Assembly detection method and device for four doors and two covers of automobile

Abstract

The invention provides an assembly detection method and device for four doors and two covers of an automobile, and the method comprises the steps: collecting to-be-detected information of a target automobile in a first state, and enabling the first state to be a state that the target automobile is provided with four doors and two covers; the to-be-detected information is input into an assembly prediction model, predicted assembly information, output by the assembly prediction model, of the target vehicle in a second state is obtained, and the second state is the state that the target vehicle is assembled with four doors, two covers and four-door-two-cover accessories; and determining four-door two-cover detection information of the target vehicle in the first state based on the predicted assembly information. By means of the method, it is avoided that maintenance is conducted again in a final assembly workshop in the later period, then the maintenance and adjustment cost is reduced, and the good appearance quality of the whole vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of automobile assembly technology, and in particular to an assembly detection method for automobile four doors and two covers. The present application also relates to an assembly detection device for automobile four doors and two covers, a computing device, and a computer-readable storage medium. Background Art

[0002] In the automobile structure, there is a certain gap between the four doors and two covers of the automobile and the body, except for the hinged connection structure. The gap is an important indicator of automobile quality. Good appearance quality requires consistent gaps. The four doors and two covers of a car usually refer to the four doors, front hood and trunk lid of the car.

[0003] However, in actual production, the four doors and two covers of a car are assembled in a welding workshop. After entering the final assembly workshop, various related accessories, such as trim panels, glass, door locks, etc., are added to the four doors and two covers of the car, which increases the weight of the four doors and two covers, causing the four doors and two covers to fall in the subsequent final assembly workshop, and then the gap between the four doors and two covers of the car and the body changes. As a result, the four doors and two covers installed in the welding workshop may be qualified, but may become unqualified after the four doors and two cover accessories are installed in the final assembly workshop. Based on this, technicians are in urgent need of a solution to solve the above problem. Summary of the invention

[0004] In view of this, the embodiment of the present application provides an assembly detection method for a four-door and two-hood vehicle. The present application also relates to an assembly detection device for a four-door and two-hood vehicle, a computing device, and a computer-readable storage medium to solve the above problems existing in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a method for detecting the assembly of four doors and two covers of a vehicle is provided, comprising:

[0006] Collecting information to be detected of the target vehicle in a first state, wherein the first state is a state in which the target vehicle is equipped with four doors and two covers;

[0007] Inputting the information to be detected into an assembly prediction model, obtaining the predicted assembly information of the target vehicle in a second state output by the assembly prediction model, wherein the second state is a state in which the target vehicle is equipped with four doors and two covers and four doors and two covers accessories;

[0008] Based on the predicted assembly information, four-door and two-hood detection information of the target vehicle in the first state is determined.

[0009] According to a second aspect of an embodiment of the present application, there is provided an assembly detection device for a vehicle with four doors and two covers, comprising:

[0010] A collection module is configured to collect information to be detected of the target vehicle in a first state, wherein the first state is a state in which the target vehicle is equipped with four doors and two covers;

[0011] A prediction module is configured to input the information to be detected into an assembly prediction model, and obtain the predicted assembly information of the target vehicle output by the assembly prediction model in a second state, wherein the second state is a state in which the target vehicle is equipped with four doors and two covers and four doors and two covers accessories;

[0012] The detection module is configured to determine the four-door and two-hood detection information of the target vehicle in the first state based on the predicted assembly information.

[0013] According to a third aspect of an embodiment of the present application, a computing device is provided, comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein the processor implements the steps of the assembly detection method for four doors and two covers of a vehicle when executing the computer instructions.

[0014] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer instructions. When the computer instructions are executed by a processor, the steps of the assembly detection method for four doors and two covers of a vehicle are implemented.

[0015] The present application provides an assembly detection method for a four-door two-hood automobile, which collects information to be detected of a target vehicle in a first state, wherein the first state is a state in which the target vehicle is assembled with four doors and two hoods; inputs the information to be detected into an assembly prediction model, and obtains predicted assembly information of the target vehicle in a second state output by the assembly prediction model, wherein the second state is a state in which the target vehicle is assembled with four doors and two hoods and four-door two-hood accessories; and determines four-door two-hood detection information of the target vehicle in the first state based on the predicted assembly information.

