A health degree calculation method, device, equipment, medium and product of an industrial device

Abstract

The application discloses a health degree calculation method, device, equipment, medium and product of an industrial equipment, relates to the technical field of data processing, and comprises the following steps: acquiring abnormal parameters and a current running time count of the industrial equipment; analyzing the abnormal parameters based on preset health degree basic configuration parameters, and determining abnormal information corresponding to each abnormal parameter; wherein, the abnormal information comprises abnormal source information and index abnormal type of the abnormal parameters; processing the abnormal information corresponding to each abnormal parameter based on a pre-constructed target health degree mapping model and the health degree basic configuration parameters, and obtaining a comprehensive deduction value; and calculating the comprehensive deduction value and the current running time count based on a pre-constructed final health degree mapping model and the health degree basic configuration parameters, and obtaining the final health degree of the industrial equipment. The application improves the accuracy of health degree calculation of the industrial equipment.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment, medium and product for calculating the health status of industrial equipment. Background Technology

[0002] In the field of industrial equipment condition monitoring and health management, key equipment such as centrifugal pumps, circulating water pumps, centrifugal fans, motors, reducers, and gearboxes are composed of multiple functional components, which generate multi-dimensional monitoring parameters such as vibration, temperature, current, and pressure during operation. Although existing monitoring systems can output early warning and fault diagnosis information, the abnormal information from multiple components and parameters is scattered and varies in form, making it difficult to directly use it for a unified evaluation of the overall health of industrial equipment.

[0003] Currently, the health status calculation of industrial equipment mainly adopts simple weighting, threshold mapping or empirical rules, which lacks a unified evaluation framework. It is impossible to effectively integrate the abnormal classification information of multiple components and multiple parameters, making it difficult to accurately calculate the health status of industrial equipment and failing to meet the actual needs of intelligent operation and maintenance of industrial equipment. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, equipment, medium, and product for calculating the health status of industrial equipment, which can improve the accuracy of calculating the health status of industrial equipment.

[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a method for calculating the health status of industrial equipment, including: Acquire abnormal parameters and current running time count of industrial equipment; The abnormal parameters are analyzed based on the preset health status configuration parameters to determine the abnormal information corresponding to each abnormal parameter; wherein, the abnormal information includes the abnormal source information and the indicator abnormal type of the abnormal parameter, the abnormal source information is the early warning abnormal information or the diagnostic abnormal information, and the indicator abnormal type is the critical indicator abnormal type or the non-critical indicator abnormal type. Based on the pre-built target health mapping model and the basic health configuration parameters, the abnormal information corresponding to each abnormal parameter is processed to obtain a comprehensive deduction value; Based on the pre-built final health mapping model and the basic health configuration parameters, the comprehensive deduction value and the current running time count are calculated to obtain the final health of the industrial equipment.

[0006] Optionally, the preset basic health configuration parameters include target health values ​​and health decay parameters corresponding to different warning anomaly levels, target health values ​​and health decay parameters corresponding to different diagnostic fault types, anomaly source weight allocation relationship, indicator anomaly type weight allocation relationship, and time span parameters corresponding to different comprehensive anomaly levels; wherein: The sum of the warning weight and the diagnosis weight included in the anomaly source weight allocation relationship is 1; The sum of the weights of key indicator anomaly types and non-key indicator anomaly types in the weight allocation relationship of the indicator anomaly types is 1.

[0007] Optionally, the step of analyzing the abnormal parameters based on preset health baseline configuration parameters to determine the abnormal information corresponding to each abnormal parameter specifically includes: The abnormal source information of the abnormal parameters is determined based on the preset health status configuration parameters; The abnormality type of the abnormal parameter is determined based on the preset health status configuration parameters; If the anomaly source information is early warning anomaly information, then the early warning anomaly level of the early warning anomaly information is determined; and based on the anomaly source information, the early warning anomaly level, and the indicator anomaly type, anomaly information corresponding to the anomaly parameter is generated; If the abnormality source information is diagnostic abnormality information, then the diagnostic fault type of the diagnostic abnormality information is determined; and based on the abnormality source information, the diagnostic fault type, and the indicator abnormality type, the abnormality information corresponding to the abnormal parameter is generated.

[0008] Optionally, the step of processing the abnormal information corresponding to each abnormal parameter based on the pre-built target health mapping model and the basic health configuration parameters to obtain a comprehensive deduction value specifically includes: Based on the aforementioned basic health configuration parameters, determine the target health value corresponding to the abnormal source information of each abnormal parameter; Based on the pre-built target health mapping model and the target health value of each abnormal parameter, the basic deduction value of each abnormal parameter is determined. Based on the health decay parameter corresponding to the warning anomaly level, the basic deduction values ​​of the anomaly parameters of the same warning anomaly level are merged to determine the anomaly level parameter set of the same warning anomaly level; wherein, the anomaly level parameter set contains anomaly level parameter information of different warning anomaly levels, and the anomaly level parameter information contains the current warning anomaly level, the indicator anomaly type and the actual deduction value. Based on the health decay parameter corresponding to the diagnosed fault type, the base deduction values ​​of abnormal parameters of the same diagnosed fault type are merged to determine the abnormal fault parameter set of the same diagnosed fault type; wherein, the abnormal fault parameter set contains fault parameter information of different diagnosed fault types, and the fault parameter information contains the current diagnosed fault type, the abnormal indicator type, and the actual deduction value. Based on the anomaly type of the indicator, the set of anomaly level parameters is divided into a set of critical anomaly level parameters and a set of non-critical anomaly level parameters. Based on a preset aggregation coefficient, the critical anomaly level parameter set and the non-critical anomaly level parameter set are calculated respectively to obtain the critical anomaly level aggregated deduction value of the critical anomaly level parameter set and the non-critical anomaly level aggregated deduction value of the non-critical anomaly level parameter set. Based on the anomaly type of the indicator, the set of abnormal fault parameters is divided into a set of critical abnormal fault parameters and a set of non-critical abnormal fault parameters. Based on a preset aggregation coefficient, the critical fault parameter set and the non-critical fault parameter set are calculated respectively to obtain the critical fault level aggregated deduction value of the critical fault parameter set and the non-critical fault aggregated deduction value of the non-critical fault parameter set. A comprehensive deduction value is calculated based on the warning weight, the diagnosis weight, the key indicator anomaly type weight, the non-key indicator anomaly type weight, the key anomaly level aggregate deduction value, the non-key anomaly level aggregate deduction value, the key fault level aggregate deduction value, and the non-key anomaly fault aggregate deduction value.

[0009] Optionally, the calculation of the comprehensive deduction value and the current running time count based on the pre-built final health mapping model and the basic health configuration parameters to obtain the final health of the industrial equipment specifically includes: The comprehensive deduction value is input into the pre-built final health mapping model to obtain the current health value; Based on the aforementioned basic health configuration parameters, determine the time span parameter corresponding to the current running time count and the current health value; The final health status of the industrial equipment is calculated by inputting the preset curve shape parameters, the current running time count, and the time span parameters into the final health status mapping model.

[0010] Optionally, the formula for calculating the current health value is: ; in, The current health value is represented by β, which represents the preset first health curve parameter, and γ represents the preset second health curve parameter. This represents the total deduction value.

