Device health detection method

Abstract

The application discloses a kind of equipment health degree detection methods. By obtaining the equipment data of equipment to be detected and the measuring point data of at least one to be detected point;Measuring point data at least includes: measuring point position information, transmission relationship between measuring points, measuring point vibration signal data;Based on measuring point vibration signal data, determine equipment failure evaluation attribute;According to measuring point data, determine measuring point abnormal evaluation attribute;Based on equipment life evaluation model, equipment data is processed, and equipment life evaluation attribute is determined;In equipment failure evaluation attribute, measuring point abnormal evaluation attribute and equipment life evaluation attribute, determine the associated evaluation attribute corresponding to the calibration dimension;Associated evaluation attribute is checked and handled, and at least one calibration result under the calibration dimension is obtained;According to at least one calibration result, equipment failure evaluation attribute, measuring point abnormal evaluation attribute and equipment life evaluation attribute are processed, and target health degree is obtained.The application improves the accuracy, comprehensiveness and reliability of equipment health degree detection.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method for detecting the health status of equipment. Background Technology

[0002] In coal mining, transportation, and other operational scenarios, the health status of related equipment directly affects the normal operation of coal mining, production efficiency, and operational safety.

[0003] Currently, the health assessment of relevant equipment typically involves comparing vibration signal data from measuring points with preset thresholds to determine the corresponding health level. However, this method relies on a single dimension for evaluation, which can be somewhat one-sided. Furthermore, evaluating solely based on preset thresholds introduces subjectivity and cannot guarantee the accuracy of the assessment results. Summary of the Invention

[0004] This invention provides a method for detecting equipment health status, which improves the accuracy, comprehensiveness, and reliability of equipment health status detection.

[0005] According to one aspect of the present invention, a method for detecting the health status of a device is provided, applied to a device to be tested, wherein the device to be tested has at least one point to be tested, the method comprising: Acquire equipment data of the device to be tested and measurement point data of at least one of the test points within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times; Based on vibration signal data of at least one of the test points at multiple acquisition times, determine the equipment fault assessment attributes; Based on the measurement data of at least one of the measurement points to be detected, determine the measurement point anomaly assessment attributes; The equipment maintenance data and equipment operating condition data are processed based on a pre-trained equipment life assessment model to determine the equipment life assessment attributes. For at least one verification dimension, among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute, an associated assessment attribute related to the verification dimension is determined; wherein, the at least one verification dimension includes one or more of the following: change trend verification dimension, consistency verification dimension, and confidence level verification dimension; The associated evaluation attributes are validated to obtain the validation results under the validation dimensions. Based on at least one of the verification results, the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute are processed to obtain the target health of the equipment under test.

[0006] According to another aspect of the present invention, a device health detection apparatus is provided, applied to a device to be tested, wherein the device to be tested has at least one detection point, the apparatus comprising: The data acquisition module is used to acquire equipment data of the device to be tested and measurement point data of at least one of the test points within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times; The equipment fault assessment module is used to determine the equipment fault assessment attributes based on the vibration signal data of at least one of the test points at multiple acquisition times. The measurement point anomaly assessment module is used to determine the measurement point anomaly assessment attribute based on the measurement point data of at least one of the measurement points to be detected. The equipment life assessment module is used to process the equipment maintenance data and equipment operating condition data based on a pre-trained equipment life assessment model to determine the equipment life assessment attributes. The associated evaluation attribute determination module is used to determine, for at least one verification dimension, an associated evaluation attribute among the equipment failure evaluation attribute, the measurement point anomaly evaluation attribute, and the equipment lifespan evaluation attribute; wherein, the at least one verification dimension includes one or more of the following: a change trend verification dimension, a consistency verification dimension, and a confidence level verification dimension. The verification result determination module is used to perform verification processing on the associated evaluation attributes and obtain the verification result under the verification dimension; The equipment health determination module is used to process the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute based on at least one of the verification results to obtain the target health of the equipment to be tested.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the device health detection method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the device health detection method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the device health detection method as described in any embodiment of the present invention.

[0010] The technical solution of this invention is applied to a device under test. At least one test point is set in the device under test. Device data and measurement point data of at least one test point are acquired within a first preset time period. Based on the vibration signal data of at least one test point at multiple acquisition times, the device fault assessment attribute of the device under test is determined. Based on the measurement point data of at least one test point, the measurement point anomaly assessment attribute of the device under test is determined. The device maintenance data and device operating condition data are processed according to a device lifespan assessment model to obtain the device lifespan assessment attribute. This achieves a multi-dimensional health assessment of the device under test, ensuring the comprehensiveness of the health assessment and improving the accuracy of the subsequently determined device health. For at least one verification dimension, among the device fault assessment attribute, measurement point anomaly assessment attribute, and device lifespan assessment attribute, a related assessment attribute associated with the verification dimension is determined, and the corresponding related assessment attribute is verified to obtain the verification result under the corresponding verification dimension. Based on at least one verification result, the device fault assessment attribute, measurement point anomaly assessment attribute, and device lifespan assessment attribute are processed to obtain the target health of the device under test. The above-described method enables dynamic adjustment of each evaluation attribute based on the verification results, effectively avoiding the problem of health distortion caused by conflicts between evaluation attributes, and improving the accuracy and consistency of evaluation attributes. This invention solves the problems of bias and subjectivity caused by evaluation based on a single-dimensional preset threshold in existing technologies. By conducting multi-dimensional evaluation of the device under test and combining the verification results of the evaluation attributes, the target health level is determined, improving the accuracy, comprehensiveness, and reliability of device health detection.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a device health detection method provided in an embodiment of the present invention; Figure 2 This is a flowchart of a device health detection method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a device for detecting equipment health according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the device health detection method of this invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] 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 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.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] Before introducing the embodiments of the present invention, the application scenarios of the embodiments of the present invention can be described first. The embodiments of the present invention are applicable to any industrial equipment that requires equipment health assessment. For example, in the scenario of coal mining and transportation, the technical solution provided by the embodiments of the present invention can be used to perform health detection on coal mining transportation and related equipment, so as to adjust the corresponding equipment according to the determined equipment health status, and ensure the smooth and safe operation of coal mining transportation.

[0018] It should be noted that since the technical solution provided in this embodiment of the invention can be applied to every piece of industrial equipment to achieve equipment health detection, the industrial equipment currently requiring health detection can be considered as the equipment to be tested. One or more test points are set in the equipment to be tested to determine its vibration status. These test points can be understood as detection location points within the equipment.

[0019] Example 1 Figure 1 This is a flowchart of a device health detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the health assessment of any industrial equipment. The method can be executed by a device health detection device, which can be implemented in hardware and / or software. This device can be configured in electronic devices such as mobile phones, computers, or servers. Figure 1 As shown, the method includes: S110. Acquire equipment data of the device to be tested and measurement point data of at least one test point within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points and vibration signal data of measurement points at multiple acquisition times.

[0020] The first preset duration can be a pre-set duration preceding the current moment. Device data can be data acquired during data collection from the device under test. Measurement point data can be data determined during data collection from the points under test.

[0021] Equipment maintenance data can be used to characterize the equipment maintenance status of the equipment under test within a first preset time period. Optionally, the equipment maintenance data may include equipment fault information, equipment maintenance information, etc. For example, the equipment maintenance data may include faults that occurred in the equipment under test within the first preset time period, the maintenance time for each fault, and the corresponding maintenance measures taken.

[0022] Equipment operating condition data is used to characterize the operating status of the equipment under test within a first preset time period. Optionally, the equipment operating condition data may include equipment operating parameters (such as speed, current, voltage, etc.) and equipment status information (such as running time, downtime, standby time, etc.) of the equipment under test.

