Hardware production line monitoring management method and system based on Internet of Things

By deploying IoT devices on hardware production lines, real-time monitoring and analysis of production data, generating control instructions, predicting and classifying faults, the problem that traditional hardware production line management cannot be coordinated is solved, and efficient, safe and intelligent production management is achieved. Improved overall production efficiency and product quality.

CN118938836APending Publication Date: 2024-11-12DONGGUAN HONGQIAO HARDWARE CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411138227.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Traditional hardware production line monitoring and management cannot achieve effective collaborative management, resulting in the inability to produce normally in other links when the production process is abnormal, and there is a lack of effective solutions.

Method used

Deploy IoT devices on hardware production lines, including sensors, cameras and wireless radio frequency identification electronic tags, monitor and analyze production data in real time through the IoT platform, generate control instructions, predict and classify faults, and realize equipment operation status and production process parameters. Real-time monitoring and early warning.

Benefits of technology

It improves production efficiency, reduces equipment failure rate, optimizes resource allocation, improves product quality, reduces production costs, and enhances security management and remote monitoring capabilities, promoting the digital and intelligent transformation of the industry.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938836A_ABST
    Figure CN118938836A_ABST
Patent Text Reader

Abstract

The invention discloses a hardware production line monitoring management method and system based on the Internet of Things, and relates to the technical field of hardware production management, and the method comprises the steps: deploying Internet of Things equipment at each node on a hardware production line; each node of the hardware production line comprises a metal material machining node, a metal material cutting node, a metal material forming node and a metal material welding node. Monitoring hardware production data through the Internet of Things equipment, and transmitting the hardware production data to the hardware management Internet of Things platform through a communication protocol; monitoring and analyzing the received hardware production data on the hardware management Internet of Things platform, and obtaining equipment operation conditions and production process parameters; the production condition of the hardware is displayed on the management terminal through a network; and an alarm is given for abnormal conditions on the hardware production line. According to the hardware production system, integration and collaboration of the hardware production system are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of hardware production management, and more specifically, to a hardware production line monitoring and management method and system based on the Internet of Things. Background Art

[0002] Traditional hardware generally refers to gold, silver, copper, iron, and tin. In today's mechanical manufacturing, hardware also refers to metals in general. Hardware processing is the process of processing metal materials into various hardware parts, such as screws, plates, shafts, etc., using lathes, milling machines, drilling machines, grinders and other equipment according to design drawings or samples.

[0003] At present, the monitoring and management of hardware production lines still use preset control rules for management, which cannot be effectively coordinated. Therefore, when an abnormality occurs in one link of the production process, other links will not be able to produce normally.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a hardware production line monitoring and management method and system based on the Internet of Things to solve the above-mentioned technical problems.

[0006] The present application provides a monitoring and management method for a hardware production line based on the Internet of Things, comprising: deploying an Internet of Things device at each node on the hardware production line; wherein each node of the hardware production line comprises a metal material processing node, a metal material cutting node, a metal material forming node, and a metal material welding node;

[0007] Wherein, the IoT device is compatible with the hardware management IoT platform, and the IoT device includes a sensor, a camera, and a wireless radio frequency identification electronic tag;

[0008] Monitor the hardware production data through the IoT device, and transmit the hardware production data to the hardware management IoT platform through the communication protocol;

[0009] On the hardware management IoT platform, the received hardware production data is monitored and analyzed to obtain the equipment operation status and production process parameters; and the production status of the hardware is displayed on the management terminal through the network;

[0010] An alarm is issued for abnormal situations occurring on the hardware production line, and the alarm information is displayed on the main interface of the hardware management Internet of Things platform.

[0011] Before monitoring and analyzing the received hardware production data on the hardware management IoT platform to obtain equipment operation status and production process parameters, the method further includes:

[0012] On the hardware management IoT platform, the historical hardware production data monitored by the IoT device is converted into standardized digital information, and the standardized digital information is transmitted to the control terminal;

[0013] The control terminal generates hardware standard production reference information based on the standardized digital information and hardware production process standard information;

[0014] The hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management Internet of Things platform; wherein the control instructions are used to indicate the operating standards in the hardware production process.