[0011] Secondly, this application provides a health status calculation device for industrial equipment, comprising: The acquisition unit is used to acquire abnormal parameters of industrial equipment and the current running time count; The determination unit is used to analyze the abnormal parameters based on preset health status configuration parameters and determine the abnormal information corresponding to each abnormal parameter; wherein, the abnormal information includes the abnormal source information and the indicator abnormal type of the abnormal parameter, the abnormal source information is early warning abnormal information or diagnostic abnormal information, and the indicator abnormal type is a key indicator abnormal type or a non-key indicator abnormal type. The processing unit is used to process the abnormal information corresponding to each abnormal parameter based on the pre-built target health mapping model and the basic health configuration parameters to obtain a comprehensive deduction value. The calculation unit is used to calculate the comprehensive deduction value and the current running time count based on the pre-built final health mapping model and the basic health configuration parameters to obtain the final health of the industrial equipment.

[0012] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the health calculation method for industrial equipment described in any one of the above.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the health calculation method for industrial equipment described above.

[0014] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the health calculation method for industrial equipment described above.

[0015] Sixthly, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run a program or instructions, and the processor executing the program or instructions implementing the steps of the health calculation method for industrial equipment described above.

[0016] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, equipment, medium, and product for calculating the health status of industrial equipment. By distinguishing between the source of anomalies (early warning or diagnosis) and the type of indicators (critical or non-critical), and by introducing runtime counting, it overcomes the biases caused by the simple weighting or threshold mapping of multi-source anomaly information in traditional methods. Specifically, this method can differentiate the processing according to the importance and source of different anomalies, ensuring that the impact of critical failures on health status is prominently reflected. At the same time, it uses a time continuity mechanism to suppress score jumps caused by single anomaly fluctuations, allowing the health status to change smoothly as the equipment deteriorates. As a result, the final output health status result more closely reflects the actual operating state of the equipment, significantly improving the accuracy of industrial equipment health status calculation and providing a more reliable quantitative basis for equipment condition assessment and operation and maintenance decisions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for calculating the health status of industrial equipment according to an embodiment of this application; Figure 2 A schematic diagram illustrating the classification and grading of abnormal parameters according to an embodiment of this application; Figure 3 A schematic diagram illustrating a calculation process for a comprehensive deduction value provided in an embodiment of this application; Figure 4 A schematic diagram of a similar abnormal attenuation calculation curve provided in an embodiment of this application; Figure 5 A schematic diagram of a total deduction score and health score mapping curve provided for an embodiment of this application; Figure 6 A schematic diagram of a continuous curve showing the change of health status over time, provided in an embodiment of this application; Figure 7 This is a schematic diagram of a device health status change curve provided in an embodiment of this application; Figure 8 A functional module schematic diagram of a health calculation device for industrial equipment provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] In one exemplary embodiment, such as Figure 1 As shown, a method for calculating the health status of industrial equipment is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, it includes the following steps 101 to 104. Wherein: Step 101: Obtain the abnormal parameters of the industrial equipment and the current running time count.

[0022] In this embodiment, the abnormal parameters of the industrial equipment can be abnormal data generated during the operation of the industrial equipment. Abnormal parameters can be categorized into early warning abnormal information and diagnostic abnormal information based on the source of the abnormality. Specifically: The early warning anomaly information comes from industrial equipment operation monitoring data and is the result of identification through feature threshold judgment, feature trend analysis or statistical analysis methods. The early warning anomaly result is obtained after executing the anomaly identification method configured on the feature parameters. The specific anomaly identification method may include: simple threshold judgment rules, trend recognition, similar comparison, etc., where the features come from the data collected by sensors on specific equipment.

[0023] Diagnostic anomaly information originates from industrial equipment operation monitoring data and is identified through fault diagnosis model analysis or expert rule reasoning. The diagnostic anomaly result is generated by analyzing collected data using corresponding fault diagnosis models, expert rule reasoning, and other methods, and then outputting corresponding diagnostic results.

[0024] The frequency of acquiring abnormal parameters of industrial equipment is generally consistent with the data acquisition frequency. The data acquisition frequency is controlled by the acquisition system. The data format is determined according to the usage method, such as outputting results in JSON format.

[0025] Step 102: Analyze the abnormal parameters based on the preset health status configuration parameters to determine the abnormal information corresponding to each abnormal parameter.

[0026] In this embodiment, the abnormal information includes the abnormal source information and the abnormal indicator type of the abnormal parameter. The abnormal source information is either early warning abnormal information or diagnostic abnormal information, and the abnormal indicator type is either a critical indicator abnormal type or a non-critical indicator abnormal type. Diagnostic experts can classify the importance of various monitoring signals, characteristic indicators, and fault types acquired during equipment operation based on equipment status characterization indicators and their impact on equipment safety, reliability, and production continuity. Abnormalities are further divided into critical indicator abnormal types (such as temperature, bearing cage failure, etc.) and non-critical indicator abnormal types (effective speed value, poor bearing lubrication, etc.), providing a basis for subsequent differentiated modeling. Diagnostic experts classify the importance of various monitoring signals and characteristic indicators acquired during equipment operation based on equipment status characterization indicators and their impact on equipment safety, reliability, and production continuity, forming critical indicator abnormal types and non-critical indicator abnormal types. That is, whether it will directly lead to rapid equipment deterioration or even shutdown. If it will lead to rapid equipment deterioration or even shutdown, it is a critical indicator abnormal type; otherwise, it is a non-critical indicator abnormal type.

[0027] In this embodiment, the preset basic health configuration parameters include target health values ​​and health decay parameters corresponding to different warning anomaly levels, target health values ​​and health decay parameters corresponding to different diagnostic fault types, anomaly source weight allocation relationship, indicator anomaly type weight allocation relationship, and time span parameters corresponding to different comprehensive anomaly levels; wherein: the sum of the warning weight and the diagnostic weight included in the anomaly source weight allocation relationship is 1; the sum of the weight of the key indicator anomaly type and the weight of the non-key indicator anomaly type included in the indicator anomaly type weight allocation relationship is 1.

[0028] For example, a basic health configuration parameter `health_cfg` is predefined. This `health_cfg` is a dictionary, and its structure is defined as follows: health_cfg = { "alm_target_health": {"level":[ , ,..., ], "score": [ , ,..., ]}, "dig_target_health": {"fault": [ , ,..., ], "score": [ , ,..., ]}, "level_decay_cfg": { : , : }, "alm_dig_weight": { "alarm": {alarm_weight: { "key_indicator":{"weight":key_weight, "feature_list": [ ]}, "no_key_indicator":{"weight": no_key_weight, "feature_list": [ ]}}, "diagnosis": {diagnosis_weight: { "key_indicator":{"weight": key_weight, "feature_list": [ ]}, "no_key_indicator":{"weight": no_key_weight, "feature_list": [ ]}}}, "xmax_list":{ : , : }} Among them, alm_target_health is used to define the health target value (score) corresponding to different warning anomaly levels (level), which serves as the health benchmark of the device status when only a warning is triggered.

