are fully recorded, and identify the damage data of the relevant sheet metal parts in the image, including the type, size, curvature, material type, degree of cracks, damage, and location and coordinates of the damage of automobile sheet metal parts, and sort the continuous image frames in the corresponding order according to the data information in the image and the shooting order; and determine the sheet metal technician information assigned to the corresponding parts in combination with the automobile maintenance history data information.

[0032] Among them, the level of the sheet metal technician's position is determined by his own experience and years of full-time work, which can be divided into junior technicians, intermediate technicians and senior technicians respectively.

[0033] Using wavelet denoising technology, the data information in several image frames is decomposed through wavelet transform, and the noise component is removed in the wavelet domain. Several image frames are reconstructed back to the original domain through inverse transform, and histogram equalization is used to adjust the brightness, stretch the image range value, and adjust the image contrast; Image enhancement technology is used to extract key feature information from image frames, identify and analyze defective areas in the image, and select and adjust the degree of difference between different areas in the image frame based on their characteristics.

[0034] Example 3 Please refer to Figure 1 Specifically, the damaged area ratio Pszb is associated with the crack depth Lfsd. After dimensionless processing, the wear state factor Hsyz is obtained by the following formula:

[0035] Where Wxcs is the number of maintenance times, and They are respectively represented by the weight values ​​of the damaged area proportion Pszb, crack depth Lfsd and repair times Wxcs, where: , , ,and , C represents the constant correction coefficient; The damage assessment coefficient Dsxs is obtained by the following formula:

[0036] Where Pms is the number of damaged surfaces.

[0037] The above-mentioned number of repairs Wxcs refers to the total number of repairs in the historical records for the damaged position of the car, and is collected from the internal system of the insurance company or the maintenance and repair history database of the repair shop and the vehicle manufacturer; The damaged area percentage Pszb, crack depth Lfsd and damaged surface number Pms are collected and obtained through infrared camera equipment; The damage assessment coefficient Dsxs is compared and analyzed with a preset damage assessment threshold Q to determine whether the automobile sheet metal parts are in need of replacement or repair: If the damage assessment coefficient Dsxs is greater than or equal to the preset damage assessment threshold Q, that is, Dsxs ≥ Q, it means that the current automobile sheet metal parts need to be directly replaced; If the damage assessment coefficient Dsxs is lower than the preset damage assessment threshold Q, that is, Dsxs<Q, it means that the current automobile sheet metal parts need to continue to be repaired.

[0038] In this embodiment, data such as the damaged area ratio Pszb, crack depth Lfsd and number of damaged surfaces Pms collected by the infrared camera equipment provide an accurate damage assessment for the maintenance project, and further reflect the maintenance history and current damage status of the automobile parts through the wear state factor Hsyz based on the historical maintenance record information. The damage assessment coefficient Dsxs can be used for further decision-making to determine whether the automobile sheet metal parts need to be replaced or further repaired. Comparing and analyzing the damage assessment coefficient Dsxs with the pre-set damage assessment threshold Q can provide an objective decision-making basis for car owners, repair shops and insurance companies. If the damage assessment coefficient Dsxs is higher than or equal to the damage assessment threshold Q, it means that replacement of parts is necessary; if the damage assessment coefficient Dsxs is lower than the damage assessment threshold Q, it means that continued repair is feasible.

[0039] Example 4 Please refer to Figure 1 Specifically, the maintenance personnel Wxrs are associated with the full-time years Zznx to obtain the labor generation coefficient Llxs, and after dimensionless processing, the labor generation coefficient Llxs is obtained by the following formula:

[0040] In the formula, It is expressed as the weight value of the number of maintenance personnel Wxrs. It is expressed as the weight value of full-time years Zznx, where: , ,and , P represents the constant correction coefficient.