[0023] For the device under test, a vibration sensor can be installed at at least one preset location within the device. The preset location is the test point within the device. The vibration sensor is used to collect vibration signal data of the test point in real time during the operation of the device. The vibration signal data can include the vibration waveform data of the test point. Within a first preset time period, vibration signal data of each test point can be collected at multiple acquisition times.

[0024] For at least one test point in the equipment under test, the measurement point position information can be determined based on the location of each test point within the equipment. That is, the measurement point position information is used to characterize the location of the test point within the equipment. Correspondingly, the test point may correspond to the position of certain components within the equipment, and these components have certain mechanical transmission relationships during equipment operation. Therefore, the transmission relationship between measurement points can be determined based on the mechanical transmission relationship between the equipment components to which at least one test point belongs. That is, the transmission relationship between measurement points can be used to characterize the mechanical transmission relationship between the equipment components to which the test point belongs.

[0025] Specifically, at least one test point is set in the device under test, and a vibration sensor is deployed at each test point. When the device under test is detected to be in operation, vibration signal data of the corresponding test point are collected in real time at multiple collection times within a first preset time period based on the vibration sensor.

[0026] Based on the location of each test point within the equipment under test, determine the measurement point position information. Based on the mechanical transmission relationship between the components to which each test point belongs within the equipment under test, determine the transmission relationship between the measurement points. The vibration signal data, measurement point position information, and transmission relationship between measurement points are then used as the measurement point data for each test point.

[0027] Accordingly, the equipment maintenance data and equipment operating condition data of the device under test are acquired within a first preset time period. This equipment maintenance data and equipment operating condition data are then used as the equipment data for the device under test.

[0028] S120. Based on the vibration signal data of at least one test point at multiple acquisition times, determine the equipment fault assessment attributes.

[0029] Among them, the equipment failure assessment attribute is used to characterize the probability of the equipment under test failing. Optionally, the equipment failure assessment attribute can be characterized by a probability value. For example, if the equipment failure assessment attribute is 50%, it means that the probability of the equipment under test failing is 50%.

[0030] It should be noted that the equipment fault assessment attributes are specific to the equipment under test, meaning they can be determined by combining the vibration signal data of all test points of the equipment under test at each acquisition time.

[0031] Specifically, for multiple acquisition times, fault assessment processing is performed on the vibration signal data of at least one test point in the device under test at each acquisition time to determine the assessment attribute corresponding to each acquisition time. Based on the assessment attributes at multiple acquisition times, the device fault assessment attribute is determined.

[0032] Optionally, the evaluation attributes at multiple acquisition times can be averaged or extreme values ​​can be taken to determine the equipment fault evaluation attributes.

[0033] Optionally, the determination method for equipment fault assessment attributes may be as follows: For multiple acquisition times, feature extraction is performed on the vibration signal data of at least one test point at each acquisition time to obtain signal feature parameters; wherein, the signal feature parameters include at least one or more of the following: time-domain feature parameters, frequency-domain feature parameters, and time-frequency feature parameters; the signal feature parameters are input into a pre-trained equipment fault assessment model to obtain a first assessment attribute; the first assessment attribute is subjected to nonlinear mapping processing according to a preset function to obtain a second assessment attribute, wherein the coefficients in the preset function are determined based on the historical assessment attributes corresponding to historical vibration signal data; the equipment fault assessment attribute is determined based on the second assessment attribute at multiple acquisition times.

[0034] Feature extraction can include at least one of time-domain feature extraction, frequency-domain feature extraction, and time-frequency-domain feature extraction. That is, signal feature parameters can include feature parameters obtained by performing time-domain feature extraction, frequency-domain feature extraction, and / or time-frequency-domain feature extraction on the vibration signal data at the measurement point.

[0035] Accordingly, the determined signal characteristic parameters include at least one or more of the following: time-domain characteristic parameters, frequency-domain characteristic parameters, and time-frequency characteristic parameters. The time-domain characteristic parameters can be calculated based on the vibration signal data from the measurement point. Time-domain characteristic parameters can be used to reflect the amplitude, distribution characteristics, etc., of the vibration signal. For example, time-domain characteristic parameters may include: signal mean, signal RMS value, and signal peak value.

[0036] Frequency domain feature parameters can be obtained from the spectral data extracted after performing a Fourier transform on the vibration signal data at the measurement point. Frequency domain feature parameters reflect the periodic signal changes of the device under test. For example, frequency domain feature parameters may include: spectral mean, spectral peak value, and spectral variance. Time-frequency feature parameters can be used to characterize the frequency components of the vibration signal as a function of time.

[0037] A device fault assessment model can be used to predict the probability of a fault occurring in the device under test at the current data acquisition time. Optionally, the device fault assessment model can be a neural network model used to detect faults in the device under test and determine the fault attributes of the device under test under various fault types. That is, by inputting signal feature parameters into the device fault assessment model, the fault attributes of each fault type occurring in the device under test at the current data acquisition time can be obtained. The first assessment attribute can be the maximum fault attribute among multiple fault attributes. That is, the first assessment attribute is used to characterize the maximum probability of a fault occurring in the device under test at the current data acquisition time.

[0038] For example, if the signal characteristic parameters are input into the equipment fault assessment model, and the fault attribute of the device under test at the current acquisition time is 70% for type A fault, 50% for type B fault, and 20% for type C fault, then 70% is taken as the first assessment attribute.

[0039] A preset function is used to perform a non-linear mapping process on the first evaluation attribute, converting it into an evaluation attribute within a preset data range. For example, if the first evaluation attribute is 70%, the preset function can convert 70% into a percentage-based evaluation attribute. Correspondingly, the evaluation attribute within the preset data range after conversion becomes the second evaluation attribute.

[0040] The preset function can be an S-shaped curve function with dynamically updated inflection point thresholds and slope. Correspondingly, the coefficients of the preset function include the inflection point threshold and the slope. The inflection point threshold and slope can be dynamically updated based on historical evaluation attributes corresponding to historical vibration signal data.

[0041] Historical vibration signal data can be vibration signal data collected from measuring points within a preset historical time period. Historical evaluation attributes can be used to characterize the probability of the tested equipment failing within the preset historical time period. Historical evaluation attributes can be determined by processing the signal characteristic parameters of historical vibration signal data based on a pre-trained equipment failure assessment model.

[0042] For the function inflection point threshold, a sliding time window corresponding to a historical preset duration can be continuously maintained, and the distribution of historical evaluation attributes within the sliding time window can be determined to extract the corresponding statistical features. The function inflection point threshold can be adaptively adjusted based on these statistical features and the preset benchmark threshold.

[0043] For example, when the device under test operates at a high vibration level for a long time, the function inflection point threshold is automatically and appropriately increased to avoid inaccurate evaluation due to operating conditions; if the device under test operates within the normal vibration range for a long time, the function inflection point threshold can be appropriately reduced to improve the sensitivity to early slight degradation trends.

[0044] The function slope reflects the "aversion" of the device under test to failure risk. The function slope can be adjusted based on the importance level of the device under test and the failure frequency over a preset historical period. For example, for devices with high importance or high safety requirements, the curve slope is increased to ensure a rapid response when failure symptoms appear. For devices under test whose failure frequency exceeds a preset failure frequency threshold over a preset historical period, the curve slope can also be appropriately increased. For non-critical devices or devices with a failure frequency below the preset failure frequency threshold, the curve slope can be maintained within the preset slope range.

