Automobile part processing flow management system based on artificial intelligence

Abstract

The invention discloses an automobile part processing flow management system based on artificial intelligence, relates to the technical field of processing flow management, and effectively improves the flexibility and accuracy of processing flow supervision. The method comprises the following steps: establishing a production flow tree and a processing dynamic image model of each processing step through historical production records, setting a plurality of processing identification points in the processing dynamic image model, and further obtaining a standard position change track interval of each processing identification point; a multi-dimensional machining step image model is established according to real-time operation data of machining equipment and automobile parts, machining recognition points which are the same as the machining dynamic image model are arranged on the multi-dimensional machining step image model, and then whether the machining recognition points are in corresponding standard position change track intervals or not is judged; and a local cutting adjusting instruction or a local temperature adjusting instruction is generated according to the judgment result, and then the machining equipment is adjusted according to the local cutting adjusting instruction or the local temperature adjusting instruction.

Description

Technical Field

[0001] The invention relates to the technical field of processing flow management, and in particular to an automobile parts processing flow management system based on artificial intelligence. Background Art

[0002] In the modern automotive industry, with the advancement of technology and the continuous changes in market demand, the processing of automotive parts has become increasingly complex. Traditional processing process management often relies on human experience and manual operation, which is not only inefficient but also prone to errors and quality control problems. In order to meet these challenges, more and more companies are beginning to introduce advanced AI technology.

[0003] Traditional AI systems often require a large amount of high-quality data for training, but the training results are usually only optimized for specific types of parts or production processes. They are not adaptable enough to new or complex parts, and are unable to make accurate compensation decisions in a timely and flexible manner based on processing errors that occur in real time during the processing of automotive parts.

[0004] Therefore, how to monitor the production process of multiple automotive parts at the same time and flexibly make accurate equipment adjustment processes based on real-time processing errors is a difficulty in the existing technology. For this purpose, an automotive parts processing process management system based on artificial intelligence is provided. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an automobile parts processing flow management system based on artificial intelligence.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An automobile parts processing process management system based on artificial intelligence includes a cloud computing platform, wherein the cloud computing platform is communicatively connected with a production step analysis module, a production line monitoring module and a production process monitoring module;

[0008] The production step analysis module is used to establish a production process tree and a processing dynamic image model of each processing step according to the pre-stored historical production records of automobile parts, set a number of processing identification points in the processing dynamic image model, and then obtain the standard position change trajectory interval of each processing identification point, and bind the standard position change trajectory interval of each processing identification point with the production process tree to obtain a production supervision decision tree;

[0009] The production line monitoring module is used to install several types of sensors on each processing equipment, and establish corresponding processing instructions for each processing equipment according to the production monitoring decision tree, and then when each processing equipment executes the processing instruction, various sensors are called to collect the real-time operation data of the processing equipment and the real-time status data of the automobile parts, and the processing equipment is adjusted according to the local cutting adjustment instruction or the local temperature adjustment instruction from the production process monitoring module;

[0010] The production process monitoring module is used to establish a multi-dimensional processing step image model based on the real-time operation data of the processing equipment and automobile parts, set the same processing identification points as the processing dynamic image model on the multi-dimensional processing step image model, and then judge whether each processing identification point is in the corresponding standard position change trajectory interval, and generate a local cutting adjustment instruction or a local temperature adjustment instruction according to the judgment result.

[0011] Furthermore, the process of establishing the production process tree includes:

[0012] The production step analysis module pre-stores several historical production records of N types of automobile parts, wherein the historical production records include the name of the automobile part, the processing flow, the name of each processing step, and the processing video data, wherein N is a natural number greater than 0;

[0013] The processing flow has the sequence of each processing step and the name of the related processing equipment. According to the number of processing steps of each type of automobile parts, corresponding processing nodes are established, and the corresponding processing step names are marked on the processing nodes. Then, according to the processing flow in the historical production records, each processing node is connected to obtain a production flow tree of the corresponding type of automobile parts;

[0014] At the same time, corresponding equipment nodes are established according to the number of types of processing equipment names recorded in the processing flow, and then each equipment node is bound to the relevant processing node in the production process tree according to the processing equipment name associated with each processing step in the processing flow.

