A cloud-based collaborative manufacturing device health management method

Abstract

The application relates to the technical field of equipment health management, and particularly relates to an equipment health management method based on cloud collaborative manufacturing. The method comprises a data acquisition module, which is arranged on equipment, is used for collecting various types of equipment state data in real time, and uploads the collected equipment state data to a cloud platform server; a data storage module, which is used for distributing each equipment to a corresponding equipment period group of a service stage according to service time length according to pre-stored equipment information, and storing the equipment state data to a state database of the corresponding equipment period group according to associated equipment information; a health analysis module, which is used for performing data mining on the equipment state data of the equipment period groups of different service stages, and respectively identifying the health states of each equipment of the equipment period groups of different stages; and an equipment portrait module, which is used for obtaining elite equipment groups of the equipment period groups of each service stage to perform historical data.

Description

Technical Field

[0001] This invention relates to the field of equipment health management technology, and specifically to an equipment health management method based on cloud collaborative manufacturing. Background Technology

[0002] With the development of modern industry and science and technology, a general trend in the development of modern equipment is towards increasing complexity, intelligence, and automation. Equipment is becoming increasingly valuable, and enterprises are investing more and more. To create maximum economic value, many companies operate equipment at full capacity and continuously, leading to problems such as frequent use, harsh operating conditions, high power consumption, heavy loads, and excessive wear. If timely inspection and appropriate maintenance are not implemented, not only will the lifespan of the equipment be reduced, but it may also affect its normal operation, causing damage and even serious safety accidents. The urgency of ensuring safe and reliable equipment operation is becoming increasingly prominent, and the safety and maintenance of equipment during service are receiving increasing attention.

[0003] Traditional equipment monitoring methods typically use sensors to monitor parameters during equipment operation. This approach has significant limitations, primarily the inability to query and analyze historical data to extract valuable information. Therefore, equipment health monitoring systems have emerged. The development of equipment health monitoring systems has progressed through three stages: stand-alone online monitoring systems, distributed monitoring systems, and remote monitoring systems. Stand-alone online monitoring systems install a dedicated status monitoring system for each piece of equipment. Information transmission and processing within each system is confined to its own internal loop, preventing information sharing between systems. Distributed monitoring systems use local area network (LAN) technology to connect computers at various monitoring points, forming an open system that enables resource sharing, decentralized monitoring, and centralized diagnostics. However, sharing is limited to the enterprise's own LAN and cannot be shared with other enterprises. Internet-based remote monitoring systems utilize internet technology to establish a remote monitoring system. Users can log in via the internet to obtain equipment health status parameters to understand the equipment's current condition. If equipment malfunctions, users can log in to the system and utilize the system's diagnostic center for remote diagnosis. However, due to factors such as the large amount of data collected by many devices and network bandwidth latency, it is impossible to meet the needs of real-time monitoring of the health status of existing complex devices. Summary of the Invention

[0004] The technical problem solved by this invention is to provide a cloud-based collaborative manufacturing-based equipment health management method that can meet the needs of real-time monitoring of the health status of existing complex equipment.

[0005] The basic solution provided by this invention is: a method for equipment health management based on cloud collaborative manufacturing, including a cloud platform server and a data acquisition module, a data storage module, a health analysis module, an equipment profiling module, and a health suggestion module; The data acquisition module is deployed on the device to collect various device status data in real time and upload the collected device status data to the cloud platform server. The data storage module is used to allocate each device to the corresponding service stage device group according to the service duration based on the pre-stored device information, and to store the device status data to the status database of the corresponding device group according to the associated device information; The health analysis module is used to perform data mining on the equipment status data of equipment groups at different service stages, identify the health status of each piece of equipment in different service stages, obtain its production data, and identify the elite equipment groups in each service stage that meet the preset health status and production efficiency of the corresponding equipment group based on the health status and production data of each piece of equipment. The equipment profiling module is used to obtain historical data of elite equipment groups in each service stage. The historical data includes historical equipment status data, historical operation and maintenance data, and historical generation data to obtain equipment profiles of elite equipment groups. The health advice module is used to generate health management advice for each piece of equipment in the previous service phase based on the equipment profile of each equipment group in each service phase and the health status of each piece of equipment in the previous service phase.

