An intelligent processing system and method for the entire process of R&D experiments based on the Internet of Things

Abstract

The present application relates to the technical field of industrial intelligent platforms, and in particular to an intelligent processing system and method for the entire process of R&D experiments based on the Internet of Things, which includes: an acquisition module for collecting raw data from each link; an Internet of Things platform for classifying and storing the raw data; a local knowledge base for acquiring the raw data and retrieving associated local data; an intelligent processing module for performing comparative analysis based on the raw data and associated local data to generate and distribute guidance strategies for process guidance, and also for obtaining feedback results; the intelligent processing module uses the adjusted data as full-process data based on the feedback results, and also generates a design assistance strategy based on the feedback results; a design module for uploading design object information, acquiring corresponding full-process data to formulate basic parameters, and obtaining a design assistance strategy for assisting comparison. The present application has the effect of connecting and associating data in all manufacturing links to propose guidance strategies for each link.

Description

Technical Field

[0001] The present application relates to the technical field of industrial intelligent platforms, and in particular to an intelligent processing system and method for the entire process of R&D experiments based on the Internet of Things. Background Art

[0002] In the manufacturing industry, for products such as vacuum pumps, it is necessary to collect and record a number of corresponding data throughout the entire manufacturing process. The data from each link can be used to analyze whether the vacuum pump is manufactured in compliance with regulations and whether the product is qualified.

[0003] However, there are the following deficiencies in the prior art:

[0004] Most of the data are in paper form, which is not convenient for archiving and statistical analysis;

[0005] Data from each step of the manufacturing process is distributed in a point-by-point manner, making it difficult to correlate with each other. This hinders subsequent data analysis and makes it difficult to formulate guiding strategies for the entire design.

[0006] The data of each link is only used for verification and traceability in the current stage, and to detect whether the design requirements are met, but it is difficult to associate and combine with the data of other links to guide the design source and propose optimization strategies. Summary of the Invention

[0007] In order to achieve data integration and association in all aspects of manufacturing and to propose guiding strategies for each link, this application provides an intelligent processing system and method for the entire R&D experiment process based on the Internet of Things.

[0008] In the first aspect, the present application provides an intelligent processing system for the entire process of R&D experiments based on the Internet of Things, which adopts the following technical solutions:

[0009] An intelligent processing system for the entire R&D experiment process based on the Internet of Things, including:

[0010] The acquisition module is used to collect raw data from each link and upload it to the IoT platform;

[0011] An Internet of Things platform, used to classify the raw data and store them in data sets corresponding to different links;

[0012] A local knowledge base, used to obtain the raw data in each of the data sets and retrieve the associated local data and package and send it to the intelligent processing module;

[0013] an intelligent processing module, configured to compare and analyze the raw data with the associated local data to generate a guidance strategy and issue it to each link for process guidance, and also to obtain feedback results generated in each link after adjustment based on the guidance strategy;

[0014] The intelligent processing module uploads the adjusted data as full-process data to the local knowledge base based on the feedback result, and the intelligent processing module also generates a design assistance strategy including several key design exception items based on the feedback result;

[0015] The design module uploads the design object information, obtains the corresponding full-process data in the local knowledge base to formulate the basic parameters of the design process, and connects to the intelligent processing module to obtain the design assistance strategy to assist in the comparison of the design process.

[0016] In some embodiments, the steps include a quality inspection step, in which:

[0017] Obtaining the collected quality inspection data and uploading it to the Internet of Things platform;

[0018] The local knowledge base retrieves a locally stored quality inspection list based on the quality inspection object in the quality inspection data;

[0019] Filling the quality inspection data into the corresponding quality inspection checklist and then sending it to the intelligent processing module, and the intelligent processing module verifies each quality inspection data based on the specification requirements in the quality inspection checklist;

[0020] A risk item is generated based on the verification result, wherein the verification result at least includes deviation and data missing.

[0021] In some embodiments, the intelligent processing module is further configured to retrieve corresponding processing opinions and cause analysis from the local knowledge base based on the content, quantity, and combination correlation coefficient of the risk items;

[0022] The handling opinions include measures, priorities, responsible parties and completion deadlines;

[0023] The cause analysis includes abnormal events and corresponding compliance probabilities, which are obtained based on the following steps:

[0024] Selecting a list of reasons with corresponding numbers in the local knowledge base based on the verification result;

[0025] generating a basic probability of each abnormal event in the cause list based on the content of the risk item;

[0026] A combined risk set is generated based on the number and content of the risk items, a combined correlation coefficient is calculated based on the combined risk set in combination with an empirical algorithm, and the basic probability is adjusted based on the combined correlation coefficient to obtain the compliance probability.

[0027] In some embodiments, the steps include an assembly step, in which:

[0028] The intelligent processing module obtains assembly data in the Internet of Things platform and obtains a matching rule document matching the assembly object in the local knowledge base;

[0029] The intelligent processing module arranges and combines the plurality of assembly objects that have an assembly relationship, and calculates assembly parameters corresponding to each combination based on the matching rule document;

[0030] Based on the matching rule document, assembly standards are extracted, and each assembly parameter is classified according to the assembly standard to issue evaluation indicators of corresponding levels, and each combination is allocated to a corresponding application environment according to each evaluation indicator.

[0031] In some embodiments, the step includes a testing step, in which:

[0032] The intelligent processing module obtains test data in the Internet of Things platform and obtains test items matching the test object in the local knowledge base;

[0033] The test items are issued for testing, and a change curve of each test data under different test items is obtained in real time;

[0034] The test data with abnormal change curves are packaged with the test items to obtain key test items.