[0029] The alert level can be divided into four levels: Level 0, Level 1, Level 2, Level 3, and Level 4. Specifically: Level 0: Normal Operation – This means that all vibration parameters of the equipment meet the requirements of vibration standard ISO 10816, and the equipment is in good operating condition. Level 1: Potential Faults – These refer to situations where certain parameters have high vibration values ​​due to structural factors or design, but the potential fault value is not large. After comprehensive analysis, these faults can be monitored during operation. Level 2: Minor fault – This refers to equipment vibration amplitude exceeding the high alarm threshold or the presence of certain potential faults, and the amplitude is increasing. This should be given special attention or necessary inspection should be carried out. Level 3: Obvious fault – This refers to equipment vibration amplitude exceeding the high alarm threshold or the existence of a minor fault that is slowly deteriorating. Troubleshooting or maintenance plans should be arranged promptly. Level 4: Severe fault – This refers to equipment vibration amplitude exceeding the high alarm threshold or the presence of obvious faults that are rapidly deteriorating, requiring immediate repair measures.

[0030] Furthermore, the warning anomaly level can be divided into more or fewer levels depending on the specific device, and the level division is not fixed at four levels. This application does not limit this aspect.

[0031] `dig_target_health` defines the target health score for different diagnosed fault types or combinations thereof, serving as a health benchmark for the equipment's condition when a specific fault exists. Diagnosed fault types can include bearing damage, gearbox failure, rotor abnormality, coupling misalignment, structural loosening, etc. There are no strict type restrictions; as long as the corresponding characteristics exist in the condition monitoring data, it can be defined and identified.

[0032] level_decay_cfg is used to define different exception levels ( ) or fault type ( The corresponding health decay parameter is used to control the degree of decay in health deduction caused by a single anomaly when similar anomalies occur repeatedly or the number of anomalies increases, thereby preventing excessive decline in health due to repeated anomalies. Attenuation factors corresponding to different levels and different fault types.

[0033] alm_dig_weight is used to characterize the weighting relationship between early warning information and diagnostic information in the comprehensive evaluation of equipment health.

[0034] Among them, the alarm weight and diagnosis weight satisfy the constraint that the sum is 1, so as to standardize the relative contribution ratio of different information sources in the health score calculation.

[0035] Furthermore, within the early warning and diagnosis dimensions, weight constraints are set for key and non-key indicators, respectively. The sum of the weights of key indicators (key_indicator) and non-key indicators (no_key_indicator) is 1, used to distinguish the influence intensity of indicators of different importance on the equipment health status assessment results, thereby achieving hierarchical fusion of multi-source information in the health calculation process. `feature_list` is a list of features and fault types for early warning and diagnosis. The weight allocation relationship is defined by diagnostic experts based on equipment status, fault characteristics, and on-site operation and maintenance experience, and there are no fixed values. For specific equipment, if early warning is more important, the early warning weight will increase accordingly; if diagnosis is more critical, the diagnosis weight will increase accordingly.

[0036] xmax_list is used to define different exception levels ( ) or fault type ( The time span parameter of health status changes over time is used to characterize the duration of equipment degradation under different degrees of abnormality, and serves as the boundary constraint condition for the health status time evolution curve.

[0037] The aforementioned basic configurations are uniformly stored in the system configuration module, serving as global constraints for health calculations during device operation and providing a consistent calculation basis for subsequent steps.

[0038] Please refer to the following: Figure 2 , Figure 2 This is a schematic diagram illustrating the classification and grading of abnormal parameters according to an embodiment of this application. As shown in the figure, the present invention first uniformly classifies abnormal information generated during equipment operation, dividing abnormalities into early warning abnormalities and diagnostic abnormalities according to their source. Based on this, a mechanism for grading the importance of abnormalities is further introduced. According to the degree of influence of various monitoring indicators on the safety and health status of equipment operation, early warning abnormalities and diagnostic abnormalities are respectively divided into critical indicator abnormalities and non-critical indicator abnormalities. Critical indicator abnormalities are types of abnormalities that have a significant impact on the safe operation and structural health of the equipment; their occurrence usually indicates a high risk or potential failure of the equipment. Non-critical indicator abnormalities are types of abnormalities that have a relatively small impact on the operating status of the equipment and do not directly threaten the safety of the equipment in the short term. In this embodiment, both early warning abnormalities and diagnostic abnormalities are graded in four levels (level 1 to level 4). Early warning critical indicators include temperature abnormalities, and diagnostic critical abnormalities include rolling bearing cage damage. All other abnormalities are considered non-critical.

[0039] In this embodiment, the basic health configuration parameter health_cfg is formulated by equipment domain experts or engineers based on equipment structure, fault mechanisms, historical operating data and fault data, and on-site operation and maintenance experience. This forms a health assessment parameter system that can be used for specific equipment. Specifically: 1. Based on equipment status characterization indicators and their impact on equipment safety, reliability, and production continuity, various monitoring signals and their characteristic indicators acquired during equipment operation are classified by importance (core basis: whether the indicator will directly lead to rapid equipment deterioration or even shutdown), forming key indicator anomaly types and non-key indicator anomaly types, which are then filled into the key indicator anomaly type set and non-key indicator anomaly type set under the warning dimension and diagnosis dimension in alm_dig_weight, respectively, to support subsequent weight allocation and hierarchical calculation.

[0040] The types of anomalies for critical and non-critical indicators are categorized by diagnostic experts based on equipment mechanisms, the degree of impact of faults, and operational experience. Abnormal types of key indicators include early warning indicators (such as temperature) and diagnostic indicators (such as bearing cage failure). Abnormalities in these indicators can directly lead to rapid equipment deterioration or even shutdown.

[0041] Non-critical indicator anomaly types: Other monitoring and diagnostic indicators that have little impact on the safe operation of equipment and production continuity and will not cause rapid equipment shutdown, in addition to critical indicators.

[0042] Based on the impact of equipment status characterization indicators on equipment safety, reliability, and production continuity, diagnostic experts determine the importance of monitoring signals and characteristic indicators, distinguish between critical and non-critical indicator anomaly types, form an indicator list and classify it into corresponding sets to support subsequent weight allocation and hierarchical calculation.

[0043] 2. Based on this, and in conjunction with the rules for classifying abnormal levels and the definition of diagnostic fault types, corresponding health benchmarks are set for different warning abnormal levels, forming a correspondence between each warning level and the health target value in alm_target_health; At the same time, for different diagnostic fault types or combinations of fault types, corresponding health benchmarks are set to form a mapping relationship between diagnostic fault types and health target values ​​in dig_target_health, so as to reflect the health benchmarks of equipment under different fault states.

[0044] 3. Furthermore, considering the persistent existence or cumulative number of anomalies over time, based on the impact characteristics of anomalies on equipment degradation speed, cumulative effect, and reversibility, health decay parameters are set for different anomaly levels or fault types to form level_decay_cfg, in order to control the changing trend of the health deduction magnitude of a single anomaly when similar anomalies occur repeatedly.

[0045] 4. At the same time, in order to characterize the degradation rate and duration of equipment under different anomaly severity conditions, based on historical operating patterns and engineering experience, time span parameters for the health status evolution over time are set for different anomaly levels or types, forming xmax_list, which serves as the boundary constraint condition for the health status time evolution curve.

[0046] Through the above process, the basic configuration parameters in health_cfg are standardized, enabling them to fully reflect the differences in the importance of indicators, the differences in the degree of abnormal impact, and the time characteristics of equipment degradation, and providing a consistent and configurable rule basis for subsequent health calculation and dynamic assessment.