[0006] Furthermore, the health analysis module, health evaluation module, production evaluation module, and comprehensive evaluation module are included. The health assessment module is used to identify various equipment status data, including vibration data, temperature data, and noise data, and to obtain the equipment health index based on these data over a period of time.

[0007] in This represents the standard deviation of the status data for the nth type of device. The weight of the nth type of device status data is represented by m, where m represents the number of types of device status data. The production evaluation module is used to analyze and score equipment production efficiency based on production data, including actual output, preset standard output for the current service stage, normal operating time, and total operating time.

[0008] The comprehensive evaluation module is used to obtain a comprehensive score for the equipment based on its health index and production efficiency score.

[0009] in Indicates the weight, when the overall score is... Higher than the preset scoring threshold At that time, it was determined that the equipment was an elite device in the current service phase.

[0010] Furthermore, the health analysis module also includes a data processing module, a cluster analysis module, a scoring module, and a feature recognition module; The data processing module is used to construct equipment health feature vectors for non-elite equipment in various service stages using their equipment status data. And standardize each feature vector; The clustering analysis module is used to perform clustering analysis on the equipment health feature vectors to obtain several equipment anomaly clusters:

[0011] Where k represents the number of clusters. Indicates the j-th cluster. Cluster The centroid vector; The scoring module is used to score the saliency of feature vectors within a cluster.

[0012] in As an influence factor, As a significant factor, As an importance factor;

[0013] in For clusters The number of devices in the middle, This indicates the number of non-elite devices in the device cluster;

[0014] in Cluster Chinese characteristics The average value, This indicates the characteristics of elite equipment within the equipment group during this service phase. The average value, Characteristics of all equipment in the equipment group during this service phase. Standard deviation;

[0015] in Representation of features Pearson correlation coefficient with productivity score; The feature recognition module is used to obtain key anomaly features based on the saliency score within the cluster of each feature vector.

[0016] Furthermore, the device profiling module includes a data collection module, a data feature module, an event feature module, a feature synthesis module, and a profiling generation module; The data set module is used to set up elite equipment sets for elite equipment in service phase s. Where k represents the number of elite devices in this service phase, and a set of device status data is generated based on the historical data of each elite device. Operation and maintenance data set and production data sets ; The feature construction module is used to build features based on the device status data set. and production data sets Constructing numerical features:

[0017] in, This represents the mean, indicating the average operating level. The standard deviation represents operational stability. This indicates an extreme value, representing an extreme operating condition. Indicates a trend, representing the changing trend of the parameter; The event feature module is used to identify events based on the operation and maintenance data set. Build event characteristics, including the failure frequency of various operation and maintenance events. and average repair time , where j represents the number of types of operation and maintenance events; The feature synthesis module is used to aggregate the numerical and event features of all elite devices in the current stage.

[0018] in , representing the average level of the elite group on feature i. , representing the degree of dispersion of the elite group on feature i. , representing the acceptable range of the elite group on feature i;

[0019] in This represents the average event frequency of the elite group. This represents the average processing time of the elite group; The profile generation module is used to concatenate clustered sets into high-dimensional vectors, serving as a baseline for profiles of elite equipment during this service phase. .

[0020] Furthermore, it also includes a data reporting module, which is used to report the quantity change trend of non-elite equipment at each service stage according to a preset period, and to identify the correlation between the change trend of non-elite equipment and the feature adjustment range based on the quantity change trend of non-elite equipment. The data reporting module includes a period setting module, a feature adjustment range acquisition module, a quantity change trend acquisition module, a significance judgment module, and a report output module. The cycle setting module is used to set a preset cycle and periodically obtain the number of non-elite equipment at each service stage from the health analysis module. The number of non-elite equipment at each time point is stored in the time series database, and the records include timestamp, service stage identifier, and number of non-elite equipment. The feature adjustment amplitude acquisition module obtains the adjustment amplitude, defined as the difference between the current period's elite device profile vector and the previous period's profile vector, thus obtaining the feature adjustment amplitude. :

[0021] in This represents the elite equipment profile vector at time t. This represents the elite equipment profile vector at time t-1. Represents Euclidean distance. This indicates the range of characteristic adjustments during the service phase s; The quantity change trend acquisition module is used to extract the number of non-elite equipment for several cycles in each service stage s, and fit the quantity change trend T(s) over time through linear regression. The significance assessment module is used to calculate the trend T of the number of non-elite devices and the feature adjustment magnitude. Pearson correlation coefficient ρ:

[0022] according to The significance of the feature adjustment magnitude and the trend of quantity change is judged, and an early warning is issued when it exceeds a preset significance threshold; The report output module is used to generate reports periodically, including historical curves of the number of non-elite equipment at each service stage, trends in the number of non-elite equipment, historical curves of feature adjustment magnitudes, and correlation analysis results.