[0015] Furthermore, the process of establishing the processing dynamic image model of each processing step includes:

[0016] The production step analysis module extracts the production video data of each processing step from the historical production records, and establishes a processing dynamic image model of the corresponding processing step based on the production video data, and then annotates the product dynamic model and the equipment dynamic model from the processing dynamic image model through the image feature extraction technology, and annotates the product dynamic model and each equipment dynamic model with the corresponding automobile parts name and processing equipment name;

[0017] Set a processing timeline, set a number of time nodes on the processing timeline, and map the processing dynamic image model on the processing timeline;

[0018] According to the start and end time of the interaction between each equipment dynamic model and the product dynamic model in the processing dynamic image model, a corresponding number of time nodes are intercepted on the processing time axis and marked as equipment operation time periods, and each equipment operation time period is marked with the corresponding processing equipment name;

[0019] During the equipment operation period when any equipment dynamic model interacts with the product dynamic model, the image model parts where the two interact are marked on the equipment dynamic model and the product dynamic model respectively, and recorded as the equipment working part and the product processing part respectively.

[0020] Furthermore, the process of obtaining the standard position change trajectory interval of the processing identification point includes:

[0021] A number of processing identification points are set at the same time on the equipment working part and the product processing part, and then the position change track of each processing identification point on the equipment working part and the product processing part is recorded respectively;

[0022] Establish a three-dimensional coordinate system, generate the position change trajectory of the same processing equipment, production steps and the same processing identification point for each type of automotive parts in each historical production record, and overlap and map them in the three-dimensional coordinate system;

[0023] According to the distribution of time nodes on the processing time axis, each position change trajectory on the three-dimensional coordinate system is divided into a number of position change segments, and a trajectory distribution inspection box is set at the same time. The trajectory distribution inspection box is a blank data filling space in a cubic style;

[0024] The position change segments between each time node are traversed through the trajectory distribution inspection box, and the overlapping number of the position change segments of each traversed position is counted, and then the position change segment of the traversed position with the largest number of overlaps is selected as the position change segment interval between the corresponding time nodes.

[0025] Further, the position change segment intervals between the various time nodes are sequentially spliced ​​to obtain the standard position change trajectory intervals corresponding to the processing identification points, and the standard position change trajectory intervals of the processing identification points are mapped onto the processing dynamic image model;

[0026] The processing dynamic image model is bound to the processing nodes corresponding to the same processing step in the production process tree, and then the production supervision decision tree of each type of automobile parts is obtained.

[0027] Furthermore, the process of collecting the real-time operation data of the processing equipment and the real-time status data of the automobile parts includes:

[0028] The production line supervision module installs several types of sensors on each processing equipment on the production line, sets a number for each processing equipment, retrieves the corresponding production supervision decision tree according to the name of the automobile parts, establishes the corresponding production route according to the name and arrangement order of the processing equipment corresponding to each processing node in the production supervision decision tree, and the arrangement order of the processing equipment on the production line, and sends processing instructions to the corresponding processing equipment on the production line according to the production route;

[0029] Each processing equipment on the production line processes the raw materials in sequence according to the processing instructions. At the same time, each sensor located on the processing equipment collects real-time operation data of the processing equipment and real-time status data of automobile parts.