[0047] As an optional implementation, step 102, which analyzes the abnormal parameters based on preset health baseline configuration parameters to determine the abnormal information corresponding to each abnormal parameter, may include: The abnormal source information of the abnormal parameters is determined based on the preset health status configuration parameters; The abnormality type of the abnormal parameter is determined based on the preset health status configuration parameters; If the anomaly source information is early warning anomaly information, then the early warning anomaly level of the early warning anomaly information is determined; and based on the anomaly source information, the early warning anomaly level, and the indicator anomaly type, anomaly information corresponding to the anomaly parameter is generated; If the abnormality source information is diagnostic abnormality information, then the diagnostic fault type of the diagnostic abnormality information is determined; and based on the abnormality source information, the diagnostic fault type, and the indicator abnormality type, the abnormality information corresponding to the abnormal parameter is generated.

[0048] This implementation method, when identifying abnormal information, further distinguishes the severity level of warning anomalies and the specific fault type of diagnosed anomalies, and performs hierarchical analysis based on the source of the anomaly and the importance of the indicators. This meticulous classification method allows the system to take more targeted deduction actions according to the "urgency" of different anomalies, avoiding biases caused by general assessments. At the same time, standardized analysis through preset basic configuration parameters ensures the uniformity and repeatability of the calculation process, thereby effectively improving the accuracy and engineering practicality of equipment health calculations.

[0049] Step 103: Based on the pre-built target health mapping model and the basic health configuration parameters, process the abnormal information corresponding to each abnormal parameter to obtain a comprehensive deduction value.

[0050] In this embodiment of the application, a comprehensive deduction value can be calculated by an anomaly deduction model. By quantifying and modeling the deduction of early warning anomalies and diagnostic anomalies, multi-source and multi-level anomaly information is uniformly mapped into an accumulative health loss. Furthermore, an attenuation and weighted aggregation mechanism is introduced to characterize the superposition effect of anomalies in the time and type dimensions and their primary and secondary influence relationships.

[0051] Please refer to the following: Figure 3 and Figure 4 , Figure 3 A schematic diagram illustrating a calculation process for a comprehensive deduction value provided in an embodiment of this application; Figure 4 This is a schematic diagram of a similar abnormal attenuation calculation curve provided in an embodiment of this application; as shown... Figure 3 As shown, the deduction model includes three steps: a deduction value reverse calculation model, an anomaly superposition attenuation rule, and a comprehensive deduction calculation. The deduction value reverse calculation model is used to calculate the basic deduction value corresponding to each anomaly level or fault type based on a preset target health level. The anomaly superposition attenuation rule introduces an attenuation coefficient when similar anomalies occur multiple times, avoiding excessive health decline due to simple superposition of anomalies. The attenuation curve is shown in the figure. Figure 4 As shown; the comprehensive deduction calculation is based on this, and combines the weight of the abnormal source and the weight of the indicator importance to weight and summarize the deduction results of various abnormalities to obtain the comprehensive deduction value of the equipment in the current statistical period.

[0052] As an optional implementation, step 103, based on the pre-built target health mapping model and the basic health configuration parameters, processes the abnormal information corresponding to each abnormal parameter to obtain a comprehensive deduction value, and may include the following steps 1031 to 1039: Step 1031: Based on the basic health configuration parameters, determine the target health value corresponding to the abnormal source information of each abnormal parameter.

[0053] Step 1032: Based on the pre-built target health mapping model and the target health value of each abnormal parameter, determine the basic deduction value for each abnormal parameter.

[0054] In this embodiment of the application, the pre-constructed target health mapping model can be: in, The target health value (0~100) is any abnormal parameter. β and γ are the parameters of the first health curve and the second health curve, respectively. (β and γ have no fixed universal values. The core is that the diagnostic experts customize the settings based on the actual operating characteristics of the equipment, the failure evolution law and the on-site safety operation and maintenance requirements to ensure that the health curve can truly reflect the full life cycle status of the equipment from normal operation to serious failure.) Based on the base deduction value, The weights for abnormal sources (which may include warning weights and diagnostic weights) are used. Weights are assigned to indicator types (which may include weights for critical indicator anomalies and weights for non-critical indicator anomalies).

[0055] Therefore, the base deduction value can be deduced as follows: By employing a reverse-engineering method to determine the deduction value, the relative consistency of the impact of different anomaly levels on health status can be ensured. This avoids human bias and insufficient model robustness caused by setting deduction values ​​based on experience, thereby improving the controllability and consistency of health status calculation results. The basic deduction value is used to characterize the degree of impact of a single anomaly on the health status of the equipment.

[0056] Step 1033: Based on the health decay parameter corresponding to the warning anomaly level, merge the basic deduction values ​​of the anomaly parameters of the same warning anomaly level to determine the anomaly level parameter set of the same warning anomaly level; wherein, the anomaly level parameter set contains anomaly level parameter information of different warning anomaly levels, and the anomaly level parameter information contains the current warning anomaly level, indicator anomaly type and actual deduction value.

[0057] In this embodiment of the application, the calculation method for the actual deduction value in the anomaly level parameter information of any warning anomaly level can be as follows: in, Let n be the actual deduction value in the anomaly level parameter information for any given warning anomaly level, where n represents the number of times the same type of anomaly occurs within that given warning anomaly level. This is the health decay parameter (range 0-1) corresponding to any given warning abnormality level.

[0058] In this embodiment, when multiple similar anomalies correspond to the same anomaly source information or the same warning anomaly level, an anomaly attenuation mechanism can be introduced to reduce the deduction value of subsequent anomalies. The core of the actual deduction value is used to statistically analyze the actual deduction value when similar anomalies occur repeatedly, avoiding excessive accumulation of deductions and ensuring that the health calculation results conform to the actual operating law of the equipment's "decreasing rate of degradation of similar anomalies".

[0059] By setting an attenuation mechanism, we can ensure that the impact of subsequent new anomalies of the same type on the health status is less than that of previous anomalies, thus avoiding excessive decline in health status due to the accumulation of anomalies. This makes the changes in health status more consistent with the actual degradation process of the equipment.

[0060] Step 1034: Based on the health decay parameter corresponding to the diagnosed fault type, merge the basic deduction values ​​of abnormal parameters of the same diagnosed fault type to determine the abnormal fault parameter set of the same diagnosed fault type; wherein, the abnormal fault parameter set contains fault parameter information of different diagnosed fault types, and the fault parameter information contains the current diagnosed fault type, the abnormal index type and the actual deduction value.

[0061] In this embodiment, the method for determining the set of abnormal fault parameters of the same diagnostic fault type is the same as that for the set of abnormal level parameters of the same early warning abnormal level, and will not be repeated here.

[0062] Step 1035: Based on the anomaly type of the indicator, divide the set of anomaly level parameters into a set of critical anomaly level parameters and a set of non-critical anomaly level parameters.

[0063] Step 1036: Calculate the critical anomaly level parameter set and the non-critical anomaly level parameter set based on the preset aggregation coefficient to obtain the critical anomaly level aggregated deduction value of the critical anomaly level parameter set and the non-critical anomaly level aggregated deduction value of the non-critical anomaly level parameter set.

[0064] For example, the key anomaly level parameters in the key anomaly level parameter set have the same anomaly type and are all key anomaly types; the non-key anomaly level parameters in the non-key anomaly level parameter set have the same anomaly type and are all non-key anomaly types.