[0035] In some embodiments, the intelligent processing module is further configured to:

[0036] The risk items, the handling opinions and the cause analysis are used as the first guidance strategy, and are distributed to the responsible parties in the corresponding quality inspection links based on priority for process guidance;

[0037] The evaluation index is used as a second guidance strategy and is sent to the assembly link in the corresponding application environment for assembly guidance;

[0038] Each of the test key items is used as a third guidance strategy and is sent to the corresponding test object in the test link for test guidance.

[0039] In some embodiments, the intelligent processing module is further configured to obtain feedback results from the quality inspection link, the assembly link, and the testing link, respectively, and determine whether the guidance strategy corresponding to each link is effective based on the feedback results;

[0040] If valid, the intelligent processing module sends the adjusted optimization data to the local knowledge base for storage and adds a project case number;

[0041] If invalid, the intelligent processing module marks the local data in the local knowledge base and reselects the local data to generate a new guidance strategy until the feedback result is valid;

[0042] When the project case number corresponds to the entire process, the local knowledge base uses all data in the same project case number as the entire process data.

[0043] In some embodiments, the key design abnormal items include data corresponding to when the feedback result is valid and adjusted based on the guidance strategy, and data corresponding to when the feedback result is invalid.

[0044] In some embodiments, the intelligent processing module uses the design key anomaly item as a key feature and selects corresponding quality inspection data and / or assembly data and / or test data as key data;

[0045] Obtaining a preset bias in the local knowledge base based on the key feature;

[0046] Calculating an influence parameter matrix corresponding to each of the key features based on the key data and the preset bias, wherein the influence parameter matrix includes a number of influence parameters for characterizing the influence of the key data corresponding to each of the key features on the target result in the design process;

[0047] The design assistance strategy is generated based on the influencing parameters.

[0048] Secondly, this application provides an intelligent processing method for the entire R&D experiment process based on the Internet of Things, which adopts the following technical solutions:

[0049] An intelligent processing method for the entire process of R&D experiments based on the Internet of Things includes the following steps:

[0050] Collect raw data from each link;

[0051] Classifying the raw data and storing them in data sets corresponding to different links;

[0052] Obtaining the original data in each of the data sets and retrieving associated local data;

[0053] Comparing and analyzing the original data with the associated local data to generate a guidance strategy and issuing it to each link for process guidance, while obtaining feedback results generated in each link after adjustment based on the guidance strategy;

[0054] Based on the feedback results, the adjusted data is used as full-process data, and a design assistance strategy including several key design exception items is generated according to the feedback results;

[0055] Upload the design object information, obtain the corresponding full-process data to formulate the basic parameters of the design process, and obtain the design assistance strategy to assist in comparing the design process.

[0056] The technical solutions provided by the embodiments of this application have the following technical effects:

[0057] First, through the combination of the acquisition module and the IoT platform, different types of data from all links in the entire manufacturing process are uniformly collected and stored. This can preserve all key data from the equipment R&D and assembly process in a long-term and stable manner, facilitating subsequent analysis.

[0058] The original data of each link, the local reference materials corresponding to the guidance strategy, and the data adjusted after guidance are all managed in a unified manner to build a local knowledge base. Through the accumulation of big data, local knowledge is continuously enriched. In the subsequent monitoring and management of each link, the parameter information, process information, and process information of each link can be directly and independently guided by the intelligent processing module.

[0059] While providing distributed guidance, with the support of full-process data consisting of multiple links, the design source can be directly guided and assisted through data-feedback results, realizing the control of link processes through data analysis and guiding the design process with link results. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a module connection diagram of an intelligent processing system for the entire process of R&D experiments based on the Internet of Things provided in this embodiment.

[0061] Figure 2 It is a schematic diagram corresponding to the quality inspection checklist in the quality inspection phase of the embodiment of the present application.

[0062] Figure 3 This is a schematic diagram of risk item marking in an embodiment of the present application.

[0063] Figure 4 It is a schematic diagram of the processing opinions and cause analysis of the embodiment of this application.

[0064] Figure 5 It is a schematic diagram of the list in the assembly process of the embodiment of the present application.

[0065] Figure 6 This is a schematic diagram corresponding to the design assistance strategy of the embodiment of the present application.

[0066] Figure 7 This is a schematic diagram of the steps of the intelligent processing method for the entire process of R&D experiments based on the Internet of Things provided in this embodiment. DETAILED DESCRIPTION

[0067] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. However, it should be understood by those skilled in the art that the present application can be implemented without these details. In some cases, in order to avoid unnecessary descriptions that make various aspects of the present application obscure, the well-known methods, processes, systems, components and / or circuits that have been described at a higher level will not be described in detail. It is obvious to those skilled in the art that various changes can be made to the embodiments disclosed in the present application, and the general principles defined in the present application can be applied to other embodiments and application scenarios without departing from the principles and scope of the present application. Therefore, the present application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope claimed for protection in the present application.

[0068] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0069] In the description of this application, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0070] In the description of this application, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any combination in one or more embodiments or examples.

[0071] like Figure 1 As shown, the embodiment of the present application discloses an intelligent processing system for the entire process of R&D experiments based on the Internet of Things, including:

[0072] The acquisition module is used to collect raw data from each link and upload it to the Internet of Things platform.