[0030] Furthermore, the generation process of the local cutting adjustment instruction or the local temperature adjustment instruction includes:

[0031] Annotating a multidimensional real-time product image model and a multidimensional real-time equipment image model from the multidimensional processing step image model, and annotating processing identification points at the same position on the multidimensional real-time product image model and the multidimensional real-time equipment image model according to the processing dynamic image model;

[0032] The production process monitoring module updates the multi-dimensional processing step image model in real time, and as the multi-dimensional processing step image model is updated, obtains the real-time position change trajectory of each processing identification point on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model;

[0033] Set a deviation quantity threshold to determine whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory interval. If the processing identification points located on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model have a number of processing identification points less than the deviation quantity threshold whose real-time position change trajectories are within the corresponding standard position change trajectory interval, then the corresponding processing step is determined to be normal;

[0034] Otherwise, the corresponding processing step is judged to be abnormal, and then according to the processing identification point that is not in the corresponding standard position change trajectory interval, the corresponding local cutting adjustment instruction or local temperature adjustment instruction is generated relative to the deviation direction of the standard position change trajectory interval in the multi-dimensional real-time product image model or the multi-dimensional real-time equipment image model.

[0035] Furthermore, the execution process of the local cutting adjustment instruction or the local temperature adjustment instruction includes:

[0036] The production line monitoring module adjusts the cutting force or angle of the processing equipment through a local cutting adjustment instruction, or controls the temperature of the processing equipment at the corresponding processing identification point through a local temperature adjustment instruction, and after the execution of the local cutting adjustment instruction or the local temperature adjustment instruction, re-collects the real-time operation data of the processing equipment and the real-time status data of the automobile parts and sends them to the production process monitoring module;

[0037] Repeat the process of judging whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory range, and generating a local cutting adjustment instruction or a local temperature adjustment instruction, until all processing steps of the corresponding type of automotive parts are completed.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention sets a plurality of processing identification points in a processing dynamic image model, thereby obtaining a standard position change trajectory interval of each processing identification point, establishes a multi-dimensional processing step image model according to real-time operation data of processing equipment and automobile parts, sets processing identification points identical to the processing dynamic image model on the multi-dimensional processing step image model, thereby determining whether each processing identification point is in a corresponding standard position change trajectory interval, generates a local cutting adjustment instruction or a local temperature adjustment instruction according to the determination result, and then adjusts the processing equipment through the local cutting adjustment instruction or the local temperature adjustment instruction, thereby achieving production process supervision of a variety of automobile parts while flexibly making accurate equipment adjustment results according to real-time processing errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention.

[0041] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0042] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0043] like Figure 1As shown, an automobile parts processing flow management system based on artificial intelligence includes a cloud computing platform, and the cloud computing platform is communicatively connected with a production step analysis module, a production line monitoring module and a production process monitoring module;

[0044] The production step analysis module is used to establish a production process tree and a processing dynamic image model of each processing step according to the pre-stored historical production records of automobile parts, set a number of processing identification points in the processing dynamic image model, and then obtain the standard position change trajectory interval of each processing identification point, and bind the standard position change trajectory interval of each processing identification point with the production process tree to obtain a production supervision decision tree;

[0045] The production line monitoring module is used to install several types of sensors on each processing equipment, and establish corresponding processing instructions for each processing equipment according to the production monitoring decision tree, and then when each processing equipment executes the processing instruction, various sensors are called to collect the real-time operation data of the processing equipment and the real-time status data of the automobile parts, and the processing equipment is adjusted according to the local cutting adjustment instruction or the local temperature adjustment instruction from the production process monitoring module;

[0046] The production process monitoring module is used to establish a multi-dimensional processing step image model based on the real-time operation data of the processing equipment and automobile parts, set the same processing identification points as the processing dynamic image model on the multi-dimensional processing step image model, and then judge whether each processing identification point is in the corresponding standard position change trajectory interval, and generate a local cutting adjustment instruction or a local temperature adjustment instruction according to the judgment result.

[0047] Further, the working principle of the present invention is described below by way of examples:

[0048] The production step analysis module pre-stores several historical production records of N types of automobile parts, wherein the historical production records include the name of the automobile part, the processing flow, the name of each processing step, and the processing video data, wherein N is a natural number greater than 0;

[0049] The processing flow includes the sequence of each processing step and the name of the relevant processing equipment, wherein the processing steps are divided into rough processing, heat treatment, finishing, etc.;

[0050] The production step analysis module establishes corresponding processing nodes according to the number of processing steps for each type of auto parts, and labels the processing nodes with corresponding processing step names. Then, according to the processing flow in the historical production records, each processing node is connected to obtain the production process tree of the corresponding type of auto parts.