[0045] Specifically, to ensure the accuracy of the processed vibration signal data from the measuring points, preprocessing such as denoising and filtering can be performed on the vibration signal data from the measuring points before feature extraction to obtain preprocessed vibration signal data from the measuring points.

[0046] For multiple acquisition times, time-domain feature extraction, frequency-domain feature extraction, and / or time-frequency-domain feature extraction are performed on the preprocessed vibration signal data of at least one detection point at each acquisition time to obtain the signal feature parameters corresponding to the acquisition time.

[0047] For multiple acquisition times, signal feature parameters are input into a pre-trained equipment fault assessment model to obtain a first assessment attribute corresponding to each acquisition time. The first assessment attribute is then substituted into a preset function to obtain a second assessment attribute corresponding to the first assessment attribute.

[0048] The equipment fault assessment attributes are obtained by averaging or taking extreme values ​​of the second assessment attributes at multiple acquisition times.

[0049] S130. Determine the anomaly assessment attribute of the measuring point based on the measuring point data of at least one measuring point to be tested.

[0050] The measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times.

[0051] Specifically, for at least one detection point, anomaly assessment is performed on the measurement data of each detection point to determine the corresponding assessment attribute for each detection point. Based on the assessment attribute corresponding to each detection point, the anomaly assessment attribute of the measurement point is determined.

[0052] Optionally, the evaluation attributes corresponding to at least one detection point can be averaged or extreme valued to obtain the anomaly evaluation attributes of the measurement point.

[0053] Optionally, the method for determining the measurement point anomaly assessment attribute can be as follows: for the vibration signal data of at least one measurement point at multiple acquisition times, determine the third assessment attribute of the measurement point at each acquisition time based on the vibration signal data and the first mapping relationship; determine the fourth assessment attribute of the measurement point at each acquisition time based on the third assessment attribute, the measurement point location information, and the transmission relationship between measurement points; perform exponential weighted moving average processing on the fourth assessment attribute to obtain the fifth assessment attribute of the measurement point at each acquisition time; and determine the measurement point anomaly assessment attribute based on the fifth assessment attribute of at least one measurement point at each acquisition time.

[0054] The first mapping relationship is used to characterize the correspondence between the vibration signal data of the measuring point and the risk level. Optionally, the first mapping relationship between the vibration signal data of the measuring point and the risk level can be set according to the equipment type, equipment location and operating conditions of the equipment to be tested.

[0055] Risk level is used to characterize the degree of risk of abnormality at the test point. For different risk levels, there are preset evaluation attributes that correspond to that risk level. For example, risk levels can be divided into four categories: "Normal," "Caution," "Warning," and "Danger." When the vibration signal data at the test point corresponds to the "Normal" risk level, the preset evaluation attribute can be 100 points. When the vibration signal data at the test point corresponds to the "Caution" risk level, the preset evaluation attribute decreases linearly as the vibration signal data increases. When the vibration signal data at the test point corresponds to "Warning" or "Danger," the preset evaluation attribute continues to decrease as the vibration signal data increases until the preset evaluation attribute reaches 0 points.

[0056] That is, when determining the risk level of the vibration signal data of the measuring point based on the vibration signal data of the measuring point and the first mapping relationship, the preset evaluation attribute corresponding to the risk level is used as the third evaluation attribute. The third evaluation attribute can be used to characterize the possibility of the measuring point having an abnormal risk.

[0057] The fourth evaluation attribute can be obtained by spatial domain filtering of the third evaluation attribute based on the measurement point location information and the transmission relationship between measurement points. The fifth evaluation attribute can be obtained by temporal domain filtering of the fourth evaluation attribute at multiple acquisition times.

[0058] Specifically, for vibration signal data of at least one detection point at multiple acquisition times, the risk level corresponding to the vibration signal data of the detection point is determined based on the vibration signal data and the first mapping relationship. The preset assessment attribute associated with the risk level is used as the third assessment attribute.

[0059] Based on the location information of the measuring points and the transmission relationship between the measuring points, the third evaluation attribute is subjected to spatial domain filtering to obtain the fourth evaluation attribute of each point to be detected at each acquisition time.

[0060] For at least one detection point, the fourth evaluation attribute of the detection point at multiple acquisition times is subjected to time-domain filtering. That is, the exponentially weighted moving average method is used to smooth the fourth evaluation attribute at multiple acquisition times to eliminate instantaneous spike interference and obtain the fifth evaluation attribute of the detection point at each acquisition time.

[0061] The fifth evaluation attribute of at least one detection point at each acquisition time is averaged and / or extreme value processed to obtain the anomaly evaluation attribute of the detection point.

[0062] For example, if the device under test has 3 test points and 5 data acquisition times, then the fifth evaluation attribute for each of the 3 test points at the 5 data acquisition times can be determined. These 15 fifth evaluation attributes can be averaged to determine the anomaly evaluation attribute for the test point. Alternatively, the average of the 5 fifth evaluation attributes for each test point can be obtained as the mean evaluation attribute. The extreme values ​​of the mean evaluation attributes for the 3 test points can then be taken to obtain the anomaly evaluation attribute for the test point. Alternatively, the extreme values ​​of these 15 fifth evaluation attributes can also be taken to obtain the anomaly evaluation attribute for the test point.

[0063] The above-mentioned method, by performing joint spatial and temporal domain filtering and noise reduction on the third evaluation attribute, solves the problems of vibration signal data being easily affected by instantaneous spike interference and inaccurate evaluation caused by single-point sensor anomalies. It improves the signal-to-noise ratio of the measurement point anomaly evaluation attribute, ensures the accuracy of the measurement point anomaly evaluation attribute, and enhances the anti-interference capability of measurement point anomaly evaluation in complex industrial environments.

[0064] It should also be noted that the method for obtaining the fifth evaluation attribute by applying an exponentially weighted moving average to the fourth evaluation attribute can be as follows: For at least one detection point at multiple acquisition times, the fourth evaluation attribute of each detection point is used to determine the attribute change rate within the first preset time period based on multiple fourth evaluation attributes of each detection point and the first preset time period. When the attribute change rate is negative and the absolute value of the attribute change rate is greater than the first value, it indicates that the device under test may have a real fault or accelerated degradation. In this case, the balance factor in the exponentially weighted moving average method is increased to reduce the smoothing strength of the fourth evaluation attribute. When the difference between the attribute change rate and zero is less than the second value, or the absolute value of the attribute change rate is lower than the first value, it indicates that the state of the device under test is relatively stable. In this case, the balance factor in the exponentially weighted moving average method is decreased to enhance the smoothing strength of the fourth evaluation attribute and effectively filter out noise interference.

[0065] Optionally, the method for determining the fourth evaluation attribute based on the third evaluation attribute, measurement point location information, and transmission relationship between measurement points can be as follows: determine the measurement point topology of the device to be tested based on the third evaluation attribute of at least one point to be tested, the measurement point location information, and the transmission relationship between measurement points; for any target measurement point in the measurement point topology, determine at least one neighboring measurement point associated with the target measurement point and the neighborhood average evaluation attribute; determine the fourth evaluation attribute based on the third evaluation attribute and the neighborhood average evaluation attribute of the target measurement point.

[0066] In this topology graph, nodes represent the points to be detected, and node attributes are the third evaluation attribute. Edges in the topology graph are determined based on the location information of the points to be detected. That is, the location information of the points is used to determine the spatial relationships between nodes in the topology graph. Edge attributes are quantified based on the transmission relationships between the points.

[0067] In this embodiment of the invention, the method for determining the fourth evaluation attribute is similar for each point to be detected. Therefore, the currently selected point to be detected is taken as the target measurement point, and the process of determining the fourth evaluation attribute is explained using the target measurement point.

