A digital operation management system and method

Abstract

The application discloses a kind of digital operation management system and method, it is related to digital operation management technical field, including operation monitoring module, for through network interface and distributed industrial internet of things node communication, production environment parameter and process data are collected, equipment baseline parameter is formed;Knowledge graph engine module is based on equipment baseline parameter, equipment relationship network and process flow mapping are constructed;Predictive maintenance module is used for equipment life assessment and failure early warning according to the relationship data of the knowledge graph engine module;Decision support module is based on equipment life assessment and failure early warning, combines historical decision effect, generates resource scheduling scheme, and is transmitted to digital twin display module;Digital twin display module is used for presenting factory real-time running state using three-dimensional visualization technology.The application improves the data processing efficiency, resource utilization and flexibility in production process, realizes the global monitoring and intelligent optimization of production process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital operation management, in particular to a digital operation management system and method. BACKGROUND

[0002] In the traditional industrial production environment, passive maintenance strategies are mostly adopted for equipment management, i.e. the fault-repair mode, lacking systematic management of the whole life cycle of equipment. In recent years, the fusion application of industrial Internet of Things, big data analysis and artificial intelligence technology has brought revolutionary changes to manufacturing industry, making data-driven intelligent decision-making possible. However, the existing industrial management systems mostly present fragmented characteristics, and the data flow between subsystems is blocked, leading to the widespread existence of information islands. At the same time, although the traditional monitoring system can realize basic parameter collection and display, it lacks deep understanding of complex process flow and system-level correlation analysis capability, and cannot build a dynamic knowledge network reflecting the interdependence between equipment, which seriously restricts the realization of predictive maintenance and intelligent decision support function. In addition, the existing systems mostly adopt centralized architecture in data processing, leading to insufficient real-time performance, difficulty in coping with emergencies in the production environment, and lack of edge computing capability, which cannot realize the localized processing and caching of key data.

[0003] In the prior art, although some advanced systems have begun to try to introduce digital twin technology for visual display, the application depth is limited, mostly staying at the level of static three-dimensional models, lacking dynamic mapping and interactive functions with actual process flow. At the same time, in terms of decision support, the existing systems mostly rely on preset rules or simple threshold judgment, and cannot perform global optimization according to the equipment relationship network, leading to low efficiency of resource scheduling. Especially in complex production environments, due to the lack of accurate modeling of the causal relationship between equipment, the existing systems are difficult to accurately identify the root cause of failure and predict the risk of cascading failure, causing unreasonable allocation of maintenance resources and decline of production efficiency. On the other hand, the existing systems generally lack a unified knowledge graph engine as the core architecture, which cannot realize the deep integration and intelligent analysis of equipment data, process flow and maintenance decision, making it difficult for the system to adapt to the dynamic changes of the production environment and the continuous optimization of process requirements.

[0004] In summary, the existing industrial operation management technology has problems such as information islands, lack of system-level correlation analysis, insufficient predictive maintenance capability, simple decision support, and non-optimal resource scheduling. The present application proposes a digital operation management system and method, which realizes accurate mapping of the relationship network between equipment and process flow, solves the problems of real-time data processing and abnormal judgment, and realizes intuitive visualization of the production environment through digital twin technology. SUMMARY

[0005] In view of the problems of inaccurate equipment health prediction, insufficient analysis of inter-equipment dependency relationship and lack of flexibility in resource scheduling optimization in existing digital operation management systems, the present application is proposed.

[0006] Therefore, the problem to be solved by the present application is how to improve the accuracy of equipment health prediction, optimize the analysis of inter-equipment dependency relationship and realize more flexible and refined management in resource scheduling by introducing a knowledge graph engine, a predictive maintenance module and digital twin display technology, thereby improving production efficiency, reducing failure rate and optimizing resource allocation.

[0007] To solve the above technical problems, the present application provides the following technical solutions:

[0008] In a first aspect, the present application provides a digital operation management system, which comprises an operation monitoring module for communicating with distributed industrial Internet of Things nodes through a network interface and collecting production environment parameters and process data to form equipment baseline parameters; a knowledge graph engine module for constructing an equipment relationship network and a process flow mapping based on the equipment baseline parameters; a predictive maintenance module for performing equipment life assessment and failure warning based on the relationship data of the knowledge graph engine module; a decision support module for generating a resource scheduling scheme based on the equipment life assessment and failure warning and combining historical decision effects, and transmitting the resource scheduling scheme to a digital twin display module; and the digital twin display module for presenting a real-time running state of a factory using three-dimensional visualization technology and supporting virtual roaming and multi-angle viewing of a production line state.