[0016] An embodiment of the present application realizes obtaining the information to be detected when the target vehicle is in the first state. The first state specifically refers to the state in which four doors and two covers are installed on the vehicle body during installation in the welding workshop. The information to be detected at this time specifically refers to the gap information of the four doors and two covers installed on the vehicle body. The predicted assembly information of the current vehicle in the second state is predicted based on the information to be detected and the pre-trained assembly prediction model. The second state specifically refers to the state after various accessories are installed on the four doors and two covers in the final assembly workshop. The predicted assembly information at this time specifically refers to the gap information of the four doors and two covers of the four doors and two covers in the second state. The detection information of the information to be detected in the current first state is judged based on the predicted assembly information, and the welding workshop determines whether the vehicle enters the next operation workshop or the maintenance workshop based on the detection information. Therefore, the maintenance and adjustment work is started at the welding workshop, avoiding the need for maintenance in the final assembly workshop at a later stage, thereby reducing the cost of maintenance and adjustment and improving the good appearance quality of the whole vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a structural diagram of an assembly detection system for a vehicle with four doors and two covers provided by an embodiment of the present application;

[0018] Figure 2 This is a flow chart of an assembly inspection method for four doors and two covers of a car provided by an embodiment of the present application;

[0019] Figure 3 This is a processing flow chart of an assembly detection method for four doors and two covers of an A-type automobile provided by an embodiment of the present application;

[0020] Figure 4 This is a structural schematic diagram of an assembly detection device for four doors and two covers of a car provided by an embodiment of the present application;

[0021] Figure 5 It is a structural block diagram of a computing device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0023] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0024] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0025] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards in the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0026] In the automobile structure, there is a certain gap between the four doors and two covers of the automobile and the body, except for the hinged connection structure. This gap is an important indicator of automobile quality. Good appearance quality requires consistent gaps.

[0027] However, in actual production, the four doors and two covers of the car are assembled in the welding workshop. After entering the final assembly workshop, various related accessories such as trim, glass, door locks, etc. are added to the four doors and two covers of the car, which increases the weight of the four doors and two covers, causing the four doors and two covers of the car to fall in the subsequent final assembly workshop, and then the gap between the four doors and two covers of the car and the body changes, so that if the four doors and two covers are installed in the welding workshop, they may fail to meet the requirements after the four doors and two covers are installed in the final assembly workshop, resulting in the car being unable to be used offline and high maintenance costs. Therefore, a detection method for assembling four doors and two covers for cars is urgently needed to improve the qualified rate when assembling four doors and two covers.

[0028] Based on this, in the present application, a method for assembly detection of a four-door and two-hood automobile is provided. The present application also relates to an assembly detection device for a four-door and two-hood automobile, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0029] See also Figure 1 , Figure 1 The structure diagram of an assembly detection system for a four-door and two-hood vehicle provided by an embodiment of the present specification is shown. The assembly detection system for a four-door and two-hood vehicle may include a client 100 and a server 200;

[0030] The client 100 is used to send the information to be detected to the server 200, wherein the information to be detected is the detection information of the target vehicle in the first state, and the first state is the state in which the target vehicle is equipped with four doors and two covers;

[0031] The server 200 is used to input the information to be detected into the assembly prediction model, obtain the predicted assembly information of the target vehicle in the second state output by the assembly prediction model, determine the four-door two-hood detection information of the target vehicle in the first state based on the predicted assembly information, wherein the second state is the state where the target vehicle is equipped with four doors and two hoods and four-door two-hood accessories; and send the four-door two-hood detection information to the client 100;

[0032] The client 100 is also used to receive the four-door and two-cover detection information sent by the server 200.

[0033] By applying the scheme of the embodiment of this specification, when the target vehicle is in the first state, the information to be detected is obtained. The first state specifically refers to the state in which four doors and two covers are installed on the vehicle body during installation in the welding workshop. The information to be detected at this time specifically refers to the gap information of the four doors and two covers installed on the vehicle body. The predicted assembly information of the current vehicle in the second state is predicted based on the information to be detected and the pre-trained assembly prediction model. The second state specifically refers to the state after various accessories are installed on the four doors and two covers in the final assembly workshop. The predicted assembly information at this time specifically refers to the gap information of the four doors and two covers of the four doors and two covers in the second state. The detection information of the information to be detected in the current first state is judged based on the predicted assembly information, and the welding workshop is determined based on the detection information whether the vehicle enters the next operation workshop or the maintenance workshop. Thus, the maintenance and adjustment work is started in the welding workshop, avoiding the need for maintenance in the final assembly workshop at a later stage, thereby reducing the cost of maintenance and adjustment and improving the good appearance quality of the whole vehicle.

[0034] The automobile four-door two-hood assembly detection system may include multiple clients 100 and a server 200, wherein the client 100 may be referred to as a terminal-side device and the server 200 may be referred to as a cloud-side device. Multiple clients 100 may establish a communication connection through the server 200. In the automobile four-door two-hood assembly detection scenario, the server 200 is used to provide automobile four-door two-hood assembly detection services between multiple clients 100. Multiple clients 100 may serve as a sender or a receiver, respectively, and realize communication through the server 200.