[0068] The neighboring measurement points of the target measurement point can be any point to be detected that is associated with the target measurement point. That is, in the measurement point topology graph, the points to be detected that are connected to the target measurement point. The neighborhood average evaluation attribute is determined by weighted averaging of the third evaluation attributes of at least one neighboring measurement point. Optionally, the neighborhood average evaluation attribute can be determined by the following function: ; in, This represents the average evaluation attribute of the neighborhood of target measurement point i. This represents the edge attribute of neighboring measurement point j, that is, the weight coefficient corresponding to the third evaluation attribute of the neighboring measurement point. This represents the third evaluation attribute of neighboring measurement point j.

[0069] The fourth evaluation attribute can be the evaluation attribute determined by modifying the third evaluation attribute based on the neighborhood average evaluation attribute.

[0070] Specifically, for at least one point in the device under test, the node attributes in the measurement point topology graph are determined based on the third evaluation attribute of the point. The edges in the measurement point topology graph are determined based on the measurement point location information. Furthermore, the edge attributes in the measurement point topology graph are determined based on the transmission relationships between measurement points. In this way, the measurement point topology graph of the device under test is constructed.

[0071] For any point to be detected in the measurement point topology graph, the currently selected point to be detected is taken as the target measurement point. At least one neighboring measurement point associated with the target measurement point and the edge attributes corresponding to each neighboring measurement point are determined. Based on the edge attributes corresponding to each neighboring measurement point, a weighted average of the third evaluation attributes of at least one neighboring measurement point is performed to obtain the neighborhood average evaluation attribute corresponding to the target measurement point.

[0072] If the third evaluation attribute is less than the neighborhood average evaluation attribute, and the attribute difference between the third evaluation attribute and the neighborhood average evaluation attribute is greater than a preset difference threshold, then the neighborhood average evaluation attribute is used as the fourth evaluation attribute. If the third evaluation attribute is greater than the neighborhood average evaluation attribute, or the attribute difference between the third evaluation attribute and the neighborhood average evaluation attribute is less than a preset difference threshold, then the third evaluation attribute is used as the fourth evaluation attribute. In this way, the fourth evaluation attribute of the currently selected detection point is obtained.

[0073] Accordingly, select the next point to be tested and repeat the process of determining the fourth evaluation attribute as described above until the fourth evaluation attribute of each point to be tested in the test point topology map is determined.

[0074] The above processing achieves the correction of the third evaluation attribute of the test point by neighborhood weighted averaging, effectively eliminating the misjudgment of test point abnormalities caused by single-point vibration sensor failure or local accidental impact.

[0075] S140. Based on the pre-trained equipment life assessment model, process the equipment maintenance data and equipment operating condition data to determine the equipment life assessment attributes.

[0076] The equipment life assessment model can be a neural network model used to assess the remaining lifespan of the equipment under test. Optionally, the equipment life assessment model can be a Long Short-Term Memory (LSTM) network model. The equipment life assessment attributes are used to characterize the remaining usable time of the equipment under test.

[0077] Specifically, equipment maintenance data and equipment operating condition data are input into a pre-trained equipment life assessment model to obtain the equipment life assessment attributes of the equipment under test.

[0078] It should be noted that the pre-trained equipment life assessment model is a model obtained by repeatedly adjusting the model parameters of the equipment life assessment model to be trained based on the training sample set and the test and validation sample set.

[0079] S150. For at least one verification dimension, among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute, determine the associated assessment attribute related to the verification dimension.

[0080] The verification dimension includes at least one of the following: a trend verification dimension, a consistency verification dimension, and a confidence level verification dimension. The associated evaluation attribute can be an evaluation attribute corresponding to the verification dimension and requiring verification under that specific verification dimension.

[0081] The trend verification dimension is used to verify whether the probability of a device's failure changes gradually over time. For the trend verification dimension, the trend can be assessed by the rate of change of the attribute corresponding to the first assessment attribute at multiple data collection times corresponding to the device failure assessment attribute. Correspondingly, the associated assessment attribute corresponding to the trend verification dimension can be the device failure assessment attribute.

[0082] The consistency verification dimension is used to assess whether the equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment lifespan assessment attributes can corroborate each other, and whether there are any contradictions or conflicts. Accordingly, the associated assessment attributes corresponding to the consistency verification dimension can include: equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment lifespan assessment attributes.

[0083] The confidence level check dimension is used to assess the reliability of equipment life assessment attributes. Correspondingly, the associated assessment attributes linked to the confidence level check dimension can be equipment life assessment attributes.

[0084] Specifically, for at least one verification dimension, among the equipment fault assessment attribute, measurement point anomaly assessment attribute, and equipment lifespan assessment attribute, the associated assessment attribute corresponding to the trend verification dimension is determined to be the equipment fault assessment attribute; the associated assessment attributes corresponding to the consistency verification dimension include the equipment fault assessment attribute, measurement point anomaly assessment attribute, and equipment lifespan assessment attribute; and the associated assessment attribute corresponding to the confidence level verification dimension is determined to be the equipment lifespan assessment attribute. In this way, the associated assessment attributes can be verified based on the corresponding verification dimensions to obtain verification results.

[0085] S160. Perform validation processing on the associated evaluation attributes to obtain the validation results under the validation dimensions.

[0086] The validation results can be the results obtained by validating the corresponding associated evaluation attributes. The number of validation results is consistent with the number of validation dimensions.

[0087] Specifically, for the trend verification dimension, the equipment fault assessment attributes are subjected to trend verification processing to obtain the verification results corresponding to the trend verification dimension. For the consistency verification dimension, the equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes are subjected to consistency verification to obtain the verification results corresponding to the consistency verification dimension. For the confidence verification dimension, the equipment life assessment attributes are subjected to confidence verification to obtain the verification results corresponding to the confidence verification dimension.

[0088] S170. Based on at least one verification result, process the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute to obtain the target health of the equipment to be tested.

[0089] The target health level can be understood as the health status of the device under test. The target health level can be data obtained by comprehensively quantifying the fault conditions, component abnormalities, and remaining lifespan of the device under test.

[0090] Specifically, based on at least one verification result, the weight coefficients of the equipment fault assessment attribute, the weight coefficients of the measurement point anomaly assessment attribute, and the weight coefficients of the equipment life assessment attribute are adjusted to obtain the adjusted weight coefficients. A weighted summation is then performed on the equipment fault assessment attribute, the measurement point anomaly assessment attribute, the equipment life assessment attribute, and the adjusted weight coefficients to obtain the target health level of the equipment under test.

[0091] The technical solution of this embodiment is applied to a device under test. At least one test point is set in the device under test. Device data and measurement point data of at least one test point are acquired within a first preset time period. Based on the vibration signal data of at least one test point at multiple acquisition times, the device fault assessment attribute of the device under test is determined. Based on the measurement point data of at least one test point, the measurement point anomaly assessment attribute of the device under test is determined. The device maintenance data and device operating condition data are processed according to the device life assessment model to obtain the device life assessment attribute. This achieves a multi-dimensional health assessment of the device under test, ensuring the comprehensiveness of the health assessment and improving the accuracy of the subsequently determined device health. For at least one verification dimension, among the device fault assessment attribute, measurement point anomaly assessment attribute, and device life assessment attribute, a related assessment attribute associated with the verification dimension is determined, and the corresponding related assessment attribute is verified to obtain the verification result under the corresponding verification dimension. Based on at least one verification result, the device fault assessment attribute, measurement point anomaly assessment attribute, and device life assessment attribute are processed to obtain the target health of the device under test. The above-described method enables dynamic adjustment of each evaluation attribute based on the verification results, effectively avoiding the problem of health distortion caused by conflicts between evaluation attributes, and improving the accuracy and consistency of evaluation attributes. This invention solves the problems of bias and subjectivity caused by evaluation based on a single-dimensional preset threshold in existing technologies. By conducting multi-dimensional evaluation of the device under test and combining the verification results of the evaluation attributes, the target health level is determined, improving the accuracy, comprehensiveness, and reliability of device health detection.

