CN117010666A

CN117010666A - Intelligent management method and system for production workstation of automobile repair tool

Info

Publication number: CN117010666A
Application number: CN202311245935.1A
Authority: CN
Inventors: 黄远东; 魏水钧
Original assignee: Shenzhen Besita Technology Co ltd
Current assignee: Shenzhen Besita Technology Co ltd
Priority date: 2023-09-26
Filing date: 2023-09-26
Publication date: 2023-11-07
Anticipated expiration: 2043-09-26
Also published as: CN117010666B

Abstract

The invention relates to the technical field of production workstation management methods, in particular to an intelligent management method and system for a production workstation of a gas repair tool, which construct a pre-processing three-dimensional model diagram of a workpiece according to pre-processing image information; comparing the pre-processed three-dimensional model diagram with a standard three-dimensional model diagram to obtain a processing deviation model diagram, and obtaining weight vector information of the processing deviation model diagram; performing fault prediction on a corresponding production workstation in a target production workshop according to the weight vector information of the processing deviation model diagram to obtain estimated maintenance time of the corresponding fault type of the production workstation; and acquiring workpiece order information, generating a final scheduling plan based on the estimated maintenance time of the production workstation in corresponding fault type and the workpiece order information, and outputting the final scheduling plan. The method can enable the production planning of each production workstation in the production workshop to be more reasonable, and improves the economic benefit.

Description

Intelligent management method and system for production workstation of automobile repair tool

Technical Field

The invention relates to the technical field of production workstation management methods, in particular to an intelligent management method and system for a production workstation of a gas repair tool.

Background

The development of the automobile industry is increasingly rapid, and the automobile maintenance market is expanding continuously. The use of various automotive repair tools is becoming increasingly important in automotive repair processes. When the blank is processed into a finished product of the repairing tool, the forging processing of the blank by the forging production work stations is a necessary step, a large number of forging production work stations exist in a production workshop, and each work station can be processed and produced independently. In order to increase the productivity and management level of the repair tools and reduce the errors and losses of manual operations, an intelligent method is needed to manage the numerous repair tool forging production stations in the production plant. The traditional management method of the forging production workstation of the gas repair tool has the problems of low processing efficiency, high product rejection rate, dependence on manual shift and the like, and needs to introduce new technical means for improvement.

Disclosure of Invention

The invention overcomes the defects of the prior art and provides an intelligent management method and system for a production workstation of a gas repair tool.

The technical scheme adopted by the invention for achieving the purpose is as follows:

the invention discloses an intelligent management method for a production workstation of a vehicle repair tool, which comprises the following steps:

S102: preprocessing each production workstation in a target production workshop, acquiring preprocessing image information of a workpiece after preprocessing of each production workstation, and constructing a preprocessing three-dimensional model diagram of the workpiece according to the preprocessing image information;

s104: comparing the pre-processed three-dimensional model diagram with a standard three-dimensional model diagram to obtain a processing deviation model diagram, and obtaining weight vector information of the processing deviation model diagram;

s106: performing fault prediction on a corresponding production workstation in a target production workshop according to the weight vector information of the processing deviation model diagram to obtain estimated maintenance time of the corresponding fault type of the production workstation;

s108: and acquiring workpiece order information, generating a final scheduling plan based on the estimated maintenance time of the production workstation in corresponding fault type and the workpiece order information, and outputting the final scheduling plan.

Further, in a preferred embodiment of the present invention, preprocessing image information of a workpiece after preprocessing at each production workstation is obtained, and a preprocessing three-dimensional model diagram of the workpiece is constructed according to the preprocessing image information, specifically:

the method comprises the steps of obtaining pre-processing image information of a workpiece after pre-processing of each production workstation through a camera mechanism, and carrying out noise reduction and median filtering treatment on the pre-processing image information to obtain processed pre-processing image information;

Matching the processed preprocessing image information through an ORB algorithm to obtain a plurality of characteristic points; calculating the isolated score of each characteristic point through an isolated forest algorithm, and eliminating the characteristic points with the isolated score being larger than a preset isolated score to obtain a plurality of evacuation characteristic points;

constructing a three-dimensional coordinate system, and importing a plurality of evacuation characteristic points into the three-dimensional coordinate system value to obtain three-dimensional coordinate values of each evacuation characteristic point; calculating Chebyshev distances among the evacuation feature points according to the three-dimensional coordinate values, and carrying out matching processing on the evacuation feature points according to the Chebyshev distances to obtain a plurality of pairs of evacuation feature point pairs;

carrying out connection processing on each pair of evacuation characteristic points to obtain a plurality of characteristic lines, and carrying out discrete processing on the plurality of characteristic lines to obtain a plurality of discrete characteristic points; obtaining dense feature points based on the evacuation feature points and the discrete feature points;

taking each dense characteristic point as a node of the graph, constructing the graph by connecting adjacent points, then reconstructing the curved surface by using a graph theory algorithm to generate a plurality of curved surface models, and combining the plurality of curved surface models to obtain a complete curved surface model graph;

