A mechanical chain production process control method and system based on machine recognition

Through the mechanical chain production process control method based on machine identification, through the use of classification, quality inspection and optimization control parameters, the problem of low chain production pass rate in the existing technology is solved, and the precise control and cost reduction of chain production processes are achieved.

CN115877807BActive Publication Date: 2024-11-22SUZHOU FUBANG MASCH CHAIN TRANSMISSION MFG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211602877.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-13
Publication Date
2024-11-22
Estimated Expiration
2042-12-13

AI Technical Summary

Technical Problem

The existing machine chain production methods have insufficient control over production process, quality inspection, process status and proofing processing in the production process, resulting in a low pass rate of the final product and an increased labor cost.

Method used

The mechanical chain production process control method based on machine identification is adopted, and the rationalization and precise control of the chain production process is achieved through the classification of the processing chain, the analysis of historical quality inspection data, the proofing processing and the input of optimization control parameters. The specific steps include classifying the target chain, generating dimension marks and inputting process parameter control models, collecting historical quality detection data for process status analysis, proofing and processing based on process parameter data, generating quality detection data, and entering these data into parameter optimization model Processing control is performed with output optimization control parameters.

Benefits of technology

It improves the pass rate of machine chain production, realizes rational and precise control of the production process, reduces labor costs, and improves the quality of the finished product of the chain.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115877807B_ABST
    Figure CN115877807B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for controlling the production process of a mechanical chain based on machine identification, and relates to the field of process processing technology. The method comprises: classifying target mechanical chains to be processed, inputting dimension identification into a process parameter control model, collecting and obtaining historical quality inspection data of a first process, performing process state analysis of the first process, performing a first process proofing processing of the mechanical chain to be processed based on the process parameter data to generate quality inspection data, inputting the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and outputting optimized control parameters to perform the first process processing control of the mechanical chain to be processed. The present invention solves the problem of insufficient control over the manufacturing process, quality inspection, process state and proofing processing in the production process of the machine chain production method in the prior art, and realizes the rational and precise control over the machine chain production process, thereby improving the qualified rate of machine chain production while reducing labor costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of process processing technology, and in particular to a method and system for controlling the production process of a mechanical chain based on machine identification. Background Art

[0002] With the development of science and technology, especially the development of chain processing technology, chains have been widely used in production and life. Most chain manufacturers use multiple machines to produce chains in steps, which not only requires a lot of manpower and material resources, but also cannot improve the production progress, which is easy to delay the delivery of products. In addition, since the machines in each section are not closely connected, the semi-finished chain products are easily damaged during transportation, which reduces the qualified rate of the finished chain products.

[0003] The existing machine chain production method has a low final machine chain production qualification rate and increases labor costs due to insufficient control over the manufacturing process, quality inspection, process status and proofing processing in the production process. Summary of the invention

[0004] The present application provides a method and system for controlling the production process of a mechanical chain based on machine identification, which is used to solve the technical problems in the prior art of the production method of a mechanical chain, which is caused by insufficient control over the manufacturing process, quality inspection, process status and proofing processing in the production process, resulting in a low final machine chain production qualification rate and increased labor costs.

[0005] In view of the above problems, the present application provides a method and system for controlling the production process of a mechanical chain based on machine identification.

[0006] In the first aspect, the present application provides a method for controlling the production process of a mechanical chain based on machine identification, the method comprising: classifying the target mechanical chain to be processed to obtain a classification result, wherein the classification result has a size identification; inputting the size identification into a process parameter control model to output process parameter data; acquiring historical quality inspection data of a first process, performing a process state analysis of the first process based on the historical quality inspection data, and generating a process state analysis result; performing a first process proofing processing of the mechanical chain to be processed based on the process parameter data, and generating quality inspection data based on the proofing processing result; inputting the process state analysis result, the proofing processing result, and the process parameter data into a parameter optimization model to output optimized control parameters; and performing the first process processing control of the mechanical chain to be processed through the optimized control parameters.

