Remote monitoring method and system for automobile polishing and waxing machine production line based on Internet of Things
Through IoT technology, remote monitoring of the automotive polishing and waxing machine production line, analyzing process flow and component data, formulating and implementing production adjustment strategies, solving the problems of low accuracy and low efficiency of traditional manual monitoring, and improving production efficiency and product quality .
Patent Information
- Application Number
- CN202411374110.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-12-31
AI Technical Summary
The traditional automotive polishing and waxing machine production line monitoring method relies on manual inspection, resulting in low monitoring accuracy and low efficiency, making it difficult to discover and solve problems in the production process in a timely manner, affecting production efficiency and product quality.
Using the remote monitoring method based on the Internet of Things, the process flow data of the production line is obtained and analyzed, the component clustering analysis is performed, the global mechanical structure data is generated, simulation analysis and operation prediction is carried out, production adjustment strategies are formulated, and adjustments are performed through remote terminals. instruction.
Intelligent control and optimization of the production line is realized, production efficiency and product quality are improved, and the problems of low monitoring accuracy and low efficiency are solved.
Smart Images
Figure CN119225249A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent control technology, and in particular to a remote monitoring method and system for a production line of an automobile polishing and waxing machine based on the Internet of Things. Background Art
[0002] With the rapid development of the automobile manufacturing industry, automobile polishing and waxing machines are important equipment on automobile production lines. Their performance and production efficiency directly affect the appearance quality and production efficiency of the whole vehicle. However, with the continuous expansion of the automobile market and the diversification of consumer demand, the production line of automobile polishing and waxing machines is also facing more and more complex process flows and higher production efficiency requirements.
[0003] Traditional monitoring methods for automobile polishing and waxing machine production lines often rely on manual inspections and on-site operations, which have problems such as low efficiency and low monitoring accuracy. In addition, due to the large number of equipment and complex process flows on the production line, manual monitoring is difficult to achieve comprehensive coverage and real-time response, which often makes it difficult to discover and solve problems in the production process in a timely manner, thus affecting production efficiency and product quality. Summary of the invention
[0004] The present application provides a remote monitoring method and system for a production line of automobile polishing and waxing machines based on the Internet of Things, which is used to solve the technical problems of low monitoring accuracy and low efficiency in production line monitoring in the prior art.
[0005] In view of the above problems, the present application provides a remote monitoring method and system for a car polishing and waxing machine production line based on the Internet of Things.
[0006] The first aspect of the present application provides a remote monitoring method for a car polishing and waxing machine production line based on the Internet of Things, the method comprising:
[0007] Acquire a plurality of parts, wherein the plurality of parts are all parts of a target polishing and waxing machine; perform cluster analysis on the plurality of parts based on a plurality of process flows of a production line extracted from IoT data to generate a plurality of part categories, wherein the plurality of part categories correspond to the plurality of parts; sequentially combine the plurality of parts according to the plurality of part categories to generate global mechanical structure data of the target polishing and waxing machine, wherein the global mechanical structure data includes a plurality of local mechanical structure data; perform simulation analysis based on the plurality of local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; perform operation quality inspection based on the operation prediction data set, and formulate a production adjustment strategy based on the quality inspection results; connect to a remote terminal, transmit the real-time production data set of the production line to the remote terminal, and execute the production adjustment strategy according to an execution instruction output by the remote terminal.
[0008] The second aspect of the present application provides a remote monitoring system for a car polishing and waxing machine production line based on the Internet of Things, the system comprising:
[0009] A parts acquisition module, wherein the parts acquisition module acquires a plurality of parts, wherein the plurality of parts are all parts of a target polishing and waxing machine; a parts category generation module, wherein the parts category generation module extracts a plurality of process flows of a production line based on IoT data and performs cluster analysis on the plurality of parts to generate a plurality of parts categories, wherein the plurality of parts categories correspond to the plurality of parts; a global mechanical structure data generation module, wherein the global mechanical structure data generation module sequentially combines the plurality of parts according to the plurality of parts categories to generate global mechanical structure data of a target polishing and waxing machine, wherein the global mechanical structure data includes a plurality of local mechanical structure data; an operation prediction data set generation module, wherein the operation prediction data set generation module performs simulation analysis based on the plurality of local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; a production adjustment strategy formulation module, wherein the production adjustment strategy formulation module performs operation quality inspection based on the operation prediction data set and formulates a production adjustment strategy based on the quality inspection results; a production adjustment strategy execution module, wherein the production adjustment strategy execution module is connected to a remote terminal, transmits a real-time production data set of a production line to the remote terminal, and executes the production adjustment strategy according to an execution instruction output by the remote terminal.