[0073] The acquisition module can collect raw data from all aspects of manufacturing and R&D. The types of raw data include but are not limited to electronic document data, handwritten paper data, image data, and sensor data. The acquisition module includes computers, mobile tablets, image recognition devices, and various types of IoT sensors.

[0074] After collecting the original data from each link, the acquisition module uploads various types of data to the Internet of Things platform for storage.

[0075] Based on the Internet of Things platform, various types of data from all links are integrated, collected and stored in a unified manner, which facilitates subsequent data processing and the generation of guidance strategies.

[0076] The Internet of Things platform is used to classify a number of raw data and store them in data sets corresponding to different links.

[0077] After receiving the raw data, the IoT platform first processes the data to convert it into structured data. The processing methods include but are not limited to data cleaning, NLTK-based text parsing, semantic understanding, etc.

[0078] Structured data generally includes tables, lists, and lists, while unstructured raw data includes text data.

[0079] When storing raw data, both the raw data and the corresponding processed structured data must be stored.

[0080] After all the data in each link are stored, the data corresponding to each link are integrated into a data set based on the link where each data is collected.

[0081] The local knowledge base is used to obtain the original data in each data set and retrieve the associated local data and package it to send to the intelligent processing module;

[0082] Local data includes original data from the historical process, historical data adjusted by guidance strategies, various standardization requirement materials, various rule lists, various drawings and other process materials.

[0083] The local knowledge base serves as a fusion database, which stores all the data materials corresponding to data analysis and processing. At the same time, the newly acquired data during real-time operation will also be stored in the local knowledge base for updating.

[0084] At the same time, when data for a certain link is obtained later and guidance is needed for that link, it is necessary to search the local knowledge base through the type, object, characteristics, link requirements, etc. corresponding to the link data. After retrieving the related auxiliary materials, comparison materials, requirement materials, etc., the corresponding materials will be used as the basic comparison materials for subsequent determination of whether the data for each link needs guidance and how to provide guidance.

[0085] The intelligent processing module is used to compare and analyze the original data with the associated local data to generate guidance strategies and send them to each link for process guidance. It is also used to obtain feedback results generated in each link after adjustment based on the guidance strategies.

[0086] The intelligent processing module is a big data intelligent AI model integrated into the system. It is mainly used to analyze and reason about various types of data, perform intelligent retrieval in the local knowledge base, and subsequently generate guidance strategies corresponding to each link.

[0087] It first compares and analyzes each original data with the matching local data. Depending on the different links, the comparison objects, comparison methods, and comparison requirements are all different. Then, based on different comparison results, corresponding guidance strategies are generated and sent to the links corresponding to the original data for process guidance. At the same time, after obtaining the guidance strategy, each link will choose whether to adjust and whether the adjustment is effective based on the guidance strategy, and provide feedback on the corresponding results.

[0088] Based on the feedback results, the intelligent processing module uploads the adjusted data as full-process data to the local knowledge base. The intelligent processing module also generates a design assistance strategy containing several key design exception items based on the feedback results.

[0089] At the same time, the intelligent processing module also integrates the adjusted data in each link as the whole process data through feedback information, and uploads the whole process data to the local knowledge base. It should be noted that all link data of each model of workpiece corresponds to one whole process data.

[0090] The intelligent processing module can also infer and judge the abnormal content in each link based on the feedback results, and mark the key design abnormal items corresponding to different parameter objects. The key design abnormal items correspond to the design source, and are characterized by analyzing the parameter conditions in the actual manufacturing steps to analyze the main guidance details that can guide the design source. The analyzed key abnormal items are used as design assistance strategies.

[0091] The design module uploads the design object information and obtains the corresponding full-process data in the local knowledge base to formulate the basic parameters of the design process, and connects to the intelligent processing module to obtain the design assistance strategy to assist in the comparison of the design process.

[0092] The design module is used by designers to design the parameters, processes and procedures of workpieces and components. After uploading the object information to be designed, such as the type, parameters and process flow of the workpiece, the designer will obtain the full-process data corresponding to this type of product in the local knowledge base. This full-process data serves as the basic parameters corresponding to the entire design link. The basic data is used to provide overall guidance based on historical analysis at the beginning of the design, so that designers can know in advance the approximate parameter size and parameter relationship of this type of product, the items that need to be tested in subsequent links, feedback on whether it meets the requirements of the link, etc.

[0093] At the same time, the intelligent processing module will also send the corresponding key abnormal items to the design module based on the design object for design assistance, so as to remind designers at the source of the design which parameter characteristics will be the focus of data in subsequent links or the characteristics that have a greater impact on the performance of the finished product.

[0094] Through the above method, first, the different types of data in each link of the entire manufacturing process are uniformly collected and stored through the combination of the acquisition module and the Internet of Things platform, which can preserve all key data in the equipment research and development and assembly process for a long time and stably, facilitating subsequent analysis work; the original data in each link, the local reference materials corresponding to the guidance strategy, the data adjusted after guidance, etc. are all uniformly managed to build a local knowledge base. Through the accumulation of big data, the local knowledge is continuously enriched. In the subsequent monitoring and management process of each link, the parameter information, process information, process information, etc. in each link process can be directly distributed and independently guided by the intelligent processing module; at the same time as the distributed guidance, with the support of the full process data composed of multiple links, the design source can also be directly guided and assisted through the data-feedback results, realizing the control of the link process by data analysis and the guidance of the design process by the link results.