[0007] In a second aspect, the present application provides a mechanical chain production process control system based on machine identification, the system comprising: a first classification result module, the first classification result module is used to classify the target mechanical chain to be processed and obtain a classification result, wherein the classification result has a size identifier; a process parameter data module, the process parameter data module is used to input the size identifier into a process parameter control model and output process parameter data; a state analysis result module, the state analysis result module is used to collect and obtain historical quality inspection data of a first process, perform process state analysis of the first process based on the historical quality inspection data, and generate a process state analysis result; a quality inspection data module, the quality inspection data module is used to perform a first process proofing processing of the mechanical chain to be processed based on the process parameter data, and generate quality inspection data based on the proofing processing result; an optimization control parameter module, the optimization control parameter module is used to input the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and output optimization control parameters; a first process processing control module, the first process processing control module is used to perform a first process processing control of the mechanical chain to be processed through the optimization control parameters.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The present application provides a method for controlling the production process of a mechanical chain based on machine identification, which relates to the field of process processing technology. It solves the technical problem in the prior art that the final machine chain production qualification rate is low due to insufficient control over the manufacturing process, quality inspection, process status and proofing processing in the production process. It realizes the rational and precise control of the machine chain production process, thereby improving the qualification rate of the machine chain production. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a process flow of a mechanical chain production process control method based on machine identification is provided for this application;

[0011] Figure 2 A schematic diagram of the process of obtaining classification results in a method for controlling the production process of a mechanical chain based on machine recognition is provided for this application;

[0012] Figure 3 A schematic diagram of a parameter compensation optimization process in a mechanical chain production process control method based on machine identification is provided for this application;

[0013] Figure 4 A structural schematic diagram of a mechanical chain production process control system based on machine identification is provided for this application.

[0014] Explanation of the accompanying drawings: first classification result module 1, process parameter data module 2, state analysis result module 3, quality inspection data module 4, optimization control parameter module 5, first process processing control module 6. DETAILED DESCRIPTION

[0015] The present application provides a mechanical chain production process control method based on machine identification, which is used to solve the technical problems in the prior art of machine chain production methods, such as low final machine chain production qualification rate and increased labor costs due to insufficient control over manufacturing process, quality inspection, process status and proofing processing in the production process.

[0016] Embodiment 1

[0017] like Figure 1 As shown, the embodiment of the present application provides a method for controlling the production process of a mechanical chain based on machine identification, the method comprising:

[0018] Step S100: classifying the target mechanical chain to be processed to obtain a classification result, wherein the classification result has a size identifier;

[0019] Specifically, by classifying the target mechanical chains to be processed, the target mechanical chains to be processed are divided into transmission chains, conveyor chains, traction chains, special chains, etc. according to different sizes, different production batches, different uses, different functions and sample data collection, and the target mechanical chains to be processed are further classified, which serves as an important reference for the later realization of the first process processing control optimization of the mechanical chains to be processed.

[0020] Step S200: inputting the dimension mark into a process parameter control model and outputting process parameter data;

[0021] Specifically, based on the size identification in the obtained classification results, the size identification is input into the process parameter control model, wherein the construction of the process parameter control model first requires obtaining training sample data; wherein the training sample data includes a plurality of process parameters of the processed sample products; the training sample data is input into the initial network model to obtain predicted adjustment values ​​of the plurality of process parameters of the sample products; the loss value is calculated based on the predicted adjustment value and the actual adjustment value obtained in advance, and by minimizing the loss value, the initial network model is updated to further generate a process parameter adjustment model.

[0022] The dimension identification is then input into the process parameter control model to output process parameter data, which is a multi-level control parameter corresponding to the above classification, laying a solid foundation for the subsequent optimization of the first process processing control of the mechanical chain to be processed.