[0051] At the same time, corresponding equipment nodes are established according to the number of types of processing equipment names recorded in the processing flow, and then each equipment node is bound to the relevant processing node in the production process tree according to the processing equipment name associated with each processing step in the processing flow.

[0052] Furthermore, the production step analysis module extracts production video data of each processing step from the historical production records, and establishes a processing dynamic image model of the corresponding processing step based on the production video data, and then annotates the product dynamic model and the equipment dynamic model from the processing dynamic image model through the image feature extraction technology, and annotates the product dynamic model and each equipment dynamic model with the corresponding automobile parts name and processing equipment name;

[0053] Set a processing timeline, set a number of time nodes on the processing timeline, and map the processing dynamic image model on the processing timeline;

[0054] According to the start and end time of the interaction between each equipment dynamic model and the product dynamic model in the processing dynamic image model, a corresponding number of time nodes are intercepted on the processing time axis and marked as equipment operation time periods, and each equipment operation time period is marked with the corresponding processing equipment name;

[0055] It should be noted that the product dynamic model has time nodes that interact with multiple device status models at the same time, so the operation time periods of various devices may partially or completely overlap;

[0056] During the equipment operation period when any equipment dynamic model interacts with the product dynamic model, the image model parts where the two interact are marked on the equipment dynamic model and the product dynamic model, and are recorded as the equipment working part and the product processing part respectively;

[0057] Since the operations of various processing equipment on the production line for processing the same type of automobile parts are fixed, the processing parts and processing operations of the processing equipment for the same type of automobile parts are the same for each processing step, wherein the processing operations include, for example, cutting automobile parts by filing, quenching partial positions of automobile parts, etc.;

[0058] A number of processing identification points are set at the same time on the equipment working part and the product processing part, and then the position change track of each processing identification point on the equipment working part and the product processing part is recorded respectively;

[0059] Establish a three-dimensional coordinate system, generate the position change trajectory of the same processing equipment, production steps and the same processing identification point for each type of automotive parts in each historical production record, and overlap and map them in the three-dimensional coordinate system;

[0060] According to the distribution of time nodes on the processing time axis, each position change trajectory on the three-dimensional coordinate system is divided into a number of position change segments, and a trajectory distribution inspection box is set at the same time. The trajectory distribution inspection box is a blank data filling space in a cubic style;

[0061] The position change segments between each time node are traversed through the trajectory distribution inspection box, and the overlapping number of the position change segments of each traversed position is counted, and then the position change segments of the traversed position with the largest number of overlaps are selected as the position change segment intervals between the corresponding time nodes;

[0062] The position change segment intervals between each time node are sequentially spliced ​​to obtain the standard position change trajectory interval of the corresponding processing identification point, and the standard position change trajectory interval of each processing identification point is mapped on the processing dynamic image model;

[0063] Bind the processing dynamic image model to the processing nodes corresponding to the same processing step in the production process tree, and then obtain the production supervision decision tree for each type of automobile parts;

[0064] The production step analysis module labels each production supervision decision tree with the corresponding automobile parts name, and then sends all production supervision decision trees to the production equipment supervision module and the production process supervision module.