[0095] In other embodiments, the steps include a quality inspection step. Quality inspection is characterized by quality inspection of parameters, dimensions, performance, etc. of each component before assembly. Only components that pass the quality inspection are qualified and can enter the subsequent steps. In the quality inspection step:

[0096] Obtain the collected quality inspection data and upload it to the IoT platform.

[0097] Quality inspection data includes component dimensions, component structure, etc., which are generally tabular data or handwritten image data.

[0098] The local knowledge base retrieves the locally stored quality inspection list based on the quality inspection object in the quality inspection data.

[0099] The local knowledge base first retrieves the locally stored quality inspection list based on the quality inspection object. The quality inspection object is represented by basic information such as the name and model of the inspected component. The quality inspection list is the quality inspection items, measurement methods, and parameter specifications corresponding to different components uploaded in advance.

[0100] When the data comparison and analysis is performed in the subsequent quality inspection stage, the corresponding data is obtained from the quality inspection data based on the quality inspection checklist and analyzed to see whether it meets the quality inspection results required by the checklist.

[0101] The quality inspection data is filled into the corresponding quality inspection checklist and then sent to the intelligent processing module, which verifies each quality inspection data based on the specification requirements in the quality inspection checklist.

[0102] First, each component is entered into the quality inspection checklist based on the component model in the structured data. Then, the corresponding data in the quality inspection data is placed into the quality inspection checklist in sequence based on the measurement items required by the quality inspection checklist. The intelligent processing module compares and verifies each quality inspection data based on the specification requirements in the quality inspection checklist.

[0103] Risk items are generated based on the verification results, which at least include deviations and missing data.

[0104] Attach Figure 2 For example, a quality inspection checklist includes the following information: part number, measurement item, drawing specifications, measurement method, and model numbers of several components. Furthermore, in the "total length" item, the total length of the component model "PM03XM" is 551.320, while the drawing specification for this item is 550±0.5. Since "PM03XM" exceeds this range, it corresponds to an out-of-tolerance risk item. Furthermore, in the "outer diameter" quality inspection item, the corresponding data for the component model "PM05XM" is missing, resulting in a missing data risk item. Each component model is specifically a rotor.

[0105] There are mainly two types of feedback information for the verification results. One is whether a quality inspection item can find corresponding data in the quality inspection data. If it cannot be found, then the blank item corresponding to the quality inspection item cannot be quality inspected and verified. The second is that after verification, it is analyzed that the error between one or some parameters and the standard parameter specifications is greater than the standard error of the item.

[0106] In the first type of feedback information, it corresponds to the risk item of missing data; in the second type of feedback information, it corresponds to the risk item of out-of-tolerance.

[0107] As attached Figure 3As shown, the system will individually classify and mark each parameter corresponding to a risk item in the quality inspection checklist. Once all items in the quality inspection checklist have been compared and verified, the quality inspection checklist will be output as a quality inspection report. The results of the individual classification and marking include the corresponding risk item number, measurement item, parameter allowable range calculated based on the drawing specifications, detected abnormal measurement value (corresponding to a numerical value if the risk item is out of tolerance; corresponding to a null value if the risk item is missing data), the degree of deviation, and the risk level (such as CRITICAL - critical, MAJOR - major).

[0108] In other embodiments, the intelligent processing module is further used to retrieve corresponding processing opinions and cause analysis from the local knowledge base based on the content, quantity and combination correlation coefficient of the risk items.

[0109] Furthermore, in order to facilitate the personnel in the quality inspection link to know how to optimize and rectify the quality inspection link, the intelligent processing module will also retrieve processing opinions and cause analysis from the local knowledge base based on the specific content and quantity of the risk items and the combination relationship between multiple risk items.

[0110] Among them, the handling opinions include measures, priorities, responsible parties, and completion deadlines. Measures represent what actions the guidance personnel need to take to resolve the risk item; priorities represent the importance of each measure when it is carried out, and the higher the priority, the faster the action needs to be carried out; responsible parties represent the specific personnel or departments that need to carry out each measure; and completion deadlines represent the time required for different measures to be completed. Among them, it should be noted that in some cases, some measures in the complete set will correspond to other departments, which are used to enable other departments to work together with the departments in the quality inspection process to guide and optimize the quality inspection data.

[0111] Through the processing opinions, each person or department in the quality inspection process can be guided to take corresponding measures quickly within the scheduled time to produce results for abnormal risk items in the quality inspection process and inform users how to re-conduct quality inspection.

[0112] As attached Figure 4 As shown, the generated handling opinions have priorities, namely urgent and important; there are four measures, namely: "Isolate out-of-tolerance parts No. 1", "Initiate missing data traceability mechanism", "Implement measurement system analysis", and "Establish automatic out-of-tolerance alarm system"; the responsible persons are the Quality Inspection Department, Production Department, Quality Department, and IT Department; and the completion deadlines are immediately, 2 hours, 48 ​​hours, and 72 hours.

[0113] Cause analysis includes abnormal events and corresponding compliance probabilities. Abnormal events represent the possible corresponding cause events when the quality inspection data of a parameter is abnormal. Compliance probability represents the corresponding occurrence probability of the cause event.

[0114] As attached Figure 4 As shown in the figure, when the quality inspection value of PM03XM is out of tolerance, the possible corresponding causes include fixture positioning offset, which has an 80% probability of occurrence, temperature compensation failure, which has a 15% probability of occurrence, and measurement system error, which has a 5% probability of occurrence.