[0009] As a preferred scheme of the digital operation management system of the present application, the knowledge graph engine module is connected with the operation monitoring module, the predictive maintenance module and the digital twin display module respectively; the predictive maintenance module is connected with the decision support module; the decision support module is connected with the digital twin display module; an edge computing unit and a local cache module are arranged on the distributed industrial Internet of Things nodes; the edge computing unit is used for performing data screening and abnormality judgment; and the local cache module is used for storing key data when the network is interrupted.

[0010] As a preferred scheme of the digital operation management system of the present application, the operation monitoring module comprises a multi-strategy scheduler; the multi-strategy scheduler is used for dynamically allocating computing resources according to production task priorities and resource utilization rates, and triggering a resource expansion mechanism in a high-load condition.

[0011] In a second aspect, the embodiments of the present application provide a digital operation management method, which comprises: establishing a device digital archive by the operation monitoring module, collecting device operation data collected by distributed industrial Internet of Things nodes to form device baseline parameters; constructing a process flow knowledge graph based on the device baseline parameters, and mapping the dependency relationship between devices and the material flow path through the knowledge graph engine module; performing real-time state monitoring through the predictive maintenance module, comparing the current operation parameters with the device health index of the device baseline parameters, and generating a predictive maintenance plan; based on the predictive maintenance plan, generating a resource scheduling scheme through the decision support module, and balancing production efficiency and device life through a multi-strategy scheduler to optimize the resource scheduling scheme.

[0012] As a preferred scheme of the digital operation management method, the method for constructing the process flow knowledge graph comprises: extracting a feature vector of the device state based on dynamic operation parameters in the device baseline parameters, wherein the feature vector is processed by principal component analysis dimension reduction; performing time series correlation analysis on device operation history data based on the feature vector using a Granger causality test method to identify the causal chain between devices; establishing a relationship matrix between devices according to the interaction data between devices in the device baseline parameters and the causal chain, wherein the relationship matrix represents the transmission direction and strength of material flow, energy flow and information flow between devices; constructing a directed edge set using the relationship matrix, assigning an edge weight value to form an initial graph structure, wherein the edge weight value is calculated according to the importance of material flow, energy flow and information flow; performing module division on the initial graph structure using a community detection algorithm to identify a subsystem group of devices, and adding semantic labels and process stage attributes to the subsystem group in combination with process flow specification documents; integrating the subsystem group, semantic labels and process stage attributes to form a hierarchical process flow knowledge graph.

[0013] As a preferred scheme of the digital operation management method, when the process flow knowledge graph is constructed, the device health index S(t) is calculated in combination with the functional characteristics of the subsystem group and the edge weight value of the relationship matrix, and the specific formula is as follows:

[0014]

[0015] wherein S(t) is the device health index at time t, α is the overall system calibration coefficient, γ i is the importance coefficient of the i-th device baseline parameter calculated based on the knowledge graph relationship matrix, λ i (t) is the time decay function of the i-th device baseline parameter, V i (t) is the standardized value of the i-th device baseline parameter at time t, and μ iis the historical average of the baseline parameter of the ith device, β is the system degradation rate coefficient, n is the total number of device baseline parameters, and t is a time variable.

[0016] As a preferred solution of the digital operation management method, the generation method of the predictive maintenance plan is that when a warning condition of the equipment health index S(t) is triggered, a maintenance resource scheduling scheme is evaluated through a resource coordination coefficient R, wherein the resource coordination coefficient R is calculated through equipment importance and failure probability; if the equipment health index S(t) satisfies a first condition and the resource coordination coefficient R≤0.3, an online maintenance mode is adopted, production is not interrupted, equipment operation data are collected through the predictive maintenance module, and a green identification is displayed in the digital twin display module; if the equipment health index S(t) satisfies a second condition and 0.3<resource coordination coefficient R≤0.7, an early warning state is entered, a yellow identification is flickered in the digital twin display module to prompt, scheduled planned shutdown maintenance is arranged, and a real-time parameter analysis is started by the edge computing unit; if the equipment health index S(t) satisfies a third condition or the resource coordination coefficient R>0.7, an emergency shutdown program is executed and a standby device is started, and a red identification is flickered in the digital twin display module; and if the maintenance count of a certain device is greater than or equal to a preset maintenance device count and the equipment health index S(t) continues to trigger a warning after maintenance, a device update evaluation process is started.