[0023] Step S300: acquiring historical quality inspection data of the first process, performing process status analysis of the first process based on the historical quality inspection data, and generating a process status analysis result;

[0024] Specifically, based on the collected historical quality inspection data of the first process, the process state of the first process is analyzed, wherein the historical quality inspection data of the first process includes the results of inspections of "marking", "dimensions", "chain length measurement", "tensile test" and "dynamic load test" and the process state analysis result of the first process refers to the process stability of mechanical processing. The process stability of mechanical processing refers to the error fluctuation of the process itself under certain processing conditions. If only accidental random factors affect the processing accuracy during the processing, that is, only random fluctuations, the process is stable. If there are systematic error factors affecting the processing accuracy, that is, there are abnormal fluctuations, the process is unstable, thereby ensuring the optimization of the first process processing control of the mechanical chain to be processed.

[0025] Step S400: performing a first process proofing process of the mechanical chain to be processed based on the process parameter data, and generating quality inspection data based on the proofing process result;

[0026] Specifically, based on the process parameter data output by the process parameter control model input according to the above-mentioned dimension identification, the first process proofing processing of the mechanical chain to be processed is carried out, wherein the proofing processing may be a few proofs or more than a dozen proofs, and based on the proofing processing results obtained from the first process proofing processing of the mechanical chain to be processed, quality inspection data is obtained, which plays a promoting role in realizing the optimization of the first process processing control of the mechanical chain to be processed.

[0027] Step S500: inputting the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and outputting an optimized control parameter;

[0028] Specifically, the process parameter data output by the obtained process parameter control model, the proofing processing result generated by the first process proofing processing of the mechanical chain to be processed, and the process state analysis result obtained by the process state analysis of the first process are input into the parameter optimization model together.

[0029] The parameter optimization model is a neural network model in machine learning that can continuously perform self-iterative optimization. The parameter optimization model is obtained by training a training data set and a supervised data set, wherein each set of training data in the training data set includes process state analysis results, proofing processing results, and process parameter data; the supervised data set is the optimized control parameter supervision data that corresponds one-to-one to the training data set.

[0030] Furthermore, the parameter optimization model construction process is as follows: each group of training data in the training data set is input into the parameter optimization model, and the output supervision adjustment of the parameter optimization model is performed through the supervision data corresponding to this group of training data. When the output result of the parameter optimization model is consistent with the supervision data, the training of the current group is completed, and when all the training data in the training data set are trained, the parameter optimization model training is completed.

[0031] In order to ensure the accuracy of the parameter optimization model, the parameter optimization model can be tested using a test data set. For example, the test accuracy can be set to 90%. When the test accuracy of the test data set meets 90%, the parameter optimization model is constructed.

[0032] The process status analysis results, proofing processing results and process parameter data are input into the parameter optimization model, and the optimization control parameter information is output, which has a far-reaching impact on the subsequent realization of the first process processing control optimization of the mechanical chain to be processed.

[0033] Step S600: performing a first process control of the mechanical chain to be processed by using the optimized control parameters.

[0034] Specifically, the first process processing control of the mechanical chain to be processed is performed according to the optimized control parameters output by the parameter optimization model, wherein the first process processing control of the mechanical chain to be processed refers to quality inspection of the processed products of the first process, and optimizing and adjusting the inspection results, so that the qualified rate of the mechanical chain after the first process processing control of the mechanical chain to be processed is increased.

[0035] Furthermore, the present invention provides a method and system for controlling the production process of a mechanical chain based on machine identification, which relates to the field of process processing technology. The method includes: classifying the target mechanical chain to be processed, inputting the size identification into a process parameter control model, collecting and obtaining historical quality inspection data of the first process, performing process status analysis of the first process, performing a first process proofing processing of the mechanical chain to be processed based on the process parameter data to generate quality inspection data, inputting the process status analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and outputting optimized control parameters to perform the first process processing control of the mechanical chain to be processed. The present invention solves the technical problem that the final machine chain production qualification rate is low due to insufficient control over the manufacturing process, quality inspection, process status and proofing processing in the production process of the machine chain production method in the prior art, and realizes the rational and precise control of the machine chain production process, thereby improving the qualification rate of the machine chain production and reducing labor costs.