[0115] When the data in number 9 is missing, the possible corresponding causes include omission of manual recording, with a probability of 70%, and interruption of sensor communication, with a probability of 30%.

[0116] The probability of compliance is obtained based on the following steps:

[0117] Based on the verification results, a list of reasons with corresponding numbers is selected from the local knowledge base.

[0118] First, after obtaining the verification result, a cause list corresponding to the measurement item with the corresponding number is obtained in the local knowledge base. The list stores all possible causes that may be triggered when the cause occurs in the certain component.

[0119] Generate the basic probability of each abnormal event in the cause list based on the content of the risk item.

[0120] Secondly, the basic probability of the abnormal event is obtained in the cause list according to the content of the risk item. Among them, deviation and data missing correspond to different basic probabilities. At the same time, the size of the deviation value also corresponds to different basic probabilities. For example, when the deviation value is small, the greater probability corresponds to the system error, and when the deviation value is large, the greater probability corresponds to the fixture positioning offset.

[0121] A combined risk set is generated based on the number and content of risk items, a combined correlation coefficient is calculated based on the combined risk set combined with an empirical algorithm, and the basic probability is adjusted based on the combined correlation coefficient to obtain the compliance probability.

[0122] After determining the basic probability through the content of a single risk item, when the number of risk items is greater than 1, it is necessary to generate a combined risk set based on the number and content of the risk items, and optimize the specific probability corresponding to each risk item through the combined risk set.

[0123] If there is a large amount of missing data in the risk concentration, and at the same time, the missing data all correspond to the same model component, then the greater probability is that it is due to omissions in manual records after quality inspection of the model component; if a large amount of missing data corresponds to various models, then the possibility of manual omissions in records by the quality inspectors corresponding to each model component is low, and the corresponding probability of sensor communication failure is greater.

[0124] If there are a large number of deviations in the risk concentration, then when the inner diameter, outer diameter, and thread accuracy all have deviations, due to the different measurement methods of each parameter, the probability of deformation caused by fixture deviation is low, while the probability of deformation of different parts due to temperature compensation failure is high.

[0125] By combining single analysis and combined analysis, we can comprehensively analyze the causes of risk items and their corresponding probabilities, so that personnel in the quality inspection process can receive intuitive guidance and quickly adjust quality inspection actions.

[0126] In other embodiments, the process includes an assembly process. Assembly is characterized by assembling parts that have passed quality inspection according to assembly requirements by assemblers. Furthermore, the corresponding accuracy levels after assembling multiple parts of different models or parts with different quality inspection parameters are different. Therefore, in order to analyze the accuracy of different assembly combinations and obtain guidance strategies for the assembly process, in the assembly process:

[0127] The intelligent processing module obtains assembly data from the IoT platform and obtains the matching rule document that matches the assembly object from the local knowledge base.

[0128] The intelligent processing module first pulls the assembly data from the IoT platform. The assembly data is generally saved in the form of a structured dimension table document, such as "JSC85 shell dimension detection data" and "JSC85 rotor dimension detection data".

[0129] At the same time, based on the type and model of the assembly object, a matching selection rule document is obtained from the local knowledge base. The document contains assembly rules such as matching each shell and rotor and performing equal diameter evaluation, as well as comparison, evaluation, and classification rules for post-assembly consideration parameters.

[0130] like Figure 5 As shown, the intelligent processing module arranges and combines several assembly objects that have an assembly relationship, and calculates the assembly parameters corresponding to each combination based on the matching rule document.

[0131] First, the intelligent processing module arranges and combines several assembly objects that have an assembly relationship to align each housing with each rotor. It then performs a global optimization to select the optimal assembly combination of each housing and each rotor, and generates a list. These steps are implemented using the LLM algorithm.

[0132] At the same time, the rules based on the matching rule document require the target parameters to be verified for the assembled assembly. The target parameters are characterized as the determining parameters used to consider the assembly effect after the combination of two or more components. For example, the target parameter after the rotor and housing are assembled is the gap.

[0133] After selection, the assembly parameters corresponding to each assembly are calculated based on the target parameters. The assembly parameters specifically include the overall parameter size and the subdivided parameter size. For example, the overall parameter is the total gap, and the subdivided parameter is the gap distribution.

[0134] Based on the matching rule document, the assembly standard is pulled, and each assembly parameter is classified according to the assembly standard to issue the corresponding level of evaluation indicators. Each combination is assigned to the corresponding application environment according to each evaluation indicator.

[0135] The standard value corresponding to the target parameter is used as the assembly standard, the assembly parameters of each assembly are compared with the assembly standard, and the assembly combinations are ranked based on the difference. The larger the difference, the worse the assembly effect.

[0136] At the same time, each combination is classified based on the size of the difference, and the classification corresponds to different levels of evaluation indicators, including "A+", "A", "A-", "B+", "B", "B-", etc. The higher the level, the higher the performance level of the assembled rotor and housing.

[0137] Finally, each combination result is assigned to the corresponding application environment based on each evaluation indicator. For example, for vacuum pumps, higher levels can be used in high-precision application scenarios such as semiconductors, while lower levels can be used in less high-precision scenarios such as photovoltaics.

[0138] In other embodiments, the process includes a testing process. The testing process is characterized by testing the performance and parameters of the components according to different test indicators after the components are assembled to see whether they meet the requirements. In the testing process:

[0139] The intelligent processing module obtains test data in the Internet of Things platform and obtains test items that match the test object.