[0023] Furthermore, it also includes a statistical analysis module, which is used to identify the changing trend of the number of elite equipment as the service stage increases.

[0024] The principles and advantages of this invention are as follows: This invention utilizes a cloud platform server to coordinate multiple functional modules, including a data acquisition module, a data storage module, a health analysis module, an equipment profiling module, and a health recommendation module. Together, they complete the entire management process from data perception to decision support. The data acquisition module is deployed on various equipment terminals to acquire real-time status data such as vibration, temperature, and noise, and uploads it to the cloud platform. The data storage module divides equipment into different stages based on their service life, achieving structured storage and phased management. The health analysis module further analyzes the equipment status data and production data of different stages. Through the comprehensive calculation of health index and production efficiency score, it identifies elite equipment groups in each stage and performs cluster analysis and anomaly feature mining on non-elite equipment. The equipment profiling module constructs statistically representative feature vectors based on the historical status, maintenance, and production data of elite equipment, forming a baseline health profile for that service stage. The health recommendation module uses the current stage profile and the actual status of equipment in the previous stage to generate forward-looking and guiding health management recommendations, thereby achieving early warning and precise intervention in the equipment degradation process.

[0025] Compared to existing technologies, this method achieves clustered, phased, and standardized equipment management. It can dynamically adjust management strategies based on the actual service status of equipment, significantly improving equipment reliability, extending service life, and reducing the risk of unexpected downtime. At the same time, through the collaborative capabilities of the cloud platform, it supports data sharing and comparative analysis among multiple devices, multiple factories, and multiple enterprises, overcoming the shortcomings of traditional stand-alone or local area network systems in terms of data integration and diagnostic depth. It is particularly suitable for high-value, high-complexity, and continuously operating industrial equipment groups. In addition, this method, through the integrated evaluation of quantitative health indicators and production efficiency, not only focuses on the status of the equipment itself but also takes into account its actual output efficiency, making management recommendations more practical and economical, ultimately achieving the goal of improving the overall operating efficiency and safety level of the manufacturing system.

[0026] Simultaneously, by periodically collecting and comparing the quantity information of non-elite equipment at each service stage, a dynamic trend change map is constructed. This map is then further correlated with the magnitude of adjustments to equipment profile features to reveal the inherent laws governing the evolution of the equipment group's health status. The core principle of this module is to shift equipment management from static, isolated assessment to dynamic, correlated, and systematic monitoring. It goes beyond simply counting the number of non-elite equipment; it aims to explore the interaction between the equipment health status reflected in quantity fluctuations and the management system's own adjustment behavior. Specifically, the module periodically obtains the list and quantity of non-elite equipment at each stage from the health analysis module, forming time-series data, and uses trend fitting algorithms to calculate the direction and intensity of its changes. Simultaneously, it captures the iterative update records of the elite equipment profile baseline from the equipment profile module, quantifying the adjustment magnitude of the feature profile within each period through vector distance calculations and other methods. Finally, through a correlation analysis model, the module matches the quantity trend of non-elite equipment with the adjustment magnitude of profile features to identify whether there is a significant statistical correlation between the two, such as whether the increase in the number of non-elite equipment is synchronous with the tightening of profile feature thresholds.