[0035] The user can interact with the server 200 through the client 100 to receive data sent by other clients 100, or send data to other clients 100, etc. In the assembly detection scenario of four doors and two hoods of a car, the user can publish a data stream to the server 200 through the client 100, and the server 200 generates four-door and two-hood detection information according to the data stream, and pushes the four-door and two-hood detection information to other clients that have established communication.

[0036] The client 100 and the server 200 are connected via a network. The network provides a medium for a communication link between the client 100 and the server 200. The network may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The data transmitted by the client 100 may need to be encoded, transcoded, compressed, etc. before being released to the server 200.

[0037] The client 100 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 100 can be based on the software development kit (SDK, Software Development Kit) of the corresponding service provided by the server 200, such as based on the real-time communication (RTC, Real Time Communication) SDK development and acquisition. The client 100 can be deployed in an electronic device, and needs to rely on the device to run or some APPs in the device to run. For example, the electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0038] The server 200 may include servers that provide various services, such as servers that provide communication services to multiple clients, servers for background training that provide support for models used on clients, and servers that process data sent by clients. It should be noted that the server 200 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0039] It is worth noting that the assembly detection method for a four-door and two-hood vehicle provided in the embodiments of this specification is generally executed by the server, but in other embodiments of this specification, the client may also have similar functions to the server, thereby executing the assembly detection method for a four-door and two-hood vehicle provided in the embodiments of this specification. In other embodiments, the assembly detection method for a four-door and two-hood vehicle provided in the embodiments of this specification may also be executed jointly by the client and the server.

[0040] Figure 2 A flowchart of an assembly detection method for four doors and two covers of a vehicle provided according to an embodiment of the present application is shown, which specifically includes the following steps:

[0041] Step 202: Collecting information to be detected of the target vehicle in a first state, wherein the first state is a state where the target vehicle is equipped with four doors and two covers.

[0042] Among them, the target vehicle specifically refers to the vehicle currently being tested, and the first state specifically refers to the state in which four doors and two covers have been assembled on the vehicle body in the welding workshop. It should be noted that the four doors and two covers in this application include the vehicle doors, front hood, trunk lid and other parts that are hinged to the vehicle body. Furthermore, the four doors and two covers of the vehicle specifically refer to the two front doors, two rear doors, a front hood and a trunk lid of the vehicle. It should be noted that the four doors and two covers of the vehicle provided in the embodiment of the present application refer to the vehicle doors, front hood and rear cover of the vehicle. In actual applications, there may also be a situation where the vehicle has only two doors, or the front is a storage box cover and the rear is a hood, etc. In this case, the two doors also fall within the scope of the four doors and two covers mentioned in this application.

[0043] In actual applications, doors, hoods, trunk doors, etc. are installed for vehicles in the welding workshop. In this workshop, only four doors and two covers are installed, and there is no need to install windows, window lifters, door locks, trim panels, etc. in the four doors and two covers. Therefore, the weight of the four doors and two covers is lighter than that in the final assembly workshop. In the current processing, it is often the case that the gaps of the four doors and two covers in the welding workshop are qualified, but the gaps of the four doors and two covers in the final assembly workshop are unqualified. Therefore, in the method provided in this application, it is necessary to predict whether the four doors and two covers are qualified in the final assembly workshop based on the information to be tested in the welding workshop.

[0044] Furthermore, the information to be detected specifically refers to information used to detect the four doors and two covers of the target vehicle in the first state. Specifically, the information to be detected includes at least one of the gap between the four doors and two covers and the vehicle body, and the reference of the four doors and two covers and the vehicle body. The gap between the four doors and two covers and the vehicle body specifically refers to the gap information between the four doors and two covers and the vehicle body, and the reference of the four doors and two covers and the vehicle body specifically refers to the decorative strips between the four doors and two covers and the vehicle body. When the four doors and two covers of the car are fully installed, the gap between the four doors and two covers and the vehicle body should be uniform, and the decorative strips on the four doors and two covers and the decorative strips on the vehicle body should be on the same horizontal line. Therefore, in the method provided in the present application, the information to be detected obtained includes at least one of the gap between the four doors and two covers and the vehicle body, and the reference of the four doors and two covers and the vehicle body.

[0045] In the welding workshop, after the four doors and two covers are installed on the car body by robotic arms and other equipment, the four doors and two covers are usually installed higher than the normal installation position so that in the subsequent assembly workshop, after various accessories are installed, the four doors and two covers are affected by gravity to reach the normal installation position.

[0046] In a specific implementation manner provided in the present application, collecting information to be detected of the target vehicle in the first state includes:

[0047] Acquire at least one image to be processed of the target vehicle in the first state;

[0048] Based on the preset collection points, the information to be detected of the target vehicle is collected from each image to be processed.