And acquiring point cloud data of each dense characteristic point, and mapping the point cloud data into the curved surface model graph to endow the curved surface model graph with textures and colors, so as to reconstruct and obtain a prefabricated three-dimensional model graph of the workpiece.

Further, in a preferred embodiment of the present invention, the pre-processed three-dimensional model map is compared with a standard three-dimensional model map to obtain a processing deviation model map, and weight vector information of the processing deviation model map is obtained, which specifically includes:

constructing a grid space coordinate system by prefabricating a standard three-dimensional model diagram of a workpiece after preprocessing, and integrating the standard three-dimensional model diagram into the grid space coordinate system;

acquiring a pre-processing three-dimensional model image of a workpiece after pre-processing of each production workstation, importing the pre-processing three-dimensional model image into the grid space coordinate system, and enabling the standard three-dimensional model image to coincide with a processing reference surface of the pre-processing three-dimensional model image so as to register the standard three-dimensional model image with the pre-processing three-dimensional model image;

after registration is completed, removing the model part of the pre-processing three-dimensional model graph and the model part of the standard three-dimensional model graph, which are overlapped in a grid space coordinate system, and reserving the model part which is not overlapped to obtain a processing deviation model graph;

Acquiring the corner points of the processing deviation model diagram through a Harris corner point detection algorithm, and defining a local area for each detected corner point, wherein the local area comprises the corner points and neighbor points within a preset range; for each local region, obtaining a group of feature combinations to represent geometrical properties of the corner points; wherein the feature combination is an angle feature, a curvature feature, a normal variation and a corner point density combination;

for each corner point, combining the obtained features into a feature vector, and collecting all the feature vectors to obtain a feature vector set; and carrying out weighting treatment on the characteristic vector set to obtain weight vector information of the processing deviation model diagram.

Further, in a preferred embodiment of the present invention, according to the weight vector information of the process deviation model diagram, fault prediction is performed on a corresponding production workstation in the target production shop, so as to obtain an estimated maintenance time when the production workstation generates a corresponding fault type, which specifically includes:

s202: constructing a Bayesian network, and defining nodes in the Bayesian network as variables related to the states of the production workstations; importing the weight vector information into the Bayesian network, and acquiring the conditional probability distribution of each node according to the weight vector information;

S204: determining the state transition probability between the prefabricated three-dimensional model diagram and the corresponding production workstation based on the conditional probability distribution of each node, and determining the fault probability of the corresponding production workstation according to the state transition probability;

s206: comparing the fault probability of the production workstation with a preset fault probability; if the fault probability of the production workstation is larger than the preset fault probability, acquiring the fault type of the production workstation;

s208: and generating a search tag according to the fault type, and searching the big data network based on the search tag to search the estimated maintenance time of the production workstation corresponding to the fault type.

Further, in a preferred embodiment of the present invention, work order information is obtained, a final scheduling plan is generated based on the estimated maintenance time of the production workstation for the corresponding failure type and the work order information, and the final scheduling plan is output, specifically:

acquiring effective processing time of each production workstation in actual production processing within a preset time period according to the estimated maintenance time of the corresponding fault type of each production workstation;

constructing a sorting table, importing the effective processing time of a production workstation in actual production processing into the sorting table for sorting, and obtaining a sorting result of sorting from big to small in the effective processing time after sorting is completed; determining an initial scheduling plan of each production workstation in the target production workshop according to the sequencing result;

Determining a production workstation needing to be processed and produced according to the initial scheduling plan, and acquiring the limit manufacturing precision of the production workstation needing to be processed and produced in the initial scheduling plan;

acquiring workpiece order information, and acquiring minimum manufacturing precision required by processing a current batch of workpieces according to the workpiece order information; comparing the limit manufacturing precision of a production workstation which needs to be processed and produced in the initial scheduling plan with the minimum manufacturing precision required by processing the workpieces in the current batch;

and if the limit manufacturing precision of the production work stations which need to be processed and produced in the initial scheduling plan is larger than the minimum manufacturing precision required by processing the workpieces in the current batch, outputting the initial scheduling plan as a final scheduling plan.