[0041] By associating the labor generation coefficient Llxs with the damage assessment coefficient Dsxs, the time consumption index Xhzs is obtained, and after dimensionless processing, the time consumption index Xhzs is obtained by the following formula;

[0042] In the formula, Expressed as the weight value of the labor generation coefficient Llxs, It is expressed as the weight value of the damage assessment coefficient Dsxs, and B is expressed as the constant correction coefficient. , ,and .

[0043] When inspecting a vehicle, the bodywork technician locks in the determined repair range value, including known problems or damaged parts, and analyzes the image data set to determine the additional repair range value, and compares the additional repair range value with the determined repair range value to generate a proportional value Blz.

[0044] The extra working hours index Egzs is obtained by the following formula:

[0045] The significance of this formula is to determine the range of the extra working hours index Egzs based on the proportional relationship between the determined maintenance range value and the extra maintenance range value.

[0046] In this embodiment, by determining the extra work time index Egzs, it is helpful to quantify the impact of the extra maintenance work on the total work time, make the work time estimation more accurate and comprehensive, and reduce the erroneous evaluation of the maintenance work time.

[0047] Example 5 Please refer to Figure 1 Specifically: the working time evaluation index Pgzs is compared and analyzed with a preset evaluation threshold K to obtain a working time estimation report; wherein the evaluation threshold K includes a first threshold K1 and a second threshold K2, and the first threshold K1 is greater than the evaluation threshold K, and the second threshold K2 is less than the evaluation threshold K. The working time estimation report content is as follows: If the man-hour evaluation index Pgzs ≤ the second threshold value K2, it indicates that the current maintenance complexity of the automobile sheet metal parts is within 20%; If the second threshold value K2 < the man-hour evaluation index Pgzs ≤ the evaluation threshold value K, it indicates that the maintenance complexity of the current automobile sheet metal parts is within 20%-30%; If the evaluation threshold K < the man-hour evaluation index Pgzs ≤ the first threshold K1, it indicates that the maintenance complexity of the current automobile sheet metal parts has exceeded 30%; The corresponding estimate report will be assigned to the sheet metal technician of the corresponding level through the data information recorded in the personnel file and combined with the sheet metal technician's duty roster.

[0048] In this embodiment, based on the comparison of the working time evaluation index Pgzs with the first threshold value K1 and the second threshold value K2, it is convenient to further evaluate the maintenance complexity of automobile sheet metal parts. According to the different maintenance complexities, the working time estimation report is divided into three levels, which respectively represent different maintenance difficulty ranges. Such grading helps car owners and repair shops to better understand the complexity of maintenance projects; by combining personnel file data and the sheet metal technician's duty roster, the method can assign the estimation report to the sheet metal technician of the corresponding level, which helps to optimize personnel allocation and ensure that sheet metal technicians with appropriate experience and skills handle maintenance work of corresponding complexity.

[0049] Example: A certain auto repair shop has introduced a method for estimating the labor time for repairing auto sheet metal parts. The following is an example for the certain auto repair shop: Data collection: the proportion of damaged area Pszb is 25%; the crack depth Lfsd is 10; the number of repairs Wxcs is 3; is 0.25; is 0.43; is 0.50; C is 2; the number of damaged surfaces Pms is 6; the number of maintenance personnel Wxrs is 4; the professional years Zznx is 4.5; is 0.23; is 0.46; P is 5; B is 3; is 0.40; is 0.56; the proportion value Blz is 23%; the purchase quantity Cgsl is 2; is 0.30; is 0.35; is 0.45; R is 6; With the above data, the following calculations can be performed: Wear state factor Hsyz= =4.97; Damage coefficient Dsxs= =29.82; Labor generation coefficient Llxs= =4.33+5=9.33; Time consumption index =34.82+1495.41+3=1533.21; Extra working hours index Egzs= =9.0; Working hours evaluation index Pgzs= =712.48+0.9+6=719.38; If the preset evaluation threshold K is 700, the first threshold K1 is 725, and the second threshold K2 is 670, then the evaluation threshold K is less than the working hour evaluation index Pgzs≤the first threshold K1, indicating that the current maintenance complexity of automobile sheet metal parts has exceeded 30%. The corresponding estimate report is assigned to the sheet metal technician of the corresponding level through the data information recorded in the personnel file and combined with the sheet metal technician's duty roster.