[0065] Furthermore, the production line monitoring module installs several types of sensors on each processing equipment on the production line, and sets a number a1, a2, a3, ..., a m , where m is a natural number greater than 0;

[0066] The processing equipment includes turning tools, angle milling cutters, electric spark emitters, high temperature furnaces, etc.;

[0067] The sensors include cameras, infrared sensors, laser signal devices, etc.;

[0068] The staff uploads the names of the automobile parts to be produced to the production line supervision module, and then the production supervision model retrieves the corresponding production supervision decision tree according to the names of the automobile parts, establishes the corresponding production route according to the names and arrangement order of the processing equipment corresponding to each processing node in the production supervision decision tree, and the arrangement order of the processing equipment on the production line, and sends processing instructions to the corresponding processing equipment on the production line according to the production route;

[0069] The staff loads the raw materials for the planned production of automotive parts onto the production line, and then the various processing equipment on the production line processes the raw materials in turn according to the processing instructions. At the same time, the various sensors located on the processing equipment collect real-time operating data of the processing equipment and real-time status data of automotive parts.

[0070] Furthermore, the production line monitoring module sets numbers for the real-time operation data and the real-time status data according to the numbers of the processing equipment where each sensor is located, and synchronously sends the real-time operation data and the real-time status data to the production process monitoring module;

[0071] The production process monitoring module generates corresponding real-time scene image models according to the data types of real-time operation data and real-time status data, for example, generates a real-time infrared scene image model according to the infrared video data of the infrared sensor;

[0072] Since the data collected by each sensor are of different types, but the data reflect and display the same things, the real-time scene image models generated according to different types of real-time operation data and real-time status data must be related, and since the distance between the two is close during the processing of the processing equipment on the automotive parts, the data collected by the sensors on the two must also contain the corresponding data of each other;

[0073] Firstly, real-time scene image models generated by different types of real-time operation data or real-time status data corresponding to the same processing equipment or automobile parts are overlapped and mapped to obtain a multi-dimensional real-time scene image model centered on the processing equipment or automobile parts;

[0074] Then, the multi-dimensional real-time scene image models of processing equipment and automobile parts are divided into H local multi-dimensional real-time model regions of the same size, and h local multi-dimensional real-time model regions are randomly selected and recorded as multi-dimensional matching model regions;

[0075] Match the multidimensional matching model areas in the multidimensional real-time scene image models of processing equipment and automobile parts with each other. If two multidimensional matching model areas and their surrounding local multidimensional real-time model areas are more than three similar, then the corresponding multidimensional matching model areas and the surrounding similar local multidimensional real-time model areas are marked together as multidimensional associated model areas, otherwise no operation is performed;

[0076] According to the multidimensional correlation model area in the multidimensional real-time scene image model of the processing equipment and the automobile parts, the multidimensional real-time scene image model of the processing equipment and the automobile parts is spliced ​​to obtain the corresponding multidimensional processing step image model.

[0077] Furthermore, a multidimensional real-time product image model and a multidimensional real-time equipment image model are annotated from the multidimensional processing step image model through image feature extraction technology, and at the same time, the multidimensional processing step image model retrieves the corresponding processing dynamic image model from the production supervision decision tree, and the processing identification points at the same position are annotated on the multidimensional real-time product image model and the multidimensional real-time equipment image model according to the processing dynamic image model;

[0078] According to the real-time operation data and real-time status data continuously received from the production line monitoring module, the production process monitoring module updates the multi-dimensional processing step image model in real time, and obtains the real-time position change track of each processing identification point on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model as the multi-dimensional processing step image model is updated;

[0079] Set a deviation quantity threshold to determine whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory interval. If the processing identification points located on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model have a number of processing identification points less than the deviation quantity threshold whose real-time position change trajectories are within the corresponding standard position change trajectory interval, then the corresponding processing step is determined to be normal;

[0080] Otherwise, the corresponding processing step is judged to be abnormal, and then the processing identification point that is not in the corresponding standard position change trajectory interval is judged to deviate from the standard position change trajectory interval in the multi-dimensional real-time product image model or the multi-dimensional real-time device image model;

[0081] For rough machining or fine machining, which requires machining equipment to perform cutting machining on the surface or inside of automobile parts through turning tools, angle milling cutters, electric spark launchers, etc., a corresponding local cutting adjustment instruction is generated in the deviation direction of the corresponding optical image layer or laser signal image layer in the multi-dimensional real-time product image model or the multi-dimensional real-time equipment image model according to the trajectory interval of the machining identification point relative to the standard position;