[0027] Traditional management methods often focus on judging the status of individual devices or at a single point in time, lacking a macro-level review and feedback on the effectiveness of management strategies themselves. This module, by continuously tracking the group-wide changes in non-elite devices, can provide early warnings of potential systemic degradation risks or management strategy failures for the entire device group. More importantly, by correlating this trend with the adjustment range of elite device profiles, the system can assess whether the current management standards are appropriate and whether the evolution of profile characteristics is reasonable. For example, if a significant increase in the number of non-elite devices is accompanied by a drastic adjustment of profile characteristic benchmarks, it may indicate that the management standards are too stringent or that the profile construction fails to accurately reflect the normal degradation process of the devices, thus prompting managers to recalibrate model parameters or review data quality. This data-driven feedback mechanism transforms the device health management system from a static, one-way evaluation system into an intelligent system that can continuously adapt and learn as the actual operating status of the devices and data accumulation increases. This greatly improves the accuracy, foresight, and robustness of management, ultimately providing a powerful macro-management tool for maintaining the long-term stable and efficient operation of the device group and optimizing the allocation of maintenance resources. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of an embodiment of the present invention. Detailed Implementation

[0029] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: A cloud-based collaborative manufacturing-based equipment health management method includes a cloud platform server and a data acquisition module, a data storage module, a health analysis module, an equipment profiling module, and a health recommendation module; The data acquisition module is deployed on the device to collect various device status data in real time and upload the collected device status data to the cloud platform server. The data storage module is used to allocate each device to the corresponding service stage device group according to the service duration based on the pre-stored device information, and to store the device status data to the status database of the corresponding device group according to the associated device information; The health analysis module is used to perform data mining on the equipment status data of equipment groups at different service stages, identify the health status of each piece of equipment in different service stages, obtain its production data, and identify the elite equipment groups in each service stage that meet the preset health status and production efficiency of the corresponding equipment group based on the health status and production data of each piece of equipment. The equipment profiling module is used to obtain historical data of elite equipment groups in each service stage. The historical data includes historical equipment status data, historical operation and maintenance data, and historical generation data to obtain equipment profiles of elite equipment groups. The health advice module is used to generate health management advice for each piece of equipment in the previous service phase based on the equipment profile of each service phase group and the health status of each piece of equipment in the previous service phase.

[0030] The health analysis module, health evaluation module, production evaluation module, and comprehensive evaluation module are described. The health assessment module is used to identify various equipment status data, including vibration data, temperature data, and noise data, and to obtain the equipment health index based on these data over a period of time.

[0031] in This represents the standard deviation of the status data for the nth type of device. The weight of the nth type of device status data is represented by m, where m represents the number of types of device status data. The production evaluation module is used to analyze and score equipment production efficiency based on production data, including actual output, preset standard output for the current service stage, normal operating time, and total operating time.

[0032] The comprehensive evaluation module is used to obtain a comprehensive score for the equipment based on its health index and production efficiency score.

[0033] in Indicates the weight, when the overall score is... Higher than the preset scoring threshold At that time, it was determined that the equipment was an elite device in the current service phase.

[0034] The health analysis module also includes a data processing module, a cluster analysis module, a scoring module, and a feature recognition module; The data processing module is used to construct equipment health feature vectors for non-elite equipment in various service stages using their equipment status data. And standardize each feature vector; The clustering analysis module is used to perform clustering analysis on the equipment health feature vectors to obtain several equipment anomaly clusters:

[0035] Where k represents the number of clusters. Indicates the j-th cluster. Cluster The centroid vector; The scoring module is used to score the saliency of feature vectors within a cluster.

[0036] in As an influence factor, As a significant factor, As an importance factor;

[0037] in For clusters The number of devices in the middle, This indicates the number of non-elite devices in the device cluster;

[0038] in Cluster Chinese characteristics The average value, This indicates the characteristics of elite equipment within the equipment group during this service phase. The average value, Characteristics of all equipment in the equipment group during this service phase. Standard deviation;

[0039] in Representation of features Pearson correlation coefficient with productivity score; The feature recognition module is used to obtain key anomaly features based on the saliency score within the cluster of each feature vector.

[0040] The device profiling module includes a data collection module, a data feature module, an event feature module, a feature synthesis module, and a profiling generation module; The data set module is used to set up elite equipment sets for elite equipment in service phase s. Where k represents the number of elite devices in this service phase, and a set of device status data is generated based on the historical data of each elite device. Operation and maintenance data set and production data sets ; The feature construction module is used to build features based on the device status data set. and production data sets Constructing numerical features:

[0041] in, This represents the mean, indicating the average operating level. The standard deviation represents operational stability. This indicates an extreme value, representing an extreme operating condition. Indicates a trend, representing the changing trend of the parameter; The event feature module is used to identify events based on the operation and maintenance data set. Build event characteristics, including the failure frequency of various operation and maintenance events. and average repair time , where j represents the number of types of operation and maintenance events; The feature synthesis module is used to aggregate the numerical and event features of all elite devices in the current stage.

