Equipment health degree real-time monitoring method and system based on multi-index decision
By establishing a multi-dimensional indicator governance model and lineage map, and dynamically adjusting the equipment health assessment model, the issues of subjectivity and adaptability in equipment health monitoring are resolved, enabling real-time and accurate assessment of equipment health and optimization of operation and maintenance strategies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAN TPRI POWER PLANT INFORMATION TECHNOLOGY CO LTD
- Filing Date
- 2026-01-12
- Publication Date
- 2026-05-05
AI Technical Summary
Existing equipment health monitoring methods suffer from problems such as strong subjectivity, poor adaptability, and monitoring lag. They cannot achieve dynamic weighted fusion of multiple indicators and have weak anti-interference capabilities, resulting in inaccurate health assessments.
By establishing a multi-dimensional indicator governance model, constructing a lineage map, calculating the initial and dynamic weights of governance indicators at each level, and combining the real-time operating conditions of the equipment to calculate the dynamic adjustment coefficient of the weights, a multi-dimensional decision-making equipment health assessment model is constructed to achieve real-time health assessment and output of key impact indicators.
It enables accurate and real-time assessment of equipment health, reduces operation and maintenance costs, adapts to dynamic changes under different equipment and operating conditions, has anti-noise interference capabilities, and provides accurate operation and maintenance decision-making basis.
Smart Images
Figure CN121980415A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment condition monitoring and fault diagnosis technology, specifically to a method and system for real-time monitoring of equipment health based on multi-indicator decision-making. Background Technology
[0002] Existing equipment health monitoring methods are mainly divided into two categories: single-index monitoring and multi-index monitoring. Single-index monitoring methods judge the equipment status only through a single physical quantity such as vibration, temperature, and pressure, which has the problems of limited monitoring dimensions and high misjudgment rate. For example, judging equipment failure solely based on an increase in vibration amplitude may misjudge instantaneous fluctuations under normal operating conditions as fault signals, or miss hidden faults caused by the coupling of multiple factors.
[0003] While multi-indicator monitoring methods incorporate multiple state parameters, they suffer from significant shortcomings in indicator fusion and decision-making mechanisms. Firstly, most methods employ simple weighted summation to integrate indicators, with weight allocation relying on human experience, resulting in strong subjectivity and an inability to adapt to dynamic changes in indicator importance under different equipment and operating conditions. Secondly, they lack real-time preprocessing and anomaly identification capabilities for indicator data, making it difficult to cope with noise interference under complex operating conditions, leading to delayed and inaccurate health assessments. Furthermore, existing methods employ coarse-grained health level classifications, failing to accurately reflect the gradual transition of equipment from "healthy" to "faulty," which is detrimental to the development of refined maintenance strategies.
[0004] Therefore, there is an urgent need for a real-time monitoring method for equipment health that can achieve dynamic weighted fusion of multiple indicators, strong anti-interference ability, and accurate assessment, in order to solve the problems of strong subjectivity, poor adaptability, and monitoring lag in existing technologies. Summary of the Invention
[0005] The purpose of this invention is to provide a real-time monitoring method for equipment health based on multi-indicator decision-making, so as to solve the problems of strong subjectivity, poor adaptability and monitoring lag in existing multi-indicator monitoring methods.
[0006] To address the aforementioned problems, this invention proposes a real-time monitoring method for equipment health based on multi-indicator decision-making. The technical solution adopted is as follows: A method for real-time monitoring of equipment health based on multi-indicator decision-making includes the following steps: Establish a multi-dimensional indicator governance model based on equipment measurement points; The lineage relationship between governance indicators at different levels in the multi-dimensional indicator governance model is extracted based on the time series graph engine, and a lineage graph is constructed. The initial weights of governance indicators at each level are calculated based on the kinship map. The dynamic adjustment coefficients of the weights of each level of governance indicators are calculated based on the real-time operating conditions of the equipment. Based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators, the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment are obtained. A multi-dimensional decision-making equipment health assessment model is constructed based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment. The comprehensive score of the real-time health of the equipment is calculated and key governance indicators affecting the equipment are obtained.