[0017] As a preferred solution of the digital operation management method, the optimization method of the resource scheduling scheme is that based on process stage attributes of a subsystem group, a maintenance resource demand prediction and a maintenance strategy type are generated through a multi-strategy scheduler; based on the maintenance resource demand prediction and the maintenance strategy type, maintenance tasks are classified and a corresponding resource configuration scheme is established; and when resource competition occurs, based on a hierarchical structure of the process flow knowledge graph, a resource scheduling scheme is dynamically optimized in combination with a production task priority.

[0018] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory and a processor, and the memory stores a computer program, wherein the computer program instructions are executed by the processor to realize the steps of the digital operation management system according to the first aspect of the present application.

[0019] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program instructions are executed by the processor to realize the steps of the digital operation management system according to the first aspect of the present application.

[0020] The present application has the beneficial effects that: through integrating the operation monitoring module, the knowledge graph engine module, the predictive maintenance module, the decision support module and the digital twin display module, the real-time monitoring of the equipment state, the fault early warning and the intelligent resource scheduling are realized; through collecting the production data and constructing the equipment baseline parameters, the system can accurately evaluate the equipment health state, predict the fault and optimize the maintenance plan; meanwhile, combined with the process flow knowledge graph, the system dynamically adjusts the resource allocation, improves the production efficiency and reduces the downtime; the digital twin display provides intuitive real-time state feedback, helps the managers to quickly make decisions and improves the operation reliability and flexibility of the production line. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0022] Fig. 1 It is a system framework diagram of the digital operation management system of embodiment 1.

[0023] Fig. 2 It is an operation monitoring module architecture diagram of the digital operation management system of embodiment 1.

[0024] Fig. 3 It is a flow chart of the digital operation management method of embodiment 2. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0026] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0027] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0028] Embodiment 1

[0029] Reference Figs. 1-2For the first embodiment of the present application, the embodiment provides a digital operation management system, comprising an operation monitoring module, a knowledge graph engine module, a predictive maintenance module, a decision support module and a digital twin display module.

[0030] Specifically, the operation monitoring module is configured to communicate with distributed industrial Internet of Things nodes through a network interface, collect production environment parameters and process data, and form device baseline parameters; the knowledge graph engine module is configured to construct a device relationship network and a process flow mapping based on the device baseline parameters; the predictive maintenance module is configured to perform device life assessment and fault warning based on the relationship data of the knowledge graph engine module; the decision support module is configured to generate a resource scheduling scheme based on the device life assessment and the fault warning, and transmit the resource scheduling scheme to the digital twin display module; and the digital twin display module is configured to present a real-time running state of a factory using three-dimensional visualization technology, and support virtual roaming and multi-angle viewing of a production line state.

[0031] Further, the knowledge graph engine module is connected with the operation monitoring module, the predictive maintenance module and the digital twin display module respectively; the predictive maintenance module is connected with the decision support module; and the decision support module is connected with the digital twin display module.

[0032] Still further, an edge computing unit and a local cache module are arranged on the distributed industrial Internet of Things nodes; the edge computing unit is configured to perform data filtering and abnormality judgment; and the local cache module is configured to store key data when the network is interrupted.

[0033] Specifically, the operation monitoring module comprises a multi-strategy scheduler; the multi-strategy scheduler is configured to dynamically allocate computing resources according to production task priorities and resource utilization rates, and trigger a resource expansion mechanism in a high-load condition.

[0034] Embodiment 2

[0035] Reference Fig. 3 For the second embodiment of the present application, the embodiment further provides a digital operation management method, comprising:

[0036] S1: establishing a device digital archive by the operation monitoring module, collecting device running data collected by the distributed industrial Internet of Things nodes, and forming device baseline parameters.

[0037] Specifically, the establishment process of the device digital archive is as follows: collecting device basic information, and using a data template to structure the device basic information according to the ISO 14224 standard for storage, so as to ensure the standardization and traceability of the data; the device basic information includes the model specification, manufacturer information, installation date and maintenance record of the device.