[0065] When the anomaly type of an indicator is consistent with the anomaly type of critical indicator / non-critical indicator, the actual deduction values ​​are aggregated and calculated. During the aggregation process, the most severe anomaly (prioritizing the highest anomaly level, for example, if the current maximum anomaly level is 4, then the warning or fault corresponding to level 4 is the most severe anomaly) takes the lead, and the remaining actual deduction values ​​participate in the calculation with reduced weight, so as to highlight the leading role of critical anomalies in the health status of equipment.

[0066] The formula for calculating the aggregated deduction value for critical anomaly levels / aggregated deduction value for non-critical anomaly levels can be: in, You can aggregate deduction values ​​for critical anomaly levels / aggregate deduction values ​​for non-critical anomaly levels; A preset aggregation coefficient (range 0-1) can be set, which can be determined by diagnostic experts based on equipment failure mechanisms and maintenance experience. This coefficient controls the weighting of non-most severe anomalies in the aggregation calculation, highlighting the dominant role of the highest-level anomalies. It is not a fixed value and can be selected based on the specific equipment. In this implementation example, It can be set to 0.2. argmax can represent the index corresponding to the maximum actual deduction value.

[0067] Step 1037: Based on the abnormality type of the indicator, divide the abnormal fault parameter set into a critical abnormal fault parameter set and a non-critical abnormal fault parameter set.

[0068] Step 1038: Calculate the critical fault level aggregated deduction value of the critical fault level set and the non-critical fault level set based on the preset aggregation coefficient, respectively, to obtain the non-critical fault aggregated deduction value of the non-critical fault level set and the non-critical fault level aggregated deduction value of the non-critical fault level set.

[0069] For example, the key abnormal fault parameters in the set of key abnormal fault parameters have the same abnormality type and are all key abnormality types; the non-key abnormality level parameters in the set of non-key abnormality level parameters have the same abnormality type and are all non-key abnormality types.

[0070] In this embodiment of the application, the calculation method of the aggregated deduction value of critical fault level / aggregated deduction value of non-critical fault level is the same as the calculation method of the aggregated deduction value of critical anomaly level / aggregated deduction value of non-critical anomaly level, and will not be repeated here.

[0071] Step 1039: Calculate the comprehensive deduction value based on the warning weight, the diagnosis weight, the key indicator anomaly type weight, the non-key indicator anomaly type weight, the key anomaly level aggregate deduction value, the non-key anomaly level aggregate deduction value, the key fault level aggregate deduction value, and the non-key anomaly fault aggregate deduction value.

[0072] In this embodiment, the deduction values ​​of various anomalies are weighted and summed according to the weight of the anomaly source type and the weight of the indicator importance to obtain the comprehensive deduction value of the device. The formula can be: The overall deduction score is used to characterize the overall degree of equipment abnormality within the current statistical period.

[0073] This implementation method, when processing abnormal information and calculating the comprehensive deduction value, first uses the target health level to deduce the basic deduction value for each abnormality. Then, it attenuates and merges the deductions according to the abnormality level or fault type, avoiding excessive score drops caused by repeated deductions for similar abnormalities. Next, it aggregates based on key and non-key indicator types, introducing an aggregation coefficient to highlight the dominant role of the most severe abnormality. Finally, it combines the hierarchical weighting of early warning and diagnosis. This hierarchical, categorized, and prioritized calculation method ensures that the comprehensive deduction value reflects the overall impact of multi-parameter abnormalities while preventing secondary abnormalities from interfering with the main judgment, thereby effectively improving the rationality and accuracy of equipment health calculation.

[0074] In this implementation example, both early warning anomalies and diagnostic anomalies are classified into four levels. The parameters for each level are determined by diagnostic experts by combining equipment lifecycle maintenance data, historical fault statistics, fault degradation patterns, industry maintenance standards, and business requirements.

[0075] Based on the degree of impact of different levels of faults on equipment operation, the target health levels are set to 93, 84, 72, and 55 for Level 1, Level 2, Level 3, and Level 4, respectively.

[0076] The target health scores of 93, 84, 72, and 55 are determined by diagnostic experts based on a comprehensive analysis of equipment lifecycle maintenance data, failure degradation patterns, and industry maintenance standards. The core logic is as follows: 1. Data Foundation: Based on historical fault data of similar equipment, statistical analysis is conducted on the quantitative values ​​corresponding to the actual health status of the equipment when level 1-4 warning / diagnostic anomalies occur (e.g., when a level 1 anomaly (potential fault) occurs, the equipment can still operate stably, corresponding to a health level of 93; when a level 4 anomaly (serious fault) occurs, the equipment is close to the risk of shutdown, corresponding to a health level of 55). 2. Business Adaptation: Combine the equipment operation and maintenance requirements (e.g., Level 1 anomalies do not require shutdown, only monitoring, so the health level is set above 90; Level 4 anomalies require emergency repair, so the health level is set below 60), and refer to equipment vibration / operation standards such as ISO10816 to ensure that the values ​​are consistent with on-site operation and maintenance decisions. 3. Gradient design: The health level decreases in a stepwise manner according to the severity of the anomaly from level 1 to 4 (93→84→72→55). The decrease rate matches the actual degradation rate of the fault from "potential degradation" to "severe failure", avoiding sudden changes in health level or excessively slow decay.

[0077] The attenuation coefficient for similar anomalies was uniformly set to 0.3, taking into account historical anomaly evolution data and expert experience. Meanwhile, to reflect the differences in the impact of different anomaly types and monitoring indicators on equipment status, in the health calculation, diagnostic experts set the weights for early warning and diagnosis to 0.45 and 0.55 respectively, based on the equipment's operating characteristics; and the weights for key indicators and non-key indicators to 0.55 and 0.45 respectively.

[0078] These values ​​are not fixed and can be adjusted flexibly according to the actual scenario. The adjustment is mainly based on the following three points: 1. Equipment type / operating condition changes: Different equipment (such as centrifugal pumps, motors, gearboxes) have different fault tolerance. For example, high-speed motors deteriorate faster when they fail, so the level 4 target health can be lowered from 55 to 50; if the equipment operates under milder conditions (such as low load), the level 1 target health can be raised from 93 to 95. 2. Adjustment of operation and maintenance strategy: If the on-site operation and maintenance requirements are changed from "post-event maintenance" to "preventive maintenance", the health of each level of target can be increased (e.g., level 4 can be increased from 55 to 60) to trigger maintenance warnings in advance; if operation and maintenance resources are tight, the target health can be appropriately reduced to extend the window period for equipment to operate with faults. 3. Historical data iteration and optimization: As equipment operation data accumulates, if it is found that the target health level does not match the actual fault development (e.g., when the health level is 84 for a level 2 anomaly, the actual fault risk of the equipment is much higher than expected), the value can be corrected based on new fault data to ensure that the health level is consistent with the true state of the equipment.

[0079] Please refer to the following: Figure 5 and Figure 6 , Figure 5 This application provides a schematic diagram of a total deduction score and health status mapping curve according to an embodiment of the present application; the obtained comprehensive deduction score is substituted into a preset health status mapping model, and the current health status value of the device is calculated according to an exponential mapping relationship, wherein the health status curve parameters β are set to 6 and γ are set to 2, and the correspondence between the comprehensive deduction score and the health status is obtained as follows. Figure 5 As shown, the health level is limited to a value range of 0 to 100; where a larger health level value indicates a better health status of the device, and a smaller value indicates a worse health status of the device. When the health level reaches the lower limit, its minimum value is 0.