[0049] Specifically, in the welding workshop, four doors and two covers are installed on the vehicle body by a mechanical arm and other equipment, so that the target vehicle is in the first state, that is, the vehicle body is equipped with four doors and two covers. In this case, the information to be detected of the target vehicle is collected by the information collection equipment. Furthermore, the information collection equipment can be an ISLA detector, an LMI detector, a detection camera, etc.

[0050] Taking the information acquisition device as a detection camera as an example, the detection camera is used to collect at least one image to be processed of the target vehicle in the first state. In actual applications, images including the gaps between each of the four doors and two covers and the vehicle body will be taken according to the actual situation of the target vehicle, and then the information to be detected will be collected from each image to be processed according to the pre-configured acquisition points.

[0051] For example, taking target vehicle A as an example, the left side of target vehicle A has a left front door, a left rear door, a right front door, a right rear door, a front hood, and a trunk lid. In the gaps between the four doors and two lids and the body of the vehicle, several collection points are preset, and the gap information between the four doors and two lids and the body of the vehicle is collected at each collection point as the information to be detected of target vehicle A.

[0052] In practical applications, different vehicle models have different corresponding collection points. It is also necessary to consider the collection points corresponding to each vehicle model and collect the information to be detected corresponding to each vehicle model according to the collection points corresponding to each vehicle type information.

[0053] Step 204: input the information to be detected into an assembly prediction model, and obtain the assembly prediction model outputting predicted assembly information of the target vehicle in a second state, wherein the second state is a state where the target vehicle is assembled with four doors and two covers and four doors and two covers accessories.

[0054] Among them, the assembly prediction model specifically refers to a trained machine learning model, which is used to predict the predicted assembly information of the target vehicle after the four-door two-cover accessories are assembled on the basis of the information to be detected. The second state is the state where the four-door two-cover accessories are assembled on the four doors and two covers of the target vehicle, and the second state is usually the state in the final assembly workshop. The predicted assembly information specifically refers to the prediction result output by the assembly prediction model after the information to be detected is input into the assembly prediction model, and the predicted assembly information represents the expected assembly information of the target vehicle after the four-door two-cover accessories are assembled.

[0055] In practical applications, each vehicle model has different configurations and models, and its corresponding four-door and two-cover accessories are also different. Accordingly, its corresponding predicted assembly information is also different. Based on this, in a specific implementation provided by the present application, the method further includes:

[0056] Obtaining vehicle type information of the target vehicle;

[0057] Accordingly, the information to be detected is input into the assembly prediction model, including:

[0058] The vehicle type information and the information to be detected are input into an assembly prediction model.

[0059] The vehicle type information includes vehicle model, vehicle configuration and other information. Before inputting the information to be detected into the assembly prediction model, the vehicle type information of the target vehicle needs to be obtained. The vehicle type information of the target vehicle is input into the assembly prediction model together with the information to be detected, so that the assembly prediction model can generate predicted assembly information more accurately.

[0060] In a specific implementation manner provided in the present application, taking the vehicle type information of the target vehicle as "model a, high configuration" as an example, in the above steps, the information to be detected info1 of the target vehicle in the first state is obtained, and the information to be detected Info1 and the vehicle type information "model a, high configuration" are input into the assembly prediction model to obtain the predicted assembly information Info2 output by the assembly prediction model.

[0061] In one or more specific implementations provided in the present application, the model architecture of the assembly prediction model is not limited, and it can be a machine learning model based on an encoding-decoding structure, such as a Transformer model, a Bert model, etc. This is not limited in the present application and is subject to actual application.

[0062] In a specific embodiment provided in the present application, the assembly prediction model is obtained by training through the following steps:

[0063] Acquire sample detection information and sample assembly information, wherein the sample detection information is assembly information of the sample vehicle in a first state, and the sample assembly information is assembly information of the sample vehicle in a second state;

[0064] Inputting the sample detection information into an assembly prediction model to obtain predicted assembly information of the target vehicle in the second state output by the assembly prediction model;

[0065] Calculating a model loss value according to the predicted assembly information and the sample assembly information;

[0066] The model parameters of the assembly prediction model are adjusted according to the model loss value, and the assembly prediction model is continuously trained until a model training stop condition is reached.

[0067] Among them, the sample detection information and the sample assembly information appear in pairs, which are sample pairs used to predict the assembly prediction model. In practical applications, the sample pairs are specifically training sample pairs composed of assembly information of sample vehicles within a preset time interval.