[0042] in , representing the average level of the elite group on feature i. , representing the degree of dispersion of the elite group on feature i. , representing the acceptable range of the elite group on feature i;

[0043] in This represents the average event frequency of the elite group. This represents the average processing time of the elite group; The profile generation module is used to concatenate clustered sets into high-dimensional vectors, serving as a baseline for profiles of elite equipment during this service phase. .

[0044] It also includes a data reporting module, which is used to report the quantity change trend of non-elite equipment at each service stage according to a preset period, and to identify the correlation between the change trend of non-elite equipment and the feature adjustment range based on the quantity change trend of non-elite equipment. The data reporting module includes a period setting module, a feature adjustment range acquisition module, a quantity change trend acquisition module, a significance judgment module, and a report output module. The cycle setting module is used to set a preset cycle and periodically obtain the number of non-elite equipment at each service stage from the health analysis module. The number of non-elite equipment at each time point is stored in the time series database, and the records include timestamp, service stage identifier, and number of non-elite equipment. The feature adjustment amplitude acquisition module obtains the adjustment amplitude, defined as the difference between the current period's elite device profile vector and the previous period's profile vector, thus obtaining the feature adjustment amplitude. :

[0045] in This represents the elite equipment profile vector at time t. This represents the elite equipment profile vector at time t-1. Represents Euclidean distance. This indicates the range of characteristic adjustments during the service phase s; The quantity change trend acquisition module is used to extract the number of non-elite equipment for several cycles in each service stage s, and fit the quantity change trend T(s) over time through linear regression. The significance assessment module is used to calculate the trend T of the number of non-elite devices and the feature adjustment magnitude. Pearson correlation coefficient ρ:

[0046] according to The significance of the feature adjustment magnitude and the trend of quantity change is judged, and an early warning is issued when it exceeds a preset significance threshold; The report output module is used to generate reports periodically, including historical curves of the number of non-elite equipment at each service stage, trends in the number of non-elite equipment, historical curves of feature adjustment magnitudes, and correlation analysis results.

[0047] It also includes a statistical analysis module, which is used to identify the changing trend of the number of elite equipment as the service stage increases.

[0048] This invention utilizes a cloud platform server to coordinate multiple functional modules, including a data acquisition module, a data storage module, a health analysis module, an equipment profiling module, and a health recommendation module. Together, they complete the entire management process from data perception to decision support. The data acquisition module is deployed on various equipment terminals to acquire real-time status data such as vibration, temperature, and noise, and uploads it to the cloud platform. The data storage module divides equipment into different stages based on their service life, achieving structured storage and phased management. The health analysis module further analyzes the equipment status data and production data of different stages. Through the comprehensive calculation of health index and production efficiency score, it identifies elite equipment groups in each stage and performs cluster analysis and anomaly feature mining on non-elite equipment. The equipment profiling module constructs statistically representative feature vectors based on the historical status, maintenance, and production data of elite equipment, forming a baseline health profile for that service stage. The health recommendation module uses the current stage profile and the actual status of equipment in the previous stage to generate forward-looking and guiding health management recommendations, thereby achieving early warning and precise intervention in the equipment degradation process.

[0049] Compared to existing technologies, this method achieves clustered, phased, and standardized equipment management. It can dynamically adjust management strategies based on the actual service status of equipment, significantly improving equipment reliability, extending service life, and reducing the risk of unexpected downtime. At the same time, through the collaborative capabilities of the cloud platform, it supports data sharing and comparative analysis among multiple devices, multiple factories, and multiple enterprises, overcoming the shortcomings of traditional stand-alone or local area network systems in terms of data integration and diagnostic depth. It is particularly suitable for high-value, high-complexity, and continuously operating industrial equipment groups. In addition, this method, through the integrated evaluation of quantitative health indicators and production efficiency, not only focuses on the status of the equipment itself but also takes into account its actual output efficiency, making management recommendations more practical and economical, ultimately achieving the goal of improving the overall operating efficiency and safety level of the manufacturing system.