Further, in a preferred embodiment of the present invention, the method further comprises the steps of:

s302: if the limit manufacturing precision of the production workstation which needs to be processed and produced in the initial scheduling plan is not more than the minimum manufacturing precision required by processing the workpieces in the current batch, extracting the production workstation with the limit manufacturing precision not more than the minimum manufacturing precision in the initial scheduling plan;

S304: searching a production workstation in an idle state in a target production workshop according to the sorting result, replacing a production workstation with limit manufacturing precision not greater than minimum manufacturing precision in an initial scheduling plan with the production workstation in the idle state, and updating the initial scheduling plan to obtain a secondary scheduling plan;

s306: determining a production workstation needing to be processed and produced according to the secondary scheduling plan, and acquiring the limit manufacturing precision of the production workstation needing to be processed and produced in the secondary scheduling plan; comparing the limit manufacturing precision of a production workstation which needs to be processed and produced in the secondary scheduling plan with the minimum manufacturing precision required by processing the workpieces in the current batch;

s308: if the limit manufacturing precision of the production workstation which needs to be processed and produced in the secondary scheduling plan is larger than the minimum manufacturing precision required by processing the workpieces in the current batch, outputting the secondary scheduling plan as a final scheduling plan;

s310: and if the limit manufacturing precision of the production work station required to be processed and produced in the secondary scheduling plan is not more than the minimum manufacturing precision required to process the workpieces in the current batch, repeating the steps S304-308 until the limit manufacturing precision of the production work station required to be processed and produced in the secondary scheduling plan is more than the minimum manufacturing precision required to process the workpieces in the current batch, and outputting the secondary scheduling plan as a final scheduling plan.

The invention discloses an intelligent management system for a production workstation of a gas repair tool, which comprises a memory and a processor, wherein the memory stores an intelligent management method program for the production workstation of the gas repair tool, and when the intelligent management method program for the production workstation of the gas repair tool is executed by the processor, the intelligent management system realizes the following steps:

preprocessing each production workstation in a target production workshop, acquiring preprocessing image information of a workpiece after preprocessing of each production workstation, and constructing a preprocessing three-dimensional model diagram of the workpiece according to the preprocessing image information;

comparing the pre-processed three-dimensional model diagram with a standard three-dimensional model diagram to obtain a processing deviation model diagram, and obtaining weight vector information of the processing deviation model diagram;

performing fault prediction on a corresponding production workstation in a target production workshop according to the weight vector information of the processing deviation model diagram to obtain estimated maintenance time of the corresponding fault type of the production workstation;

and acquiring workpiece order information, generating a final scheduling plan based on the estimated maintenance time of the production workstation in corresponding fault type and the workpiece order information, and outputting the final scheduling plan.

constructing a Bayesian network, and defining nodes in the Bayesian network as variables related to the states of the production workstations; importing the weight vector information into the Bayesian network, and acquiring the conditional probability distribution of each node according to the weight vector information;

determining the state transition probability between the prefabricated three-dimensional model diagram and the corresponding production workstation based on the conditional probability distribution of each node, and determining the fault probability of the corresponding production workstation according to the state transition probability;

comparing the fault probability of the production workstation with a preset fault probability; if the fault probability of the production workstation is larger than the preset fault probability, acquiring the fault type of the production workstation;

and generating a search tag according to the fault type, and searching the big data network based on the search tag to search the estimated maintenance time of the production workstation corresponding to the fault type.

if the limit manufacturing precision of the production workstation which needs to be processed and produced in the initial scheduling plan is not more than the minimum manufacturing precision required by processing the workpieces in the current batch, extracting the production workstation with the limit manufacturing precision not more than the minimum manufacturing precision in the initial scheduling plan;

searching a production workstation in an idle state in a target production workshop according to the sorting result, replacing a production workstation with limit manufacturing precision not greater than minimum manufacturing precision in an initial scheduling plan with the production workstation in the idle state, and updating the initial scheduling plan to obtain a secondary scheduling plan;

determining a production workstation needing to be processed and produced according to the secondary scheduling plan, and acquiring the limit manufacturing precision of the production workstation needing to be processed and produced in the secondary scheduling plan; comparing the limit manufacturing precision of a production workstation which needs to be processed and produced in the secondary scheduling plan with the minimum manufacturing precision required by processing the workpieces in the current batch;

If the limit manufacturing precision of the production workstation which needs to be processed and produced in the secondary scheduling plan is larger than the minimum manufacturing precision required by processing the workpieces in the current batch, outputting the secondary scheduling plan as a final scheduling plan;

and if the limit manufacturing precision of the production work station required to be processed and produced in the secondary scheduling plan is not more than the minimum manufacturing precision required to process the workpieces in the current batch, repeating the steps S304-308 until the limit manufacturing precision of the production work station required to be processed and produced in the secondary scheduling plan is more than the minimum manufacturing precision required to process the workpieces in the current batch, and outputting the secondary scheduling plan as a final scheduling plan.