[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0011] The present application obtains multiple parts, which are all parts of the target polishing and waxing machine; extracts multiple process flows of the production line based on the Internet of Things data, performs cluster analysis on the multiple parts, generates multiple part categories, and there is a corresponding relationship between the multiple part categories and the multiple parts; combines the multiple parts in sequence according to the multiple part categories to generate the global mechanical structure data of the target polishing and waxing machine, and the global mechanical structure data includes multiple local mechanical structure data; performs simulation analysis based on the multiple local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; performs operation quality inspection based on the operation prediction data set, and formulates a production adjustment strategy based on the quality inspection results; connects to a remote terminal, transmits the real-time production data set of the production line to the remote terminal, and executes the production adjustment strategy according to the remote terminal output execution instruction. The present invention solves the technical problems of low monitoring accuracy and low efficiency in the existing technology for production line monitoring, and realizes intelligent control and optimization of the production line by real-time monitoring and analysis of the operation status and process parameters of the production line, thereby achieving the technical effect of improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0013] Figure 1 A schematic diagram of a remote monitoring method for a car polishing and waxing machine production line based on the Internet of Things provided in an embodiment of the present application;
[0014] Figure 2 A schematic diagram of the structure of a remote monitoring system for a car polishing and waxing machine production line based on the Internet of Things provided in an embodiment of the present application.
[0015] Explanation of the reference numerals: parts acquisition module 11, parts category generation module 12, global mechanical structure data generation module 13, operation prediction data set generation module 14, production adjustment strategy formulation module 15, production adjustment strategy execution module 16. DETAILED DESCRIPTION
[0016] This application provides a remote monitoring method and system for a car polishing and waxing machine production line based on the Internet of Things, aiming to solve the technical problems of low monitoring accuracy and low efficiency in the existing production line monitoring technology. By real-time monitoring and analysis of the operating status and process parameters of the production line, intelligent control and optimization of the production line can be achieved, thereby achieving the technical effect of improving production efficiency and product quality.
[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0018] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.
[0019] Embodiment 1
[0020] like Figure 1 As shown, the present application provides a remote monitoring method for a car polishing and waxing machine production line based on the Internet of Things, the method comprising:
[0021] Step S100: Acquire multiple parts, where the multiple parts are all parts of the target polishing and waxing machine;
[0022] In the embodiment of the present application, all parts are prepared in advance before production begins. These parts include various mechanical parts, electronic components, fasteners, etc., and the parts are all parts of the target polishing and waxing machine.
[0023] The parts are transferred to the production line through an automated logistics system, such as using conveyor belts or other material handling equipment.
[0024] Step S200: performing cluster analysis on the multiple parts based on the multiple process flows of the production line extracted from the IoT data to generate multiple part categories, wherein the multiple part categories correspond to the multiple parts;
[0025] In the embodiment of the present application, the Internet of Things technology is used to collect data from various process flows on the production line. These data include the processing time, temperature, pressure, equipment information used, production batch, etc. of the parts. The collected raw data is cleaned and formatted to remove outliers and noise to ensure the accuracy and consistency of the data. Then, features related to the process flow of parts are extracted, such as processing time, equipment type, processing sequence, etc. A suitable clustering algorithm is selected, such as partitioning method, hierarchical method, density-based method, etc., and clustering is performed according to the similarity of parts in the process flow.
[0026] In the clustering process, the performance of parts in each process flow, such as processing difficulty, time consumption, required resources, etc., is used as the basis for clustering. Through cluster analysis, parts with similar process flows are grouped into one category to form multiple part categories. Each part corresponds to a unique part category.
[0027] Step S300: combining the multiple parts in sequence according to the multiple part categories to generate global mechanical structure data of the target polishing and waxing machine, wherein the global mechanical structure data includes multiple local mechanical structure data;
[0028] In the embodiment of the present application, a combination strategy is formulated according to the category of parts. For example, parts of the same category are combined according to their designed functions and positions to form a local mechanical structure.
[0029] Local mechanical structure data generation: For each part category, the parts are virtually assembled through CAD according to the predetermined combination strategy to form a local mechanical structure. The data of each local mechanical structure is recorded, including the position, connection method, relative relationship, etc. of the parts. These data constitute the local mechanical structure data.
[0030] After all local mechanical structure data are generated, they are integrated together to form the global mechanical structure data of the target polishing and waxing machine.
[0031] Step S400: performing simulation analysis based on the plurality of local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set;
[0032] In the embodiment of the present application, the model is subjected to mechanical, thermal and other simulation analysis to simulate the operating state of the polishing and waxing machine in actual work. The performance under different working conditions is analyzed, such as the operation under different loads, speeds and working environments. All data generated during the simulation analysis are recorded, including stress distribution, temperature changes, vibration conditions, etc.