[0050] Simultaneously, by periodically collecting and comparing the quantity information of non-elite equipment at each service stage, a dynamic trend change map is constructed. This map is then further correlated with the magnitude of adjustments to equipment profile features to reveal the inherent laws governing the evolution of the equipment group's health status. The core principle of this module is to shift equipment management from static, isolated assessment to dynamic, correlated, and systematic monitoring. It goes beyond simply counting the number of non-elite equipment; it aims to explore the interaction between the equipment health status reflected in quantity fluctuations and the management system's own adjustment behavior. Specifically, the module periodically obtains the list and quantity of non-elite equipment at each stage from the health analysis module, forming time-series data, and uses trend fitting algorithms to calculate the direction and intensity of its changes. Simultaneously, it captures the iterative update records of the elite equipment profile baseline from the equipment profile module, quantifying the adjustment magnitude of the feature profile within each period through vector distance calculations and other methods. Finally, through a correlation analysis model, the module matches the quantity trend of non-elite equipment with the adjustment magnitude of profile features to identify whether there is a significant statistical correlation between the two, such as whether the increase in the number of non-elite equipment is synchronous with the tightening of profile feature thresholds.

[0051] Traditional management methods often focus on judging the status of individual devices or at a single point in time, lacking a macro-level review and feedback on the effectiveness of management strategies themselves. This module, by continuously tracking the group-wide changes in non-elite devices, can provide early warnings of potential systemic degradation risks or management strategy failures for the entire device group. More importantly, by correlating this trend with the adjustment range of elite device profiles, the system can assess whether the current management standards are appropriate and whether the evolution of profile characteristics is reasonable. For example, if a significant increase in the number of non-elite devices is accompanied by a drastic adjustment of profile characteristic benchmarks, it may indicate that the management standards are too stringent or that the profile construction fails to accurately reflect the normal degradation process of the devices, thus prompting managers to recalibrate model parameters or review data quality. This data-driven feedback mechanism transforms the device health management system from a static, one-way evaluation system into an intelligent system that can continuously adapt and learn as the actual operating status of the devices and data accumulation increases. This greatly improves the accuracy, foresight, and robustness of management, ultimately providing a powerful macro-management tool for maintaining the long-term stable and efficient operation of the device group and optimizing the allocation of maintenance resources.

[0052] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for equipment health management based on cloud-based collaborative manufacturing, characterized in that: It includes a cloud platform server and data acquisition module, a data storage module, a health analysis module, a device profiling module, and a health advice module; The data acquisition module is deployed on the device to collect various device status data in real time and upload the collected device status data to the cloud platform server. The data storage module is used to allocate each device to the corresponding service stage device group according to the service duration based on the pre-stored device information, and to store the device status data to the status database of the corresponding device group according to the associated device information; The health analysis module is used to perform data mining on the equipment status data of equipment groups at different service stages, identify the health status of each piece of equipment in different service stages, obtain its production data, and identify the elite equipment groups in each service stage that meet the preset health status and production efficiency of the corresponding equipment group based on the health status and production data of each piece of equipment. The equipment profiling module is used to obtain historical data of elite equipment groups in each service stage. The historical data includes historical equipment status data, historical operation and maintenance data, and historical generation data to obtain equipment profiles of elite equipment groups. The health advice module is used to generate health management advice for each piece of equipment in the previous service phase based on the equipment profile of each service phase group and the health status of each piece of equipment in the previous service phase.

2. The equipment health management method based on cloud collaborative manufacturing according to claim 1, characterized in that: The health analysis module, health evaluation module, production evaluation module, and comprehensive evaluation module are described. The health assessment module is used to identify various equipment status data, including vibration data, temperature data, and noise data, and to obtain the equipment health index based on these data over a period of time. in This represents the standard deviation of the status data for the nth type of device. The weight of the nth type of device status data is represented by m, where m represents the number of types of device status data. The production evaluation module is used to analyze and score equipment production efficiency based on production data, including actual output, preset standard output for the current service stage, normal operating time, and total operating time. The comprehensive evaluation module is used to obtain a comprehensive score for the equipment based on its health index and production efficiency score. in Indicates the weight, when the overall score is... Higher than the preset scoring threshold At that time, it was determined that the equipment was an elite device in the current service phase.