[0068] The sample vehicle specifically refers to a vehicle that has been assembled, the sample detection information specifically refers to the assembly information of the sample vehicle in the first state, and the sample assembly information specifically refers to the assembly information of the same sample vehicle in the second state. Furthermore, the sample detection information specifically refers to the gap information of the four doors and two covers of the sample vehicle in the first state, and the sample assembly information specifically refers to the gap information of the four doors and two covers of the sample vehicle in the second state.

[0069] In practical applications, after obtaining the sample detection information, the sample detection information is input into the assembly prediction model. After being processed by the assembly prediction model, predicted assembly information is generated. The predicted assembly information specifically refers to the information predicted by the assembly prediction model based on the sample detection information. Furthermore, the predicted assembly information refers to the information predicted by the assembly prediction model based on the sample detection information and the vehicle type information of the sample vehicle.

[0070] Since the assembly prediction model at this time is an untrained model, there will be a deviation between the predicted assembly information and the actual sample assembly information, and the model parameters of the assembly prediction model need to be adjusted. Specifically, the model loss value can be calculated according to the predicted assembly information and the sample assembly information. The loss function for calculating the model loss value can be a 0-1 loss function, an absolute value loss function, a square loss function, a cross entropy loss function, etc. in actual applications. In this application, the choice of loss function is not limited, and the actual application shall prevail. Here, the cross entropy loss function is taken as an example for explanation, see the following formula 1:

[0071]

[0072] Among them, C represents the model loss value Loss, x represents the sample detection information, y represents the sample assembly information, a represents the predicted assembly information, and n represents the total number of samples. After calculating the Loss value, adjust the model parameters of the component classification model according to the Loss value through back propagation. Specifically, you can adjust the learning rate parameter, Batch_size parameter, parameter weight, etc. in the assembly prediction model. Continue to train the assembly prediction model with the next batch of sample data until the model training stop condition is reached.

[0073] Specifically, the model training stopping conditions include that the model loss value is less than a preset threshold and / or the training rounds reach a preset round.

[0074] In a specific implementation provided in the present application, the model training stop condition can be set to a model loss value less than a preset threshold, or the training stop condition can be set to a preset training round, such as 10 rounds of training. In the present application, the preset threshold of the loss value and / or the training round are not specifically limited, and are subject to actual application.

[0075] Step 206: Determine four-door and two-hood detection information of the target vehicle in the first state based on the predicted assembly information.

[0076] The four-door and two-cover detection information specifically includes whether the four-door and two-cover of the target vehicle are qualified or unqualified in the first state. That is, according to the predicted assembly information output by the assembly prediction model, it is judged whether the sewing information of the target vehicle in the first state meets the requirements. Therefore, it is further judged whether the four-door and two-cover in the first state need to be adjusted.

[0077] In a specific implementation provided by the present application, determining the four-door and two-lid detection information of the target vehicle in the first state based on the predicted assembly information includes:

[0078] In the case where the predicted assembly information satisfies the preset assembly condition, determining that the four-door and two-lid detection information of the target vehicle in the first state is qualified;

[0079] When the predicted assembly information does not satisfy the preset assembly condition, the four-door and two-hood detection information of the target vehicle in the first state is determined to be adjustment.

[0080] The preset assembly conditions specifically refer to the qualified conditions of the target vehicle in the second state. Specifically, it is necessary to determine whether the predicted assembly information output by the assembly prediction model meets the preset assembly conditions. If so, it means that the four-door and two-cover detection information of the target vehicle assembled with four doors and two covers in the first state is qualified; if not, it means that the four-door and two-cover detection information of the target vehicle assembled with four doors and two covers in the first state is adjusted, that is, unqualified, and the four doors and two covers in the first state need to be adjusted.

[0081] If the four-door and two-lid detection information is determined to be qualified, the target vehicle can be transferred to the next processing flow; if the four-door and two-lid detection information is determined to be adjusted, the target vehicle is transferred to the maintenance workshop, where the target vehicle is adjusted. The target vehicle's information to be detected in the first state is collected again, and the step of detecting the four-door and two-lid detection information of the target vehicle is executed according to the information to be detected.

[0082] In a specific implementation provided by the present application, when it is determined that the four-door and two-cover detection information is adjustment, the method further includes:

[0083] According to the predicted assembly information and the preset assembly conditions, adjusted assembly information is generated, wherein the adjusted assembly information is used to adjust the four doors and two covers so that the predicted assembly information meets the preset assembly conditions.

[0084] When the four-door and two-hood detection information is adjusted, adjustment assembly information can also be generated according to the predicted assembly information and the preset assembly conditions. The adjustment assembly information is used to guide the adjustment of the four-door and two-hood of the target vehicle so that the adjusted four-door and two-hood to-be-detected information can meet the preset assembly conditions.