[0033] Based on the results of the simulation analysis, key performance indicators are extracted, such as work efficiency, energy consumption, failure rate, etc. These indicators are associated with different working conditions and time nodes to form a prediction data set containing multiple possible operating conditions. The prediction data set contains the operation prediction under normal conditions, as well as the prediction of possible abnormal conditions or failure modes.
[0034] Step S500: performing operation quality inspection based on the operation prediction data set, and formulating a production adjustment strategy according to the quality inspection result;
[0035] In the embodiment of the present application, the real-time operation data is compared with the operation prediction data set to check whether there are data points that significantly deviate from the prediction range. These data points indicate that there are problems or anomalies in the actual operation process. Abnormal data is identified using statistical methods or other anomaly detection techniques. Abnormal data includes excessively high temperatures, abnormal vibration frequencies, and energy consumption that exceeds expectations.
[0036] Once abnormal data is detected, the source and pattern of the abnormal data are analyzed to determine which local mechanical structure has a problem.
[0037] According to the specific situation and source of the abnormality, formulate targeted adjustment plans for each local mechanical structure where the abnormality occurs.
[0038] Step S600: connecting to a remote terminal, transmitting the real-time production data set of the production line to the remote terminal, and executing the production adjustment strategy according to the execution instruction output by the remote terminal.
[0039] In an embodiment of the present application, a secure remote connection protocol, such as SSH, VPN or dedicated remote desktop software, is used to connect the production line remote monitoring system and the remote terminal.
[0040] Collect production data in real time from sensors and other data sources on the production line. These data include equipment status, production speed, product quality indicators, etc.
[0041] Format the collected raw data into a format suitable for transmission, such as JSON, XML, or a custom binary format. Transmit the formatted real-time production data set to the remote terminal via WebSocket, MQTT, or other real-time data streaming protocols.
[0042] Issue execution instructions on the remote terminal. These instructions are transmitted back to the production line monitoring system through the previously established remote connection. The production line monitoring system will execute the corresponding production adjustment strategy. This includes adjusting equipment parameters, changing production processes, or triggering specific maintenance procedures.
[0043] Furthermore, step S200 in the method provided in the application embodiment also includes:
[0044] Retrieving historical production process logs through the IoT data to divide the process flow of the production line according to process steps, and generating the multiple process flows;
[0045] Dividing the plurality of components into k component groups in advance according to the plurality of process flows;
[0046] Randomly select k parts as k initial cluster centers;
[0047] Taking the k initial cluster centers as origins, calculating the distances between the components in the k component groups and the k initial cluster centers to obtain a minimum value, and obtaining a first minimum distance value;
[0048] Extracting components in the k component groups as k first cluster centers according to the first minimum distance value, taking the k first cluster centers as origins, calculating the minimum distance between the components in the k component groups and the k first cluster centers, and obtaining a second minimum distance value;
[0049] Extracting components in the k component groups as k second cluster centers according to the second minimum distance value, iterating until each component in the plurality of components has a corresponding cluster center, and obtaining a cluster analysis result;
[0050] The multiple components are matched with identifiers according to the cluster analysis results, and the matching results are added to the multiple component categories.
[0051] In the embodiment of the present application, the historical production process log is first collected through the Internet of Things. The historical production process log contains detailed information of each process step on the production line. According to the characteristics and sequence of the process steps, the entire production process is divided into several independent process flows. The process flow includes welding, painting, assembly, etc.
[0052] According to the divided process flow, the parts are divided into k groups. Each group of parts is associated with a specific process flow.
[0053] A component is randomly selected from each component group as the initial cluster center of the group, and k initial cluster centers are obtained.
[0054] Taking k initial cluster centers as the origin, calculate the distance between the parts in each part group and these cluster centers through Euclidean distance, Manhattan distance, etc. Find the minimum distance from each part to the initial cluster center in its group, that is, the first minimum distance value.
[0055] According to the first minimum distance value, the components closest to the initial cluster center are extracted from each component group, and these components constitute k first cluster centers.
[0056] With the first cluster center as the new origin, repeat the above distance calculation and minimum distance determination steps to obtain the second cluster center, and so on for iteration.
[0057] The iterative process terminates when each component has a corresponding cluster center and the cluster center no longer changes significantly in consecutive iterations.
[0058] The final cluster center obtained through the iterative process represents the center position of each component group, and each component is assigned to the nearest cluster center.
[0059] Based on the clustering results, match each component with the cluster center, i.e., the identifier, to which it belongs. First, assign a unique identifier to each cluster center. This identifier represents the component category to which the cluster center corresponds. When assigning identifiers, ensure that each component category has a unique identifier. Based on the results of the cluster analysis, each component is assigned to a specific cluster center. Match the component with the identifier of the cluster center to which it belongs.