[0140] First, pull the test data from the IoT platform. The test data includes the type of test object and the parameters that need to be tested.

[0141] At the same time, the test items matching the test object are obtained in the local database based on the test object. The test items are characterized as test items that must be performed for different types of components, such as performance index test, temperature index test, rigidity index test, flip index test, etc.

[0142] The test items are issued for testing, and the change curves of each test data under different test items are obtained in real time.

[0143] Perform preliminary screening of test data based on test items, and monitor the change curve corresponding to the change of test data in real time.

[0144] The test data with abnormal change curves are packaged with the test items to obtain the key test items.

[0145] Based on the data trends before and after the change curve and the historical test data of the same type of devices that have passed the test stored in the local database, it is determined whether there is test data with large deviations under different test items. If so, these data will be used as test focus items.

[0146] In other embodiments, after comparing and analyzing the original data of each link with the local data, the intelligent processing module can generate guidance strategies for each link based on the analysis results and send them to the corresponding links. Specifically:

[0147] Risk items, handling opinions and cause analysis are used as the first guidance strategy, and are distributed to the responsible parties in the corresponding quality inspection links based on priority for process guidance.

[0148] First, the risk items, handling opinions and cause analysis are used as the first guiding strategy and issued to each responsible party in the quality inspection link. After the corresponding data of the quality inspection link is analyzed, it is fed back to the quality inspection link to inform which quality inspection parameters have risks, how to deal with them and the reasons for their occurrence. The personnel in the quality inspection link can adjust the quality inspection work of this time according to the first guiding strategy, and can also make corresponding adjustments and preventions to subsequent quality inspection work based on the first guiding strategy.

[0149] The evaluation indicators are used as the second guidance strategy and sent to the assembly links in the corresponding application environment for assembly guidance.

[0150] The evaluation index is used as the second guiding strategy to provide feedback to guide the assembly personnel on which selection method corresponds to the highest performance, and to guide the assembly personnel on which application environment to classify each assembled component.

[0151] Each key test item is used as the third guidance strategy and distributed to the corresponding test objects in the test phase for test guidance.

[0152] Use the test focus items as the third guidance strategy to provide feedback to guide testers in the test phase to focus on and / or repeat testing of some key data.

[0153] In other embodiments, the intelligent processing module is further used to obtain feedback results from the quality inspection link, assembly link, and testing link respectively, and determine whether the guidance strategy corresponding to each link is effective based on the feedback results.

[0154] The intelligent processing module obtains feedback results of each link on the guidance strategy, and the feedback results include whether adjustments are made, whether there are improvements after adjustments, and the adjusted parameters.

[0155] Based on the feedback results, we specifically analyze whether the guidance strategy in this link is effective. If the link makes adjustments after receiving the guidance strategy and the adjusted parameters become better, the guidance strategy is effective; if the link does not make adjustments after receiving the guidance strategy or the adjusted parameters do not become better, the guidance strategy is invalid.

[0156] If valid, the intelligent processing module will send the adjusted optimization data to the local knowledge base for storage and add a project case number.

[0157] If the guidance strategy is effective, the intelligent processing module will send the adjusted optimization data of each link to the local knowledge base and add a project case number. A project case number corresponds to the complete manufacturing process of a model of component.

[0158] The local knowledge base will uniformly store the optimized data and its corresponding original data and local data to construct full-process data that includes the representation of the pre-guidance status, reference during guidance, and post-guidance data.

[0159] If it is invalid, the intelligent processing module marks the local data in the local knowledge base and reselects the local data to generate a new guidance strategy until the feedback result is valid.

[0160] If the guidance strategy is invalid, the intelligent processing module will mark the local data used in the analysis of this link, and the marked local data can inform the system user to replace, update and verify it.

[0161] At the same time, the intelligent processing module will select a new guidance strategy from the local knowledge base to re-analyze and guide the data in the link until the guidance strategy for the link is effective.

[0162] When the project case number corresponds to the entire process, the local knowledge base will use all data in the same project case number as the entire process data.

[0163] When all feedback results are valid, all data in the completed whole process will be integrated as whole process data. The whole process data will be used to trace the design source and further guide the design link at the source.

[0164] In other embodiments, the key design exception items include data corresponding to valid feedback results and adjustments based on the guidance strategy, and data corresponding to invalid feedback results.

[0165] When providing guidance on the design phase, the main focus is on guiding key design anomalies, such as which data are prone to anomalies in subsequent quality inspection, assembly, and testing phases. In the subsequent design of other components, these data need to be focused on and analyzed.

[0166] Key design anomalies include data with valid feedback and adjustments based on the guidance strategy, as well as data with invalid feedback. These data are generally characterized by abnormalities detected in various stages after analysis. These abnormal data require special marking in subsequent design stages to facilitate attention to these parameters. Invalid feedback data, however, represents data for which the local knowledge base cannot provide accurate local data for comparison. These data present a high risk of abnormalities in subsequent stages, and therefore require early attention during the design phase.

[0167] Through the above method, the data analysis and guidance strategy feedback in each historical link are used to generate advance guidance plans for subsequent new design products, so as to optimize some data, processes, shapes, etc. in a targeted manner from the design source, and realize a feedback closed loop that guides the front-end design link from the data of the rear link. While monitoring the data of each link, positive feedback guidance of the link and reverse feedback guidance of the design link are realized based on the analysis results and knowledge base.

[0168] In other embodiments, the intelligent processing module uses the design key abnormal items as key features and selects corresponding quality inspection data and / or assembly data and / or test data as key data.