[0007] Furthermore, the establishment of a multi-dimensional indicator governance model based on equipment measurement points includes: Acquire measurement point data related to the entire lifecycle of the equipment; The indicator dimensions are divided based on the measurement point data; Core monitoring indicators are selected from the indicator dimensions and standardized, thereby constructing a multi-dimensional indicator governance model.
[0008] Furthermore, the indicator dimensions include at least one of the following: operational status dimension, performance parameter dimension, environmental impact dimension, and operation and maintenance history dimension; the standardization process includes data cleaning, outlier removal, and normalization transformation.
[0009] Furthermore, the step of extracting the lineage relationships between governance indicators at various levels in the multi-dimensional indicator governance model based on the time-series graph engine and constructing a lineage graph includes: The time series graph engine is used to analyze the data sources, calculation logic and dependencies of governance indicators at each level, and to extract the direct and indirect relationships between governance indicators at each level. Using governance indicators at each level as nodes and direct and indirect kinship relationships as edges, a visualized kinship graph is constructed, thereby obtaining the transmission path and influence weight correlation between governance indicators at each level.
[0010] Furthermore, the initial weights for calculating governance indicators at each level based on kinship maps include: The node weights of each level of governance indicators are determined based on the hierarchical relationship of each level of governance indicators in the bloodline graph, and then the initial weights of each level of governance indicators are obtained. The calculation formula for the node weights of the governance indicators at each level is shown in Equation 1: Formula 1 Where d represents the depth of the hierarchy in the kinship map. Attenuation coefficient, and .
[0011] Furthermore, the determination of node weights for each level of governance indicators based on the hierarchical relationship of governance indicators in the kinship graph, thereby obtaining the initial weights for each level of governance indicators, includes: Based on the hierarchical relationship of governance indicators at each level in the bloodline graph, the node weight of each level of governance indicator is determined, and based on the node weight of each level of governance indicator, the initial weight of the governance indicator of each node in the same level is determined, thereby obtaining the initial weight of each level of governance indicator. The process of determining the initial weight of the governance indicator for each node at the same level based on the node weight of the governance indicator at each level, thereby obtaining the initial weight of the governance indicator at each level, includes: First, for each node at the same level, the calculation frequency is divided into seven levels: second, minute, hour, day, week, month, and year, based on the governance indicators. The frequency weights are as follows: , , , , , and ; Then, the percentage 's' of the 10 latest status codes of the statistical governance indicator is calculated as the proportion of normal status codes. The initial weight of the governance indicator corresponding to the j-th node in the i-th layer is then determined. As shown in Equation 2: Formula 2 in, The frequency weight of the governance metric corresponding to the j-th node in the i-th layer is... The percentage of normal status codes among the latest 10 status codes of the governance metric corresponding to the j-th node in the i-th layer; Let be the node weight of the governance indicator at level i; This represents the total number of nodes in the i-th layer.
[0012] Furthermore, the step of calculating the dynamic adjustment coefficients of the weights of each level of governance indicators based on the real-time operating conditions of the equipment, and obtaining the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators, includes: Real-time acquisition of equipment operating parameters; establishment of an operating condition-weight influence model. Based on the working condition-weighted influence model, the differences in the degree of influence of different real-time working condition parameters on governance indicators at each level are analyzed, and the dynamic adjustment coefficients of the weights of governance indicators at each level are calculated. The initial weights of each level of governance indicators are corrected by using the dynamic adjustment coefficients of the weights of each level of governance indicators, so as to obtain the dynamic weights of each level of governance indicators that are adapted to the real-time operating conditions of the equipment. The dynamic weight set W of the governance indicators at each level under the real-time operating conditions of the adaptive equipment is obtained from Equation 3: Formula 3 in, Set of equipment management indicators The corresponding initial threshold set =[ ]; This is the equipment operating condition parameter score matrix.