[0038] Further, according to the importance of the device and the monitoring requirements, the Internet of Things nodes are deployed, and a hierarchical deployment strategy is adopted; for key devices, high-performance edge computing nodes are configured, and the sampling frequency can reach milliseconds; for auxiliary devices, standard nodes are used, and the sampling frequency is set to seconds; each node is equipped with a data preprocessing module to perform real-time signal filtering, anomaly detection and data compression, effectively reducing data transmission load.

[0039] Further, industrial-grade sensor networks are used to collect device operation data, and protocol conversion gateways are used to realize unified access of data; based on the device operation data, a dynamic adaptive algorithm is used to form device baseline parameters; at the same time, a hierarchical caching strategy is implemented during data collection, and a local cache pool is set at the edge node, which can ensure the continuity and integrity of data when the network fluctuates.

[0040] S2: Based on the device baseline parameters, a process flow knowledge graph is constructed, and a knowledge graph engine module is used to map the dependency relationship between devices and the material flow path.

[0041] Specifically, the construction method of the process flow knowledge graph is to extract the feature vector of the device state based on the dynamic operation parameters in the device baseline parameters, wherein the feature vector is processed by principal component analysis for dimension reduction.

[0042] Further, based on the feature vector, a Granger causality test method is used to analyze the time series correlation of the device operation history data, and the causal chain between devices is identified; according to the interaction data between devices in the device baseline parameters and the causal chain, a relationship matrix between devices is established, wherein the relationship matrix represents the transmission direction and strength of material flow, energy flow and information flow between devices.

[0043] It should be noted that each directed edge represents a specific type of relationship from an upstream device to a downstream device; a material transfer specification, energy consumption and quality influence coefficient are added to each relationship edge in the directed edge set; the material transfer specification records the material type, flow range and ideal flow value; the energy consumption represents the energy conversion efficiency during material transfer; and the quality influence coefficient quantifies the influence degree of upstream device state change on downstream product quality.

[0044] Further, the relationship matrix is used to construct a directed edge set, assign edge weight values, and form an initial graph structure, wherein the edge weight values are calculated according to the importance of material flow, energy flow and information flow.

[0045] Specifically, a community detection algorithm is used to divide the initial graph structure into modules, identify the subsystem groups of devices, and add semantic labels and process stage attributes to the subsystem groups in combination with process flow specification documents.

[0046] Further, the subsystem group, semantic label and process stage attribute are integrated to form a hierarchical process flow knowledge graph.

[0047] Further, when the process flow knowledge graph is constructed, the device health index S(t) is calculated in combination with the functional characteristics of the subsystem group and the edge weight value of the relationship matrix, and the specific formula is as follows:

[0048]

[0049] Wherein, S(t) is the device health index at time t, a is the overall calibration coefficient of the system, γ i is the importance coefficient of the i th device baseline parameter based on the knowledge graph relationship matrix, λ i (t) is the time decay function of the i th device baseline parameter, V i (t) is the standardized value of the i th device baseline parameter at time t, μ i is the historical mean value of the i th device baseline parameter, β is the system degradation rate coefficient, n is the total number of device baseline parameters, and t is the time variable.

[0050] S3: Real-time state monitoring is performed through the predictive maintenance module, the current operating parameters are compared with the device health index of the device baseline parameters, and a predictive maintenance plan is generated.

[0051] Specifically, the generation method of the predictive maintenance plan is that when the early warning condition of the device health index S(t) is triggered, the maintenance resource scheduling scheme is evaluated through the resource coordination coefficient R, wherein the resource coordination coefficient R is calculated through the device importance and failure probability.

[0052] Further, if the device health index S(t) satisfies the first condition and the resource coordination coefficient R≤0.3, the online maintenance mode is adopted, the production is not interrupted, the device operation data is collected through the predictive maintenance module, and the green identification is displayed in the digital twin display module; if the device health index S(t) satisfies the second condition and 0.3<resource coordination coefficient R≤0.7, the warning state is entered, the yellow identification is flickered in the digital twin display module, the planned shutdown maintenance is arranged, and the edge computing unit is started for real-time parameter analysis; if the device health index S(t) satisfies the third condition or the resource coordination coefficient R>0.7, the emergency shutdown program is executed and the standby device is started, and the red identification is flickered in the digital twin display module.