[0060] Through the above steps, each component is associated with the component category identifier to which it belongs, and a corresponding relationship between the component and the component category is established.
[0061] Furthermore, the plurality of components are divided into k component groups in advance according to the plurality of process flows, and the method further comprises:
[0062] Defining the combination relationship of the plurality of parts based on the plurality of process flows of the target polishing and waxing machine;
[0063] Formulate grouping constraints for the plurality of components based on the combination relationship;
[0064] The multiple components are divided into k component groups according to the grouping constraint conditions and the combination relationship.
[0065] In the embodiment of the present application, the assembly drawings and operation manual of the polishing and waxing machine are first analyzed to determine the role and position of each component in the assembly process. The function of each component and its role in the polishing and waxing process are determined by analysis, and which components are functionally related to each other are identified. After that, components that achieve the same or similar functions are classified into one category, such as motors and transmission components, polishing wheels and fixtures, etc. At the same time, components that need to be installed or debugged at the same time during the assembly process are identified and combined together.
[0066] When formulating grouping constraints, ensure that the components in the same group match each other in function and can work together. The components in the same group are completed in the same assembly step. Based on the constraints and combination relationships, the components are divided into k groups.
[0067] Furthermore, step S300 in the method provided in the application embodiment also includes:
[0068] Integrate data of the plurality of components based on the plurality of part categories to obtain a component assembly plan;
[0069] Extracting functional requirement data of a target polishing and waxing machine, performing combination weight configuration on the plurality of components according to the component assembly plan, and generating combination weight allocation information;
[0070] A component combination plan is formulated based on the combination weight allocation information.
[0071] In an embodiment of the present application, data of multiple components are integrated according to the determined multiple part categories, the components are classified and stored according to their categories, and detailed parameters of each component, such as size, weight, functional characteristics, etc., are recorded.
[0072] Based on product design and engineering knowledge, assembly rules are formulated, and genetic algorithms are used to generate component assembly plans based on the physical relationships between parts, assembly sequences, and constraints.
[0073] Determine the functional requirements of the polishing and waxing machine through engineers. Determine the core functions of the polishing and waxing machine based on the functional requirements, such as polishing, waxing, vacuuming, etc. Further subdivide each core function into more specific sub-functions, such as the polishing function is divided into rough polishing and fine polishing, etc. List all the parts of the polishing and waxing machine, including motors, polishing heads, wax storage systems, etc. Map each sub-function to a specific component and clarify the role of the component in achieving the function.
[0074] After completing the function mapping, the functional requirements, parts and other elements of the polishing and waxing machine are organized in a hierarchical structure through the hierarchical analysis method. For each layer of elements, a judgment matrix is constructed, and their relative importance is determined by pairwise comparison. Finally, the eigenvector of the judgment matrix is calculated using mathematical methods to obtain the weight value of each element and generate the combined weight distribution information.
[0075] Finally, sort and classify the parts according to the weight distribution results. High-weight parts, such as key driving parts or core functional parts, are placed at the core of the combination scheme. Next, determine the combination method between the parts based on the functional associations and assembly relationships between them. For example, for parts that require close fit, use precise axial assembly methods or reference assembly methods to ensure their assembly accuracy and stability. For parts that require a certain range of motion, use the constraint assembly method to limit their position and movement by adding appropriate constraints to meet design requirements. After determining the combination method of the parts, start with the main structure or main parts, and then gradually add other parts.
[0076] Through the above process, the parts combination plan is completed.
[0077] Furthermore, the method further comprises:
[0078] Performing feature analysis on the multiple components to generate a component feature set;
[0079] Execute the component combination scheme to construct combination constraints according to the feature sets of the multiple components;
[0080] Acquire a mechanical structure construction rule according to the design structure of the target polishing and waxing machine, perform combination based on the combination constraint according to the mechanical structure construction rule, and acquire a plurality of local combination information, wherein the plurality of local combination information includes a plurality of local mechanical structure data;
[0081] The plurality of local mechanical structure data are assembled and connected according to the plurality of process flows to generate the global mechanical structure data.
[0082] In the embodiment of the present application, when performing feature analysis on multiple parts, functional feature analysis is first performed to analyze the movement mode and role of the parts in the mechanical system, such as rotation, sliding, transmitting force or torque, etc. Determine the role of the parts in the overall machinery, such as support, connection, transmission, positioning, etc. Then perform structural feature analysis to determine the external shape and internal structure of the parts, such as cylindrical, cubic, conical, etc. Identify and mark the connection points, interfaces or mating surfaces on the parts, such as threaded holes, keyways, etc. Use professional CAD software or 3D scanning technology to assist in identifying specific features on the parts, such as holes, slots, bosses, etc. For each identified feature, record detailed information such as its position, size and shape. Finally, analyze the matching relationship between these features to determine which features are used to cooperate with each other, such as the cooperation between pins and holes, the cooperation between keys and keyways, etc. The identified functional features and structural features are classified and sorted to form a component feature set.