[0080] Figure 6 This is a schematic diagram of a continuous curve showing the change of health status over time, provided in one embodiment of this application. Combining the time span parameters corresponding to the anomaly levels (in this embodiment, the time spans corresponding to each anomaly level increase sequentially, specifically the time span parameters for levels 4 to 0), the health status is processed to achieve time continuity. By constructing a continuously changing curve that monotonically decreases with operating time, the equipment health status smoothly declines over time within the same anomaly level stage, and automatically enters a new health status evolution stage when the anomaly level changes. The relationship between health status and time is as follows: Figure 6 As shown, this avoids frequent jumps in health status results within adjacent statistical periods, thereby improving the stability, continuity, and interpretability of equipment health status assessment results.

[0081] Step 104: Based on the pre-built final health mapping model and the basic health configuration parameters, calculate the comprehensive deduction value and the current running time count to obtain the final health of the industrial equipment.

[0082] In this embodiment of the application, the pre-constructed final health mapping model can be: This model is the formula for calculating the current health value.

[0083] As an optional implementation, step 104, based on a pre-built final health mapping model and the basic health configuration parameters, calculates the comprehensive deduction value and the current running time count to obtain the final health of the industrial equipment. This can be achieved through methods such as: The comprehensive deduction value is input into the pre-built final health mapping model to obtain the current health value; Based on the aforementioned basic health configuration parameters, determine the time span parameter corresponding to the current running time count and the current health value; The final health status of the industrial equipment is calculated by inputting the preset curve shape parameters, the current running time count, and the time span parameters into the final health status mapping model.

[0084] This implementation method incorporates runtime counts and corresponding time span parameters when calculating the final health score, smoothing the current health score value. As a result, the health score is no longer a simple instantaneous value, but gradually decreases as the anomaly persists, avoiding score jumps caused by single anomaly fluctuations and making the health score curve more continuous and stable. Simultaneously, the degradation rate can be flexibly controlled through curve shape parameters, closely reflecting the actual evolution of equipment from minor anomalies to severe failures. This continuous time processing significantly improves the stability and accuracy of equipment health assessment, providing a more reliable basis for long-term condition trend analysis.

[0085] In this embodiment of the application, the formula for calculating the current health value is: ; in, The current health value is represented by β, which represents the preset first health curve parameter, and γ represents the preset second health curve parameter. This represents the total deduction value.

[0086] To ensure that the health status exhibits a smooth and monotonous deterioration trend over time, the time span parameter corresponding to the anomaly level is used. Perform continuous processing, assuming the initial health level for the current stage is... The current stage running time count is x, and a smooth curve is used for continuity: Where α is a preset curve shape parameter. And when hour, The final health score ranges from 0 to 100, with a higher score indicating a better health status and a lower score indicating a worse health status.

[0087] (The time span of health decline corresponding to each anomaly level) is set by diagnostic experts based on the degradation rate of different fault levels of the equipment, the operation and maintenance handling cycle, and the differences in historical fault data: Core logic: The higher the anomaly level (the more severe the fault), the shorter the time span for the equipment health to drop to the lower limit. The smaller the value, the better it aligns with the equipment operation pattern of "high-level faults deteriorate faster and require intervention in a shorter time"; Values ​​are based on the average time (in hours / days) from the occurrence of a fault to the need for downtime maintenance for similar equipment at fault levels 1-4. Level 0 (no abnormalities) is the natural decay period of the equipment's normal operating health.

[0088] These are non-fixed parameters and can be set differently based on specific equipment type, operating conditions, maintenance strategies, and historical fault data. Different values ​​can be used for different equipment or different application scenarios to more accurately reflect the actual degradation pattern of the equipment.

[0089] Please refer to the following: Figure 7 , Figure 7 This is a schematic diagram of the health status change curve of a certain device, provided as an embodiment of this application. Specifically, it is a schematic diagram of the health status change curve of a device during a complete operating event from January 1, 2021 to January 26, 2021. This event includes the entire process of slight wear caused by poor lubrication in the initial stage, local overheating and increased vibration caused by wear accumulation in the middle stage, and the subsequent development of bearing cage-related failures, followed by shutdown and maintenance before resuming operation. During continuous operation, the horizontal axis represents the operating time, and the vertical axis represents the device health status value. Figure 7It can be seen that in the early stages of the event, the internal friction conditions of the bearing changed due to the gradual deterioration of lubrication, and operating parameters such as temperature and vibration showed slight abnormalities. However, no obvious structural failures had yet formed, and the overall equipment health remained at a high level, slowly declining over time. In the middle stages of the event, as the poor lubrication persisted, slight wear occurred on the bearing rolling elements and raceway surfaces. The wear effect gradually accumulated, further aggravating the related abnormalities and increasing the abnormality level. This led to a slightly faster rate of decline in equipment health compared to the initial stage, but the overall change remained gradual and continuous. In the later stages of the event, internal bearing wear further developed. Under alternating loads and long-term operation, the wear gradually extended to the cage structure, and cage-related failures began to appear and worsen. These failures had a significant impact on the equipment's operating status, causing a rapid decline in equipment health within a short period. Subsequently, the equipment entered a shutdown and maintenance phase due to the further development of cage-related failures. During the shutdown, the equipment ceased operation, effectively interrupting the deterioration process, and the health value remained relatively stable during this period. After the shutdown and maintenance were completed, the bearing cage-related faults were addressed, the lubrication condition was improved, and the equipment was put back into operation. The equipment's health condition recovered to some extent compared to before the shutdown and maintenance, but it did not fully return to the initial level of the incident. During subsequent operation, due to the influence of residual wear factors, the equipment's health condition showed a trend of gradually declining over time. Figure 7 It provides a relatively complete picture of the health status evolution of equipment caused by poor lubrication, which, through wear accumulation, eventually evolves into bearing cage failure.

[0090] Implementing steps 101 to 104 improves the accuracy of industrial equipment health calculations, providing a more reliable quantitative basis for equipment condition assessment and maintenance decisions. Furthermore, this application can standardize the analysis using preset basic configuration parameters, ensuring the uniformity and repeatability of the calculation process, thereby effectively improving the accuracy and engineering applicability of equipment health calculations. In addition, this application can effectively improve the rationality and accuracy of equipment health calculations. Moreover, this application can improve the stability and accuracy of equipment health assessments, providing a more reliable basis for long-term condition trend analysis.

[0091] Based on the same inventive concept, this application also provides a health calculation device for industrial equipment to implement the above-described health calculation method for industrial equipment. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the health calculation device for industrial equipment provided below can be found in the limitations of the health calculation method for industrial equipment described above, and will not be repeated here.