The invention solves the technical defects existing in the background technology, and has the following beneficial effects: the method can ensure that the workpieces processed in each production workstation meet the manufacturing precision requirement of the target order, and reduce the rejection rate; the processing production time required for processing the workpiece of the target order can be minimized, so that the processing efficiency is further improved; the number of production work stations required for processing the work pieces of the target order batch can be minimized, more idle production work stations can be saved, so that the idle production work stations can process the work pieces of other orders, and the processing cost can be effectively saved; the production planning of each production workstation in the production workshop is more reasonable, and the economic benefit is improved.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a first method flow diagram of a method for intelligent management of a production workstation of a repair tool;

FIG. 2 is a second method flow diagram of a method for intelligent management of a production workstation of a repair tool;

FIG. 3 is a third method flow diagram of a method for intelligent management of a production workstation of a repair tool;

FIG. 4 is a system block diagram of an intelligent management system for a production workstation of a repair tool.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

As shown in fig. 1, the first aspect of the present invention discloses an intelligent management method for a production workstation of a repair tool, comprising the following steps:

The pre-machining refers to forging pre-machining by putting a certain number of blanks (such as 1, 3 or 5 blanks) through a production workstation, and aims to calculate the fault state and fault probability of the corresponding workstation in mass production through the actual condition of the forged workpiece finished product.

The preprocessing image information of the workpiece after the preprocessing is acquired by an industrial camera or the like mounted on the production workstation, and then the preprocessing image information is preprocessed by an image preprocessing technique, so that the preprocessed preprocessing image information is obtained. After a plurality of feature points are obtained through ORB algorithm matching, abnormal feature points such as drift and displacement exist in the plurality of feature points, and the abnormal feature points are outliers, so that in order to eliminate the influence of the outliers on modeling accuracy, the outliers need to be detected and removed. And when outlier feature points are removed, the number of the left feature points is often not large, and the outlier feature points are the evacuation feature points, and if the preprocessing three-dimensional model diagram is directly reconstructed according to the evacuation feature points, the obtained preprocessing three-dimensional model diagram has abnormal phenomena of local deletion, and the model precision is low, so that more feature points are required to be further acquired, thereby obtaining dense feature points, and then the preprocessing three-dimensional model diagram is reconstructed according to the dense feature points and based on a point cloud reconstruction mode. The method can reconstruct and obtain the prefabricated three-dimensional model diagram with high precision and high integrity according to the image information, further improve the analysis precision of the follow-up model and improve the reliability of the scheduling plan of each production workstation.

It should be noted that ORB (Oriented FAST and Rotated BRIEF) is a feature point detection and description algorithm commonly used in computer vision, and has the advantages of high speed, and suitability for real-time application and devices with limited computing resources. The isolated forest algorithm is an anomaly detection method based on a tree structure, adopts a high-efficiency random segmentation strategy, detects abnormal points in data by constructing a plurality of isolated trees, and has the main ideas that: the outliers are sparsely distributed in the dataset and thus may be separated from other outliers by less random segmentation.

The standard three-dimensional model diagram of the workpiece after the pre-processing is obtained through three-dimensional modeling software, and the standard three-dimensional model diagram is a standard specification model of size parameters, texture parameters and the like of a blank after the blank is forged and processed by a production workstation. The Harris corner detection algorithm (Harris corner detection algorithm) mainly aims at detecting pixel points near corner points by applying small windows at different positions in an image, wherein the corner points are usually obvious change areas in the image, and compared with the flat areas and edges, the flat areas and edges are usually not changed greatly, and the algorithm judges whether the pixel points are positioned at the corner point positions or not by calculating gray level changes of the pixel points in different directions. The construction method of the feature vector may vary from task to task, and depending on the specific requirements, the selection of the features, the calculation mode and the normalization method may need to be adjusted, and the quality and effectiveness of the feature vector depend on the selected features and their performances in different scenes. The fitting effect of the prefabricated three-dimensional model diagram and the standard three-dimensional model diagram is quantified through weight vector information, and the smaller the weight vector information is, the higher the coincidence degree between the prefabricated three-dimensional model diagram and the standard three-dimensional model diagram is, which means that the higher the quality of the prefabricated three-dimensional model diagram is.