[0015] Furthermore, on the hardware management IoT platform, after monitoring and analyzing the received hardware production data and obtaining the equipment operation status and production process parameters, the method further includes:

[0016] According to the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node, combined with the identified control instructions, the operation status of the hardware production equipment at each node on the hardware production line is analyzed to obtain preliminary analysis results;

[0017] Classifying the preliminary analysis result based on the identified control instruction to obtain a fault classification result;

[0018] When the fault classification result indicates that a first fault occurs in a first production equipment among the hardware production equipment at each node on the hardware production line, other hardware production equipment associated with the first fault is predicted.

[0019] Further, the preliminary analysis result includes fault characteristic data, and the operation status of the hardware production equipment at each node on the hardware production line is analyzed based on the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node, combined with the identified control instruction, to obtain a preliminary analysis result; the preliminary analysis result is classified based on the identified control instruction to obtain a fault classification result, including:

[0020] Extracting the fault characteristic data from the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node;

[0021] Determining a weight coefficient of each data item in the fault characteristic data according to the identified control instruction;

[0022] Constructing a fault classification network according to each data item corresponding to a different weight coefficient in the fault feature data;

[0023] Establishing a first adjacency matrix and a second adjacency matrix according to the constructed fault classification network;

[0024] Normalizing the first adjacency matrix and the second adjacency matrix to obtain a third adjacency matrix and a fourth adjacency matrix;

[0025] Based on the identified control instruction, a fault classification matrix is ​​output based on the third adjacency matrix and the fourth adjacency matrix; wherein the fault classification matrix is ​​used to indicate a fault classification result.

[0026] Further, the hardware production data includes data generated by hardware production equipment at each node on the hardware production line; when the fault classification result indicates that a first production equipment among the hardware production equipment at each node on the hardware production line has a first fault, after predicting other hardware production equipment associated with the first fault, the method further includes:

[0027] Based on the data generated by the first production equipment where the first fault occurs and the data generated by other hardware production equipment predicted to be associated with the first fault, future failure conditions of the hardware production equipment at each node on the hardware production line are predicted.

[0028] Further, predicting future failure conditions of hardware production equipment at each node on the hardware production line based on the data generated by the first production equipment where the first failure occurs and the data generated by other production equipment predicted to be associated with the first failure includes:

[0029] Based on the data generated by the first production equipment where the first fault occurs and the data generated by other hardware production equipment predicted to be associated with the first fault, assembling a fault vector sequence for each data and each time point in a preset time period;

[0030] Based on the fault vector sequence, a correlation graph of data generated by hardware production equipment and fault events is constructed; wherein the nodes in the correlation graph include the hardware production data feature nodes and the fault event feature nodes, and the edges between the hardware production data feature nodes and the fault event feature nodes represent that there is a correlation relationship between the hardware production data feature nodes and the fault event feature nodes;

[0031] The nodes in the fault event characteristic nodes are respectively used as current fault nodes, and the following steps are performed: determining a set of associated nodes having an associated relationship with the current fault node; calculating an associated vector representation matrix of the current fault node based on the associated node set;

[0032] updating the association graph according to the association vector representation matrix;

[0033] Based on the updated association graph, future failure conditions of the hardware production equipment at each node on the hardware production line are predicted.

[0034] Furthermore, the data generated by the hardware production equipment include feeding data of the vibration feeding device, handling data of the robot, coating data of the coating device, polishing data of the polishing device, spraying data of the coolant spraying device, cleaning data of the high-pressure airflow cleaning device and separation data of the waste separation device.

[0035] The present application provides a hardware production line monitoring and management system based on the Internet of Things, including an Internet of Things device deployment unit, a hardware production data transmission unit, a hardware production data monitoring and analysis unit, and a hardware production abnormality alarm unit; wherein,

[0036] The IoT device deployment unit is used to deploy IoT devices at various nodes on the hardware production line; wherein the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes; wherein the IoT devices are compatible with the hardware management IoT platform, and the IoT devices include sensors, cameras and wireless radio frequency identification electronic tags;

[0037] The hardware production data transmission unit is used to monitor the hardware production data through the Internet of Things device and transmit the hardware production data to the hardware management Internet of Things platform through a communication protocol;

[0038] The hardware production data monitoring and analysis unit is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, obtain equipment operation status and production process parameters; and display the production status of hardware on the management terminal through the network;

[0039] The hardware production abnormality alarm unit is used to alarm for abnormal situations occurring on the hardware production line and display the alarm information on the main interface of the hardware management Internet of Things platform.