[0083] Based on the feature set of the parts, determine which features need to cooperate with each other, such as the matching of holes and shafts, the correspondence of keys and keyways, etc. Construct geometric constraints to ensure that the spatial position and shape of the parts can be accurately matched when combined. Construct motion constraints to ensure that the relative motion relationship and dynamic behavior of the parts after assembly meet the design requirements. Formalize these constraints and establish a constraint model.
[0084] According to the design requirements of the target polishing and waxing machine, the relevant mechanical structure design rules are obtained. These rules include the layout of components, connection methods, strength requirements, etc. On the basis of following the design structure rules, the established combination constraint model is used to determine which parts can be combined together to form a local combination. According to these rules and constraints, the parts are partially combined to obtain multiple local combination information. This information contains the data of the local mechanical structure, such as the relative position and connection method between the components.
[0085] According to the manufacturing process of the polishing and waxing machine, determine the position and function of each local combination in the global mechanical structure. According to the order of the process flow, assemble and connect the data of each local mechanical structure. After the assembly of all local structures is completed, the global mechanical structure data of the complete target polishing and waxing machine will be formed.
[0086] Furthermore, step S400 in the method provided in the application embodiment also includes:
[0087] Set boundary conditions and operating loads according to the real-time operating data of the target polishing and waxing machine;
[0088] Establishing a virtual operation model according to the boundary conditions and the operation load;
[0089] Synchronizing the plurality of local mechanical structure data to the virtual operation model for dynamic simulation to generate a plurality of simulation operation data;
[0090] The plurality of simulated operation data are analyzed to perform operation prediction and generate the operation prediction data set.
[0091] In the embodiment of the present application, the real-time operation data of the target polishing and waxing machine is pre-collected. The real-time operation data of the target polishing and waxing machine include the current, voltage, and rotation speed of the motor, the motion trajectory and speed of the waxing head, and the temperature and vibration of the whole machine. The real-time operation data of the target polishing and waxing machine are processed and analyzed to extract key operation parameters and features. These parameters and features are used for the setting of boundary conditions and operation loads. Boundary conditions refer to the physical limitations or constraints to which the polishing and waxing machine is subjected during operation. For example, the maximum range of motion of the waxing head, the maximum current limit of the motor, etc. The boundary conditions are set according to the real-time operation data and the design specifications of the polishing and waxing machine. The operation load refers to the various forces and torques that the polishing and waxing machine bears under normal working conditions. According to the real-time operation data, the average load, maximum load, and load variation law that the polishing and waxing machine bears under different working conditions are calculated.
[0092] Use professional mechanical system dynamics simulation software, such as ADAMS, MATLAB, etc. to build a virtual model based on the design parameters of the polishing and waxing machine and the set boundary conditions and operating loads.
[0093] Synchronize multiple local mechanical structure data of the polishing and waxing machine, such as the geometric dimensions and material properties of key components, into the virtual operation model. Perform dynamic simulation in the virtual operation model to simulate the operation status and performance of the polishing and waxing machine under different working conditions. During the simulation, the model performs real-time calculations and adjustments based on the set boundary conditions and operating loads. Through dynamic simulation, generate multiple simulated operation data. The simulated operation data includes the motion trajectory, speed, acceleration, force conditions, etc. of the polishing and waxing machine.
[0094] The simulation operation data is preprocessed, including data cleaning, feature extraction and standardization, to ensure the quality and consistency of the data. Next, the appropriate prediction algorithm is selected according to the characteristics of the data and the prediction target. These algorithms include time series analysis, regression analysis, and fault prediction and health management algorithms.
[0095] In terms of time series analysis, ARIMA, SARIMA and other models are used to capture the time dependency in the simulation data and predict the performance trend of the polishing and waxing machine over time. The relationship between input variables and output variables is determined through regression analysis, and then a prediction model is constructed. The input variables include workload, environmental conditions, etc., and the output variables include performance indicators, etc. For the prediction of potential failure points, algorithms and technologies in the field of PHM are used to monitor the operating status of the equipment and predict potential failures or performance degradation.
[0096] Through the above steps, a running prediction data set is generated.