[0092] Example 2 Figure 2 This is a flowchart of a device health detection method provided in Embodiment 2 of the present invention. This embodiment is a preferred embodiment of the above embodiments. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes: S210. Acquire equipment data of the device to be tested and measurement data of at least one test point within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times.

[0093] S220. Based on the vibration signal data of at least one test point at multiple acquisition times, determine the equipment fault assessment attributes.

[0094] S230. Determine the anomaly assessment attribute of the measuring point based on the measuring point data of at least one measuring point to be tested.

[0095] S240. Based on the pre-trained equipment life assessment model, process the equipment maintenance data and equipment operating condition data to determine the equipment life assessment attributes.

[0096] S250. For at least one verification dimension, among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute, determine the associated assessment attribute related to the verification dimension.

[0097] Among them, at least one verification dimension includes one or more of the following: trend verification dimension, consistency verification dimension, and confidence verification dimension.

[0098] S260. Perform validation processing on the associated evaluation attributes to obtain the validation results under the validation dimensions.

[0099] Among them, the associated evaluation attribute related to the change trend verification dimension is the equipment failure evaluation attribute.

[0100] The equipment fault assessment attributes are validated to obtain validation results under the trend validation dimension, including: determining the rate of change of the first attribute within a second preset duration and the rate of change of the second attribute within a third preset duration based on the first assessment attribute at multiple collection times; wherein the second preset duration and the third preset duration are both partial durations within the first preset duration, and the second preset duration is longer than the third preset duration; determining the degradation trend factor based on the rate of change of the first attribute and the rate of change of the second attribute; and determining the degradation trend factor as the validation result under the trend validation dimension.

[0101] The second preset duration can be a pre-set portion of the first preset duration. The third preset duration can also be a portion of the second preset duration. That is, the third preset duration is shorter than the second preset duration. For example, the first preset duration could be one week prior to the current time, the second preset duration could be 24 hours prior to the current time, and the third preset duration could be one hour prior to the current time.

[0102] The rate of change of the first attribute can be the average rate of change of the first evaluation attribute within a second preset time period. The rate of change of the first attribute is used to reflect the long-term degradation trend of the device under test, reflecting the slow deterioration process of the device. Accordingly, the rate of change of the first attribute can be determined based on the first evaluation attribute at at least one acquisition time within the second preset time period.

[0103] The rate of change of the second attribute can be the average rate of change of the first evaluation attribute within a third preset time period. The rate of change of the second attribute reflects the instantaneous degradation trend of the device under test and is sensitive to sudden failures. Optionally, the rate of change of the second attribute can be determined based on the first evaluation attribute at at least one acquisition time within the third preset time period. The degradation trend factor can be used to characterize the rate at which the probability of failure of the device under test changes over time.

[0104] Specifically, based on the first evaluation attribute at multiple acquisition times, the first evaluation attribute at at least one acquisition time within a second preset time period, and the rate of change of the first attribute corresponding to the second preset time period, are determined. Correspondingly, the first evaluation attribute at at least one acquisition time within a third preset time period, and the rate of change of the second attribute corresponding to the third preset time period, are determined.

[0105] The rate of change of the attribute with the largest change between the first and second attributes is determined as the degradation trend factor. This degradation trend factor serves as the verification result under the dimension of change trend verification.

[0106] Optional, associated evaluation attributes related to the consistency verification dimension include: equipment failure evaluation attributes, measurement point anomaly evaluation attributes, and equipment lifespan evaluation attributes.

[0107] The equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes are validated to obtain validation results under the consistency validation dimension. This includes: performing consistency validation on the equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes to determine the first conflict information; and determining the validation results under the consistency validation dimension based on the first conflict information.

[0108] Among them, the first conflict information is used to characterize the degree of conflict between equipment failure assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes.

[0109] Specifically, consistency checks are performed on equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment lifespan assessment attributes. If these attributes are consistent and have a low degree of conflict, it indicates that the attributes can corroborate each other, thus identifying the first conflict information. If these attributes contradict each other and have a high degree of conflict, it indicates that there is a conflict, thus identifying the first conflict information. Based on the first conflict information, the verification results under the consistency check dimension are determined.

[0110] Optionally, the associated evaluation attribute related to the confidence verification dimension is the device lifetime evaluation attribute.

[0111] The equipment life assessment attributes are validated to obtain validation results under the confidence level validation dimension. This includes: performing quality validation on the equipment maintenance data and equipment operating condition data corresponding to the equipment life assessment attributes to obtain a first validation sub-result; performing confidence validation on the equipment life assessment attributes to obtain a second validation sub-result; determining the historical life assessment attributes of the equipment to be tested within a preset historical time period; performing trend validation on the historical life assessment attributes and the equipment life assessment attributes to determine a third validation sub-result; and performing weighted summation on the first, second, and third validation sub-results to determine the validation result corresponding to the confidence level validation dimension.

[0112] The quality verification is used to check whether there are any missing, omitted, or inconsistent time intervals in the equipment maintenance data and equipment operating condition data within a first preset time period. The first verification sub-result is used to characterize the data integrity and continuity of the equipment maintenance data and equipment operating condition data. The worse the data integrity and continuity, the less input data the equipment life assessment model processes, the worse the continuity of the input data, and correspondingly, the lower the reliability of the equipment life assessment attributes.

[0113] The confidence level check is used to verify the reliability of the equipment life assessment attributes. The second check result is used to characterize the dispersion of the output data of the equipment life assessment model. When the dispersion is small, it indicates that the equipment life assessment model's prediction of the remaining equipment life is relatively accurate, and the confidence level of the equipment life assessment attributes is high. When the dispersion is large, it indicates that the equipment life assessment model's prediction of the remaining equipment life is relatively vague, and the confidence level of the equipment life assessment attributes is low.

[0114] The historical preset duration can be pre-set, representing a period of time prior to the first preset duration. Historical life assessment attributes can be determined based on equipment maintenance data and equipment operating condition data within the historical preset duration using an equipment life assessment model.

[0115] The trend verification is used to check whether the trend of the equipment life assessment attributes changing over time is consistent with the standard life degradation trend of the equipment under test. Correspondingly, the third verification result is used to characterize whether the trend of the historical life assessment attributes and the equipment life assessment attributes is consistent with the standard life degradation trend.

[0116] Specifically, the quality of equipment maintenance data and equipment operating condition data is verified to obtain the first verification sub-result. Confidence verification of equipment lifespan assessment attributes is performed to obtain the second verification sub-result. Based on the equipment lifespan assessment model, equipment maintenance data and equipment operating condition data within a preset historical timeframe are processed to determine the historical lifespan assessment attributes of the equipment under test within that timeframe. The changing trends corresponding to the historical lifespan assessment attributes and the equipment lifespan assessment attributes are determined. Based on these changing trends and the standard lifespan degradation trend of the equipment under test, the third verification sub-result is determined.

[0117] The results of the first, second, and third verification sub-tests are weighted and summed according to preset weights to obtain the verification result corresponding to the confidence level verification dimension. Optionally, the data range of the verification result corresponding to the confidence level verification dimension can be [0, 100]. A higher verification result indicates a more reliable equipment lifespan assessment attribute.