[0082] For heat treatment and other processing steps that require processing equipment to process the state or material of automobile parts through high-temperature furnaces and other devices, the corresponding local temperature adjustment instructions are generated according to the deviation direction of the image layer representing the temperature change in the multi-dimensional real-time product image model or the multi-dimensional real-time device image model based on the change trajectory interval of the processing identification point relative to the standard position, wherein the image layer representing the temperature change is, for example, the real-time scene image model corresponding to the data collected by the infrared sensor;

[0083] The production process monitoring module sends the local cutting adjustment instruction or the local temperature adjustment instruction to the production line monitoring module, and then the production line monitoring module adjusts the cutting force or angle of the processing equipment through the local cutting adjustment instruction, or controls the temperature of the processing equipment at the corresponding processing identification point through the local temperature adjustment instruction, and after the local cutting adjustment instruction or the local temperature adjustment instruction is executed, the real-time operation data of the processing equipment and the real-time status data of the automobile parts are re-collected and sent to the production process monitoring module;

[0084] Repeat the above process of determining whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory range, and generating a local cutting adjustment instruction or a local temperature adjustment instruction, until all processing steps of the corresponding type of automotive parts are completed.

[0085] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An automotive parts processing process management system based on artificial intelligence, including a cloud computing platform, It is characterized in that The cloud computing platform is communicatively connected to a production step analysis module, a production line monitoring module, and a production process monitoring module; The production step analysis module is used to establish a production process tree and a processing dynamic image model of each processing step according to the pre-stored historical production records of automobile parts, set a number of processing identification points in the processing dynamic image model, and then obtain the standard position change trajectory interval of each processing identification point, and bind the standard position change trajectory interval of each processing identification point with the production process tree to obtain a production supervision decision tree; The production line monitoring module is used to install several types of sensors on each processing equipment, and establish corresponding processing instructions for each processing equipment according to the production monitoring decision tree, and then when each processing equipment executes the processing instruction, various sensors are called to collect the real-time operation data of the processing equipment and the real-time status data of the automobile parts, and the processing equipment is adjusted according to the local cutting adjustment instruction or the local temperature adjustment instruction from the production process monitoring module; The production process monitoring module is used to establish a multi-dimensional processing step image model based on the real-time operation data of the processing equipment and automobile parts, set the same processing identification points as the processing dynamic image model on the multi-dimensional processing step image model, and then judge whether each processing identification point is in the corresponding standard position change trajectory interval, and generate a local cutting adjustment instruction or a local temperature adjustment instruction according to the judgment result.

2. According to claim 1, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The process of establishing the production process tree includes: Historical production records include the name of the auto parts, the processing flow, the names of each processing step, and processing video data; The processing flow has the sequence of each processing step and the name of the related processing equipment. Processing nodes are established according to the number of processing steps of each type of automobile parts, and the names of the processing steps are marked on the processing nodes. Then, according to the processing flow in the historical production records, each processing node is connected to obtain a production flow tree of the corresponding type of automobile parts; At the same time, corresponding equipment nodes are established according to the number of types of processing equipment names recorded in the processing flow, and then each equipment node is bound to the relevant processing node in the production process tree according to the processing equipment name associated with each processing step in the processing flow.

3. According to claim 2, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The process of establishing the processing dynamic image model of each processing step includes: Extract production video data of each processing step from historical production records, and establish a processing dynamic image model of the corresponding processing step based on the production video data, annotate the product dynamic model and the equipment dynamic model from the processing dynamic image model, and annotate the product dynamic model and each equipment dynamic model with the corresponding automobile parts name and processing equipment name; Set a processing timeline, set a number of time nodes on the processing timeline, and map the processing dynamic image model on the processing timeline; According to the start and end time of the interaction between each equipment dynamic model and the product dynamic model in the processing dynamic image model, a corresponding number of time nodes are intercepted on the processing time axis and marked as equipment operation time periods, and each equipment operation time period is marked with the corresponding processing equipment name; During the equipment operation period when any equipment dynamic model interacts with the product dynamic model, the image model parts where the two interact are marked on the equipment dynamic model and the product dynamic model respectively, and recorded as the equipment working part and the product processing part respectively.