[0097] Furthermore, the method further comprises:
[0098] Perform real-time data collection based on the multiple process flows to obtain a real-time production data set;
[0099] Synchronize the real-time production data set to the remote terminal, determine whether the production adjustment strategy matches the real-time production data, and if so, generate an execution instruction to execute the production adjustment strategy based on the production line;
[0100] If there is no match, the unmatched process nodes are obtained based on the production line traversal, traceability identification is performed based on the unmatched process nodes, and an alarm instruction is generated to correct the production adjustment strategy.
[0101] In the embodiment of the present application, various data on the production line, such as equipment status, process parameters, product quality, etc., are collected in real time through IoT devices and technologies, such as sensors and wireless communication technologies, and these data are transmitted to a remote terminal in real time. The real-time collected data is synchronized and integrated at the remote terminal to form a real-time production data set.
[0102] Use pattern recognition, statistical analysis and other technologies to match real-time production data sets and production adjustment strategies to determine whether the production adjustment strategies are suitable for the current production status.
[0103] When the matching judgment result shows that the production adjustment strategy matches the real-time production data, an execution instruction is automatically generated and sent to the production line to perform the corresponding adjustment operation.
[0104] When the production adjustment strategy does not match the real-time production data, starting from the starting point of the production line, each node in the entire production process is traversed step by step, and the equipment, process steps, etc. on the production line are comprehensively checked. During the traversal process, the real-time production data set is compared and analyzed with the preset standards or thresholds of each process node. The standards or thresholds are set based on historical data, expert experience or production needs. Through comparative analysis, process nodes that do not match the real-time production data or exceed the preset standards are identified. These nodes are the key points that cause the production adjustment strategy to fail. For the identified mismatched process nodes, traceability analysis is performed to determine the specific reasons for the mismatch. Traceability analysis includes inspections of upstream processes, equipment status, raw material quality, process parameters, and other aspects. In order to facilitate key monitoring and management, these mismatched process nodes are identified and special tags or status are set in the system.
[0105] After setting the identification, these mismatched process nodes are monitored in detail, and relevant data is collected and analyzed in real time to promptly discover and resolve potential problems.
[0106] Based on the results of the source tracing analysis, corresponding warning instructions are generated. These instructions will detail the cause of the mismatch, the scope of impact, and the recommended corrective measures.
[0107] After receiving the alarm instruction, the production adjustment strategy is automatically corrected. The correction includes adjusting parameter settings, replacing equipment, optimizing process flow and other aspects.
[0108] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:
[0109] The present application obtains multiple parts, which are all parts of the target polishing and waxing machine; extracts multiple process flows of the production line based on the Internet of Things data, performs cluster analysis on the multiple parts, generates multiple part categories, and there is a corresponding relationship between the multiple part categories and the multiple parts; combines the multiple parts in sequence according to the multiple part categories to generate the global mechanical structure data of the target polishing and waxing machine, and the global mechanical structure data includes multiple local mechanical structure data; performs simulation analysis based on the multiple local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; performs operation quality inspection based on the operation prediction data set, and formulates a production adjustment strategy based on the quality inspection results; connects to a remote terminal, transmits the real-time production data set of the production line to the remote terminal, and executes the production adjustment strategy according to the remote terminal output execution instruction. The present invention solves the technical problems of low monitoring accuracy and low efficiency in the existing technology for production line monitoring, and realizes intelligent control and optimization of the production line by real-time monitoring and analysis of the operation status and process parameters of the production line, thereby achieving the technical effect of improving production efficiency and product quality.
[0110] Embodiment 2
[0111] Based on the same inventive concept as the method for remote monitoring of a car polishing and waxing machine production line based on the Internet of Things in the aforementioned embodiment, Figure 2 As shown, the present application provides a remote monitoring system for a car polishing and waxing machine production line based on the Internet of Things. The system and method embodiments in the present application are based on the same inventive concept. The system includes:
[0112] A parts acquisition module 11, wherein the parts acquisition module 11 acquires a plurality of parts, wherein the plurality of parts are all parts of a target polishing and waxing machine;
[0113] A part category generating module 12, wherein the part category generating module 12 performs cluster analysis on the multiple parts based on the multiple process flows of the production line extracted from the IoT data to generate multiple part categories, wherein the multiple part categories correspond to the multiple parts;
[0114] A global mechanical structure data generating module 13, wherein the global mechanical structure data generating module 13 sequentially combines the multiple parts according to the multiple part categories to generate global mechanical structure data of the target polishing and waxing machine, wherein the global mechanical structure data includes multiple local mechanical structure data;
[0115] An operation prediction data set generation module 14, wherein the operation prediction data set generation module 14 performs simulation analysis based on the plurality of local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set;
[0116] A production adjustment strategy formulation module 15, wherein the production adjustment strategy formulation module 15 performs operation quality inspection based on the operation prediction data set and formulates a production adjustment strategy according to the quality inspection result;
[0117] The production adjustment strategy execution module 16 is connected to a remote terminal, transmits the real-time production data set of the production line to the remote terminal, and executes the production adjustment strategy according to the execution instruction output by the remote terminal.