[0169] The intelligent processing module takes each key abnormal item of the design as the key feature, and pulls the corresponding data from the corresponding link data as the key data to bind the content that needs to be guided for the design link.

[0170] When selecting key features, you can select all key abnormal items or only some key abnormal items. At the same time, the data corresponding to each model component can be pulled out and a table can be drawn.

[0171] Obtain preset biases in the local knowledge base based on key features.

[0172] The bias corresponding to each key feature is obtained in the local knowledge base. The bias is represented as a fixed deviation term that is independent of the characteristics of each data itself. It is used to adjust the size of the influencing parameters in subsequent calculations to improve the accuracy and robustness of the model. Through continuous training, the bias is continuously optimized in random values ​​and updated based on the feedback propagation algorithm.

[0173] The influence parameter matrix corresponding to each key feature is calculated based on the key data and preset bias. The influence parameter matrix contains several influence parameters used to characterize the influence of the key data corresponding to each key feature on the target result in the design link.

[0174] After obtaining the bias, the influence parameter matrix corresponding to each key feature is calculated based on the key data and the bias. The influence of the data of each feature of each model in the matrix on the final target result is represented as the influence parameter.

[0175] The larger the influencing parameter is, the more critical the feature is, and the abnormality of the feature will cause a greater impact on the final target result.

[0176] Generate design assistance strategies based on influencing parameters.

[0177] Finally, the influencing parameters of each feature corresponding to each model are sorted out to obtain a corresponding list, which is then sent to the design stage as a design assistance strategy. Designers in the design stage can combine the design parameters in the design process with the influencing parameters and put them into the model of the intelligent processing module as input items. Finally, the corresponding target parameters are output through calculation by the model.

[0178] Specifically, such as Figure 6 As shown in the figure, the design assistance strategy first corresponds to different types of linear screw rotors and several key features, such as tooth root arc radius, suction lead, exhaust lead, rotor clearance, internal pressure ratio, etc., and also includes the key data parameters corresponding to these key features, as well as the target results of "gas work" and the numerical values ​​of the target results of each model.

[0179] At the same time, the bias corresponding to each key feature is obtained from the local knowledge base, and the linear matrix formula is combined to calculate the influencing parameter size corresponding to the key feature value of each model. The linear matrix formula is specifically:

[0180] ;

[0181] in, It is represented by the numerical value corresponding to the nth key feature of the mth model. It is represented by the influencing parameter corresponding to the mth key feature, y is represented by the predicted gas work, and b is represented by the bias.

[0182] Through the above formula, after clarifying the size of the influencing parameters of each key feature, the corresponding list is sent to the design stage. Designers can know the impact of a key feature in different types of components on the final target data through the size of the influencing parameters, and use this as a guide to pay attention to the key data. At the same time, after designing the size, performance and other data of each feature of the component, designers can directly predict the gas work by introducing the linear matrix formula combined with the bias and influence coefficient. At the same time, the predicted gas work is compared with the test value of the final test stage. According to the comparison results, it is judged whether the assistance strategy of the design stage and the guidance strategy of the test stage match, thereby once again realizing the feedback closed loop.

[0183] like Figure 7 As shown, the present application also discloses an intelligent processing method for the entire process of R&D experiments based on the Internet of Things, comprising the following steps:

[0184] S100, collecting raw data in each link.

[0185] S200, classify a number of original data and store them in data sets corresponding to different links.

[0186] S300: Obtain original data from each data set and retrieve associated local data.

[0187] S400 , performing comparison and analysis between the original data and the associated local data to generate a guidance strategy and sending it to each link for process guidance, while obtaining feedback results generated in each link after adjustment based on the guidance strategy.

[0188] S500: Based on the feedback results, the adjusted data is used as the full process data, and a design assistance strategy including several key design exception items is generated according to the feedback results.

[0189] S600, uploading design object information, obtaining corresponding full-process data to formulate basic parameters of the design process, and obtaining design assistance strategies to assist in comparison of the design process.

[0190] The implementation principle is:

[0191] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps and they may be performed in other orders.

[0192] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. An intelligent processing system for the entire process of R&D experiments based on the Internet of Things, characterized by: include: The acquisition module is used to collect raw data from each link and upload it to the IoT platform; An Internet of Things platform, used to classify the raw data and store them in data sets corresponding to different links; A local knowledge base, used to obtain the raw data in each of the data sets and retrieve the associated local data and package and send it to the intelligent processing module; an intelligent processing module for performing a comparison analysis based on the raw data and the associated local data; at the same time, based on different links, the objects, methods, and requirements of the comparison analysis are different; generating corresponding guidance strategies based on different comparison results and issuing them to each link corresponding to the raw data for process guidance; and also for obtaining feedback results generated in each link after adjustment based on the guidance strategies; The intelligent processing module uploads the adjusted data as full-process data to the local knowledge base based on the feedback result. The intelligent processing module also generates a design assistance strategy containing several key design exceptions based on the feedback result, wherein the key design exceptions include data where the feedback result is valid and is adjusted based on the guidance strategy, and data where the feedback result is invalid; The design module uploads the design object information and obtains the corresponding full-process data in the local knowledge base to formulate the basic parameters of the design process, and connects with the intelligent processing module to obtain the design assistance strategy to assist in the comparison of the design process to prompt the key features in each link, wherein the basic parameters are used to provide an overall guiding idea including parameter size, parameter relationship, test items, and link requirement feedback.