[0040] Furthermore, the IoT-based hardware production line monitoring and management system also includes: a control instruction parsing unit, which is used to monitor and analyze the received hardware production data on the hardware management IoT platform, and before obtaining the equipment operation status and production process parameters, on the hardware management IoT platform, convert the historical hardware production data monitored by the IoT device into standardized digital information, and transmit the standardized digital information to the control terminal; the control terminal generates hardware standard production reference information based on the standardized digital information and hardware production process standard information; the hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management IoT platform; wherein, the control instructions are used to indicate the operating standards in the hardware production process.

[0041] Furthermore, the IoT-based hardware production line monitoring and management system also includes: a fault-associated equipment prediction unit, which is used to monitor and analyze the received hardware production data on the hardware management IoT platform, and after obtaining the equipment operation status and production process parameters, analyze the operation status of the hardware production equipment at each node on the hardware production line based on the monitored hardware production data of the metal material processing nodes, the metal material cutting nodes, the metal material forming nodes, and the metal material welding nodes, in combination with the identified control instructions, to obtain preliminary analysis results; classify the preliminary analysis results based on the identified control instructions to obtain fault classification results; and predict other hardware production equipment associated with the first fault when the fault classification result indicates that the first production equipment among the hardware production equipment at each node on the hardware production line has a first fault.

[0042] Based on the embodiment provided by the present application, IoT devices are deployed at each node on the hardware production line; wherein each node of the hardware production line includes metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes; the hardware production data is monitored by IoT devices, and the hardware production data is transmitted to the hardware management IoT platform through the communication protocol; on the hardware management IoT platform, the received hardware production data is monitored and analyzed to obtain the equipment operation status and production process parameters; and the production status of the hardware is displayed on the management terminal through the network; an abnormal situation on the hardware production line is alarmed, and the alarm information is displayed on the main interface of the hardware management IoT platform. Thus, the integration and coordination of the hardware production system is realized. Specifically, it has the following beneficial effects: Improve production efficiency: By real-time monitoring of each node of the production line, problems in the production process can be discovered and dealt with in a timely manner, thereby reducing production downtime and improving overall production efficiency; Reduce equipment failure rate: IoT devices can collect equipment operation data in real time, analyze this data through an intelligent early warning system, predict and solve potential equipment problems in advance, and reduce unexpected downtime; Optimize resource allocation: Through data analysis functions, intelligent monitoring software can help discover bottlenecks in the production process, optimize production processes and resource allocation, and improve resource utilization; Improve product quality: Real-time monitoring of key parameters on the production line can ensure that production conditions are always kept in the best state, reduce the occurrence of product quality problems, and improve production. Improve product qualification rate; Reduce production costs: Through predictive maintenance and optimization of production processes, it is possible to reduce waste of raw materials and energy consumption, thereby reducing production costs; Enhance safety management: IoT devices can monitor safety indicators in the production environment, promptly identify potential safety hazards and take measures to improve workplace safety; Realize remote monitoring and management: Managers can remotely monitor production conditions through the IoT platform, respond to production line needs in a timely manner, and improve management efficiency; Support decision-making: By collecting and analyzing production data, it can provide accurate information support to management and help formulate more scientific production plans and strategic decisions; Promote industrial upgrading: The application of IoT technology can help the hardware industry achieve digital and intelligent transformation and enhance the overall competitiveness of the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 It is a flowchart of an optional method for monitoring and managing a hardware production line based on the Internet of Things according to an embodiment of the present application;

[0045] Figure 2 This is a structural diagram of an optional IoT-based hardware production line monitoring and management system according to an embodiment of the present application.

[0046] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0048] Alternatively, if Figure 1 As shown, the present application provides a hardware production line monitoring and management method based on the Internet of Things, including:

[0049] S101, deploying IoT devices at various nodes on the hardware production line; wherein the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes, and metal material welding nodes;

[0050] Among them, IoT devices are compatible with the hardware management IoT platform, and IoT devices include sensors, cameras, and wireless radio frequency identification electronic tags;

[0051] S102, monitoring hardware production data through IoT devices, and transmitting the hardware production data to a hardware management IoT platform through a communication protocol;

[0052] S103, monitoring and analyzing the received hardware production data on the hardware management IoT platform, obtaining equipment operation status and production process parameters; and displaying the production status of the hardware on the management terminal through the network;

[0053] S104, an alarm is issued for abnormal conditions occurring on the hardware production line, and the alarm information is displayed on the main interface of the hardware management Internet of Things platform.