4. According to claim 3, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The process of obtaining the standard position change trajectory interval of the processing identification point includes: A number of processing identification points are set at the same time on the equipment working part and the product processing part, and then the position change track of each processing identification point on the equipment working part and the product processing part is recorded respectively; Establish a three-dimensional coordinate system, generate the position change trajectory of the same processing equipment, production steps and the same processing identification point for each type of automotive parts in each historical production record, and overlap and map them in the three-dimensional coordinate system; Divide each position change trajectory on the three-dimensional coordinate system into a number of position change segments, and set a trajectory distribution inspection frame, wherein the trajectory distribution inspection frame is a blank data filling space in a cubic style; The position change segments between each time node are traversed through the trajectory distribution inspection box, and the overlapping number of the position change segments of each traversed position is counted, and then the position change segment of the traversed position with the largest number of overlaps is selected as the position change segment interval between the corresponding time nodes.

5. According to claim 4, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The position change segment intervals between each time node are sequentially spliced ​​to obtain the standard position change trajectory interval of the corresponding processing identification point, and the standard position change trajectory interval of each processing identification point is mapped on the processing dynamic image model; The processing dynamic image model is bound to the processing nodes corresponding to the same processing step in the production process tree, and then the production supervision decision tree of each type of automobile parts is obtained.

6. According to claim 5, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The process of collecting the real-time operation data of the processing equipment and the real-time status data of the automobile parts includes: Retrieve the corresponding production supervision decision tree according to the name of the automobile parts, and send processing instructions to the corresponding processing equipment on the production line according to the name and arrangement order of the processing equipment corresponding to each processing node in the production supervision decision tree and the arrangement order of the processing equipment on the production line; Each processing equipment on the production line processes the raw materials in sequence according to the processing instructions. At the same time, each sensor located on the processing equipment collects real-time operation data of the processing equipment and real-time status data of automobile parts.

7. According to claim 6, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The generation process of the local cutting adjustment instruction or the local temperature adjustment instruction includes: Annotating a multidimensional real-time product image model and a multidimensional real-time equipment image model from the multidimensional processing step image model, and annotating processing identification points at the same position on the multidimensional real-time product image model and the multidimensional real-time equipment image model according to the processing dynamic image model; The real-time position change trajectory of each processing identification point on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model is obtained, and a deviation quantity threshold is set to determine whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory interval. If the real-time position change trajectories of the processing identification points located on the multi-dimensional real-time product image model and the multi-dimensional real-time equipment image model are within the corresponding standard position change trajectory interval, the corresponding processing step is determined to be normal; Otherwise, the corresponding processing step is judged to be abnormal, and then according to the processing identification point that is not in the corresponding standard position change trajectory interval, the corresponding local cutting adjustment instruction or local temperature adjustment instruction is generated in the deviation direction relative to the standard position change trajectory interval.

8. According to claim 7, an artificial intelligence-based automobile parts processing process management system, It is characterized in that The execution process of the local cutting adjustment instruction or the local temperature adjustment instruction includes: The production line monitoring module adjusts the cutting force or angle of the processing equipment through a local cutting adjustment instruction, or controls the temperature of the processing equipment at the corresponding processing identification point through a local temperature adjustment instruction, and after the execution of the local cutting adjustment instruction or the local temperature adjustment instruction, re-collects the real-time operation data of the processing equipment and the real-time status data of the automobile parts and sends them to the production process monitoring module; Repeat the process of determining whether the real-time position change trajectory of each processing identification point is within the corresponding standard position change trajectory range, and generating a local cutting adjustment instruction or a local temperature adjustment instruction, until all processing steps of the corresponding type of automotive parts are completed.

Images