[0118] The advantages of the above-mentioned verification results under the confidence verification dimension are: it provides data support for subsequent weight coefficient correction, avoids the problem of over-reliance on unreliable equipment life assessment attributes when the equipment life assessment model fails or the input data is missing, and provides a reliable reference for the equipment life assessment attributes.

[0119] S270. Based on at least one verification result, determine the weight coefficient correction information.

[0120] The weighting coefficient correction information can be used to adjust the preset weighting coefficients corresponding to equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes.

[0121] Specifically, based on the verification results corresponding to the trend verification dimension, the consistency verification dimension, and the confidence verification dimension, the weight coefficient correction information is determined according to the weight coefficient adjustment rules. The weight coefficient adjustment rules may include one or more of the following: Rule 1: If the verification result (deterioration trend factor) corresponding to the trend verification dimension is high, and the verification result (first conflict information) under the consistency verification dimension is high, it indicates that the equipment under test may have a sudden failure (e.g., impact) leading to an increased probability of vibration failure. In this case, the weight corresponding to the equipment failure assessment attribute can be increased, while the weight corresponding to the equipment life assessment attribute can be decreased.

[0122] Rule 2: If the verification result (deterioration trend factor) corresponding to the trend verification dimension is low, and the verification result (confidence level) corresponding to the confidence verification dimension is high, it indicates that the equipment under test is in a normal wear and tear stage, and the equipment life assessment attribute can be used as the main basis for health assessment. In this case, the weight of the equipment life assessment attribute can be increased, and the weight of the equipment failure assessment attribute can be decreased.

[0123] Rule 3: If the verification result (confidence) corresponding to the confidence verification dimension is low, but the verification result (first conflict information) under the consistency verification dimension is high, it indicates that the confidence of the equipment life assessment model is poor. In this case, the health assessment can be mainly based on the equipment failure assessment attribute and the measurement point anomaly assessment attribute. In this situation, the weight of the equipment failure assessment attribute can be increased, and the weight of the equipment life assessment attribute can be significantly reduced.

[0124] Rule 4: If the verification result (first conflict information) under the consistency verification dimension is low, it means that the equipment failure assessment attribute, the measurement point anomaly assessment attribute and the equipment life assessment attribute are consistent, and the weights do not need to be adjusted.

[0125] By using at least one of the aforementioned weighting coefficient adjustment rules, a fuzzy set of weighting coefficient correction values ​​corresponding to the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute can be determined. The centroid method is then used for defuzzification to convert the fuzzy set into precise weighting coefficient correction information.

[0126] The above method addresses the limitations of traditional static weight fusion methods by dynamically and adaptively adjusting the weight coefficients of equipment fault assessment attributes, measurement point anomaly assessment attributes, and equipment life assessment attributes based on the verification results of at least one verification dimension. This makes the determined target health level more suitable for the real-time operating status of the equipment under test, ensuring the accuracy, real-time performance, and stability of the target health level.

[0127] S280. Based on the weight coefficient correction information, adjust the original weight information to obtain the first weight coefficient corresponding to the equipment failure assessment attribute, the second weight coefficient corresponding to the measurement point anomaly assessment attribute, and the third weight coefficient corresponding to the equipment life assessment attribute.

[0128] The original weight information may include preset weight coefficients corresponding to equipment failure assessment attributes, preset weight coefficients corresponding to measurement point anomaly assessment attributes, and preset weight coefficients corresponding to equipment life assessment attributes.

[0129] The first weighting coefficient can be obtained by adjusting the preset weighting coefficients corresponding to the equipment failure assessment attribute based on the weighting coefficient correction information. Similarly, the second weighting coefficient can be obtained by adjusting the preset weighting coefficients corresponding to the measurement point anomaly assessment attribute based on the weighting coefficient correction information. The third weighting coefficient can be obtained by adjusting the preset weighting coefficients corresponding to the equipment lifespan assessment attribute based on the weighting coefficient correction information.

[0130] Specifically, based on the weight coefficient correction information, the preset weight coefficients corresponding to the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute are adjusted respectively to obtain the first weight coefficient corresponding to the equipment failure assessment attribute, the second weight coefficient corresponding to the measurement point anomaly assessment attribute, and the third weight coefficient corresponding to the equipment life assessment attribute.

[0131] S290. Based on equipment failure assessment attributes, first weight coefficient, measurement point anomaly assessment attributes, second weight coefficient, equipment life assessment attributes, and third weight coefficient, determine the target health level.

[0132] Specifically, the equipment failure assessment attribute, the first weight coefficient, the measurement point anomaly assessment attribute, the second weight coefficient, the equipment life assessment attribute, and the third weight coefficient are weighted to obtain the target health score.

[0133] Optionally, the target health level is determined based on the equipment failure assessment attribute, the first weight coefficient, the measurement point anomaly assessment attribute, the second weight coefficient, the equipment life assessment attribute, and the third weight coefficient, including: determining the adjusted failure assessment attribute based on the equipment failure assessment attribute and the first weight coefficient; determining the adjusted measurement point assessment attribute based on the measurement point anomaly assessment attribute and the second weight coefficient; determining the adjusted life assessment attribute based on the equipment life assessment attribute and the third weight coefficient; and determining the target health level based on the adjusted failure assessment attribute, the adjusted measurement point assessment attribute, and the adjusted life assessment attribute.

[0134] Specifically, the adjusted fault assessment attribute can be determined by multiplying the equipment fault assessment attribute and the first weighting coefficient. Similarly, the adjusted measurement point assessment attribute can be determined by multiplying the measurement point anomaly assessment attribute and the second weighting coefficient. The adjusted lifespan assessment attribute can be determined by multiplying the equipment lifespan assessment attribute and the third weighting coefficient.

[0135] Specifically, the adjusted fault assessment attribute is determined by multiplying the equipment fault assessment attribute and the first weighting coefficient. The adjusted measurement point assessment attribute is determined based on the measurement point anomaly assessment attribute and the second weighting coefficient. The adjusted lifespan assessment attribute is determined based on the equipment lifespan assessment attribute and the third weighting coefficient. The target health level is then obtained based on the adjusted fault assessment attribute, the adjusted measurement point assessment attribute, and the adjusted lifespan assessment attribute.

[0136] Furthermore, based on the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes, the target health level can be determined as follows: The adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes are summed to obtain an initial health level; consistency checks are performed on the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes to determine the second conflict information; adjustment parameters are determined based on the second conflict information; and the initial health level is adjusted based on the adjustment parameters to obtain the target health level.

[0137] The initial health level can be determined by summing the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes. The second conflict information is used to characterize the degree of consistency among the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes. Adjustment parameters can be parameters used to adjust the initial health level.

[0138] Specifically, the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes are summed to obtain the initial health level. To improve the reliability of the equipment health assessment, consistency checks can be performed on the adjusted fault assessment attributes, adjusted measurement point assessment attributes, and adjusted lifespan assessment attributes to identify second conflict information. Based on the second conflict information, adjustment parameters are determined, and the initial health level is adjusted based on these parameters to obtain the target health level.