[0054] Based on the embodiment provided by the present application, IoT devices are deployed at various nodes on the hardware production line; wherein, the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes; the hardware production data is monitored by IoT devices, and the hardware production data is transmitted to the hardware management IoT platform through the communication protocol; on the hardware management IoT platform, the received hardware production data is monitored and analyzed to obtain the equipment operation status and production process parameters; and the production status of the hardware is displayed on the management terminal through the network; an abnormal situation on the hardware production line is alarmed, and the alarm information is displayed on the main interface of the hardware management IoT platform. The hardware production system integration and collaboration can be realized. Specifically, it has the following beneficial effects: Improve production efficiency: By real-time monitoring of each node of the production line, problems in the production process can be discovered and dealt with in a timely manner, thereby reducing production downtime and improving overall production efficiency; Reduce equipment failure rate: IoT devices can collect equipment operation data in real time, analyze this data through an intelligent early warning system, predict and solve potential equipment problems in advance, and reduce unexpected downtime; Optimize resource allocation: Through data analysis functions, intelligent monitoring software can help discover bottlenecks in the production process, optimize production processes and resource allocation, and improve resource utilization; Improve product quality: Real-time monitoring of key parameters on the production line can ensure that production conditions are always kept in the best state, reduce the occurrence of product quality problems, and improve production. Improve product qualification rate; Reduce production costs: Through predictive maintenance and optimization of production processes, it is possible to reduce waste of raw materials and energy consumption, thereby reducing production costs; Enhance safety management: IoT devices can monitor safety indicators in the production environment, promptly identify potential safety hazards and take measures to improve workplace safety; Realize remote monitoring and management: Managers can remotely monitor production conditions through the IoT platform, respond to production line needs in a timely manner, and improve management efficiency; Support decision-making: By collecting and analyzing production data, it can provide accurate information support to management and help formulate more scientific production plans and strategic decisions; Promote industrial upgrading: The application of IoT technology can help the hardware industry achieve digital and intelligent transformation and enhance the overall competitiveness of the industry.

[0055] Before monitoring and analyzing the received hardware production data on the hardware management IoT platform and obtaining the equipment operation status and production process parameters, the method further includes:

[0056] On the hardware management IoT platform, the historical hardware production data monitored by IoT devices is converted into standardized digital information, and the standardized digital information is transmitted to the control terminal;

[0057] The control terminal generates standard production reference information for hardware parts based on standardized digital information and standard information of hardware parts production process;

[0058] The hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management Internet of Things platform; among which, the control instructions are used to indicate the operating standards in the hardware production process.

[0059] Based on the embodiments provided in this application, the following beneficial effects are achieved: improving data processing efficiency: by converting historical production data into standardized digital information, it can be conveniently stored, processed and analyzed, thereby improving the efficiency and accuracy of data processing; optimizing the production process: the control terminal generates standard production reference information for hardware based on standardized digital information and standard information on the hardware production process, which helps to optimize the production process and achieve standardization and normalization of the production process; improving decision-making quality: the standard production reference information generated by the control terminal can provide accurate decision-making support for production management personnel, thereby improving the scientific nature and effectiveness of decision-making; enhancing production transparency: parsing standard production reference information into control instructions that can be recognized by the Internet of Things platform, making the production process more transparent, and management personnel can monitor the production status in real time, and promptly discover and solve problems; achieving accurate control: control instructions are used to indicate the operating standards in the hardware production process, which helps to achieve accurate control of the production process and improve product quality and production efficiency.

[0060] Furthermore, on the hardware management IoT platform, after monitoring and analyzing the received hardware production data and obtaining the equipment operation status and production process parameters, the method further includes:

[0061] According to the monitored hardware production data of metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes, combined with the identified control instructions, the operation status of the hardware production equipment at each node on the hardware production line is analyzed to obtain preliminary analysis results;

[0062] Classify the preliminary analysis results based on the identified control instructions to obtain fault classification results;

[0063] When the fault classification result indicates that a first fault occurs in a first production device among the hardware production devices at each node on the hardware production line, other hardware production devices associated with the first fault are predicted.

[0064] Based on the embodiments provided in the present application, the following beneficial effects are achieved: improving the accuracy of fault detection: by comprehensively analyzing the production data of various nodes such as metal material processing, cutting, forming and welding, combined with control instructions, it is possible to more accurately identify abnormal conditions in equipment operation, and achieve early detection and early warning of faults; optimizing fault classification: classifying the preliminary analysis results based on the identified control instructions to obtain fault classification results, which helps to further clarify the nature of the fault and the priority of handling, and provide more targeted guidance for maintenance personnel; predicting the correlation of equipment faults: when the fault classification results indicate that a certain production equipment has a fault, by analyzing its correlation with other equipment, it is possible to predict and prevent in advance the chain reaction that may be caused by the fault, thereby reducing potential greater losses; reducing maintenance costs and downtime: through predictive maintenance, the life and maintenance requirements of the equipment can be predicted based on data analysis, the frequency of unnecessary maintenance can be reduced, and the waste of resources caused by premature replacement can be avoided, while minimizing equipment downtime and production interruption of the production line; improving production processes and quality control: technologies such as machine vision systems can monitor and feedback every detail and abnormality in the production process in real time, helping manufacturers analyze and improve production processes, reduce product failure rates, and improve product consistency.

[0065] Furthermore, the preliminary analysis results include fault feature data. Based on the monitored hardware production data of metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes, combined with the identified control instructions, the operation status of the hardware production equipment at each node on the hardware production line is analyzed to obtain preliminary analysis results; the preliminary analysis results are classified based on the identified control instructions to obtain fault classification results, including:

[0066] Extract fault feature data from the hardware production data of monitored metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes;

[0067] Determine a weight coefficient of each data item in the fault characteristic data according to the identified control instruction;

[0068] Constructing a fault classification network according to each data item corresponding to a different weight coefficient in the fault feature data;

[0069] Establishing a first adjacency matrix and a second adjacency matrix according to the constructed fault classification network;

[0070] The first adjacency matrix and the second adjacency matrix are normalized based on the following formula to obtain a third adjacency matrix and a fourth adjacency matrix;

[0071]

[0072]

[0073] Among them, W n is the third adjacency matrix; S n is the first adjacency matrix; T s (i,i) is the first adjacency matrix S n The product of the values ​​of the elements in the ith row and ith column of n is the fourth adjacency matrix; K n is the second adjacency matrix; T k (i,i) is the second adjacency matrix K n The product of the values ​​of the elements in the ith row and ith column of ;

[0074] Based on the embodiments provided by the present application, the following beneficial effects are achieved: Enhanced fault detection capability: By extracting fault feature data from nodes such as metal material processing, cutting, forming and welding, abnormal modes in equipment operation can be more accurately identified, thereby early warning of potential faults; Application of weight coefficients: Determining weight coefficients for each data item in the fault feature data helps to highlight features that are more critical to fault diagnosis and enhance the accuracy of diagnosis; Constructing a fault classification network: Constructing a fault classification network based on weight coefficients helps to systematically identify and classify different types of faults and provide clear guidance for maintenance personnel; Establishing and normalizing adjacency matrices: Establishing a first adjacency matrix and a second adjacency matrix, and performing normalization processing to obtain a third adjacency matrix and a fourth adjacency matrix. This step helps to achieve more balanced and effective information transfer in the graph neural network, ensuring that the influence of different features is properly weighed in the fault classification process; Improving the accuracy of fault diagnosis: Through the above method, faults can be classified more accurately, thereby improving the pertinence and efficiency of maintenance work and reducing unnecessary inspection and maintenance time.

[0075] Based on the identified control instructions, a fault classification matrix is ​​output based on the third adjacency matrix and the fourth adjacency matrix; wherein the fault classification matrix is ​​used to indicate a fault classification result.

[0076] Further, the hardware production data includes data generated by hardware production equipment at each node on the hardware production line; when the fault classification result indicates that a first production equipment among the hardware production equipment at each node on the hardware production line has a first fault, after predicting other hardware production equipment associated with the first fault, the method further includes:

[0077] Based on the data generated by the first production equipment that has a first fault and the data generated by other hardware production equipment predicted to be associated with the first fault, future fault conditions of the hardware production equipment at each node on the hardware production line are predicted.

[0078] Furthermore, based on the data generated by the first production equipment having the first fault and the data generated by other production equipment predicted to be associated with the first fault, the future fault conditions of the hardware production equipment at each node on the hardware production line are predicted, including:

[0079] Based on the data generated by the first production equipment that has the first fault and the data generated by other hardware production equipment that is predicted to be associated with the first fault, assembling a fault vector sequence for each data and each time point in a preset time period;

[0080] Based on the fault vector sequence, a correlation graph between the data generated by the hardware production equipment and the fault events is constructed; wherein the nodes in the correlation graph include hardware production data feature nodes and fault event feature nodes, and the edges between the hardware production data feature nodes and the fault event feature nodes represent the correlation relationship between the hardware production data feature nodes and the fault event feature nodes;

[0081] The nodes in the fault event feature node are respectively used as the current fault nodes, and the following steps are performed: determining a set of associated nodes having an associated relationship with the current fault node; calculating an associated vector representation matrix of the current fault node based on the associated node set;

[0082] According to the correlation vector representation matrix, the correlation graph is updated based on the following formula;

[0083]

[0084] Among them, P1 represents the updated association graph; RELATE represents the association vector representation matrix; R0 represents the identity matrix; P0 represents the association graph; f represents the adjustment parameter;

[0085] Based on the updated association graph, the future failure conditions of the hardware production equipment at each node on the hardware production line are predicted.

[0086] Based on the embodiments provided in the present application, the following beneficial effects are achieved: enhancing fault prediction accuracy: by analyzing the equipment data of each production node and combining it with historical fault data, the types and time points of possible future faults can be predicted more accurately, so as to prepare for maintenance in advance; optimizing maintenance plans: the prediction results can help formulate more reasonable equipment maintenance plans, reduce unplanned downtime, and improve the operating efficiency and reliability of the production line; reducing maintenance costs: through targeted predictive maintenance, excessive or insufficient maintenance can be avoided to maximize cost-effectiveness; improving production safety: timely predicting and handling potential faults can reduce safety risks in the production process and ensure the safety of workers; promoting continuous improvement: by continuously analyzing fault data, data support is provided for continuous improvement; constructing a dynamic association graph: the association graph constructed through the fault vector sequence can more intuitively understand the relationship between production data features and fault events; updating the association graph can dynamically reflect the development of faults in the production process, and provide support for real-time monitoring and rapid response; through these steps, the hardware production line can not only monitor the current equipment status, but also predict and respond to possible problems in the future, thereby improving overall production efficiency and product quality.

[0087] Furthermore, the data generated by the hardware production equipment include feeding data of the vibration feeding device, handling data of the robot, coating data of the coating device, polishing data of the polishing device, spraying data of the coolant spraying device, cleaning data of the high-pressure airflow cleaning device, and separation data of the waste separation device.

[0088] like Figure 2 As shown, the present application provides a hardware production line monitoring and management system based on the Internet of Things, including an Internet of Things device deployment unit 201, a hardware production data transmission unit 202, a hardware production data monitoring and analysis unit 203, and a hardware production abnormality alarm unit 204; wherein,

[0089] The IoT device deployment unit 201 is used to deploy IoT devices at various nodes on the hardware production line; wherein the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes; wherein the IoT devices are compatible with the hardware management IoT platform, and the IoT devices include sensors, cameras and wireless radio frequency identification electronic tags;

[0090] The hardware production data transmission unit 202 is used to monitor the hardware production data through the Internet of Things device and transmit the hardware production data to the hardware management Internet of Things platform through the communication protocol;

[0091] The hardware production data monitoring and analysis unit 203 is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, obtain the equipment operation status and production process parameters; and display the production status of the hardware on the management terminal through the network;

[0092] The hardware production abnormality alarm unit 204 is used to alarm abnormal situations occurring on the hardware production line and display the alarm information on the main interface of the hardware management Internet of Things platform.

[0093] Furthermore, the hardware production line monitoring and management system based on the Internet of Things also includes: a control instruction parsing unit, which is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, and before obtaining the equipment operation status and production process parameters, on the hardware management Internet of Things platform, the historical hardware production data monitored by the Internet of Things equipment is converted into standardized digital information, and the standardized digital information is transmitted to the control terminal; the control terminal generates hardware standard production reference information based on the standardized digital information and hardware production process standard information; the hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management Internet of Things platform; wherein the control instructions are used to indicate the operating standards in the hardware production process.

[0094] Furthermore, the hardware production line monitoring and management system based on the Internet of Things also includes: a fault-associated equipment prediction unit, which is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, and after obtaining the equipment operation status and production process parameters, analyze the operation status of the hardware production equipment at each node on the hardware production line based on the monitored hardware production data of the metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes, combined with the identified control instructions, to obtain preliminary analysis results; classify the preliminary analysis results based on the identified control instructions to obtain fault classification results; when the fault classification results indicate that the first production equipment among the hardware production equipment at each node on the hardware production line has a first fault, predict other hardware production equipment associated with the first fault.

[0095] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A monitoring and management method for hardware production line based on Internet of Things, It is characterized in that include: Deploy IoT devices at various nodes on a hardware production line; wherein the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes, and metal material welding nodes; Wherein, the IoT device is compatible with the hardware management IoT platform, and the IoT device includes a sensor, a camera, and a wireless radio frequency identification electronic tag; Monitor the hardware production data through the IoT device, and transmit the hardware production data to the hardware management IoT platform through the communication protocol; On the hardware management IoT platform, the received hardware production data is monitored and analyzed to obtain the equipment operation status and production process parameters; and the production status of the hardware is displayed on the management terminal through the network; An alarm is issued for abnormal situations occurring on the hardware production line, and the alarm information is displayed on the main interface of the hardware management Internet of Things platform.

2. According to the method for monitoring and managing a hardware production line based on the Internet of Things according to claim 1, It is characterized in that Before monitoring and analyzing the received hardware production data on the hardware management IoT platform to obtain equipment operation status and production process parameters, the method further includes: On the hardware management IoT platform, the historical hardware production data monitored by the IoT device is converted into standardized digital information, and the standardized digital information is transmitted to the control terminal; The control terminal generates hardware standard production reference information based on the standardized digital information and hardware production process standard information; The hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management Internet of Things platform; wherein the control instructions are used to indicate the operating standards in the hardware production process.

3. According to the method for monitoring and managing a hardware production line based on the Internet of Things according to claim 2, It is characterized in that After monitoring and analyzing the received hardware production data on the hardware management IoT platform to obtain equipment operation status and production process parameters, the method further includes: According to the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node, combined with the identified control instructions, the operation status of the hardware production equipment at each node on the hardware production line is analyzed to obtain preliminary analysis results; Classifying the preliminary analysis result based on the identified control instruction to obtain a fault classification result; When the fault classification result indicates that a first fault occurs in a first production equipment among the hardware production equipment at each node on the hardware production line, other hardware production equipment associated with the first fault is predicted.

4. According to the method for monitoring and managing a hardware production line based on the Internet of Things according to claim 3, It is characterized in that The preliminary analysis result includes fault characteristic data, and the operation status of the hardware production equipment at each node on the hardware production line is analyzed based on the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node, combined with the identified control instructions, to obtain the preliminary analysis result; The preliminary analysis result is classified based on the identified control instruction to obtain a fault classification result, including: Extracting the fault characteristic data from the monitored hardware production data of the metal material processing node, the metal material cutting node, the metal material forming node and the metal material welding node; Determining a weight coefficient of each data item in the fault characteristic data according to the identified control instruction; Constructing a fault classification network according to each data item corresponding to a different weight coefficient in the fault feature data; Establishing a first adjacency matrix and a second adjacency matrix according to the constructed fault classification network; Normalizing the first adjacency matrix and the second adjacency matrix to obtain a third adjacency matrix and a fourth adjacency matrix; Based on the identified control instruction, a fault classification matrix is ​​output based on the third adjacency matrix and the fourth adjacency matrix; wherein the fault classification matrix is ​​used to indicate a fault classification result.

5. According to the method for monitoring and managing a hardware production line based on the Internet of Things as claimed in claim 3, It is characterized in that The hardware production data includes data generated by hardware production equipment at each node on the hardware production line; when the fault classification result indicates that a first production equipment among the hardware production equipment at each node on the hardware production line has a first fault, after predicting other hardware production equipment associated with the first fault, the method further includes: Based on the data generated by the first production equipment where the first fault occurs and the data generated by other hardware production equipment predicted to be associated with the first fault, future failure conditions of the hardware production equipment at each node on the hardware production line are predicted.