[0053] It should be noted that the first condition: the equipment health index S(t) is in a slight deviation state, i.e. 0.85≤ equipment health index S(t) < 0.95; the specific performance is that some monitoring parameters of the equipment begin to deviate from the baseline value, but the equipment health index amplitude is small, and there is no rapid deterioration trend; the second condition: the equipment health index S(t) is in a moderate early warning state, i.e. 0.70≤ equipment health index S(t) < 0.85; the specific performance is that multiple key monitoring parameters appear abnormal at the same time, or a single important parameter continuously deviates from the baseline value, and shows a gradual deterioration trend; the third condition: the equipment health index S(t) is in a serious early warning state, i.e. the equipment health index S(t) < 0.70; the specific performance is that the core parameter seriously deviates from the baseline value, or the coordinated deterioration phenomenon of multiple parameters appears.

[0054] Further, if the maintenance count of a certain equipment is greater than or equal to the preset maintenance equipment count and the equipment health index S(t) continues to trigger the early warning after maintenance, the equipment update evaluation process is started.

[0055] S4: Based on the predictive maintenance plan, the resource scheduling scheme is generated through the decision support module, and the production efficiency and equipment life are balanced by using the multi-strategy scheduler to optimize the resource scheduling scheme.

[0056] Specifically, the optimization method of the resource scheduling scheme is to generate maintenance resource demand prediction and maintenance strategy type through the multi-strategy scheduler based on the process phase attribute of the subsystem group; according to the maintenance resource demand prediction and the maintenance strategy type, the maintenance task is classified and the corresponding resource configuration scheme is established.

[0057] Further, when resource competition occurs, the resource scheduling scheme is dynamically optimized based on the hierarchical structure of the process flow knowledge graph and in combination with the production task priority.

[0058] The embodiment also provides a computer device suitable for the case of the digital operation management system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the digital operation management system proposed in the above embodiment.

[0059] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved by WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0060] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the following steps: an operation monitoring module, configured to communicate with distributed industrial Internet of Things nodes through a network interface, collect production environment parameters and process data, and form device baseline parameters; a knowledge graph engine module, configured to construct a device relationship network and a process flow mapping based on the device baseline parameters; a predictive maintenance module, configured to perform device life evaluation and fault early warning according to relationship data of the knowledge graph engine module; a decision support module, configured to generate a resource scheduling scheme based on the device life evaluation and the fault early warning, in combination with historical decision effects, and transmit the resource scheduling scheme to a digital twin display module; and the digital twin display module, configured to present a real-time running state of a factory by using three-dimensional visualization technology, and support virtual roaming and multi-angle viewing of a production line state.

[0061] To sum up, the present application integrates the operation monitoring module, the knowledge graph engine module, the predictive maintenance module, the decision support module and the digital twin display module, realizes real-time monitoring of device states, fault early warning and intelligent resource scheduling, collects production data and constructs device baseline parameters, so that the system can accurately evaluate the health state of the device, predict faults and optimize maintenance plans, dynamically adjusts resource allocation in combination with the process flow knowledge graph, improves production efficiency and reduces downtime, and the digital twin display provides intuitive real-time state feedback, helps managers make decisions quickly, and improves the running reliability and flexibility of the production line.

[0062] Embodiment 3

[0063] Referring to Table 1, a third embodiment of the present application is provided, which provides a digital operation management system. In order to verify the beneficial effects of the present application, economic benefit calculation and simulation experiments are used for scientific demonstration.

[0064] Specifically, industrial IoT nodes with edge computing capabilities are deployed on each critical equipment, each equipped with an Intel Core i5 processor and 32 GB of local storage for real-time data processing and temporary storage. The operations monitoring module establishes a secure channel with these nodes through industrial Ethernet, collecting 28 key process parameters including equipment vibration, temperature, pressure, and flow, with a sampling frequency of 100 ms. The system uses a hierarchical architecture, with edge nodes performing preliminary data filtering and anomaly detection, and transmitting processed data to the central server.