[0085] In the specific implementation provided by the present application, taking the predicted assembly information as "the gap is 5 mm" and the preset assembly condition as "3 mm" as an example, the adjusted assembly information can be further determined as "adjusted downward by 2 mm" according to the predicted assembly information and the preset assembly condition. In the maintenance workshop, according to the adjusted assembly information, the door of the target vehicle can be adjusted downward by 2 mm, and then the information to be detected of the adjusted target vehicle is obtained, and the new predicted assembly information of the target vehicle is determined according to the information to be detected. When the new predicted assembly information meets the preset assembly condition, the detection information of the four doors and two covers of the target vehicle is determined to be qualified.

[0086] In a specific embodiment provided in the present application, the method further comprises:

[0087] Obtaining vehicle type information of the target vehicle;

[0088] Reference assembly information of the target vehicle is determined according to the vehicle type information, wherein the reference assembly information is used to provide reference information for assembling four doors and two lids for the target vehicle.

[0089] In practical applications, after the assembly prediction model is trained, the target vehicle can also be guided for installation information when installing four doors and two covers based on the assembly prediction model. Specifically, when the target vehicle is transported to the welding workshop, the vehicle type information of the target vehicle is obtained, which may include the vehicle model, vehicle configuration, etc. The vehicle type information of the target vehicle is input into the assembly prediction model for processing to obtain the reference assembly information output by the assembly prediction model. Before installing four doors and two covers for the target vehicle, guidance can be provided based on the reference assembly information. This provides assistance for the subsequent assembly of four doors and two covers, thereby improving the accuracy and stability of the assembly of four doors and two covers.

[0090] The assembly detection method of the four-door and two-cover of the automobile provided by the present application obtains the information to be detected when the target vehicle is in the first state. The first state specifically refers to the state in which the four-door and two-cover are installed on the vehicle body during the installation in the welding workshop. The information to be detected at this time specifically refers to the gap information of the four-door and two-cover installed on the vehicle body. The predicted assembly information of the current vehicle in the second state is predicted based on the information to be detected and the pre-trained assembly prediction model. The second state specifically refers to the state after various accessories are installed on the four-door and two-cover in the general assembly workshop. The predicted assembly information at this time specifically refers to the gap information of the four-door and two-cover of the four-door and two-cover in the second state. The detection information of the information to be detected in the current first state is judged based on the predicted assembly information, and the vehicle is determined in the welding workshop based on the detection information whether to enter the next operation workshop or the maintenance workshop. Thus, the maintenance and adjustment work is started at the welding workshop, avoiding the need for maintenance in the general assembly workshop at a later stage, thereby reducing the cost of maintenance and adjustment and improving the good appearance quality of the whole vehicle.

[0091] The following combination Figure 3 Taking the application of the assembly detection method of the four-door and two-hood of the automobile provided by the present application in the A-type automobile as an example, the assembly detection method of the four-door and two-hood of the automobile is further described. Figure 3 A processing flow chart of an assembly detection method for four doors and two covers of an A-type vehicle provided by an embodiment of the present application is shown, which specifically includes the following steps:

[0092] Step 302: Obtain vehicle type information of Model A automobile.

[0093] Step 304: Determine reference assembly information of model A automobile according to the vehicle type information.

[0094] Step 306: Install four doors and two covers for the body of the A-type automobile in a welding workshop based on the reference assembly information.

[0095] Step 308: Collect the information to be detected of the A-type automobile in the first state, wherein the first state is a state in which the body of the A-type automobile is equipped with four doors and two covers.

[0096] Step 310: Input the information to be detected and the vehicle type information into the assembly prediction model, and obtain the predicted assembly information of the model A car in the second state output by the assembly prediction model, wherein the second state is the state of the model A car with four doors and two covers installed in the final assembly workshop.

[0097] Step 312: Determine whether the predicted assembly information meets the preset assembly conditions. If yes, execute step 318; if no, execute step 314.

[0098] Step 314: Generate adjusted assembly information according to the predicted assembly information and the preset assembly conditions.

[0099] Step 316 : Adjust the four doors and two covers of the A-type vehicle based on the adjustment assembly information, and return to execute step 308 .

[0100] Step 318: Send the Model A car to the next processing workshop.