As shown in fig. 2, in a further preferred embodiment of the present invention, according to the weight vector information of the process deviation model diagram, fault prediction is performed on a corresponding production workstation in the target production shop, so as to obtain an estimated maintenance time when the production workstation generates a corresponding fault type, which specifically is:

In the process of working and running of the production workstation, when the accumulated error or performance degradation state of a plurality of sub-devices in the production workstation reaches a certain node, the production workstation shows a corresponding fault state, and the accumulated error or performance degradation state of each sub-device can be inverted through the quality of a workpiece processed by the sub-device through a bayesian network, for example, after continuous long-time forging processing is performed, transmission parts such as a transmission gear and a transmission shaft in the production workstation are worn out, and certain accumulated error is formed, when the parts are worn out to a certain extent or the accumulated error is larger than a certain threshold value, the greater the part wear degree is, the lower the dimensional quality of the processed workpiece is, and when the certain processing node is reached, the transmission parts are also failed, and the processed parts are not up to standard, at the moment, the production workstation is in the fault state. The bayesian network is a graph model for modeling and representing the dependency relationship between random variables, the process of deducing the probability of equipment faults through the bayesian network involves probability inference and calculation of conditional probability, the bayesian network can be used for modeling the relationship between the cause and effect of equipment faults, so that the probability of different fault states is deduced based on observed data or information, the possible faults of each piece of equipment can be deduced according to the fault state with the highest probability, and the probability of specific faults in a future time range can be predicted. According to the method, whether the corresponding production workstation can fail within the preset time period or not and the failure type of the failure can be deduced according to the quantized weight vector information, and the estimated maintenance time of the corresponding failure type can be further searched in a big data network according to the failure type.

If the failure probability of the production workstation is not greater than the preset failure probability, the failure probability of the production workstation is extremely low, and the estimated maintenance time of the production workstation is zero.

As shown in fig. 3, in a preferred embodiment of the present invention, the method further comprises the following steps:

By the steps, a scheduling plan which meets the requirement of the workpiece order and can minimize the production time can be planned according to the effective processing time of each production workstation in the target production workshop. The workpiece processed in each production workstation can meet the manufacturing precision requirement of a target order, and the rejection rate is reduced; the processing production time required for processing the workpiece of the target order can be minimized, so that the processing efficiency is further improved; the number of production work stations required for processing the work pieces of the target order batch can be minimized, more idle production work stations can be saved, so that the idle production work stations can process the work pieces of other orders, and the processing cost can be effectively saved; the production planning of each production workstation in the production workshop is more reasonable, the economic benefit is improved, and the method is suitable for large-scale automatic production workshops.

In addition, the intelligent management method of the production workstation of the automobile repair tool further comprises the following steps:

acquiring a final scheduling plan, and determining a production workstation for processing a target order workpiece according to the final scheduling plan;

controlling a production workstation for processing target order workpieces to process blanks, acquiring real-time workpiece image information of the workpieces, and constructing a real-time workpiece model diagram according to the real-time processing image information;

acquiring a preset workpiece model diagram of a workpiece processed by a production workstation under different processing environment combination conditions through a large data network, constructing a database, and importing the preset workpiece model diagram of the workpiece processed by the production workstation under different processing environment combination conditions into the database;

acquiring a real-time processing environment of a production workstation for processing a target order workpiece during processing, and importing the real-time processing environment into the database to obtain a preset workpiece model diagram under the real-time processing environment condition;

calculating the similarity between the real-time workpiece model diagram and a preset workpiece model diagram through a Euclidean distance algorithm; comparing the similarity with a preset similarity;

If the similarity is not greater than the preset similarity, the real-time workpiece model image and the preset workpiece model image are imported into the grid space coordinate system for pairing comparison, and a workpiece deviation model image is obtained;

searching a big data network according to the workpiece deviation model diagram to obtain the optimal processing parameters for correcting the workpiece deviation model diagram;

and comparing the optimal processing parameters with preset processing parameters of the production work station to obtain processing parameter deviation, and adjusting the preset processing parameters of the production work station based on the processing parameter deviation.