2. The whole-process intelligent processing system for R&D experiments based on the Internet of Things according to claim 1 is characterized in that: The steps include quality inspection, in which: Obtaining the collected quality inspection data and uploading it to the Internet of Things platform; The local knowledge base retrieves a locally stored quality inspection list based on the quality inspection object in the quality inspection data; Filling the quality inspection data into the corresponding quality inspection checklist and then sending it to the intelligent processing module, and the intelligent processing module verifies each quality inspection data based on the specification requirements in the quality inspection checklist; A risk item is generated based on the verification result, wherein the verification result at least includes deviation and data missing.

3. The whole-process intelligent processing system for R&D experiments based on the Internet of Things according to claim 2 is characterized in that: The intelligent processing module is further configured to retrieve corresponding processing opinions and cause analysis from the local knowledge base based on the content, quantity and combination correlation coefficient of the risk items; The handling opinions include measures, priorities, responsible parties and completion deadlines; The cause analysis includes abnormal events and corresponding compliance probabilities, which are obtained based on the following steps: Selecting a corresponding numbered reason list in the local knowledge base based on the verification result; generating a basic probability of each abnormal event in the cause list based on the content of the risk item; A combined risk set is generated based on the number and content of the risk items, a combined correlation coefficient is calculated based on the combined risk set in combination with an empirical algorithm, and the basic probability is adjusted based on the combined correlation coefficient to obtain the compliance probability.

4. The intelligent processing system for the entire process of R&D experiments based on the Internet of Things according to claim 3 is characterized in that: The steps include an assembly step, in which: The intelligent processing module obtains assembly data in the Internet of Things platform and obtains a matching rule document matching the assembly object in the local knowledge base; The intelligent processing module arranges and combines the plurality of assembly objects that have an assembly relationship, and calculates assembly parameters corresponding to each combination based on the matching rule document; Based on the matching rule document, assembly standards are extracted, and each assembly parameter is classified according to the assembly standard to issue evaluation indicators of corresponding levels, and each combination is allocated to a corresponding application environment according to each evaluation indicator.

5. The whole-process intelligent processing system for R&D experiments based on the Internet of Things according to claim 4 is characterized in that: The steps include a testing step, in which: The intelligent processing module obtains test data in the Internet of Things platform and obtains test items matching the test object in the local knowledge base; The test items are issued for testing, and a change curve of each test data under different test items is obtained in real time; The test data with abnormal change curves are packaged with the test items to obtain key test items.

6. The intelligent processing system for the entire process of R&D experiments based on the Internet of Things according to claim 5 is characterized in that: The intelligent processing module is further configured to: The risk items, the handling opinions and the cause analysis are used as the first guidance strategy, and are distributed to the responsible parties in the corresponding quality inspection links based on priority for process guidance; The evaluation index is used as a second guidance strategy and is sent to the assembly link in the corresponding application environment for assembly guidance; Each of the test key items is used as a third guidance strategy and is sent to the corresponding test object in the test link for test guidance.

7. The whole process intelligent processing system of R&D experiment based on Internet of Things according to claim 5 is characterized by: The intelligent processing module is further configured to respectively obtain feedback results from the quality inspection link, the assembly link, and the testing link, and determine whether the guidance strategy corresponding to each link is effective based on the feedback results; If valid, the intelligent processing module sends the adjusted optimization data to the local knowledge base for storage and adds a project case number; If invalid, the intelligent processing module marks the local data in the local knowledge base and reselects the local data to generate a new guidance strategy until the feedback result is valid; When the project case number corresponds to the entire process, the local knowledge base will use all data in the same project case number as the entire process data.

8. The intelligent processing system for the entire process of R&D experiments based on the Internet of Things according to claim 1 is characterized in that: The intelligent processing module uses the key design anomaly as a key feature and selects corresponding quality inspection data and / or assembly data and / or test data as key data; Obtaining a preset bias in the local knowledge base based on the key feature; Calculating an influence parameter matrix corresponding to each of the key features based on the key data and the preset bias, wherein the influence parameter matrix includes a number of influence parameters for characterizing the influence of the key data corresponding to each of the key features on the target result in the design process; The design assistance strategy is generated based on the influencing parameters.

9. An intelligent processing method for the entire process of R&D experiments based on the Internet of Things, characterized by: The system according to any one of claims 1 to 8 is implemented, comprising the following steps: Collect raw data from each link; Classifying the raw data and storing them in data sets corresponding to different links; Obtaining the original data in each of the data sets and retrieving associated local data; Used to compare and analyze the original data with the associated local data. At the same time, based on different links, the objects, methods, and requirements of the comparison and analysis are all different. Based on different comparison results, corresponding guidance strategies are generated and issued to each link corresponding to the original data for process guidance, and feedback results generated after adjustment based on the guidance strategies in each link are obtained; Based on the feedback results, the adjusted data is used as full-process data, and a design assistance strategy including several key design exception items is generated according to the feedback results, wherein the key design exception items include data where the feedback results are valid and adjusted based on the guidance strategy, and data corresponding to the feedback results being invalid; Upload the design object information, and obtain the corresponding full-process data in the local knowledge base to formulate the basic parameters of the design process, and connect to the intelligent processing module to obtain the design assistance strategy to assist in comparing the design process to prompt the key features in each link, wherein the basic parameters are used to provide an overall guiding idea including parameter size, parameter relationship, test items, and link requirement feedback.

Images