[0101] The assembly detection method of the four-door and two-cover of the automobile provided by the present application obtains the information to be detected when the target vehicle is in the first state. The first state specifically refers to the state in which the four-door and two-cover are installed on the vehicle body during the installation in the welding workshop. The information to be detected at this time specifically refers to the gap information of the four-door and two-cover installed on the vehicle body. The predicted assembly information of the current vehicle in the second state is predicted based on the information to be detected and the pre-trained assembly prediction model. The second state specifically refers to the state after various accessories are installed on the four-door and two-cover in the general assembly workshop. The predicted assembly information at this time specifically refers to the gap information of the four-door and two-cover of the four-door and two-cover in the second state. The detection information of the information to be detected in the current first state is judged based on the predicted assembly information, and the vehicle is determined in the welding workshop based on the detection information whether to enter the next operation workshop or the maintenance workshop. Thus, the maintenance and adjustment work is started at the welding workshop, avoiding the need for maintenance in the general assembly workshop at a later stage, thereby reducing the cost of maintenance and adjustment and improving the good appearance quality of the whole vehicle.

[0102] Corresponding to the above method embodiment, the present application also provides an embodiment of an assembly detection device for a four-door and two-hood vehicle. Figure 4 FIG. 1 is a schematic diagram showing the structure of an assembly detection device for four doors and two covers of a vehicle provided by an embodiment of the present application. Figure 4 As shown, the device comprises:

[0103] The collection module 402 is configured to collect information to be detected of the target vehicle in a first state, wherein the first state is a state where the target vehicle is equipped with four doors and two covers;

[0104] The prediction module 404 is configured to input the information to be detected into an assembly prediction model, and obtain the predicted assembly information of the target vehicle in a second state output by the assembly prediction model, wherein the second state is a state where the target vehicle is equipped with four doors and two covers and four doors and two covers accessories;

[0105] The detection module 406 is configured to determine the four-door and two-hood detection information of the target vehicle in the first state based on the predicted assembly information.

[0106] Optionally, the device further comprises:

[0107] An acquisition module is configured to acquire vehicle type information of the target vehicle;

[0108] Accordingly, the prediction module 404 is further configured to:

[0109] The vehicle type information and the information to be detected are input into an assembly prediction model.

[0110] Optionally, the acquisition module 402 is further configured to:

[0111] Acquire at least one image to be processed of the target vehicle in the first state;

[0112] Based on the preset collection points, the information to be detected of the target vehicle is collected from each image to be processed.

[0113] Optionally, the detection module 406 is further configured to:

[0114] In the case where the predicted assembly information satisfies the preset assembly condition, determining that the four-door and two-lid detection information of the target vehicle in the first state is qualified;

[0115] When the predicted assembly information does not satisfy the preset assembly condition, the four-door and two-hood detection information of the target vehicle in the first state is determined to be adjustment.

[0116] Optionally, the device further comprises:

[0117] The generating module is configured to generate adjustment assembly information according to the predicted assembly information and the preset assembly condition, wherein the adjustment assembly information is used to adjust the four doors and two covers so that the predicted assembly information meets the preset assembly condition.

[0118] Optionally, the device further comprises a reference module configured to:

[0119] Obtaining vehicle type information of the target vehicle;

[0120] Reference assembly information of the target vehicle is determined according to the vehicle type information, wherein the reference assembly information is used to provide reference information for assembling four doors and two lids for the target vehicle.

[0121] Optionally, the device further comprises a training module configured to:

[0122] Acquire sample detection information and sample assembly information, wherein the sample detection information is assembly information of the sample vehicle in a first state, and the sample assembly information is assembly information of the sample vehicle in a second state;

[0123] Inputting the sample detection information into an assembly prediction model to obtain predicted assembly information of the target vehicle in the second state output by the assembly prediction model;

[0124] Calculating a model loss value according to the predicted assembly information and the sample assembly information;

[0125] The model parameters of the assembly prediction model are adjusted according to the model loss value, and the assembly prediction model is continuously trained until a model training stop condition is reached.

[0126] The assembly detection device for automobile four doors and two covers provided by the present application obtains information to be detected when the target vehicle is in the first state. The first state specifically refers to the state in which four doors and two covers are installed on the vehicle body during installation in the welding workshop. The information to be detected at this time specifically refers to the gap information of the four doors and two covers installed on the vehicle body. The predicted assembly information of the current vehicle in the second state is predicted based on the information to be detected and the pre-trained assembly prediction model. The second state specifically refers to the state after various accessories are installed on the four doors and two covers in the general assembly workshop. The predicted assembly information at this time specifically refers to the gap information of the four doors and two covers of the four doors and two covers in the second state. The detection information of the information to be detected in the current first state is judged based on the predicted assembly information, and the vehicle is determined in the welding workshop based on the detection information whether to enter the next operation workshop or the maintenance workshop. Thus, the maintenance and adjustment work is started at the welding workshop, avoiding the need for maintenance in the general assembly workshop at a later stage, thereby reducing the cost of maintenance and adjustment and improving the good appearance quality of the whole vehicle.