3. The equipment health management method based on cloud collaborative manufacturing according to claim 2, characterized in that: The health analysis module also includes a data processing module, a cluster analysis module, a scoring module, and a feature recognition module; The data processing module is used to construct equipment health feature vectors for non-elite equipment in various service stages using their equipment status data. ,in Let n represent the feature vector of the nth non-elite device, and then standardize each feature vector. The clustering analysis module is used to perform clustering analysis on the equipment health feature vectors to obtain several equipment anomaly clusters: Where k represents the number of clusters. Indicates the j-th cluster. Cluster The centroid vector; The scoring module is used to score the saliency of feature vectors within a cluster. in As an influence factor, As a significant factor, As an importance factor; in For clusters The number of devices in the middle, This indicates the number of non-elite devices in the device cluster; in Cluster Chinese characteristics The average value, This indicates the characteristics of elite equipment within the equipment group during this service phase. The average value, Characteristics of all equipment in the equipment group during this service phase. Standard deviation; in Representation of features Pearson correlation coefficient with productivity score; The feature recognition module is used to obtain key anomaly features based on the saliency score within the cluster of each feature vector.

4. The equipment health management method based on cloud collaborative manufacturing according to claim 3, characterized in that: The device profiling module includes a data collection module, a data feature module, an event feature module, a feature synthesis module, and a profiling generation module; The data set module is used to set up elite equipment sets for elite equipment in service phase s. Where k represents the number of elite devices in this service phase, and a set of device status data is generated based on the historical data of each elite device. Operation and maintenance data set and production data sets ; The feature construction module is used to build features based on the device status data set. and production data sets Constructing numerical features: in, This represents the mean, indicating the average operating level. The standard deviation represents operational stability. This indicates an extreme value, representing an extreme operating condition. Indicates a trend, representing the changing trend of the parameter; The event feature module is used to identify events based on the operation and maintenance data set. Build event characteristics, including the failure frequency of various operation and maintenance events. and average repair time , where j represents the number of types of operation and maintenance events; The feature synthesis module is used to aggregate the numerical and event features of all elite devices in the current stage. in , representing the average level of the elite group on feature i. , representing the degree of dispersion of the elite group on feature i. , representing the acceptable range of the elite group on feature i; in This represents the average event frequency of the elite group. This represents the average processing time of the elite group; The profile generation module is used to concatenate clustered sets into high-dimensional vectors, serving as a baseline for profiles of elite equipment during this service phase. 。 5. The equipment health management method based on cloud collaborative manufacturing according to claim 4, characterized in that: It also includes a data reporting module, which is used to report the quantity change trend of non-elite equipment at each service stage according to a preset period, and to identify the correlation between the change trend of non-elite equipment and the feature adjustment range based on the quantity change trend of non-elite equipment. The data reporting module includes a period setting module, a feature adjustment range acquisition module, a quantity change trend acquisition module, a significance judgment module, and a report output module. The cycle setting module is used to set a preset cycle and periodically obtain the number of non-elite equipment at each service stage from the health analysis module. The number of non-elite equipment at each time point is stored in the time series database, and the records include timestamp, service stage identifier, and number of non-elite equipment. The feature adjustment amplitude acquisition module obtains the adjustment amplitude, defined as the difference between the current period's elite device profile vector and the previous period's profile vector, thus obtaining the feature adjustment amplitude. : in This represents the elite equipment profile vector at time t. This represents the elite equipment profile vector at time t-1. Represents Euclidean distance. This indicates the range of characteristic adjustments during the service phase s; The quantity change trend acquisition module is used to extract the number of non-elite equipment for several cycles in each service stage s, and fit the quantity change trend T(s) over time through linear regression. The significance assessment module is used to calculate the trend T of the number of non-elite devices and the feature adjustment magnitude. Pearson correlation coefficient ρ: according to The significance of the feature adjustment magnitude and the trend of quantity change is judged, and an early warning is issued when it exceeds a preset significance threshold; The report output module is used to generate reports periodically, including historical curves of the number of non-elite equipment at each service stage, trends in the number of non-elite equipment, historical curves of feature adjustment magnitudes, and correlation analysis results.

6. The equipment health management method based on cloud collaborative manufacturing according to claim 5, characterized in that: It also includes a statistical analysis module, which is used to identify the changing trend of the number of elite equipment as the service stage increases.

Images