[0118] Furthermore, the system is also used to implement the following functions:
[0119] Retrieving historical production process logs through the IoT data to divide the process flow of the production line according to process steps, and generating the multiple process flows;
[0120] Dividing the plurality of parts into k parts groups in advance according to the plurality of process flows;
[0121] Randomly select k parts as k initial cluster centers;
[0122] Taking the k initial cluster centers as origins, calculating the distances between the components in the k component groups and the k initial cluster centers to obtain a minimum value, and obtaining a first minimum distance value;
[0123] Extracting components in the k component groups as k first cluster centers according to the first minimum distance value, taking the k first cluster centers as origins, calculating the minimum distance between the components in the k component groups and the k first cluster centers, and obtaining a second minimum distance value;
[0124] Extracting components in the k component groups as k second cluster centers according to the second minimum distance value, iterating until each component in the plurality of components has a corresponding cluster center, and obtaining a cluster analysis result;
[0125] The multiple components are matched with identifiers according to the cluster analysis results, and the matching results are added to the multiple component categories.
[0126] Furthermore, the system is also used to implement the following functions:
[0127] Defining the combination relationship of the plurality of parts based on the plurality of process flows of the target polishing and waxing machine;
[0128] Formulate grouping constraints for the plurality of components based on the combination relationship;
[0129] The multiple components are divided into k component groups according to the grouping constraint conditions and the combination relationship.
[0130] Furthermore, the system is also used to implement the following functions:
[0131] Integrate data of the plurality of components based on the plurality of part categories to obtain a component assembly plan;
[0132] Extracting functional requirement data of a target polishing and waxing machine, performing combination weight configuration on the plurality of components according to the component assembly plan, and generating combination weight allocation information;
[0133] A component combination plan is formulated based on the combination weight allocation information.
[0134] Furthermore, the system is also used to implement the following functions:
[0135] Performing feature analysis on the multiple components to generate a component feature set;
[0136] Execute the component combination scheme to construct combination constraints according to the feature sets of the multiple components;
[0137] Acquire a mechanical structure construction rule according to the design structure of the target polishing and waxing machine, perform combination based on the combination constraint according to the mechanical structure construction rule, and acquire a plurality of local combination information, wherein the plurality of local combination information includes a plurality of local mechanical structure data;
[0138] The plurality of local mechanical structure data are assembled and connected according to the plurality of process flows to generate the global mechanical structure data.
[0139] Furthermore, the system is also used to implement the following functions:
[0140] Set boundary conditions and operating loads according to the real-time operating data of the target polishing and waxing machine;
[0141] Establishing a virtual operation model according to the boundary conditions and the operation load;
[0142] Synchronizing the plurality of local mechanical structure data to the virtual operation model for dynamic simulation to generate a plurality of simulation operation data;
[0143] The plurality of simulated operation data are analyzed to perform operation prediction and generate the operation prediction data set.
[0144] Furthermore, the system is also used to implement the following functions:
[0145] Perform real-time data collection based on the multiple process flows to obtain a real-time production data set;
[0146] Synchronize the real-time production data set to the remote terminal, determine whether the production adjustment strategy matches the real-time production data, and if so, generate an execution instruction to execute the production adjustment strategy based on the production line;
[0147] If there is no match, the unmatched process nodes are obtained based on the production line traversal, traceability identification is performed based on the unmatched process nodes, and an alarm instruction is generated to correct the production adjustment strategy.
[0148] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0149] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
[0150] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. A remote monitoring method for a car polishing and waxing machine production line based on the Internet of Things, characterized in that: The method comprises: Acquire a plurality of parts, wherein the plurality of parts are all parts of a target polishing and waxing machine; Extracting multiple process flows of the production line based on IoT data and performing cluster analysis on the multiple parts to generate multiple part categories, wherein the multiple part categories correspond to the multiple parts; Combining the multiple parts in sequence according to the multiple part categories to generate global mechanical structure data of the target polishing and waxing machine, wherein the global mechanical structure data includes multiple local mechanical structure data; Perform simulation analysis based on the multiple local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; Performing operation quality inspection based on the operation prediction data set, and formulating a production adjustment strategy according to the quality inspection results; Connect to a remote terminal, transmit the real-time production data set of the production line to the remote terminal, and execute the production adjustment strategy according to the execution instruction output by the remote terminal.