[0036] Furthermore, if Figure 2 As shown, step S100 of the present application also includes:

[0037] Step S110: obtaining the processing production batch information of the target mechanical chain to be processed, and pre-classifying the target mechanical chain to be processed based on the processing production batch information to obtain a pre-classification result;

[0038] Step S120: performing sample aggregation of the pre-classification result by using the size identifier to obtain a sample aggregation result;

[0039] Step S130: Obtain the classification result according to the sample aggregation result.

[0040] Specifically, the processing production batch information of the target processing machinery chain is collected and obtained, wherein the processing production batch refers to the previous process batch of the current process. For example, assuming that the current process is the first process, the processing production batch is the raw material production batch. Assuming that the current process is the second process, the processing production batch is the first process batch. The processing production batch information is divided according to the time and the order of the equipment in the process flow.

[0041] Furthermore, the target mechanical chains to be processed are pre-classified based on the processing production batch information, wherein the target mechanical chains to be processed are classified into the same category according to the different processing production batch information they belong to, and the pre-classification results are obtained.

[0042] The sample aggregation of the obtained pre-classification results is performed on the obtained size identification, wherein the sample aggregation is performed according to the different size identifications and pre-classification results of the target processing machinery chain. First, a coordinate system needs to be established, and the points of different size identifications of the target processing machinery chain and the points of different pre-classification results of the target processing machinery chain are marked in the coordinate system. The distance between the points is calculated, and similarities are found through distance. The unknown classes are clustered, and the categories and the number of classes are determined at the same time to improve the classification accuracy, and then the sample aggregation results are obtained, so as to obtain the classification results according to the obtained sample aggregation results, thereby achieving the technical effect of providing an important basis for the later realization of the first process processing control optimization of the machinery chain to be processed.

[0043] Furthermore, step S130 of the present application includes:

[0044] Step S131: obtaining size classification constraint information according to the target mechanical chain to be processed;

[0045] Step S132: using the size classification constraint information as an aggregation standard, aggregating the pre-classification result samples with the size identification to obtain the sample aggregation result, wherein the sample aggregation result includes the size classification identification data;

[0046] Step S133: Obtain the classification result through the size classification identification data and the sample aggregation result.

[0047] Specifically, by obtaining size grading constraint information from the information of the target mechanical chain to be processed, and taking the size grading constraint information as the aggregation standard, the pre-classification result samples with size identification are aggregated, wherein the size grading constraint information of the target mechanical chain to be processed is to divide the size of the target mechanical chain to be processed into grades according to the model and constrain it within a certain range, and further taking the size grading constraint information as the aggregation standard, the samples that meet the size grading constraint and identify the size in the above-mentioned pre-classification results are aggregated, so as to obtain the sample aggregation result, and after the size grading identification data contained in the obtained sample aggregation result is integrated with the sample aggregation result, the classification result is finally obtained to ensure the efficiency in realizing the first process processing control optimization of the mechanical chain to be processed.

[0048] Furthermore, step S300 of the present application includes:

[0049] Step S310: Time-stamp the historical quality detection data to obtain a time-stamp result;

[0050] Step S320: performing data weighting calculation of the historical quality detection data based on the time identification result to obtain weighted quality detection data;

[0051] Step S330: Calculating the device stability deviation direction and deviation value of the weighted quality detection data to generate device stability deviation data;

[0052] Step S340: using the equipment stability deviation data as the process status analysis result.