[0013] Furthermore, the equipment health assessment model, which constructs a multi-dimensional decision-making system based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment, calculates the comprehensive score of the real-time health of the equipment and obtains key governance indicators affecting its performance, including: Based on the dynamic weights of governance indicators at each level of real-time equipment operating conditions, an equipment health assessment model is constructed. By inputting real-time data of governance indicators at each level in the multi-dimensional indicator governance model into the equipment health assessment model, the comprehensive score of real-time equipment health and key impact governance indicators are obtained.
[0014] Furthermore, the calculation of the device's real-time health comprehensive score is shown in Equation 4: Formula 4 in, As governance indicators Dynamic weights, As governance indicators Objective function score; The From Equation 5, we get: Formula 5 in, As a governance indicator, As governance indicators The corresponding abnormal threshold for the indicator, As governance indicators The corresponding health threshold, and .
[0015] This invention also proposes a system for performing a real-time monitoring method for equipment health based on multi-index decision-making, comprising: The module for establishing a multi-dimensional indicator governance model establishes a multi-dimensional indicator governance model based on equipment measurement points. The kinship graph construction module extracts the kinship relationships between governance indicators at various levels in the multi-dimensional indicator governance model based on the time series graph engine, and constructs the kinship graph. The initial weight acquisition module calculates the initial weights of governance indicators at each level based on the lineage graph; The dynamic weight acquisition module calculates the dynamic adjustment coefficients of the weights of each level of governance indicators based on the real-time operating conditions of the equipment, and obtains the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators. The module for obtaining the comprehensive score of real-time equipment health constructs a multi-dimensional decision-making equipment health assessment model based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment, and calculates the comprehensive score of real-time equipment health and obtains key governance indicators that affect the equipment.
[0016] Compared with the prior art, this application has the following beneficial effects: This invention is an improved version. By establishing a multi-dimensional indicator governance model, a lineage map, and dynamically determining the dynamic weights of governance indicators at each level to adapt to the real-time operating conditions of equipment, it deeply integrates real-time data processing with a multi-criteria decision-making mechanism. This achieves real-time performance throughout the entire process of data processing of governance indicators at each level, dynamic weight adjustment of governance indicators at each level for real-time equipment operating conditions, and health assessment. The assessment results can promptly reflect the current health status of the equipment, achieving accurate and real-time assessment of equipment health. Simultaneously, it outputs key influencing indicators, solving the problems of strong subjectivity, poor adaptability, and monitoring lag in existing monitoring methods. This system provides maintenance personnel with accurate decision-making support, effectively reducing maintenance costs and the risk of unplanned downtime. It can adapt to the dynamic changes in the importance of indicators under different equipment and operating conditions. Furthermore, by constructing a lineage graph, it can clearly trace the source and impact path of indicator data, facilitating subsequent review and analysis of assessment results and further optimization of monitoring models and maintenance strategies. By calculating the dynamic adjustment coefficients of the weights of governance indicators at each level based on real-time equipment operating conditions, it enables dynamic adjustment of the weights of governance indicators at each level, achieving real-time preprocessing and anomaly identification capabilities for indicator data, and effectively addressing noise interference under complex operating conditions. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating the real-time monitoring method for equipment health based on multi-indicator decision-making according to the present invention. Figure 2 This is a schematic diagram of the lineage map in the real-time monitoring method for device health based on multi-index decision-making of the present invention. Detailed Implementation
[0018] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0020] The following describes, with reference to the accompanying drawings, a method and system for real-time monitoring of device health based on multi-indicator decision-making, according to embodiments of this application.
[0021] The following is combined Figure 1 This application provides a detailed description of the real-time monitoring method for equipment health based on multi-indicator decision-making.
[0022] First, a multi-dimensional indicator governance model is established based on the equipment measurement points.
[0023] Specifically, a multi-dimensional indicator governance model is established based on equipment measurement points. This includes: acquiring measurement point data related to the entire equipment lifecycle; dividing the measurement point data into indicator dimensions; selecting core monitoring indicators from the indicator dimensions and performing standardization processing to construct the multi-dimensional indicator governance model. The indicator dimensions include at least one of the following: operational status dimension, performance parameter dimension, environmental impact dimension, and maintenance history dimension; standardization processing includes data cleaning, outlier removal, and normalization transformation. Here, establishing a multi-dimensional indicator governance model based on equipment measurement points is done according to actual business needs.