[0127] The above is a schematic scheme of an assembly detection device for a four-door two-hood vehicle of this embodiment. It should be noted that the technical scheme of the assembly detection device for a four-door two-hood vehicle and the technical scheme of the assembly detection method for a four-door two-hood vehicle are of the same concept, and the details of the technical scheme of the assembly detection device for a four-door two-hood vehicle that are not described in detail can all be referred to the description of the technical scheme of the assembly detection method for a four-door two-hood vehicle.

[0128] Figure 5 The block diagram of a computing device 500 provided according to an embodiment of the present application is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0129] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0130] In one embodiment of the present application, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0131] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 may also be a mobile or stationary server.

[0132] When the processor 520 executes the computer instructions, the steps of the assembly detection method for the four doors and two covers of the automobile are implemented.

[0133] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for assembling and detecting four doors and two covers of a car belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned method for assembling and detecting four doors and two covers of a car.

[0134] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the above-mentioned method for assembling and inspecting the four doors and two covers of a vehicle.

[0135] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned assembly detection method of four doors and two covers of a car belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned assembly detection method of four doors and two covers of a car.

[0136] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0138] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0139] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A method for assembling and inspecting a four-door and two-lid vehicle. It is characterized in that include: Collecting information to be detected of the target vehicle in a first state, wherein the first state is a state in which the target vehicle is equipped with four doors and two covers; Inputting the information to be detected into an assembly prediction model, obtaining the predicted assembly information of the target vehicle in a second state output by the assembly prediction model, wherein the second state is a state in which the target vehicle is equipped with four doors and two covers and four doors and two covers accessories; Based on the predicted assembly information, four-door and two-hood detection information of the target vehicle in the first state is determined.

2. The method according to claim 1, It is characterized in that The method further comprises: Obtaining vehicle type information of the target vehicle; Accordingly, the information to be detected is input into the assembly prediction model, including: The vehicle type information and the information to be detected are input into an assembly prediction model.

3. The method according to claim 1, It is characterized in that Collect the information to be detected of the target vehicle in the first state, including: Acquire at least one image to be processed of the target vehicle in the first state; Based on the preset collection points, the information to be detected of the target vehicle is collected from each image to be processed.

4. The method according to claim 1, It is characterized in that Determining the four-door and two-lid detection information of the target vehicle in the first state based on the predicted assembly information includes: In the case where the predicted assembly information satisfies the preset assembly condition, determining that the four-door and two-lid detection information of the target vehicle in the first state is qualified; When the predicted assembly information does not satisfy the preset assembly condition, the four-door and two-hood detection information of the target vehicle in the first state is determined to be adjustment.

5. The method according to claim 4, It is characterized in that In the case where it is determined that the four-door and two-cover detection information is adjustment, the method further includes: According to the predicted assembly information and the preset assembly conditions, adjusted assembly information is generated, wherein the adjusted assembly information is used to adjust the four doors and two covers so that the predicted assembly information meets the preset assembly conditions.

6. The method according to claim 1, It is characterized in that The method further comprises: Obtaining vehicle type information of the target vehicle; Reference assembly information of the target vehicle is determined according to the vehicle type information, wherein the reference assembly information is used to provide reference information for assembling four doors and two lids for the target vehicle.

7. The method according to claim 1, It is characterized in that The assembly prediction model is trained by the following steps: Acquire sample detection information and sample assembly information, wherein the sample detection information is assembly information of the sample vehicle in a first state, and the sample assembly information is assembly information of the sample vehicle in a second state; Inputting the sample detection information into an assembly prediction model to obtain predicted assembly information of the target vehicle in the second state output by the assembly prediction model; Calculating a model loss value according to the predicted assembly information and the sample assembly information; The model parameters of the assembly prediction model are adjusted according to the model loss value, and the assembly prediction model is continuously trained until a model training stop condition is reached.

8. The method according to any one of claims 1 to 7, It is characterized in that The information to be detected includes at least one of a gap between the four doors and two covers and the vehicle body, and a reference object between the four doors and two covers and the vehicle body.

9. An assembly detection device for a car with four doors and two covers, It is characterized in that include: A collection module is configured to collect information to be detected of the target vehicle in a first state, wherein the first state is a state in which the target vehicle is equipped with four doors and two covers; A prediction module is configured to input the information to be detected into an assembly prediction model, and obtain the predicted assembly information of the target vehicle output by the assembly prediction model in a second state, wherein the second state is a state in which the target vehicle is equipped with four doors and two covers and four doors and two covers accessories; The detection module is configured to determine the four-door and two-hood detection information of the target vehicle in the first state based on the predicted assembly information.

10. A computing device comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer instructions, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium storing computer instructions, It is characterized in that When the computer instruction is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images