[0053] Specifically, firstly, the collected historical quality inspection data of the first process are time-stamped for different periods of the historical quality inspection data, and based on the time stamp of the obtained historical quality monitoring data, the data weighted calculation of the historical quality monitoring data is performed, wherein the historical quality inspection data of the first process includes the inspection of "marking", "dimensions", "chain length measurement", "tensile test", "dynamic load test" and other aspects, and the number of each historical quality inspection data is further expressed as: k1, k2, k3...kn; the weighted average formula is: (k1p1+k2p2+...knpn) / (k1+k2+......kn), according to the data of the historical quality inspection data, "dimensions" appears 6 times, "marking" appears 3 times, and "chain length measurement" appears 1 time. 6, 3, and 1 are weights, expressed as: (p1+p2+p3+...+pn) / n, so as to obtain the weighted quality inspection data, and further, the equipment stability deviation direction and deviation value are calculated according to the weighted quality inspection data, wherein the process stability is verified by the -R point diagram. In order to clearly distinguish normal fluctuations from abnormal fluctuations, it is necessary to draw the center line and the upper and lower control lines on the x-R point diagram. If the points do not exceed the control lines and most of the points fluctuate randomly above and below the center line, the process is stable, thereby generating equipment stability deviation data, and at the same time using the equipment stability deviation data as the result of process status analysis, ultimately achieving the technical effect of providing a reference for realizing the optimization of the first process processing control of the mechanical chain to be processed.

[0054] Furthermore, if Figure 3 As shown, step S600 of the present application also includes:

[0055] Step S610: setting an initial sampling inspection cycle, performing sampling quality inspection on the processed products of the first process based on the initial sampling inspection cycle, and obtaining sampling quality inspection results;

[0056] Step S620: performing quality deviation evaluation on the sampling quality detection result to obtain a quality deviation evaluation result;

[0057] Step S630: performing compensation optimization of control parameters of the first process based on the quality deviation evaluation result.

[0058] Specifically, the initial sampling inspection is carried out in months, and the initial sampling inspection cycle is set. At the same time, based on the set initial sampling inspection cycle, the processed products of the first process are sampled for quality inspection, wherein the sampling quality inspection result may be qualified or unqualified. Further, the obtained sampling quality inspection result is evaluated for quality deviation, wherein when the sampling quality inspection result is evaluated for quality deviation, the processed product is still qualified, and its quality deviation is a deviation within the qualified range. For example, if the qualified constraint tolerance range is 6 to 10, assuming that the initial value of the sampling quality inspection result is 8, but it is possible that with the change of time, the quality deviation may change to 8.8, 9, 9.5, etc., and the quality deviation evaluation result is further obtained, so as to compensate and optimize the control parameters of the first process according to the quality deviation evaluation result, and finally achieve the technical effect of optimizing the processing control of the first process of the mechanical chain to be processed.

[0059] Furthermore, step S630 of the present application includes:

[0060] Step S631: determining whether the quality evaluation result meets a preset quality deviation threshold;

[0061] Step S632: when the quality evaluation result meets the preset quality deviation threshold, obtaining deviation rate data according to the quality evaluation result;

[0062] Step S633: performing control parameter compensation optimization of the first process based on the deviation rate data.

[0063] Specifically, on the basis of the obtained quality evaluation results, it is judged whether the quality evaluation results meet the preset quality deviation threshold, wherein the preset quality deviation threshold may be dimensional accuracy, wherein the standard of dimensional accuracy may be roller diameter Φ7.8mm, pin shaft length L≤10.4mm, inner sheet spacing ≥3.4mm, and chain pitch 12.7mm. Assuming that the pin shaft length L≤10.4mm and the inner sheet spacing ≥3.4mm are taken as the preset quality deviation threshold, if the quality evaluation result meets the preset quality deviation threshold, that is, the pin shaft length L≤10.4mm and the inner sheet spacing ≥3.4mm, further deviation rate data is obtained according to the obtained quality evaluation results, that is, the quality evaluation results are constantly changing, and (quality evaluation result at the first moment - quality evaluation result at the zeroth moment) / (first moment minus zeroth moment) is the deviation rate data, and at the same time, based on the obtained deviation rate data, the control parameters of the first process are compensated and optimized, so that the probability of the target mechanical chain to be processed meeting the production indicators is improved, thereby realizing the control optimization of the first process processing of the mechanical chain to be processed.