[0092] In one exemplary embodiment, such as Figure 8 As shown, a health measurement device for industrial equipment is provided, comprising: The acquisition unit 801 is used to acquire abnormal parameters of industrial equipment and the current running time count; The determining unit 802 is used to analyze the abnormal parameters based on preset health baseline configuration parameters to determine the abnormal information corresponding to each abnormal parameter. The abnormal information includes the abnormal source information and the indicator abnormality type of the abnormal parameter. The abnormal source information is either early warning abnormality information or diagnostic abnormality information, and the indicator abnormality type is either a key indicator abnormality type or a non-key indicator abnormality type. The preset health baseline configuration parameters include target health values ​​and health decay parameters corresponding to different early warning abnormality levels, target health values ​​and health decay parameters corresponding to different diagnostic fault types, anomaly source weight allocation relationships, indicator abnormality type weight allocation relationships, and time span parameters corresponding to different comprehensive abnormality levels. Specifically, the sum of the early warning weight and diagnostic weight in the anomaly source weight allocation relationship is 1; the sum of the key indicator abnormality type weight and the non-key indicator abnormality type weight in the indicator abnormality type weight allocation relationship is 1.

[0093] The processing unit 803 is used to process the abnormal information corresponding to each abnormal parameter based on the pre-built target health mapping model and the basic health configuration parameters to obtain a comprehensive deduction value. The calculation unit 804 is used to calculate the comprehensive deduction value and the current running time count based on the pre-built final health mapping model and the basic health configuration parameters to obtain the final health of the industrial equipment.

[0094] As an optional implementation, the determining unit 802 analyzes the abnormal parameters based on preset health configuration parameters to determine the abnormal information corresponding to each abnormal parameter in the following specific ways: The abnormal source information of the abnormal parameters is determined based on the preset health status configuration parameters; The abnormality type of the abnormal parameter is determined based on the preset health status configuration parameters; If the anomaly source information is early warning anomaly information, then the early warning anomaly level of the early warning anomaly information is determined; and based on the anomaly source information, the early warning anomaly level, and the indicator anomaly type, anomaly information corresponding to the anomaly parameter is generated; If the abnormality source information is diagnostic abnormality information, then the diagnostic fault type of the diagnostic abnormality information is determined; and based on the abnormality source information, the diagnostic fault type, and the indicator abnormality type, the abnormality information corresponding to the abnormal parameter is generated.

[0095] This implementation method, when identifying abnormal information, further distinguishes the severity level of warning anomalies and the specific fault type of diagnosed anomalies, and performs hierarchical analysis based on the source of the anomaly and the importance of the indicators. This meticulous classification method allows the system to take more targeted deduction actions according to the "urgency" of different anomalies, avoiding biases caused by general assessments. At the same time, standardized analysis through preset basic configuration parameters ensures the uniformity and repeatability of the calculation process, thereby effectively improving the accuracy and engineering practicality of equipment health calculations.

[0096] As an optional implementation, the processing unit 803 processes the abnormal information corresponding to each abnormal parameter based on a pre-built target health mapping model and the basic health configuration parameters to obtain a comprehensive deduction value. Specifically, this can be achieved by: Based on the aforementioned basic health configuration parameters, determine the target health value corresponding to the abnormal source information of each abnormal parameter; Based on the pre-built target health mapping model and the target health value of each abnormal parameter, the basic deduction value of each abnormal parameter is determined. Based on the health decay parameter corresponding to the warning anomaly level, the basic deduction values ​​of the anomaly parameters of the same warning anomaly level are merged to determine the anomaly level parameter set of the same warning anomaly level; wherein, the anomaly level parameter set contains anomaly level parameter information of different warning anomaly levels, and the anomaly level parameter information contains the current warning anomaly level, the indicator anomaly type and the actual deduction value. Based on the health decay parameter corresponding to the diagnosed fault type, the base deduction values ​​of abnormal parameters of the same diagnosed fault type are merged to determine the abnormal fault parameter set of the same diagnosed fault type; wherein, the abnormal fault parameter set contains fault parameter information of different diagnosed fault types, and the fault parameter information contains the current diagnosed fault type, the abnormal indicator type, and the actual deduction value. Based on the anomaly type of the indicator, the set of anomaly level parameters is divided into a set of critical anomaly level parameters and a set of non-critical anomaly level parameters. Based on a preset aggregation coefficient, the critical anomaly level parameter set and the non-critical anomaly level parameter set are calculated respectively to obtain the critical anomaly level aggregated deduction value of the critical anomaly level parameter set and the non-critical anomaly level aggregated deduction value of the non-critical anomaly level parameter set. Based on the anomaly type of the indicator, the set of abnormal fault parameters is divided into a set of critical abnormal fault parameters and a set of non-critical abnormal fault parameters. Based on a preset aggregation coefficient, the critical fault parameter set and the non-critical fault parameter set are calculated respectively to obtain the critical fault level aggregated deduction value of the critical fault parameter set and the non-critical fault aggregated deduction value of the non-critical fault parameter set. A comprehensive deduction value is calculated based on the warning weight, the diagnosis weight, the key indicator anomaly type weight, the non-key indicator anomaly type weight, the key anomaly level aggregate deduction value, the non-key anomaly level aggregate deduction value, the key fault level aggregate deduction value, and the non-key anomaly fault aggregate deduction value.

[0097] This implementation method, when processing abnormal information and calculating the comprehensive deduction value, first uses the target health level to deduce the basic deduction value for each abnormality. Then, it attenuates and merges the deductions according to the abnormality level or fault type, avoiding excessive score drops caused by repeated deductions for similar abnormalities. Next, it aggregates based on key and non-key indicator types, introducing an aggregation coefficient to highlight the dominant role of the most severe abnormality. Finally, it combines the hierarchical weighting of early warning and diagnosis. This hierarchical, categorized, and prioritized calculation method ensures that the comprehensive deduction value reflects the overall impact of multi-parameter abnormalities while preventing secondary abnormalities from interfering with the main judgment, thereby effectively improving the rationality and accuracy of equipment health calculation.

[0098] As an optional implementation, the calculation unit 804 calculates the comprehensive deduction value and the current running time count based on a pre-built final health mapping model and the basic health configuration parameters to obtain the final health of the industrial equipment. Specifically, this can be achieved by: The comprehensive deduction value is input into the pre-built final health mapping model to obtain the current health value; Based on the aforementioned basic health configuration parameters, determine the time span parameter corresponding to the current running time count and the current health value; The final health status of the industrial equipment is calculated by inputting the preset curve shape parameters, the current running time count, and the time span parameters into the final health status mapping model.

[0099] This implementation method incorporates runtime counts and corresponding time span parameters when calculating the final health score, smoothing the current health score value. As a result, the health score is no longer a simple instantaneous value, but gradually decreases as the anomaly persists, avoiding score jumps caused by single anomaly fluctuations and making the health score curve more continuous and stable. Simultaneously, the degradation rate can be flexibly controlled through curve shape parameters, closely reflecting the actual evolution of equipment from minor anomalies to severe failures. This continuous time processing significantly improves the stability and accuracy of equipment health assessment, providing a more reliable basis for long-term condition trend analysis.

[0100] In this embodiment of the application, the formula for calculating the current health value is: ; in, The current health value is represented by β, which represents the preset first health curve parameter, and γ represents the preset second health curve parameter. This represents the total deduction value.