[0050] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for estimating the maintenance time of automobile sheet metal parts, characterized in that: The following steps are involved: S1. Data collection: Use image acquisition equipment to capture and obtain continuous electronic images of the automobile sheet metal parts to be estimated in advance, and combine them with the historical data of automobile maintenance to collect and record the damage data of relevant sheet metal parts and the information of the sheet metal technicians assigned to the corresponding parts; S2, data analysis: pre-process the continuous images of automobile sheet metal parts, remove noise and smooth the images, identify and extract features in the continuous images, and improve the image quality based on image enhancement technology to generate image data sets; S3. Damage assessment: using convolutional neural network learning technology to deeply analyze and calculate the internal data information of the image data set, obtain: the proportion of damaged area Pszb, the crack depth Lfsd, the number of maintenance personnel Wxrs, the professional years Zznx and the number of damaged surfaces Pms; by associating the proportion of damaged area Pszb and the crack depth Lfsd, obtain the wear state factor Hsyz, and generate the damage assessment coefficient Dsxs in combination with the number of damaged surfaces Pms, compare and analyze the damage assessment coefficient Dsxs with the preset damage assessment threshold Q, and determine whether the automobile sheet metal parts are in the process of replacement or repair; S4, data analysis: according to the inspection of the sheet metal technician during maintenance, the maintenance scope value is locked, and combined with the damage assessment coefficient Dsxs, the time consumption index Xhzs is obtained, and the additional maintenance scope value is distinguished according to the maintenance scope value, and the additional working time index Egzs is generated in combination with the image data set; The time consumption index Xhzs and the extra working time index Egzs are associated with each other by machine learning calculation to obtain the working time evaluation index Pgzs. After dimensionless processing, the working time evaluation index Pgzs is obtained by the following formula: Where Cgsl is the purchase quantity, and They are respectively expressed as the weight values ​​of the time consumption index Xhzs, the extra working hours index Egzs and the purchase quantity Cgsl, where: , , ,and , R represents the constant correction coefficient; S5. Man-hour evaluation: Compare and analyze the man-hour evaluation index Pgzs with the preset evaluation threshold K, obtain a man-hour estimation report, and adopt a corresponding work plan based on the corresponding man-hour estimation report.

2. The method for estimating the maintenance man-hours of automobile sheet metal parts according to claim 1, characterized in that: Use image acquisition equipment to capture continuous electronic images of the automotive sheet metal parts to be estimated, and continuously record relevant image frames to ensure that the entire automotive sheet metal parts are fully recorded, and identify the relevant sheet metal parts damage data in the image, including the type, size, curvature, material type, degree of cracks, damage, and location and coordinates of the damage of automotive sheet metal parts. According to the data information in the image and the shooting order, the continuous image frames are sorted in the corresponding order; and combined with the automobile maintenance history data information, the sheet metal technician information assigned to the corresponding parts is determined.

3. The method for estimating the maintenance man-hours of automobile sheet metal parts according to claim 2, characterized in that: Using wavelet denoising technology, the data information in several image frames is decomposed through wavelet transform, and the noise component is removed in the wavelet domain. Several image frames are reconstructed back to the original domain through inverse transform, and histogram equalization is used to adjust the brightness, stretch the image range value, and adjust the image contrast; Image enhancement technology is used to extract key feature information from image frames, identify and analyze defective areas in the image, and select and adjust the degree of difference between different areas in the image frame based on their characteristics.