[0064] Embodiment 2

[0065] Based on the same inventive concept as the method for controlling the production process of a mechanical chain based on machine recognition in the aforementioned embodiment, Figure 4 As shown, the present application provides a mechanical chain production process control system based on machine identification, the system comprising:

[0066] A first classification result module 1, which is used to classify the target mechanical chain to be processed to obtain a classification result, wherein the classification result has a size identifier;

[0067] A process parameter data module 2, wherein the process parameter data module 2 is used to input the dimension identifier into a process parameter control model and output process parameter data;

[0068] A state analysis result module 3, wherein the state analysis result module 3 is used to collect and obtain historical quality inspection data of the first process, perform process state analysis of the first process based on the historical quality inspection data, and generate a process state analysis result;

[0069] A quality inspection data module 4, the quality inspection data module 4 is used to perform a first process proofing process of the mechanical chain to be processed based on the process parameter data, and generate quality inspection data based on the proofing process result;

[0070] An optimization control parameter module 5, wherein the optimization control parameter module 5 is used to input the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and output an optimization control parameter;

[0071] The first process control module 6 is used to perform the first process control of the mechanical chain to be processed by the optimized control parameters.

[0072] Furthermore, the system also includes:

[0073] A pre-classification result module, the pre-classification result module is used to obtain the processing production batch information of the target mechanical chain to be processed, and pre-classify the target mechanical chain to be processed based on the processing production batch information to obtain a pre-classification result;

[0074] A first sample aggregation result module, the first sample aggregation result module is used to perform sample aggregation of the pre-classification result through the size identifier to obtain a sample aggregation result;

[0075] The second classification result module is used to obtain the classification result according to the sample aggregation result.

[0076] Furthermore, the system also includes:

[0077] A size grading constraint information module, which is used to obtain size grading constraint information according to the target mechanical chain to be processed;

[0078] A second sample aggregation result module, the second sample aggregation result module is used to use the size classification constraint information as an aggregation standard, aggregate the pre-classification result samples with the size identification, and obtain the sample aggregation result, wherein the sample aggregation result includes size classification identification data;

[0079] The third classification result module is used to obtain the classification result through the size classification identification data and the sample aggregation result.

[0080] Furthermore, the system also includes:

[0081] A time stamp result module, which is used to time stamp the historical quality detection data to obtain a time stamp result;

[0082] A weighted quality detection data module, the weighted quality detection data module is used to perform data weighted calculation of the historical quality detection data based on the time identification result to obtain weighted quality detection data;

[0083] A stable deviation data module, the stable deviation data module is used to calculate the device stable deviation direction and deviation value of the weighted quality detection data to generate device stable deviation data;

[0084] A process status analysis result module is used to use the equipment stability deviation data as the process status analysis result.

[0085] Furthermore, the system also includes:

[0086] A sampling quality inspection result module, which is used to set an initial sampling inspection cycle, perform sampling quality inspection on the processed products of the first process based on the initial sampling inspection cycle, and obtain sampling quality inspection results;

[0087] A quality deviation evaluation result module, which is used to perform quality deviation evaluation on the sampling quality detection result to obtain a quality deviation evaluation result;

[0088] The control parameter compensation optimization module of the first process is used to perform control parameter compensation optimization of the first process based on the quality deviation evaluation result.

[0089] Furthermore, the system also includes:

[0090] A preset quality deviation threshold module, which is used to determine whether the quality evaluation result meets the preset quality deviation threshold;

[0091] A deviation rate data module, the deviation rate data module is used to obtain deviation rate data according to the quality evaluation result when the quality evaluation result meets the preset quality deviation threshold;

[0092] The control parameter compensation optimization acquisition module for the first process is used to perform control parameter compensation optimization for the first process based on the deviation rate data.