[0065] Furthermore, the knowledge graph engine module uses a Neo4j graph database to construct a device relationship network, and reduces the original 28-dimensional parameters to 8 main feature vectors through principal component analysis. On this basis, an improved Granger causality test algorithm (confidence threshold set to 0.95) is used to analyze the correlation between devices, and finally a device relationship graph containing 267 nodes and 1,384 edges is constructed. The system uses the Louvain community detection algorithm to divide the devices into 12 functional subsystems.

[0066] Further, the predictive maintenance module builds a fault prediction model based on a long short-term memory network, which is trained on 3 years of historical data and evaluated using cross-validation methods. The decision support module integrates a resource scheduling algorithm based on reinforcement learning, which can dynamically generate scheduling plans based on device health indices, production task priorities, and maintenance resource availability. In addition, the system also deploys a digital twin visualization platform developed based on the Unity3D engine, supporting millisecond-level state updates and multi-dimensional data display.

[0067] Specifically, during system deployment, six typical operating conditions on the production line were selected for comparative testing: normal production conditions, slight degradation of equipment performance, equipment fluctuation, single equipment failure, multiple equipment coordinated failure, and extreme conditions (such as sudden power failure). 72 hours of continuous operation data were collected under each operating condition, and the system's early warning accuracy, decision response time, and resource scheduling efficiency were compared and analyzed.

[0068] Further, as shown in Table 1, early warning accuracy analysis: the system exhibits extremely high early warning accuracy (99.8%) under normal production conditions, and can still maintain an accuracy of 91.5% under extreme conditions, which benefits from the innovative integration of device relationship network and process mapping by the knowledge graph engine module, which can accurately capture the complex dependency between devices. System response performance analysis: the average response time increases with the complexity of the working condition, from 127ms under normal conditions to 245ms under extreme conditions, but is still much lower than the industry's general response time requirement of 500ms, which is mainly due to the localized processing capability of the edge computing unit and the dynamic resource allocation mechanism of the multi-strategy scheduler.

[0069] Table 1 Test data table

[0070]

[0071] Further, the maintenance cost reduction rate shows a significant upward trend, reaching a maximum of 32.7% under extreme conditions, which indicates that the predictive maintenance module of the present application can accurately predict device failures and significantly reduce unnecessary maintenance costs through optimized resource scheduling schemes. Production efficiency improvement: equipment utilization and production efficiency have been improved by 8.7%-13.2% and 6.9%-10.7%, respectively. This improvement is due to the innovative mechanism of the decision support module to dynamically optimize resource scheduling schemes based on historical decision effects.

[0072] Specifically, energy efficiency optimization: through real-time monitoring and optimization of the production process by digital twin technology, the system has achieved a reduction in energy consumption of 7.2%-14.5%. This effect is most pronounced under extreme conditions, proving that the present application can maintain efficient energy management under complex conditions. Downtime management: the system has significantly reduced unplanned downtime, with a reduction of 12.5%-28.9%. This improvement is mainly due to the accurate assessment of device life and fault warning mechanism of the predictive maintenance module, combined with the optimized scheduling scheme generated by the decision support module, which realizes precise arrangement of maintenance activities.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A digital operation management system, characterized in that: include, The operation monitoring module is used to communicate with distributed industrial IoT nodes through network interfaces to collect production environment parameters and process data, and form equipment baseline parameters. The knowledge graph engine module constructs an equipment relationship network and process flow mapping based on equipment baseline parameters; The predictive maintenance module is used to perform equipment life assessment and fault warning based on the relational data of the knowledge graph engine module; The decision support module, based on equipment life assessment and fault early warning, combined with the effects of historical decisions, generates a resource scheduling plan and transmits it to the digital twin display module; The digital twin display module is used to present the real-time operating status of the factory using 3D visualization technology, and supports virtual roaming and multi-angle viewing of the production line status; It also includes a digital operations management method, characterized by: The operation monitoring module establishes digital profiles for equipment, collects equipment operation data from distributed industrial IoT nodes, and forms equipment baseline parameters. Based on the equipment baseline parameters, a process flow knowledge graph is constructed, and the dependencies between equipment and material flow paths are mapped through the knowledge graph engine module. The predictive maintenance module performs real-time status monitoring, compares the current operating parameters with the equipment baseline parameters to generate a predictive maintenance plan. Based on the predictive maintenance plan, a resource scheduling scheme is generated through the decision support module, and a multi-strategy scheduler is used to balance production efficiency and equipment lifespan to optimize the resource scheduling scheme. The method for constructing the process flow knowledge graph is as follows: Based on the dynamic operating parameters in the equipment baseline parameters, feature vectors of the equipment status are extracted, wherein the feature vectors are subjected to dimensionality reduction processing through principal component analysis. Based on the aforementioned feature vectors, the Granger causality test method is used to perform time-series correlation analysis on the historical data of equipment operation to identify causal chains between equipment. Based on the device interaction data in the device baseline parameters and the causal chain, an inter-device relationship matrix is ​​established, wherein the relationship matrix describes the transmission direction and intensity of material flow, energy flow and information flow between devices; The relation matrix is ​​used to construct a set of directed edges, and edge weights are assigned to form an initial graph structure. The edge weights are calculated based on the importance of material flow, energy flow, and information flow. The initial map structure is divided into modules using a community detection algorithm to identify subsystem groups of equipment. Semantic tags and process stage attributes are added to the subsystem groups in conjunction with the process flow specification document. By integrating the subsystem groups, semantic tags, and process stage attributes, a hierarchical process flow knowledge graph is formed. Once the process knowledge graph is constructed, the equipment health index is calculated by combining the functional characteristics of the subsystem groups and the edge weights of the relationship matrix. The specific formula is as follows: ； in, Let t be the device health index at time t. For the overall system calibration coefficient, The importance coefficient of the baseline parameter of the i-th device is calculated based on the knowledge graph relation matrix. Let be the time decay function of the baseline parameters of the i-th device. Let be the standardized value of the baseline parameter of the i-th device at time t. Let be the historical mean of the baseline parameters of the i-th device. This is the system degradation rate coefficient. t represents the total number of baseline parameters for the equipment, and t is a time variable.