[0024] Secondly, based on the time series graph engine, the lineage relationships between governance indicators at each level in the multi-dimensional indicator governance model are extracted, and a lineage graph is constructed.
[0025] Specifically, such as Figure 2 As shown, the lineage relationships between governance indicators at various levels in the multi-dimensional indicator governance model are extracted based on the time series graph engine, and a lineage graph is constructed. This includes: using the time series graph engine to analyze the data source, calculation logic, and dependencies of governance indicators at various levels, and extracting the direct and indirect lineage relationships between governance indicators at various levels; using governance indicators at various levels as nodes and direct and indirect lineage relationships as edges, a visualized lineage graph is constructed, thereby obtaining the transmission path and influence weight association basis between governance indicators at various levels.
[0026] In a specific embodiment, taking a high-temperature heated surface as an example, it is necessary not only to select wall temperature measuring points for real-time temperature monitoring, but also to comprehensively evaluate it in conjunction with high-concentration application indicators such as "coal-fired power generation cost," "plant power consumption rate," and "cumulative power generation." Therefore, this embodiment constructs a lineage map by sorting out equipment measuring point data and high-concentration application indicators.
[0027] Then, the initial weights of governance indicators at each level are calculated based on the kinship map.
[0028] Specifically, the initial weights of governance indicators at each level are calculated based on the kinship graph, including: determining the node weights of each level of governance indicators based on the hierarchical relationship of each level of governance indicators in the kinship graph, thereby obtaining the initial weights of each level of governance indicators; wherein, the calculation formula for the node weights of each level of governance indicators is shown in Equation 1: Formula 1 Where d represents the depth of the hierarchy in the kinship map. Attenuation coefficient, and
[0029] The node weights of each level of governance indicators are determined based on the hierarchical relationship of each level of governance indicators in the kinship graph, and then the initial weights of each level of governance indicators are obtained. This includes: determining the node weights of each level of governance indicators based on the hierarchical relationship of each level of governance indicators in the kinship graph, and determining the initial weights of the governance indicators of each node in the same level based on the node weights of each level of governance indicators, and then obtaining the initial weights of each level of governance indicators.
[0030] In one specific embodiment, the initial weight of the governance indicator for each node in the same level is determined based on the node weight of the governance indicator at each level, thereby obtaining the initial weight of the governance indicator at each level, including: First, for each node at the same level, the calculation frequency is divided into seven levels: second, minute, hour, day, week, month, and year, based on the governance indicators. The frequency weights are as follows: , , , , , and ; Then, the percentage 's' of the 10 latest status codes of the statistical governance indicator is calculated as the proportion of normal status codes. The initial weight of the governance indicator corresponding to the j-th node in the i-th layer is then determined. As shown in Equation 2: Formula 2 in, The frequency weight of the governance metric corresponding to the j-th node in the i-th layer is... The percentage of normal status codes among the latest 10 status codes of the governance metric corresponding to the j-th node in the i-th layer; Let be the node weight of the governance indicator at level i; This represents the total number of nodes in the i-th layer.
[0031] For example, if the calculation frequency of the governance indicator corresponding to the j-th node in the i-th layer is on the hourly level, then = If, among the latest 10 values of the governance metric corresponding to the j-th node in layer i, 8 values are calculated correctly and 2 values are calculated incorrectly, then... .here, ,in, Let be the depth of the i-th level in the kinship map. Attenuation coefficient, and .
[0032] Next, the dynamic adjustment coefficients of the weights of each level of governance indicators are calculated based on the real-time operating conditions of the equipment. Based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators, the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment are obtained.