[0139] Optionally, to ensure the robustness and reliability of the target health, the adjustment parameters can be determined based on the second conflict information as follows: When the conflict degree among the adjusted fault assessment attribute, adjusted measurement point assessment attribute, and adjusted life assessment attribute is low based on the second conflict information, the adjustment parameter is set close to 1 to avoid affecting the initial health. When the conflict degree among the adjusted fault assessment attribute, adjusted measurement point assessment attribute, and adjusted life assessment attribute is high based on the second conflict information, the adjustment parameter is set according to the magnitude of the conflict degree represented by the second conflict information. The adjustment parameter can be determined based on an exponential decay function that decreases as the conflict degree increases. That is, the greater the conflict degree represented by the second conflict information, the greater the reduction in the adjustment parameter.

[0140] The above-mentioned consistency verification of the adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted life assessment attributes enables a quantitative assessment of the degree of inconsistency among multiple assessment attributes. This allows for the correction of the initial health status based on the degree of conflict, effectively avoiding the problem of health status assessment distortion caused by conflicting assessment attributes and improving the robustness and reliability of the target health status.

[0141] The technical solution of this embodiment acquires equipment data of the device under test and measurement point data of at least one test point within a first preset time period. Based on the vibration signal data of at least one test point at multiple acquisition times, the equipment fault assessment attribute of the device under test is determined. Based on the measurement point data of at least one test point, the measurement point anomaly assessment attribute of the device under test is determined. The equipment maintenance data and equipment operating condition data are processed according to the equipment life assessment model to obtain the equipment life assessment attribute. This achieves a multi-dimensional health assessment of the device under test, ensuring the comprehensiveness of the health assessment and improving the accuracy of the subsequently determined equipment health. For at least one verification dimension, among the equipment fault assessment attribute, measurement point anomaly assessment attribute, and equipment life assessment attribute, a related assessment attribute associated with the verification dimension is determined, and the corresponding related assessment attribute is verified to obtain the verification result under the corresponding verification dimension. Based on at least one verification result, weight coefficient correction information is determined; based on the weight coefficient correction information, the original weight information is adjusted to obtain a first weight coefficient corresponding to the equipment fault assessment attribute, a second weight coefficient corresponding to the measurement point anomaly assessment attribute, and a third weight coefficient corresponding to the equipment life assessment attribute. The target health level is determined based on equipment fault assessment attributes, a first weighting coefficient, a measurement point anomaly assessment attribute, a second weighting coefficient, equipment lifespan assessment attributes, and a third weighting coefficient. This method dynamically adjusts each assessment attribute based on verification results, effectively avoiding health level distortion caused by conflicts between assessment attributes and improving the accuracy and consistency of the assessment attributes. This invention solves the problems of bias and subjectivity caused by assessments based on a single-dimensional preset threshold in existing technologies. By conducting multi-dimensional assessments of the equipment under test and combining the verification results of the assessment attributes, the target health level is determined, improving the accuracy, comprehensiveness, and reliability of equipment health level detection.

[0142] Example 3 Figure 3 This is a schematic diagram of the structure of a device for detecting equipment health according to Embodiment 3 of the present invention. Figure 3As shown, the device is applied to the equipment to be tested, which has at least one test point. The device includes: a data acquisition module 310, an equipment fault assessment module 320, a test point anomaly assessment module 330, an equipment life assessment module 340, an associated assessment attribute determination module 350, a verification result determination module 360, and an equipment health determination module 370.

[0143] The data acquisition module 310 is used to acquire equipment data of the device to be tested and measurement point data of at least one of the tested points within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times; the equipment fault assessment module 320 is used to determine the equipment fault assessment attribute based on the vibration signal data of at least one of the tested points at multiple acquisition times; the measurement point anomaly assessment module 330 is used to determine the measurement point anomaly assessment attribute based on the measurement point data of at least one of the tested points; and the equipment life assessment module 340 is used to process the equipment maintenance data and equipment operating condition data based on a pre-trained equipment life assessment model. The system determines equipment lifespan assessment attributes; an association assessment attribute determination module 350 is used to determine, for at least one verification dimension, an association assessment attribute associated with the verification dimension among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment lifespan assessment attribute; wherein, the at least one verification dimension includes one or more of the following: a change trend verification dimension, a consistency verification dimension, and a confidence level verification dimension; a verification result determination module 360 ​​is used to perform verification processing on the association assessment attribute to obtain a verification result under the verification dimension; and an equipment health determination module 370 is used to process the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment lifespan assessment attribute based on at least one verification result to obtain the target health of the equipment to be tested.

[0144] The technical solution of this embodiment is applied to a device under test. At least one test point is set in the device under test. Device data and measurement point data of at least one test point are acquired within a first preset time period. Based on the vibration signal data of at least one test point at multiple acquisition times, the device fault assessment attribute of the device under test is determined. Based on the measurement point data of at least one test point, the measurement point anomaly assessment attribute of the device under test is determined. The device maintenance data and device operating condition data are processed according to the device life assessment model to obtain the device life assessment attribute. This achieves a multi-dimensional health assessment of the device under test, ensuring the comprehensiveness of the health assessment and improving the accuracy of the subsequently determined device health. For at least one verification dimension, among the device fault assessment attribute, measurement point anomaly assessment attribute, and device life assessment attribute, a related assessment attribute associated with the verification dimension is determined, and the corresponding related assessment attribute is verified to obtain the verification result under the corresponding verification dimension. Based on at least one verification result, the device fault assessment attribute, measurement point anomaly assessment attribute, and device life assessment attribute are processed to obtain the target health of the device under test. The above-described method enables dynamic adjustment of each evaluation attribute based on the verification results, effectively avoiding the problem of health distortion caused by conflicts between evaluation attributes, and improving the accuracy and consistency of evaluation attributes. This invention solves the problems of bias and subjectivity caused by evaluation based on a single-dimensional preset threshold in existing technologies. By conducting multi-dimensional evaluation of the device under test and combining the verification results of the evaluation attributes, the target health level is determined, improving the accuracy, comprehensiveness, and reliability of device health detection.

[0145] Based on the above embodiments, optionally, the equipment fault assessment module is used to extract features from the vibration signal data of at least one test point at each acquisition time for multiple acquisition times to obtain signal feature parameters; wherein, the signal feature parameters include at least one or more of time-domain feature parameters, frequency-domain feature parameters, and time-frequency feature parameters; input the signal feature parameters into a pre-trained equipment fault assessment model to obtain a first assessment attribute; perform nonlinear mapping processing on the first assessment attribute according to a preset function to obtain a second assessment attribute, wherein the coefficients in the preset function are determined based on historical assessment attributes corresponding to historical vibration signal data; and determine the equipment fault assessment attribute based on the second assessment attribute at multiple acquisition times.

[0146] Optionally, the measurement point anomaly assessment module includes: a third assessment attribute determination unit, used to determine a third assessment attribute of the measurement point at each acquisition time based on the vibration signal data of at least one measurement point at multiple acquisition times, according to the vibration signal data of the measurement point and a first mapping relationship; wherein, the first mapping relationship is used to characterize the correspondence between the vibration signal data of the measurement point and the risk level; a fourth assessment attribute determination unit, used to determine a fourth assessment attribute of the measurement point at each acquisition time based on the third assessment attribute, the measurement point location information, and the transmission relationship between the measurement points; a fifth assessment attribute determination unit, used to perform exponentially weighted moving average processing on the fourth assessment attribute to obtain a fifth assessment attribute of the measurement point at each acquisition time; and a measurement point anomaly assessment attribute determination unit, used to determine a measurement point anomaly assessment attribute based on the fifth assessment attribute of at least one measurement point at each acquisition time.