[0101] Implementing the above-described methods improves the accuracy of industrial equipment health calculations, providing a more reliable quantitative basis for equipment condition assessment and maintenance decisions. Furthermore, this application can standardize the analysis using preset basic configuration parameters, ensuring the uniformity and repeatability of the calculation process, thereby effectively improving the accuracy and engineering applicability of equipment health calculations. In addition, this application can effectively improve the rationality and accuracy of equipment health calculations. Moreover, this application can enhance the stability and accuracy of equipment health assessments, providing a more reliable basis for long-term condition trend analysis.

[0102] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 9As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores health calculation data for industrial equipment. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for calculating the health of industrial equipment.

[0103] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0105] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0106] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0107] In one exemplary embodiment, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the steps in the above method embodiments and achieve the same technical effect, and will not be described again here to avoid repetition.

[0108] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0109] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0110] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0111] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for calculating the health status of industrial equipment, characterized in that, The method for calculating the health status of the industrial equipment includes: Obtain abnormal parameters and current running time count of industrial equipment; The abnormal parameters are analyzed based on the preset health status configuration parameters to determine the abnormal information corresponding to each abnormal parameter; wherein, the abnormal information includes the abnormal source information and the indicator abnormal type of the abnormal parameter, the abnormal source information is the early warning abnormal information or the diagnostic abnormal information, and the indicator abnormal type is the critical indicator abnormal type or the non-critical indicator abnormal type. Based on the pre-built target health mapping model and the basic health configuration parameters, the abnormal information corresponding to each abnormal parameter is processed to obtain a comprehensive deduction value; Based on the pre-built final health mapping model and the basic health configuration parameters, the comprehensive deduction value and the current running time count are calculated to obtain the final health of the industrial equipment.

2. The method for calculating the health status of industrial equipment according to claim 1, characterized in that, The preset basic health status configuration parameters include target health status values ​​and health status decay parameters corresponding to different warning anomaly levels, target health status values ​​and health status decay parameters corresponding to different diagnostic fault types, anomaly source weight allocation relationship, indicator anomaly type weight allocation relationship, and time span parameters corresponding to different comprehensive anomaly levels; wherein: The sum of the warning weight and the diagnostic weight included in the anomaly source weight allocation relationship is 1; The sum of the weights of key indicator anomaly types and non-key indicator anomaly types in the weight allocation relationship of the indicator anomaly types is 1.

3. The method for calculating the health status of industrial equipment according to claim 2, characterized in that, The analysis of the abnormal parameters based on preset health status configuration parameters, and the determination of the abnormal information corresponding to each abnormal parameter, specifically includes: The abnormal source information of the abnormal parameters is determined based on the preset health status configuration parameters; The abnormality type of the abnormal parameter is determined based on the preset health status configuration parameters; If the anomaly source information is early warning anomaly information, then the early warning anomaly level of the early warning anomaly information is determined; and based on the anomaly source information, the early warning anomaly level, and the indicator anomaly type, anomaly information corresponding to the anomaly parameter is generated; If the abnormality source information is diagnostic abnormality information, then the diagnostic fault type of the diagnostic abnormality information is determined; and based on the abnormality source information, the diagnostic fault type, and the indicator abnormality type, the abnormality information corresponding to the abnormal parameter is generated.

4. The method for calculating the health status of industrial equipment according to claim 3, characterized in that, Based on the pre-built target health mapping model and the basic health configuration parameters, the abnormal information corresponding to each abnormal parameter is processed to obtain a comprehensive deduction value, specifically including: Based on the aforementioned basic health configuration parameters, determine the target health value corresponding to the abnormal source information of each abnormal parameter; Based on the pre-built target health mapping model and the target health value of each abnormal parameter, the basic deduction value of each abnormal parameter is determined. Based on the health decay parameter corresponding to the warning anomaly level, the basic deduction values ​​of the anomaly parameters of the same warning anomaly level are merged to determine the anomaly level parameter set of the same warning anomaly level; wherein, the anomaly level parameter set contains anomaly level parameter information of different warning anomaly levels, and the anomaly level parameter information contains the current warning anomaly level, the indicator anomaly type and the actual deduction value. Based on the health decay parameter corresponding to the diagnosed fault type, the base deduction values ​​of abnormal parameters of the same diagnosed fault type are merged to determine the abnormal fault parameter set of the same diagnosed fault type; wherein, the abnormal fault parameter set contains fault parameter information of different diagnosed fault types, and the fault parameter information contains the current diagnosed fault type, the abnormal indicator type, and the actual deduction value. Based on the anomaly type of the indicator, the set of anomaly level parameters is divided into a set of critical anomaly level parameters and a set of non-critical anomaly level parameters. Based on a preset aggregation coefficient, the critical anomaly level parameter set and the non-critical anomaly level parameter set are calculated respectively to obtain the critical anomaly level aggregated deduction value of the critical anomaly level parameter set and the non-critical anomaly level aggregated deduction value of the non-critical anomaly level parameter set. Based on the anomaly type of the indicator, the set of abnormal fault parameters is divided into a set of critical abnormal fault parameters and a set of non-critical abnormal fault parameters. Based on a preset aggregation coefficient, the critical fault parameter set and the non-critical fault parameter set are calculated respectively to obtain the critical fault level aggregated deduction value of the critical fault parameter set and the non-critical fault aggregated deduction value of the non-critical fault parameter set. A comprehensive deduction value is calculated based on the warning weight, the diagnosis weight, the key indicator anomaly type weight, the non-key indicator anomaly type weight, the key anomaly level aggregate deduction value, the non-key anomaly level aggregate deduction value, the key fault level aggregate deduction value, and the non-key anomaly fault aggregate deduction value.

5. The method for calculating the health status of industrial equipment according to claim 4, characterized in that, The final health status of the industrial equipment is obtained by calculating the comprehensive deduction value and the current running time count based on the pre-built final health status mapping model and the basic health status configuration parameters, specifically including: The comprehensive deduction value is input into the pre-built final health mapping model to obtain the current health value; Based on the aforementioned basic health configuration parameters, determine the time span parameter corresponding to the current running time count and the current health value; The final health status of the industrial equipment is calculated by inputting the preset curve shape parameters, the current running time count, and the time span parameters into the final health status mapping model.

6. The method for calculating the health status of industrial equipment according to claim 5, characterized in that, The formula for calculating the current health value is: ； in, The current health value is represented by β, which represents the preset first health curve parameter, and γ represents the preset second health curve parameter. This represents the total deduction value.

7. A health status calculation device for industrial equipment, characterized in that, The health calculation device for the industrial equipment includes: The acquisition unit is used to acquire abnormal parameters of industrial equipment and the current running time count; The determination unit is used to analyze the abnormal parameters based on preset health status configuration parameters and determine the abnormal information corresponding to each abnormal parameter; wherein, the abnormal information includes the abnormal source information and the indicator abnormal type of the abnormal parameter, the abnormal source information is early warning abnormal information or diagnostic abnormal information, and the indicator abnormal type is a key indicator abnormal type or a non-key indicator abnormal type. The processing unit is used to process the abnormal information corresponding to each abnormal parameter based on the pre-built target health mapping model and the basic health configuration parameters to obtain a comprehensive deduction value. The calculation unit is used to calculate the comprehensive deduction value and the current running time count based on the pre-built final health mapping model and the basic health configuration parameters to obtain the final health of the industrial equipment.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the health calculation method for industrial equipment according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the health calculation method for industrial equipment as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the health calculation method for industrial equipment as described in any one of claims 1-6.

Images