When a final scheduling plan of the processing target order is obtained, corresponding production work stations are allocated according to the final scheduling plan to process and produce the workpiece, and in the process of processing and producing the workpiece by the production work stations, a real-time workpiece model diagram of each production work station is obtained. Because the processing environment (such as temperature, humidity, dust degree and the like) has a certain influence on the processing size and shape of the workpiece, the size of the workpiece is larger when the temperature is too high, and therefore, a preset workpiece model diagram under the combined condition of different processing environments is obtained, so that the influence of the environment on the detection result is eliminated. If the similarity is not greater than the preset similarity, the fact that the deviation between the size and the shape of the workpiece and the ideal size and shape is large is indicated, and at the moment, the machining parameters of the production workstation are required to be adjusted so as to reduce the rejection rate of the workpiece, reduce the production cost and realize the functions of intelligent machining detection and adjustment.

acquiring historical operation data of each piece of sub-equipment in the production workstation under different processing environment combination conditions; constructing a prediction model, and importing historical operation data of each piece of equipment under different processing environment combination conditions into the prediction model for training to obtain a trained prediction model;

acquiring a real-time processing environment of a production workstation during processing, and importing the real-time processing environment into the trained prediction model to obtain preset operation data of each piece of equipment in the production workstation under the condition of the real-time processing environment;

acquiring actual operation data of each piece of sub-equipment in the production workstation in a preset time period; calculating a hash value between the actual operation data and preset operation data through a hash algorithm; comparing the hash value with a preset hash value;

and if the hash value is not greater than the preset hash value, marking the sub-equipment corresponding to the hash value which is not greater than the preset hash value as fault equipment.

It should be noted that, by comparing the historical operation data of each piece of sub-equipment in the production workstation with the actual operation data thereof, whether the sub-equipment in the corresponding production workstation has faults or not is analyzed, and the functions of automatic fault monitoring and automatic tracing are realized.

As shown in fig. 4, the second aspect of the present invention discloses an intelligent management system for a production workstation of a repair tool, where the intelligent management system for a production workstation of a repair tool includes a memory 78 and a processor 79, where a program of an intelligent management method for a production workstation of a repair tool is stored in the memory 78, and when the program of the intelligent management method for a production workstation of a repair tool is executed by the processor 79, the following steps are implemented:

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.

Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. The intelligent management method for the production workstation of the automobile repair tool is characterized by comprising the following steps of:

2. The intelligent management method of a production workstation of a repair tool according to claim 1, wherein the method is characterized by obtaining the pre-processing image information of the workpiece after the pre-processing of each production workstation, and constructing a pre-processing three-dimensional model diagram of the workpiece according to the pre-processing image information, and specifically comprises the following steps:

3. The intelligent management method of a production workstation of a repair tool according to claim 1, wherein comparing the pre-processed three-dimensional model diagram with a standard three-dimensional model diagram to obtain a processing deviation model diagram, and obtaining weight vector information of the processing deviation model diagram, specifically:

4. The intelligent management method of a production workstation of a repair tool according to claim 1, wherein the fault prediction is performed on a corresponding production workstation in a target production shop according to weight vector information of the processing deviation model diagram, so as to obtain estimated repair time of the corresponding fault type of the production workstation, specifically:

5. The intelligent management method of a production workstation of a repair tool according to claim 1, wherein the method is characterized in that work order information is obtained, a final scheduling plan is generated based on the estimated maintenance time of the production workstation with the corresponding fault type and the work order information, and the final scheduling plan is output, specifically:

6. The method for intelligently managing a production workstation of a repair tool according to claim 5, further comprising the steps of:

7. The intelligent management system for the production workstation of the automobile repair tool is characterized by comprising a memory and a processor, wherein the memory stores an intelligent management method program for the production workstation of the automobile repair tool, and when the intelligent management method program for the production workstation of the automobile repair tool is executed by the processor, the intelligent management method program for the production workstation of the automobile repair tool realizes the following steps:

8. The intelligent management system of a production workstation of a repair tool according to claim 7, wherein the fault prediction is performed on the corresponding production workstation in the target production shop according to the weight vector information of the process deviation model diagram, so as to obtain the estimated repair time of the corresponding fault type of the production workstation, specifically:

9. The intelligent management system of a production workstation of a repair tool according to claim 7, wherein the work order information is obtained, a final scheduling plan is generated based on the estimated repair time of the production workstation with the corresponding fault type and the work order information, and the final scheduling plan is output, specifically:

10. The intelligent management system of a repair tool production workstation of claim 9, further comprising the steps of: