Manufacturing equipment fault diagnosis system based on Internet of Things
By integrating data acquisition, node management and fault diagnosis modules in the manufacturing equipment fault diagnosis system, the accuracy and efficiency of equipment fault detection in remote monitoring are solved, and more efficient fault detection and early warning are achieved, reducing equipment maintenance time.
Patent Information
- Application Number
- CN202411143963.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-12-10
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When the prior art remotely monitors manufacturing equipment, it is difficult to accurately detect equipment failures, there are false reports and missed reports, and the data transmission delay and processing efficiency are low, resulting in inconvenient equipment management, and excessive multi-threaded processing resources, resulting in reduced processing speed.
Design a manufacturing equipment fault diagnosis system based on the Internet of Things, including data acquisition module, node management module and fault diagnosis module, collect equipment data through sensors, resource management module adjusts processing node load, fault diagnosis module analyzes the cause of the fault, and passes early warning Module reminds maintenance personnel.
Improve the accuracy and efficiency of equipment failure detection, avoid insufficient processing node resources and overload of core child nodes, reduce equipment failure repair time, and ensure full utilization of processor resources.
Smart Images
Figure CN119105446A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment fault detection, and in particular to a manufacturing equipment fault diagnosis system based on the Internet of Things. Background Art
[0002] With the rapid development of Internet computing technology, the scale of factories is also expanding. In the process of factory expansion, due to factors such as manpower and material resources, the geographical location of the branch factory is far away from the current factory, which is very inconvenient to manage. The existing technology is to detect factory equipment through remote monitoring technology and report the operating status of production equipment in real time. However, the existing technology determines whether the equipment is faulty by detecting changes in the operating status of the equipment. Due to the complex operating environment of the equipment, the operating status of the equipment is variable, and there are false reports and missed reports. It is impossible to accurately detect equipment failures, resulting in increased losses. Moreover, the operating status of the remote monitoring equipment is prone to processor load during data transmission due to the long data transmission distance and large data volume, resulting in slow data processing. In addition, when the multi-threaded processing system collects device data, it is easy for threads to occupy too many resources, resulting in insufficient resource support for some threads when multi-threaded parallel, resulting in low efficiency in multi-threaded data processing and inability to fully utilize processor resources. Therefore, it is very necessary to design a manufacturing equipment fault diagnosis system based on the Internet of Things with high accuracy and efficiency. Summary of the invention
[0003] The purpose of the present invention is to provide a manufacturing equipment fault diagnosis system based on the Internet of Things to solve the problems raised in the above background technology.
[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a manufacturing equipment fault diagnosis system based on the Internet of Things, comprising a data acquisition module, a node management module and a fault diagnosis module, characterized in that: the data acquisition module is used to collect equipment operation status data and environmental status data and manufacturing product data, the resource management module is used to detect the load condition of the processing node and allocate memory resources according to the load condition, the fault diagnosis module is used to detect equipment faults and analyze the causes of equipment faults, and the data acquisition module, the resource management module and the fault diagnosis module are electrically connected to each other;
[0005] The resource management module includes a node adjustment submodule, a process analysis submodule, a resource allocation submodule and a resource initialization submodule. The node adjustment submodule is used to allocate nodes according to the load of the processing node. The process analysis submodule is used to identify the process of fault analysis. The resource allocation submodule is used to allocate the memory resources of the process to the multithreading according to the process analysis result. The resource initialization submodule is used to initialize the allocated process memory resources.
[0006] The fault analysis module includes an operating environment detection submodule, an environment analysis submodule and a fault cause analysis submodule. The operating status detection submodule is used to perform preliminary detection on the operating status data of the equipment, the environment analysis submodule is used to analyze the equipment working environment data in real time, and the fault detection submodule is used to verify whether the equipment has a fault and predict the equipment fault.
[0007] According to the above technical solution, the data acquisition module includes a sensor module, an information entry module and a data collection module. The sensor module is used to collect the equipment's operating status data and equipment working environment data. The information entry module is used to enter the manufactured product data and the manufactured product's operating status data into the system. The data collection module is used to collect the equipment's fault characteristics and fault causes.
[0008] According to the above technical solution, the node management module includes a load detection module and a node management module. The load detection module is used to detect the load conditions of the node and the CPU in the node respectively, and the resource management module is used to adjust the processing node and allocate memory resources in the processing node.
[0009] According to the above technical solution, the node management module also includes a knowledge graph module, which is used to construct a knowledge graph based on the equipment failure characteristics and failure causes entered into the system.
[0010] According to the above technical solution, the fault diagnosis module includes a fault analysis module and an early warning module. The fault analysis module is used to analyze the fault of the equipment, and the early warning module is used to issue an alarm when a fault occurs in the equipment.
[0011] According to the above technical solution, the operation method of the equipment fault diagnosis system mainly includes the following steps:
[0012] Step S1: Record and save the equipment operation data and the environmental change data during the equipment operation process through the sensor module, enter the manufactured product data and the operation status data of the manufactured product into the system through the information entry module, and record and save the characteristics and causes of the current equipment fault through the data collection module;
[0013] Step S2: When processing the device operation status data, the system triggers the node management module to start through an electrical signal, starts analyzing the load rate of the processing node and the core sub-nodes in the processing node, and allocates the memory resources in the node according to the load analysis results;
[0014] Step S3: After the memory resource allocation is completed, a knowledge graph is constructed based on the historical fault data, and the fault analysis module is started to analyze various parameters during the operation of the equipment and determine whether the parameters are abnormal;
[0015] Step S4: When the fault analysis module determines that there is an abnormality in the equipment operation status data, the system stops the equipment operation and issues an alarm through the early warning module to remind the management personnel to repair the equipment and analyze the cause of the equipment failure based on the constructed knowledge graph.
[0016] According to the above technical solution, step S2 further includes the following steps:
[0017] Step S21: retrieve the amount of memory resources required by the current processing node to process data, and calculate the load rate of the current processing node through the formula In the formula, F represents the load rate of the current processing node, m represents the amount of memory resources required by the current processing node to process data, and M represents the total amount of memory resources of the current processing node;
[0018] Step S22: call all data processing threads in the current node, identify the process identifier in the data processing thread, classify the data processing threads according to the process identifier, compare the classified process identifiers, when the processing node load rate is greater than the second threshold value set by the system and less than the third threshold value, call the system-set percentage of memory resources in other processing nodes and allocate them to the current processing node, when the processing node load rate is greater than the third threshold value, if the process identifiers in the current processing node are all the same, call the processing nodes adjacent to the current processing node in the processor, initialize the adjacent processing nodes, and unpack the nodes, merge the memory resources in the nodes into the current processing node, otherwise call the spare processing node, identify the assigned process identifier, transfer the thread to the spare processing node for processing according to the process identifier, when the processing node load rate is less than the second threshold value and greater than the first threshold value, lock the current processing node, unlock the current processing node after processing the data, when the processing node load rate is less than the first threshold value, the current processing node stably processes the data;
[0019] Step S23: Retrieve all processes in the current processing node, identify thread data contained in the process, and allocate memory resources in the current processing node according to the thread data.
[0020] According to the above technical solution, step S23 further includes the following steps:
[0021] Step S231: call all threads in the current process, identify the processing time of all threads, compare all processing times, and when there are threads with the same processing time in the same process, calculate the number of threads with the same processing time, and compare the number of core sub-nodes in a single CPU in the current processing node. If the number of threads is greater than the number of core sub-nodes, call other CPU memory resources in the current processing node and transfer the threads to the core sub-node of the target CPU. Otherwise, call to use the current core sub-node to process the data.
[0022] Step S232: When there is no thread with the same processing time in the same process, the size of the memory resources actually occupied by the processing data in the core sub-node is retrieved, and the actual load rate of the current core sub-node is calculated by the formula Wherein, P represents the actual load rate of the current core subnode, Q represents the actual memory resource size occupied by the current core subnode when processing data, and N represents the rated memory resource size of the current core subnode. If the load rate of the current core subnode is less than the minimum threshold set by the system, the current core subnode continues to process data. If the load rate of the current core subnode is greater than the minimum threshold and less than the maximum threshold, the most recent set of data to be processed is retrieved, and the memory resource size required for processing the most recent set of data to be processed is analyzed using the data analysis model. The remaining memory resource size of the current core subnode is compared. If the remaining memory resource size of the current core subnode is greater than the memory resource size required to process the most recent set of data, the current core subnode directly processes it. Otherwise, the idle memory resources in the processing node are retrieved and allocated to the current core subnode.
[0023] According to the above technical solution, step S3 further includes the following steps:
[0024] Step S31: retrieve the historical fault data of the equipment, identify the range of various parameters under the equipment operation state, equipment operation environment data, the location and cause of the fault in the fault data, extract the fault characteristics, and perform weighted fusion of various data of the equipment operation under the current fault state, equipment operation environment data, fault location and fault cause according to the fault characteristics, and construct a knowledge graph of the equipment fault based on the fused fault data;
[0025] Step S32: retrieve the real-time status data W of the equipment under the running state, and compare it with the system database. If the real-time status data of the equipment is completely consistent with the data in the database, the equipment continues to run. If the real-time status data of the equipment is within the threshold range of the system database, further retrieve the environmental data of the current equipment operation, retrieve the historical environmental data in the database based on the environmental data and the impact on the equipment running state, and give the impact parameter α of the environmental data on the equipment running state data;
[0026] Step S33: Calculate the equipment operation status data without environmental influence by formula In the formula, D represents the equipment operation status data without environmental influence, W represents the real-time status data of the equipment under the operation state, and α represents the influence parameter of environmental data on the equipment operation status data. The equipment operation status data without environmental influence is obtained by calculation and compared with the database range. If the equipment operation status data at this time is within the threshold range, the equipment is marked as a faulty equipment to be confirmed, otherwise the equipment operation is stopped.
[0027] According to the above technical solution, in step S4, the knowledge graph and equipment operation status data are retrieved, and the equipment operation status data is compared with the knowledge graph. If the equipment operation status data at this time matches the threshold range in the knowledge graph, it means that the current equipment has a fault, and the current equipment is marked as a faulty equipment. An alarm is issued through the early warning module to remind maintenance personnel to perform repairs. Otherwise, the current equipment is marked as a normal equipment, and the historical operation status data of the equipment is retrieved. An operation status prediction model is constructed based on the historical operation status data. The operation status of the equipment is predicted based on the operation status prediction model, and the equipment code is retrieved to issue an alarm to the maintenance personnel through the early warning module to remind the maintenance personnel to perform equipment maintenance.
[0028] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by detecting the load rate of the current processing node and adjusting it step by step according to the load rate, can avoid insufficient memory resources of the current processing node, resulting in accumulation of data to be processed in the processing node, leading to data congestion of the processing node, and wasting a lot of time waiting for data processing, which can greatly improve the processing speed of the processing node, thereby greatly improving the efficiency of the system; by comparing the number of core sub-nodes in the current CPU with the number of threads in the process, each thread can be matched to a core sub-node, which can avoid the mismatch between the number of core sub-nodes and the number of threads, resulting in some threads needing to wait for idle core sub-nodes, resulting in the inability to process data in the first time, greatly improving the processing speed of thread data; by calculating the real-time load rate of the current core sub-node, it can avoid the core sub-node Node overload, and then maintain the best processing state, call the system's idle memory resources to allocate to the current core sub-node, can ensure that the core sub-node has enough memory resources to process data, avoid the core sub-node operation overload, resulting in reduced processing speed, further improve the system processing efficiency, and issue a warning through the early warning module to remind maintenance personnel to carry out maintenance. By calculating the operating status data of the equipment without the influence of environmental factors and comparing it with the database, it can avoid the impact of environmental factors on the equipment and interfere with the detection of equipment failures, greatly improving the accuracy of equipment fault detection. By constructing a device operation status prediction model, it can predict the operating status of the equipment in the future based on the operating status of the equipment within a period of time, and can predict whether the equipment will fail in advance, maintain the equipment, and reduce the repair time of equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0030] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION
[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0032] See also Figure 1, the present invention provides a technical solution: a manufacturing equipment fault diagnosis system based on the Internet of Things, including a data acquisition module, a node management module and a fault diagnosis module, characterized in that: the data acquisition module is used to collect equipment operation status data and environmental status data and manufacturing product data, the resource management module is used to detect the load condition of the processing node and allocate memory resources according to the load condition, the fault diagnosis module is used to detect equipment failure and analyze the cause of the equipment failure, and the data acquisition module, the resource management module and the fault diagnosis module are electrically connected to each other;
[0033] The resource management module includes a node adjustment submodule, a process analysis submodule, a resource allocation submodule and a resource initialization submodule. The node adjustment submodule is used to allocate nodes according to the load of the processing nodes. The process analysis submodule is used to identify the process of fault analysis. The resource allocation submodule is used to allocate the memory resources of the process to the multithreading according to the process analysis results. The resource initialization submodule is used to initialize the allocated process memory resources.
[0034] The fault analysis module includes an operating environment detection submodule, an environmental analysis submodule and a fault cause analysis submodule. The operating status detection submodule is used to perform preliminary detection on the operating status data of the equipment, the environmental analysis submodule is used to analyze the equipment working environment data in real time, and the fault detection submodule is used to verify whether the equipment has a fault and predict equipment failure.
[0035] The data acquisition module includes a sensor module, an information entry module and a data collection module. The sensor module is used to collect the equipment's operating status data and equipment working environment data. The information entry module is used to enter the manufactured product data and the manufactured product's operating status data into the system. The data collection module is used to collect the equipment's fault characteristics and fault causes.
[0036] The node management module includes a load detection module and a node management module. The load detection module is used to detect the load of the node and the CPU in the node respectively. The resource management module is used to adjust the processing node and allocate memory resources in the processing node.
[0037] The node management module also includes a knowledge graph module, which is used to construct a knowledge graph based on the equipment failure characteristics and failure causes entered into the system.
[0038] The fault diagnosis module includes a fault analysis module and an early warning module. The fault analysis module is used to analyze the fault of the equipment, and the early warning module is used to issue an alarm when a fault occurs in the equipment.
[0039] The operation method of the equipment fault diagnosis system mainly includes the following steps:
[0040] Step S1: Record and save the equipment operation data and the environmental change data during the equipment operation process through the sensor module, enter the manufactured product data and the operation status data of the manufactured product into the system through the information entry module, and record and save the characteristics and causes of the current equipment fault through the data collection module;
[0041] Step S2: When processing the device operation status data, the system triggers the node management module to start through an electrical signal, starts analyzing the load rate of the processing node and the core sub-nodes in the processing node, and allocates the memory resources in the node according to the load analysis results;
[0042] Step S3: After the memory resource allocation is completed, a knowledge graph is constructed based on the historical fault data, and the fault analysis module is started to analyze various parameters during the operation of the equipment and determine whether the parameters are abnormal;
[0043] Step S4: When the fault analysis module determines that there is an abnormality in the equipment operation status data, the system stops the equipment operation and issues an alarm through the early warning module to remind the management personnel to repair the equipment and analyze the cause of the equipment failure based on the constructed knowledge graph.
[0044] Step S2 further comprises the following steps:
[0045] Step S21: retrieve the amount of memory resources required by the current processing node to process data, and calculate the load rate of the current processing node through the formula In the formula, F represents the load rate of the current processing node, m represents the amount of memory resources required by the current processing node to process data, and M represents the total amount of memory resources of the current processing node. The above formula can quickly give the load rate of the current processing node and quickly determine whether the current processing node is overloaded.
[0046] Step S22: call all data processing threads in the current node, identify the process identifiers in the data processing threads, classify the data processing threads according to the process identifiers, compare the classified process identifiers, and when the processing node load rate is greater than the second threshold value set by the system and less than the third threshold value, call the system-set percentage of memory resources in other processing nodes and allocate them to the current processing node. When the processing node load rate is greater than the third threshold value, if the process identifiers in the current processing node are all the same, it means that there is only one process in the current processing node, call the processing nodes adjacent to the current processing node in the processor, initialize the adjacent processing nodes, and unpack the nodes to merge the memory resources in the nodes into the current processing node. , otherwise, the standby processing node is called, the assigned process identifier is identified, and the thread is transferred to the standby processing node for processing according to the process identifier. When the processing node load rate is less than the second threshold and greater than the first threshold, the current processing node is locked, and the current processing node is unlocked after the data is processed. When the processing node load rate is less than the first threshold, the current processing node processes the data stably. By detecting the load rate of the current processing node and adjusting it step by step according to the load rate, it is possible to avoid insufficient memory resources of the current processing node, resulting in accumulation of data to be processed in the processing node, causing data congestion in the processing node, and wasting a lot of time waiting for data processing, which can greatly improve the processing speed of the processing node, thereby greatly improving the efficiency of the system;
[0047] Step S23: Retrieve all processes in the current processing node, identify thread data contained in the process, and allocate memory resources in the current processing node according to the thread data.
[0048] Step S23 further includes the following steps:
[0049] Step S231: call all threads in the current process, identify the processing time of all threads, compare all processing times, and when there are threads with the same processing time in the same process, calculate the number of threads with the same processing time, and compare the number of core sub-nodes in a single CPU in the current processing node. If the number of threads is greater than the number of core sub-nodes, it means that the number of core sub-nodes in the current CPU cannot meet the process processing requirements, call other CPU memory resources in the current processing node, transfer the threads to the core sub-nodes of the target CPU, otherwise call to use the current core sub-node to process the data. By comparing the number of core sub-nodes in the current CPU with the number of threads in the process, each thread can be matched with a core sub-node, which can avoid the mismatch between the number of core sub-nodes and the number of threads, causing some threads to need to wait for idle core sub-nodes, resulting in the inability to process data in the first time, greatly improving the processing speed of thread data;
[0050] Step S232: When there is no thread with the same processing time in the same process, the size of the memory resources actually occupied by the processing data in the core sub-node is retrieved, and the actual load rate of the current core sub-node is calculated by the formula Wherein, P represents the actual load rate of the current core subnode, Q represents the actual memory resource size occupied by the current core subnode when processing data, and N represents the rated memory resource size of the current core subnode. If the load rate of the current core subnode is less than the minimum threshold set by the system, the current core subnode continues to process data. If the load rate of the current core subnode is greater than the minimum threshold and less than the maximum threshold, the most recent set of data to be processed is retrieved, and the memory resource size required for processing the most recent set of data to be processed is analyzed using the data analysis model. The remaining memory resource size of the current core subnode is compared. If the remaining memory resource size of the current core subnode is greater than the memory resource size required for processing the most recent set of data, the current core subnode directly processes it. Otherwise, the idle memory resources in the processing node are retrieved and allocated to the current core subnode. By calculating the real-time load rate of the current core subnode, the core subnode can be avoided from being overloaded, thereby maintaining the best processing state. Retrieving the idle memory resources of the system and allocating them to the current core subnode can ensure that the core subnode has sufficient memory resources to process data, avoid overloading of the core subnode, and reduce the processing speed, thereby further improving the system processing efficiency.
[0051] Step S3 further comprises the following steps:
[0052] Step S31: retrieve the historical fault data of the equipment, identify the range of various parameters under the equipment operation state, equipment operation environment data, the location and cause of the fault in the fault data, extract the fault characteristics, and perform weighted fusion of various data of the equipment operation under the current fault state, equipment operation environment data, fault location and fault cause according to the fault characteristics, and construct a knowledge graph of the equipment fault based on the fused fault data;
[0053] Step S32: retrieve the real-time status data W of the equipment under the running state, and compare it with the system database. If the real-time status data of the equipment is completely consistent with the data in the database, it means that the equipment is running normally and the equipment continues to run. If the real-time status data of the equipment is within the threshold range of the system database, it means that the equipment may fail at this time. Further retrieve the environmental data of the current equipment operation, retrieve the historical environmental data in the database based on the environmental data and the impact on the equipment running state, and give the impact parameter α of the environmental data on the equipment running state data;
[0054] Step S33: Calculate the equipment operation status data without environmental influence by formula In the formula, D represents the equipment operation status data without environmental influence, W represents the real-time status data of the equipment under the operation state, and α represents the influence parameter of environmental data on the equipment operation status data. The equipment operation status data without environmental influence is obtained by calculation and compared with the database range. If the equipment operation status data at this time is within the threshold range, the equipment is marked as a faulty equipment to be confirmed. Otherwise, the equipment operation is stopped and a warning is issued through the early warning module to remind the maintenance personnel to perform maintenance. By calculating the equipment operation status data without the influence of environmental factors and comparing it with the database, the influence of environmental factors on the equipment can be avoided, which interferes with the detection of equipment faults and greatly improves the accuracy of equipment fault detection.
[0055] In step S4, the knowledge graph and equipment operation status data are retrieved, and the equipment operation status data is compared with the knowledge graph. If the equipment operation status data at this time matches the threshold range in the knowledge graph, it means that the current equipment has a fault, and the current equipment is marked as a faulty equipment. An alarm is issued through the early warning module to remind maintenance personnel to perform repairs. Otherwise, the current equipment is marked as a normal equipment, and the historical operation status data of the equipment is retrieved. An operation status prediction model is constructed based on the historical operation status data. The operation status of the equipment is predicted according to the operation status prediction model, and the equipment code is retrieved to issue an alarm to the maintenance personnel through the early warning module to remind the maintenance personnel to perform equipment maintenance. By constructing the equipment operation status prediction model, the operation status of the equipment in the future can be predicted based on the operation status of the equipment in a period of time. It is possible to predict whether the equipment will fail in advance, maintain the equipment, and reduce the repair time of equipment failures.
[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0057] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A manufacturing equipment fault diagnosis system based on the Internet of Things, including a data acquisition module, a node management module and a fault diagnosis module, Features: The data acquisition module is used to collect the operation status data and environmental status data of the equipment and the manufacturing product data; the resource management module is used to detect the load of the processing node and allocate the memory resources according to the load; the fault diagnosis module is used to detect the equipment fault and analyze the cause of the equipment fault; the data acquisition module, the resource management module and the fault diagnosis module are electrically connected to each other; The resource management module includes a node adjustment submodule, a process analysis submodule, a resource allocation submodule and a resource initialization submodule. The node adjustment submodule is used to allocate nodes according to the load of the processing node. The process analysis submodule is used to identify the process of fault analysis. The resource allocation submodule is used to allocate the memory resources of the process to the multithreading according to the process analysis result. The resource initialization submodule is used to initialize the allocated process memory resources. The fault analysis module includes an operating environment detection submodule, an environment analysis submodule and a fault cause analysis submodule. The operating status detection submodule is used to perform preliminary detection on the operating status data of the equipment, the environment analysis submodule is used to analyze the equipment working environment data in real time, and the fault detection submodule is used to verify whether the equipment has a fault and predict the equipment fault.
2. According to the manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 1, Features: The data acquisition module includes a sensor module, an information entry module and a data collection module. The sensor module is used to collect the equipment's operating status data and equipment working environment data. The information entry module is used to enter the manufactured product data and the manufactured product's operating status data into the system. The data collection module is used to collect the equipment's fault characteristics and fault causes.
3. According to the manufacturing equipment fault diagnosis system based on the Internet of Things as described in claim 2, Features: The node management module includes a load detection module and a node management module. The load detection module is used to detect the load conditions of the node and the CPU in the node respectively. The resource management module is used to adjust the processing node and allocate memory resources in the processing node.
4. According to the manufacturing equipment fault diagnosis system based on the Internet of Things as described in claim 3, Features: The node management module also includes a knowledge graph module, which is used to construct a knowledge graph based on equipment failure characteristics and failure causes entered into the system.
5. According to the manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 4, Features: The fault diagnosis module includes a fault analysis module and an early warning module. The fault analysis module is used to analyze the fault of the equipment, and the early warning module is used to issue an alarm when a fault occurs in the equipment.
6. According to the manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 5, Features: The operation method of the equipment fault diagnosis system mainly includes the following steps: Step S1: Record and save the equipment operation data and the environmental change data during the equipment operation process through the sensor module, enter the manufactured product data and the operation status data of the manufactured product into the system through the information entry module, and record and save the characteristics and causes of the current equipment fault through the data collection module; Step S2: When processing the device operation status data, the system triggers the node management module to start through an electrical signal, starts analyzing the load rate of the processing node and the core sub-nodes in the processing node, and allocates the memory resources in the node according to the load analysis results; Step S3: After the memory resource allocation is completed, a knowledge graph is constructed based on the historical fault data, and the fault analysis module is started to analyze various parameters during the operation of the equipment and determine whether the parameters are abnormal; Step S4: When the fault analysis module determines that there is an abnormality in the equipment operation status data, the system stops the equipment operation and issues an alarm through the early warning module to remind the management personnel to repair the equipment and analyze the cause of the equipment failure based on the constructed knowledge graph.