[0093] Through the above-mentioned detailed description of a method for controlling the production process of a mechanical chain based on machine identification, those skilled in the art can clearly understand a method and system for controlling the production process of a mechanical chain based on machine identification in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0094] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling the production process of a mechanical chain based on machine recognition, characterized in that: The method comprises: Classifying the target mechanical chain to be processed to obtain a classification result, wherein the classification result has a size identifier; Input the dimension identifier into a process parameter control model and output process parameter data; Acquire historical quality inspection data of the first process, perform process status analysis of the first process based on the historical quality inspection data, and generate a process status analysis result; Performing a first process proofing process on the mechanical chain to be processed based on the process parameter data, and generating quality inspection data based on the proofing process result; Input the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and output the optimization control parameters; Performing a first process control of the mechanical chain to be processed by using the optimized control parameters; The method further comprises: Performing time stamping on the historical quality detection data to obtain a time stamping result; Performing data weighted calculation on the historical quality detection data based on the time identification result to obtain weighted quality detection data; Calculating the device stability deviation direction and deviation value of the weighted quality detection data to generate device stability deviation data; The equipment stable deviation data is used as the process status analysis result.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining processing production batch information of the target mechanical chain to be processed, and pre-classifying the target mechanical chain to be processed based on the processing production batch information to obtain a pre-classification result; Aggregating samples of the pre-classification results by using the size identifier to obtain a sample aggregation result; The classification result is obtained according to the sample aggregation result.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining size classification constraint information according to the target mechanical chain to be processed; aggregating the pre-classification result samples with the size identification using the size classification constraint information as an aggregation standard to obtain the sample aggregation result, wherein the sample aggregation result includes the size classification identification data; The classification result is obtained through the size classification identification data and the sample aggregation result.

4. The method according to claim 1, characterized in that The method further comprises: Setting an initial sampling inspection cycle, performing sampling quality inspection on the processed products of the first process based on the initial sampling inspection cycle, and obtaining sampling quality inspection results; Performing a quality deviation evaluation on the sampling quality test result to obtain a quality deviation evaluation result; Control parameter compensation optimization of the first process is performed based on the quality deviation evaluation result.

5. The method according to claim 4, characterized in that The method further comprises: Determining whether the quality deviation evaluation result meets a preset quality deviation threshold; When the mass deviation evaluation result meets the preset mass deviation threshold, obtaining deviation rate data according to the mass deviation evaluation result; Control parameter compensation optimization of the first process is performed based on the deviation rate data.

6. A mechanical chain production process control system based on machine identification, characterized in that: The system comprises: A classification result module, the classification result module is used to classify the target mechanical chain to be processed to obtain a classification result, wherein the classification result has a size identifier; A process parameter data module, wherein the process parameter data module is used to input the dimension identifier into a process parameter control model and output process parameter data; A state analysis result module, wherein the state analysis result module is used to collect and obtain historical quality inspection data of the first process, perform process state analysis of the first process based on the historical quality inspection data, and generate a process state analysis result; A quality inspection data module, the quality inspection data module is used to perform a first process proofing process of the mechanical chain to be processed based on the process parameter data, and generate quality inspection data based on the proofing process result; An optimization control parameter module, wherein the optimization control parameter module is used to input the process state analysis result, the proofing processing result and the process parameter data into a parameter optimization model, and output an optimization control parameter; A first process control module, the first process control module is used to perform a first process control of the mechanical chain to be processed by using the optimized control parameters; The system further comprises: A time stamp result module, which is used to time stamp the historical quality detection data to obtain a time stamp result; A weighted quality detection data module, the weighted quality detection data module is used to perform data weighted calculation of the historical quality detection data based on the time identification result to obtain weighted quality detection data; A stable deviation data module, the stable deviation data module is used to calculate the device stable deviation direction and deviation value of the weighted quality detection data to generate device stable deviation data; A process status analysis result module is used to use the equipment stability deviation data as the process status analysis result.