[0033] Specifically, the dynamic adjustment coefficients of the weights of governance indicators at each level are calculated based on the real-time operating conditions of the equipment. Then, based on these dynamic adjustment coefficients and the initial weights of each level of governance indicators, the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment are obtained. This process includes: real-time acquisition of equipment operating parameters and establishment of an operating condition-weight influence model; analysis of the differences in the influence of different real-time operating parameters on each level of governance indicators based on the operating condition-weight influence model, and calculation of the dynamic adjustment coefficients of the weights of each level of governance indicators; and correction of the initial weights of each level of governance indicators using the dynamic adjustment coefficients of the weights of each level of governance indicators to obtain the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment. The equipment operating parameters include load rate, operating speed, operating duration, and ambient temperature, etc.
[0034] Here, the dynamic weight set W of the governance indicators at each level that adapt to the real-time operating conditions of the equipment is obtained from Equation 3: Formula 3 in, Set of equipment management indicators The corresponding initial threshold set =[ ]; This is the equipment operating condition parameter score matrix.
[0035] In one specific embodiment, for device U, the set of governance indicators for device U is... The corresponding initial threshold set is =[ ]; The set of operating parameters for device U is as follows =[ , ... , ],in , This represents the equipment operating condition parameters and the corresponding set of operating condition threshold parameters. =[ , ... , ],in , Indicates equipment operating parameters The corresponding threshold; where, when When, it is considered a normal working condition, when When this condition is considered an abnormal working condition, a working condition score coefficient is applied. for:
[0036] Based on the equipment operating condition parameter score matrix corresponding to the above parameters ={ , ... , Then the dynamic weight set W is calculated by the following equation 3: ; That is, the dynamic weight set W = .
[0037] Finally, a multi-dimensional decision-making equipment health assessment model is constructed based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment. The comprehensive score of the real-time health of the equipment is calculated and key governance indicators affecting the equipment are obtained.
[0038] Specifically, a multi-dimensional decision-making equipment health assessment model is constructed based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment. This model calculates the comprehensive real-time health score and key impact governance indicators. The process includes: constructing the equipment health assessment model based on the dynamic weights of governance indicators at each level of the equipment's real-time operating conditions; inputting the real-time data of governance indicators at each level from the multi-dimensional indicator governance model into the equipment health assessment model to obtain the comprehensive real-time health score and key impact governance indicators. Here, the health level corresponding to the comprehensive health score is healthy, sub-healthy, fault warning, or fault.
[0039] The calculation of the device's real-time health score is shown in Equation 4: Formula 4 in, As governance indicators Dynamic weights, As governance indicators Objective function score; The From Equation 5, we get: Formula 5 in, As a governance indicator, As governance indicators The corresponding abnormal threshold for the indicator, As governance indicators The corresponding health threshold, and .
[0040] In a specific embodiment, based on the aforementioned device U, the set of governance indicators X for device U is... The corresponding set of abnormal threshold values M = The set of health threshold indicators N = The threshold sets M and N satisfy n i <m i The dynamic weight set W obtained from the above calculation = The dynamic weight set W is normalized to the interval [0,1], and =1, set the objective function It is obtained from Equation 5: Formula 5 in, As a governance indicator, As governance indicators The corresponding abnormal threshold for the indicator, As governance indicators The corresponding health threshold, and .
[0041] For device u, its overall health score is calculated as shown in Equation 4: Formula 4 in, As governance indicators Dynamic weights, As governance indicators The objective function score.
[0042] Based on the comprehensive score above, the health level (healthy, sub-healthy, fault warning, fault) corresponding to equipment U is classified, and the evaluation results and key impact indicators are output.
[0043] This application also provides a system for performing the above-described method for real-time monitoring of equipment health based on multi-index decision-making, comprising: The module for establishing a multi-dimensional indicator governance model establishes a multi-dimensional indicator governance model based on equipment measurement points. The kinship graph construction module extracts the kinship relationships between governance indicators at various levels in the multi-dimensional indicator governance model based on the time series graph engine, and constructs the kinship graph. The initial weight acquisition module calculates the initial weights of governance indicators at each level based on the lineage graph; The dynamic weight acquisition module calculates the dynamic adjustment coefficients of the weights of each level of governance indicators based on the real-time operating conditions of the equipment, and obtains the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators. The module for obtaining the comprehensive score of real-time equipment health constructs a multi-dimensional decision-making equipment health assessment model based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment, and calculates the comprehensive score of real-time equipment health and obtains key governance indicators that affect the equipment.