7. A manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 6, Features: The step S2 further comprises the following steps: Step S21: retrieve the amount of memory resources required by the current processing node to process data, and calculate the load rate of the current processing node through the formula In the formula, F represents the load rate of the current processing node, m represents the amount of memory resources required by the current processing node to process data, and M represents the total amount of memory resources of the current processing node; Step S22: call all data processing threads in the current node, identify the process identifier in the data processing thread, classify the data processing threads according to the process identifier, compare the classified process identifiers, when the processing node load rate is greater than the second threshold value set by the system and less than the third threshold value, call the system-set percentage of memory resources in other processing nodes and allocate them to the current processing node, when the processing node load rate is greater than the third threshold value, if the process identifiers in the current processing node are all the same, call the processing nodes adjacent to the current processing node in the processor, initialize the adjacent processing nodes, and unpack the nodes, merge the memory resources in the nodes into the current processing node, otherwise call the spare processing node, identify the assigned process identifier, transfer the thread to the spare processing node for processing according to the process identifier, when the processing node load rate is less than the second threshold value and greater than the first threshold value, lock the current processing node, unlock the current processing node after processing the data, when the processing node load rate is less than the first threshold value, the current processing node stably processes the data; Step S23: Retrieve all processes in the current processing node, identify thread data contained in the process, and allocate memory resources in the current processing node according to the thread data.
8. A manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 7, Features: The step S23 further comprises the following steps: Step S231: call all threads in the current process, identify the processing time of all threads, compare all processing times, and when there are threads with the same processing time in the same process, calculate the number of threads with the same processing time, and compare the number of core sub-nodes in a single CPU in the current processing node. If the number of threads is greater than the number of core sub-nodes, call other CPU memory resources in the current processing node and transfer the threads to the core sub-node of the target CPU. Otherwise, call to use the current core sub-node to process the data. Step S232: When there is no thread with the same processing time in the same process, the size of the memory resources actually occupied by the processing data in the core sub-node is retrieved, and the actual load rate of the current core sub-node is calculated by the formula Wherein, P represents the actual load rate of the current core subnode, Q represents the actual memory resource size occupied by the current core subnode when processing data, and N represents the rated memory resource size of the current core subnode. If the load rate of the current core subnode is less than the minimum threshold set by the system, the current core subnode continues to process data. If the load rate of the current core subnode is greater than the minimum threshold and less than the maximum threshold, the most recent set of data to be processed is retrieved, and the memory resource size required for processing the most recent set of data to be processed is analyzed using the data analysis model. The remaining memory resource size of the current core subnode is compared. If the remaining memory resource size of the current core subnode is greater than the memory resource size required to process the most recent set of data, the current core subnode directly processes it. Otherwise, the idle memory resources in the processing node are retrieved and allocated to the current core subnode.
9. A manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 8, Features: The step S3 further comprises the following steps: Step S31: retrieve the historical fault data of the equipment, identify the range of various parameters under the equipment operation state, equipment operation environment data, the location and cause of the fault in the fault data, extract the fault characteristics, and perform weighted fusion of various data of the equipment operation under the current fault state, equipment operation environment data, fault location and fault cause according to the fault characteristics, and construct a knowledge graph of the equipment fault based on the fused fault data; Step S32: retrieve the real-time status data W of the equipment under the running state, and compare it with the system database. If the real-time status data of the equipment is completely consistent with the data in the database, the equipment continues to run. If the real-time status data of the equipment is within the threshold range of the system database, further retrieve the environmental data of the current equipment operation, retrieve the historical environmental data in the database based on the environmental data and the impact on the equipment running state, and give the impact parameter α of the environmental data on the equipment running state data; Step S33: Calculate the equipment operation status data without environmental influence by formula In the formula, D represents the equipment operation status data without environmental influence, W represents the real-time status data of the equipment under the operation status, and α represents the influence parameter of environmental data on the equipment operation status data. The equipment operation status data without environmental influence is obtained by calculation and compared with the database range. If the equipment operation status data at this time is within the threshold range, the equipment is marked as a faulty equipment to be confirmed. Otherwise, the equipment is stopped and a warning is issued through the early warning module to remind the maintenance personnel to perform maintenance.
10. A manufacturing equipment fault diagnosis system based on the Internet of Things according to claim 9, Features: In the step S4, the knowledge graph and the equipment operation status data are retrieved, and the equipment operation status data is compared with the knowledge graph. If the equipment operation status data at this time matches the threshold range in the knowledge graph, it means that the current equipment has a fault, and the current equipment is marked as a faulty equipment. An alarm is issued through the early warning module to remind maintenance personnel to perform repairs. Otherwise, the current equipment is marked as a normal equipment, and the historical operation status data of the equipment is retrieved. An operation status prediction model is constructed based on the historical operation status data. The operation status of the equipment is predicted based on the operation status prediction model, and the equipment code is retrieved to send an alarm to the maintenance personnel through the early warning module to remind the maintenance personnel to perform equipment maintenance.