4. The method for estimating the maintenance man-hours of automobile sheet metal parts according to claim 3, characterized in that: The damaged area ratio Pszb and the crack depth Lfsd are correlated, and after dimensionless processing, the wear state factor Hsyz is obtained by the following formula: Where Wxcs is the number of maintenance times, and They are respectively represented by the weight values ​​of the damaged area proportion Pszb, crack depth Lfsd and repair times Wxcs, where: , , ,and , C represents the constant correction coefficient; The damage assessment coefficient Dsxs is obtained by the following formula: Where Pms is the number of damaged surfaces.

5. The method for estimating the maintenance man-hours of automobile sheet metal parts according to claim 4, characterized in that: The damage assessment coefficient Dsxs is compared and analyzed with a preset damage assessment threshold Q to determine whether the automobile sheet metal parts are in need of replacement or repair: If the damage assessment coefficient Dsxs is greater than or equal to the preset damage assessment threshold Q, that is, Dsxs ≥ Q, it means that the current automobile sheet metal parts need to be directly replaced; If the damage assessment coefficient Dsxs is lower than the preset damage assessment threshold Q, that is, Dsxs<Q, it means that the current automobile sheet metal parts need to continue to be repaired.

6. The method for estimating man-hours for repairing automobile sheet metal parts according to claim 5, characterized in that: The maintenance personnel Wxrs and the full-time years Zznx are associated to obtain the labor generation coefficient Llxs, and after dimensionless processing, the labor generation coefficient Llxs is obtained by the following formula: In the formula, It is expressed as the weight value of the number of maintenance personnel Wxrs. It is expressed as the weight value of full-time years Zznx, where: , ,and , P represents the constant correction coefficient.

7. The method for estimating the maintenance man-hours of automobile sheet metal parts according to claim 6, characterized in that: By associating the labor generation coefficient Llxs with the damage assessment coefficient Dsxs, the time consumption index Xhzs is obtained, and after dimensionless processing, the time consumption index Xhzs is obtained by the following formula; In the formula, Expressed as the weight value of the labor generation coefficient Llxs, It is expressed as the weight value of the damage assessment coefficient Dsxs, and B is expressed as the constant correction coefficient. , ,and .

8. The method for estimating man-hours for repairing automobile sheet metal parts according to claim 7, characterized in that: When inspecting a vehicle, the bodywork technician locks in the determined repair range value, including known problems or damaged parts, and analyzes the image data set to determine the additional repair range value, and compares the additional repair range value with the determined repair range value to generate a proportional value Blz.

9. The method for estimating man-hours for repairing automobile sheet metal parts according to claim 8, characterized in that: The extra working hours index Egzs is obtained by the following formula: The significance of this formula is to determine the range of the extra working hours index Egzs based on the proportional relationship between the determined maintenance range value and the extra maintenance range value.

10. The method for estimating man-hours for repairing automobile sheet metal parts according to claim 9, characterized in that: The man-hour evaluation index Pgzs is compared and analyzed with a preset evaluation threshold K to obtain a man-hour estimation report; wherein the evaluation threshold K includes a first threshold K1 and a second threshold K2, and the first threshold K1 is greater than the evaluation threshold K, and the second threshold K2 is less than the evaluation threshold K. The contents of the man-hour estimation report are as follows: If the man-hour evaluation index Pgzs ≤ the second threshold value K2, it indicates that the current maintenance complexity of the automobile sheet metal parts is within 20%; If the second threshold value K2 < the man-hour evaluation index Pgzs ≤ the evaluation threshold value K, it indicates that the maintenance complexity of the current automobile sheet metal parts is within 20%-30%; If the evaluation threshold K < the man-hour evaluation index Pgzs ≤ the first threshold K1, it indicates that the maintenance complexity of the current automobile sheet metal parts has exceeded 30%; The corresponding estimate report will be assigned to the sheet metal technician of the corresponding level through the data information recorded in the personnel file and combined with the sheet metal technician's duty roster.

Images