[0044] Those skilled in the art will understand that the specific methods of the above-described real-time equipment health monitoring system based on multi-indicator decision-making have been referenced above. Figures 1 to 2 The method for real-time monitoring of equipment health based on multi-indicator decision-making has been described in detail, so its repeated description will be omitted.
[0045] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. The scope of patent protection of the present invention shall be determined by the claims. Similarly, any equivalent structural changes made based on the description and drawings of the present invention shall also be included within the scope of protection of the present invention.
Claims
1. A method for real-time monitoring of equipment health based on multi-indicator decision-making, characterized in that, Includes the following steps: Establish a multi-dimensional indicator governance model based on equipment measurement points; Based on the time series graph engine, the lineage relationship between governance indicators at each level in the multi-dimensional indicator governance model is extracted, and a lineage graph is constructed. The initial weights of governance indicators at each level are calculated based on the kinship map. The dynamic adjustment coefficients of the weights of each level of governance indicators are calculated based on the real-time operating conditions of the equipment. Based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators, the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment are obtained. A multi-dimensional decision-making equipment health assessment model is constructed based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment. The comprehensive score of the real-time health of the equipment is calculated and key governance indicators affecting the equipment are obtained.
2. The real-time equipment health monitoring method based on multi-index decision-making according to claim 1, characterized in that, The establishment of a multi-dimensional indicator governance model based on equipment measurement points includes: Acquire measurement point data related to the entire lifecycle of the equipment; The indicator dimensions are divided based on the measurement point data; Core monitoring indicators are selected from the indicator dimensions and standardized, thereby constructing a multi-dimensional indicator governance model.
3. The real-time equipment health monitoring method based on multi-index decision-making according to claim 2, characterized in that, The indicator dimensions include at least one of the following: operational status dimension, performance parameter dimension, environmental impact dimension, and operation and maintenance history dimension; the standardization process includes data cleaning, outlier removal, and normalization transformation.
4. The real-time equipment health monitoring method based on multi-index decision-making according to claim 1, characterized in that, The process of extracting the lineage relationships between governance indicators at different levels in the multi-dimensional indicator governance model based on a time-series graph engine and constructing a lineage graph includes: The time series graph engine is used to analyze the data sources, calculation logic and dependencies of governance indicators at each level, and to extract the direct and indirect relationships between governance indicators at each level. Using governance indicators at each level as nodes and direct and indirect kinship relationships as edges, a visualized kinship graph is constructed, thereby obtaining the transmission path and influence weight correlation between governance indicators at each level.
5. The real-time equipment health monitoring method based on multi-index decision-making according to claim 1, characterized in that, The initial weights for calculating governance indicators at each level based on kinship maps include: The node weights of each level of governance indicators are determined based on the hierarchical relationship of each level of governance indicators in the bloodline graph, and then the initial weights of each level of governance indicators are obtained. The calculation formula for the node weights of the governance indicators at each level is shown in Equation 1: Formula 1 Where d represents the depth of the hierarchy in the kinship map. Attenuation coefficient, and .