2. The method according to claim 1, characterized in that Based on the IoT data, multiple process flows of the production line are extracted to perform cluster analysis on the multiple parts to generate multiple part categories, and the method includes: Retrieving historical production process logs through the IoT data to divide the process flow of the production line according to process steps, and generating the multiple process flows; Dividing the plurality of components into k component groups in advance according to the plurality of process flows; Randomly select k parts as k initial cluster centers; Taking the k initial cluster centers as origins, calculating the distances between the components in the k component groups and the k initial cluster centers to obtain a minimum value, and obtaining a first minimum distance value; Extracting components in the k component groups as k first cluster centers according to the first minimum distance value, taking the k first cluster centers as origins, calculating the minimum distance between the components in the k component groups and the k first cluster centers, and obtaining a second minimum distance value; Extracting components in the k component groups as k second cluster centers according to the second minimum distance value, iterating until each component in the plurality of components has a corresponding cluster center, and obtaining a cluster analysis result; The multiple components are matched with identifiers according to the cluster analysis results, and the matching results are added to the multiple component categories.
3. The method according to claim 2, characterized in that Dividing the plurality of components into k component groups in advance according to the plurality of process flows, the method comprising: Defining the combination relationship of the plurality of parts based on the plurality of process flows of the target polishing and waxing machine; Formulate grouping constraints for the plurality of components based on the combination relationship; The multiple components are divided into k component groups according to the grouping constraint conditions and the combination relationship.
4. The method according to claim 1, characterized in that Combining the multiple parts in sequence according to the multiple part categories to generate global mechanical structure data of the target polishing and waxing machine, the method includes: Integrate data of the plurality of components based on the plurality of part categories to obtain a component assembly plan; Extracting functional requirement data of a target polishing and waxing machine, performing combination weight configuration on the plurality of components according to the component assembly plan, and generating combination weight allocation information; A component combination plan is formulated based on the combination weight allocation information.
5. The method according to claim 3, characterized in that include: Performing feature analysis on the multiple components to generate a component feature set; Execute the component combination scheme to construct combination constraints according to the feature sets of the multiple components; Acquire a mechanical structure construction rule according to the design structure of the target polishing and waxing machine, perform combination based on the combination constraint according to the mechanical structure construction rule, and acquire a plurality of local combination information, wherein the plurality of local combination information includes a plurality of local mechanical structure data; The plurality of local mechanical structure data are assembled and connected according to the plurality of process flows to generate the global mechanical structure data.
6. The method according to claim 1, characterized in that Performing simulation analysis based on the multiple local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set, the method comprising: Set boundary conditions and operating loads according to the real-time operating data of the target polishing and waxing machine; Establishing a virtual operation model according to the boundary conditions and the operation load; Synchronizing the plurality of local mechanical structure data to the virtual operation model for dynamic simulation to generate a plurality of simulation operation data; The plurality of simulated operation data are analyzed to perform operation prediction and generate the operation prediction data set.
7. The method according to claim 1, characterized in that Methods include: Perform real-time data collection based on the multiple process flows to obtain a real-time production data set; Synchronize the real-time production data set to the remote terminal, determine whether the production adjustment strategy matches the real-time production data, and if so, generate an execution instruction to execute the production adjustment strategy based on the production line; If there is no match, the unmatched process nodes are obtained based on the production line traversal, traceability identification is performed based on the unmatched process nodes, and an alarm instruction is generated to correct the production adjustment strategy.
8. The remote monitoring system of automobile polishing and waxing machine production line based on Internet of Things is characterized by: The system comprises: A parts acquisition module, wherein the parts acquisition module acquires a plurality of parts, wherein the plurality of parts are all parts of a target polishing and waxing machine; A parts category generation module, wherein the parts category generation module performs cluster analysis on the multiple parts based on the multiple process flows of the production line extracted from the IoT data to generate multiple parts categories, wherein the multiple parts categories correspond to the multiple parts; A global mechanical structure data generating module, wherein the global mechanical structure data generating module sequentially combines the multiple parts according to the multiple part categories to generate global mechanical structure data of the target polishing and waxing machine, wherein the global mechanical structure data includes multiple local mechanical structure data; An operation prediction data set generation module, wherein the operation prediction data set generation module performs simulation analysis based on the plurality of local mechanical structure data of the target polishing and waxing machine to generate an operation prediction data set; A production adjustment strategy formulation module, wherein the production adjustment strategy formulation module performs operation quality inspection based on the operation prediction data set and formulates a production adjustment strategy according to the quality inspection result; A production adjustment strategy execution module is connected to a remote terminal, transmits a real-time production data set of the production line to the remote terminal, and executes the production adjustment strategy according to an execution instruction output by the remote terminal.