2. The digital operation management system as described in claim 1, characterized in that: The knowledge graph engine module is connected to the operation monitoring module, the predictive maintenance module, and the digital twin display module, respectively; the predictive maintenance module is connected to the decision support module; the decision support module is connected to the digital twin display module; the distributed industrial IoT node is equipped with an edge computing unit and a local cache module; the edge computing unit is used to perform data filtering and anomaly detection; the local cache module is used to store key data when the network is interrupted.

3. The digital operation management system as described in claim 2, characterized in that: The operation monitoring module includes a multi-strategy scheduler; the multi-strategy scheduler is used to dynamically allocate computing resources according to the priority of production tasks and resource utilization, and to trigger a resource expansion mechanism under high load conditions.

4. The digital operation management system as described in claim 1, characterized in that: The method for generating the predictive maintenance plan is as follows: When the device health index is triggered When the early warning conditions are met, the maintenance resource scheduling scheme is evaluated through the resource coordination coefficient R, wherein the resource coordination coefficient R is calculated based on the equipment importance and failure probability. If the equipment health index If the first condition is met and the resource coordination coefficient R≤0.3, then online maintenance is adopted to ensure uninterrupted production. Equipment operation data is collected through the predictive maintenance module and displayed in green in the digital twin display module. If the equipment health index If the second condition is met and 0.3 < resource coordination coefficient R ≤ 0.7, then an early warning state is entered, and a yellow indicator flashes in the digital twin display module to indicate this. Planned shutdown maintenance is arranged, and the edge computing unit is started to perform real-time parameter analysis. If the equipment health index If the third condition is met or the resource coordination coefficient R>0.7, the emergency shutdown procedure will be executed and the backup equipment will be started, which will be indicated by a flashing red icon in the digital twin display module. If the maintenance count of a certain device is greater than or equal to the preset maintenance device count and the device health index after maintenance is... If the warning continues to be triggered, the equipment update assessment process will be initiated.

5. The digital operation management system as described in claim 4, characterized in that: The optimization method for the resource scheduling scheme is as follows: Based on the process stage attributes of subsystem groups, a multi-strategy scheduler generates maintenance resource demand forecasts and maintenance strategy types. Based on the predicted maintenance resource requirements and the maintenance strategy type, maintenance tasks are classified and corresponding resource allocation schemes are established. When resource competition occurs, the resource scheduling scheme is dynamically optimized based on the hierarchical structure of the process knowledge graph and the priority of production tasks.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the digital operation management system according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the digital operation management system according to any one of claims 1 to 5.

Images