6. The real-time equipment health monitoring method based on multi-index decision-making according to claim 5, characterized in that, The process of determining the node weights of each level of governance indicators based on the hierarchical relationship in the kinship graph, and thus obtaining the initial weights of each level of governance indicators, includes: Based on the hierarchical relationship of governance indicators at each level in the bloodline graph, the node weight of each level of governance indicator is determined, and based on the node weight of each level of governance indicator, the initial weight of the governance indicator of each node in the same level is determined, thereby obtaining the initial weight of each level of governance indicator. The process of determining the initial weight of the governance indicator for each node at the same level based on the node weight of the governance indicator at each level, thereby obtaining the initial weight of the governance indicator at each level, includes: First, for each node at the same level, the calculation frequency is divided into seven levels: second, minute, hour, day, week, month, and year, based on the governance indicators. The frequency weights are as follows: , , , , , and ; Then, the percentage 's' of the 10 latest status codes of the statistical governance indicator is calculated as the proportion of normal status codes. The initial weight of the governance indicator corresponding to the j-th node in the i-th layer is then determined. As shown in Equation 2: Formula 2 in, The frequency weight of the governance metric corresponding to the j-th node in the i-th layer is... The percentage of normal status codes among the latest 10 status codes of the governance metric corresponding to the j-th node in the i-th layer; Let be the node weight of the governance indicator at level i; This represents the total number of nodes in the i-th layer.
7. The real-time equipment health monitoring method based on multi-index decision-making according to claim 1, characterized in that, The process of calculating the dynamic adjustment coefficients of the weights of governance indicators at each level based on the real-time operating conditions of the equipment, and obtaining the dynamic weights of the governance indicators at each level adapted to the real-time operating conditions of the equipment based on the dynamic adjustment coefficients of the weights of the governance indicators at each level and the initial weights of the governance indicators at each level, includes: Real-time acquisition of equipment operating parameters; establishment of an operating condition-weight influence model. Based on the working condition-weighted influence model, the differences in the degree of influence of different real-time working condition parameters on governance indicators at each level are analyzed, and the dynamic adjustment coefficients of the weights of governance indicators at each level are calculated. The initial weights of each level of governance indicators are corrected by using the dynamic adjustment coefficients of the weights of each level of governance indicators, so as to obtain the dynamic weights of each level of governance indicators that are adapted to the real-time operating conditions of the equipment. The dynamic weight set W of the governance indicators at each level under the real-time operating conditions of the adaptive equipment is obtained from Equation 3: Formula 3 in, Set of equipment management indicators The corresponding initial threshold set =[ ]; This is the equipment operating condition parameter score matrix.
8. The real-time equipment health monitoring method based on multi-index decision-making according to claim 7, characterized in that, The system constructs a multi-dimensional decision-making equipment health assessment model based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment. It calculates the comprehensive score of the equipment's real-time health and obtains key governance indicators, including: Based on the dynamic weights of governance indicators at each level of real-time equipment operating conditions, an equipment health assessment model is constructed. By inputting real-time data of governance indicators at each level in the multi-dimensional indicator governance model into the equipment health assessment model, the comprehensive score of real-time equipment health and key impact governance indicators are obtained.
9. The real-time equipment health monitoring method based on multi-index decision-making according to claim 8, characterized in that, The calculation of the device's real-time health score is shown in Equation 4: Formula 4 in, As governance indicators Dynamic weights, As governance indicators Objective function score; The From Equation 5, we get: Formula 5 in, As a governance indicator, As governance indicators The corresponding abnormal threshold for the indicator, As governance indicators The corresponding health threshold, and .
10. A system for performing a real-time monitoring method for equipment health based on multi-index decision-making, characterized in that, include: The module for establishing a multi-dimensional indicator governance model establishes a multi-dimensional indicator governance model based on equipment measurement points. The kinship graph construction module extracts the kinship relationships between governance indicators at various levels in the multi-dimensional indicator governance model based on the time series graph engine, and constructs the kinship graph. The initial weight acquisition module calculates the initial weights of governance indicators at each level based on the lineage graph; The dynamic weight acquisition module calculates the dynamic adjustment coefficients of the weights of each level of governance indicators based on the real-time operating conditions of the equipment, and obtains the dynamic weights of each level of governance indicators adapted to the real-time operating conditions of the equipment based on the dynamic adjustment coefficients of the weights of each level of governance indicators and the initial weights of each level of governance indicators. The module for obtaining the comprehensive score of real-time equipment health constructs a multi-dimensional decision-making equipment health assessment model based on the dynamic weights of governance indicators at each level and the real-time operating conditions of the equipment, and calculates the comprehensive score of real-time equipment health and obtains key governance indicators that affect the equipment.