6. According to the method for monitoring and managing a hardware production line based on the Internet of Things according to claim 5, It is characterized in that The predicting of future failure conditions of hardware production equipment at each node on the hardware production line based on the data generated by the first production equipment where the first failure occurs and the data generated by other production equipment predicted to be associated with the first failure includes: Based on the data generated by the first production equipment where the first fault occurs and the data generated by other hardware production equipment predicted to be associated with the first fault, assembling a fault vector sequence for each data and each time point in a preset time period; Based on the fault vector sequence, a correlation graph of data generated by hardware production equipment and fault events is constructed; wherein the nodes in the correlation graph include the hardware production data feature nodes and the fault event feature nodes, and the edges between the hardware production data feature nodes and the fault event feature nodes represent that there is a correlation relationship between the hardware production data feature nodes and the fault event feature nodes; The nodes in the fault event characteristic nodes are respectively used as current fault nodes, and the following steps are performed: determining a set of associated nodes having an associated relationship with the current fault node; calculating an associated vector representation matrix of the current fault node based on the associated node set; updating the association graph according to the association vector representation matrix; Based on the updated association graph, future failure conditions of the hardware production equipment at each node on the hardware production line are predicted.

7. According to claim 5, the method for monitoring and managing a hardware production line based on the Internet of Things, It is characterized in that The data generated by the hardware production equipment include feeding data of the vibration feeding device, handling data of the robot, coating data of the coating device, polishing data of the polishing device, spraying data of the coolant spraying device, cleaning data of the high-pressure airflow cleaning device and separation data of the waste separation device.

8. A hardware production line monitoring and management system based on the Internet of Things, It is characterized in that It includes an IoT device deployment unit, a hardware production data transmission unit, a hardware production data monitoring and analysis unit, and a hardware production abnormality alarm unit; among which, The IoT device deployment unit is used to deploy IoT devices at various nodes on the hardware production line; wherein the various nodes of the hardware production line include metal material processing nodes, metal material cutting nodes, metal material forming nodes and metal material welding nodes; wherein the IoT devices are compatible with the hardware management IoT platform, and the IoT devices include sensors, cameras and wireless radio frequency identification electronic tags; The hardware production data transmission unit is used to monitor the hardware production data through the Internet of Things device and transmit the hardware production data to the hardware management Internet of Things platform through a communication protocol; The hardware production data monitoring and analysis unit is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, obtain equipment operation status and production process parameters; and display the production status of hardware on the management terminal through the network; The hardware production abnormality alarm unit is used to alarm for abnormal situations occurring on the hardware production line and display the alarm information on the main interface of the hardware management Internet of Things platform.

9. According to the hardware production line monitoring and management system based on the Internet of Things as claimed in claim 8, It is characterized in that The hardware production line monitoring and management system based on the Internet of Things also includes: A control instruction parsing unit is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, and before obtaining the equipment operation status and production process parameters, on the hardware management Internet of Things platform, convert the historical hardware production data monitored by the Internet of Things device into standardized digital information, and transmit the standardized digital information to the control terminal; the control terminal generates hardware standard production reference information based on the standardized digital information and hardware production process standard information; the hardware standard production reference information generated by the control terminal is parsed into control instructions that can be recognized by the hardware management Internet of Things platform; wherein, the control instructions are used to indicate the operating standards in the hardware production process.

10. According to the Internet of Things-based hardware production line monitoring and management system of claim 8, It is characterized in that The hardware production line monitoring and management system based on the Internet of Things also includes: A fault-associated equipment prediction unit is used to monitor and analyze the received hardware production data on the hardware management Internet of Things platform, and after obtaining the equipment operation status and production process parameters, analyze the operation status of the hardware production equipment at each node on the hardware production line based on the monitored hardware production data of the metal material processing nodes, the metal material cutting nodes, the metal material forming nodes and the metal material welding nodes, in combination with the identified control instructions, to obtain preliminary analysis results; classify the preliminary analysis results based on the identified control instructions to obtain fault classification results; and predict other hardware production equipment associated with the first fault when the fault classification result indicates that the first production equipment among the hardware production equipment at each node on the hardware production line has a first fault.

Citation Information

Patent Citations

  • Intelligent ink-jet printing machine production monitoring device based on Internet of things

    CN107578614A

  • Big data based intelligent factory manufacturing management system

    CN109634229A

  • Internet of Things platform for integrating industry by using tower production workshop equipment research and development data

    CN112327770A

  • Industrial data management method and system based on cloud edge fusion

    CN117872989A

  • Artificial intelligence(AI) integrated production management system using inventory detection system and integrated production management method using the same

    KR102370131B1