[0147] Optionally, the fourth evaluation attribute determination unit is used to determine the measurement point topology of the device under test based on the third evaluation attribute of at least one of the test points, measurement point location information, and transmission relationship between measurement points; for any target measurement point in the measurement point topology, determine at least one neighboring measurement point and the neighborhood average evaluation attribute associated with the target measurement point; wherein, the neighborhood average evaluation attribute is determined by weighted averaging of the third evaluation attributes of the at least one neighboring measurement point; and determine the fourth evaluation attribute based on the third evaluation attribute and the neighborhood average evaluation attribute of the target measurement point.

[0148] Optionally, the verification result determination module includes: a change trend verification unit, wherein the associated evaluation attribute related to the change trend verification dimension is a device fault evaluation attribute, the change trend verification unit is used to determine the change rate of the first attribute within a second preset time period and the change rate of the second attribute within a third preset time period based on the first evaluation attribute at multiple collection times; wherein the second preset time period and the third preset time period are both partial durations within the first preset time period, and the second preset time period is longer than the third preset time period; a degradation trend factor is determined based on the change rate of the first attribute and the change rate of the second attribute; and the degradation trend factor is determined as the verification result under the change trend verification dimension.

[0149] Optionally, the verification result determination module includes: a consistency verification unit, wherein the associated evaluation attributes related to the consistency verification dimension include: equipment fault evaluation attribute, measurement point anomaly evaluation attribute, and equipment lifespan evaluation attribute. The consistency verification unit is used to perform consistency verification on the equipment fault evaluation attribute, the measurement point anomaly evaluation attribute, and the equipment lifespan evaluation attribute to determine first conflict information; and based on the first conflict information, to determine the verification result under the consistency verification dimension.

[0150] Optionally, the verification result determination module includes: a confidence verification unit, wherein the associated evaluation attribute related to the confidence verification dimension is an equipment lifespan assessment attribute, the confidence verification unit is used to perform quality verification on the equipment maintenance data and equipment operating condition data corresponding to the equipment lifespan assessment attribute to obtain a first verification sub-result; perform confidence verification on the equipment lifespan assessment attribute to obtain a second verification sub-result; determine the historical lifespan assessment attribute of the equipment to be tested within a preset historical time period; perform trend verification processing on the historical lifespan assessment attribute and the equipment lifespan assessment attribute to determine a third verification sub-result; and perform weighted summation processing on the first verification sub-result, the second verification sub-result, and the third verification sub-result to determine the verification result corresponding to the confidence verification dimension.

[0151] Optionally, the equipment health determination module includes: a coefficient correction information determination unit, used to determine weight coefficient correction information based on at least one of the verification results; a coefficient adjustment unit, used to adjust the original weight information based on the weight coefficient correction information to obtain a first weight coefficient corresponding to the equipment fault assessment attribute, a second weight coefficient corresponding to the measurement point anomaly assessment attribute, and a third weight coefficient corresponding to the equipment life assessment attribute; and a health determination unit, used to determine a target health level based on the equipment fault assessment attribute, the first weight coefficient, the measurement point anomaly assessment attribute, the second weight coefficient, the equipment life assessment attribute, and the third weight coefficient.

[0152] Optionally, the health determination unit includes: a fault assessment attribute adjustment subunit, used to determine an adjusted fault assessment attribute based on the equipment fault assessment attribute and the first weight coefficient; a measurement point assessment attribute adjustment subunit, used to determine an adjusted measurement point assessment attribute based on the measurement point anomaly assessment attribute and the second weight coefficient; a lifespan assessment attribute adjustment subunit, used to determine an adjusted lifespan assessment attribute based on the equipment lifespan assessment attribute and the third weight coefficient; and a health determination subunit, used to determine a target health level based on the adjusted fault assessment attribute, the adjusted measurement point assessment attribute, and the adjusted lifespan assessment attribute.

[0153] Optionally, a health determination subunit is used to sum the adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted lifespan assessment attributes to obtain an initial health level; perform consistency verification on the adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted lifespan assessment attributes to determine second conflict information; determine adjustment parameters based on the second conflict information; and adjust the initial health level based on the adjustment parameters to obtain a target health level. The equipment health detection device provided in this embodiment of the invention can execute the equipment health detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0154] Example 4 Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0155] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0156] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0157] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as device health detection methods.

[0158] In some embodiments, the device health detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the device health detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the device health detection method by any other suitable means (e.g., by means of firmware).

[0159] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs used to implement the device health detection method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0161] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0162] Example 5 Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a device health detection method applied to a device under test, wherein the device under test has at least one detection point, and the method includes: Acquire equipment data of the device to be tested and measurement point data of at least one of the test points within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times; Based on vibration signal data of at least one of the test points at multiple acquisition times, determine the equipment fault assessment attributes; Based on the measurement data of at least one of the measurement points to be detected, determine the measurement point anomaly assessment attributes; The equipment maintenance data and equipment operating condition data are processed based on a pre-trained equipment life assessment model to determine the equipment life assessment attributes. For at least one verification dimension, among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute, an associated assessment attribute related to the verification dimension is determined; wherein, the at least one verification dimension includes one or more of the following: change trend verification dimension, consistency verification dimension, and confidence level verification dimension; The associated evaluation attributes are validated to obtain the validation results under the validation dimensions. Based on at least one of the verification results, the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute are processed to obtain the target health of the equipment under test.

[0163] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0164] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0165] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0166] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0167] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the device health detection method as provided in any embodiment of this application.

[0168] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider). This program product belongs to the same inventive concept as the device health detection methods disclosed in the embodiments of this application, and therefore will not be described further here.

[0169] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0170] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting equipment health, characterized in that, Applied to a device under test, wherein the device under test has at least one point to be tested, the method includes: Acquire equipment data of the device to be tested and measurement point data of at least one of the test points within a first preset time period; wherein, the equipment data includes at least: equipment maintenance data and equipment operating condition data, and the measurement point data includes at least: measurement point location information, transmission relationship between measurement points, and vibration signal data of measurement points at multiple acquisition times; Based on vibration signal data of at least one of the test points at multiple acquisition times, determine the equipment fault assessment attributes; Based on the measurement data of at least one of the measurement points to be detected, determine the measurement point anomaly assessment attributes; The equipment maintenance data and equipment operating condition data are processed based on a pre-trained equipment life assessment model to determine the equipment life assessment attributes. For at least one verification dimension, among the equipment failure assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute, an associated assessment attribute related to the verification dimension is determined; wherein, the at least one verification dimension includes one or more of the following: change trend verification dimension, consistency verification dimension, and confidence level verification dimension; The associated evaluation attributes are validated to obtain the validation results under the validation dimensions. Based on at least one of the verification results, the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute are processed to obtain the target health of the equipment under test.

2. The method according to claim 1, characterized in that, The determination of equipment fault assessment attributes based on vibration signal data of at least one of the test points at multiple acquisition times includes: For multiple acquisition times, feature extraction is performed on the vibration signal data of at least one point to be detected at each acquisition time to obtain signal feature parameters; wherein, the signal feature parameters include at least one or more of the following: time domain feature parameters, frequency domain feature parameters, and time-frequency feature parameters; The signal feature parameters are input into a pre-trained equipment fault assessment model to obtain the first assessment attribute; The first evaluation attribute is nonlinearly mapped according to a preset function to obtain the second evaluation attribute, wherein the coefficients in the preset function are determined based on the historical evaluation attributes corresponding to historical vibration signal data. Based on the second evaluation attribute at multiple data acquisition times, the equipment fault evaluation attribute is determined.

3. The method according to claim 1, characterized in that, The step of determining the anomaly assessment attribute of a measurement point based on measurement point data of at least one of the measurement points to be detected includes: For vibration signal data of at least one detection point at multiple acquisition times, a third evaluation attribute of the detection point at each acquisition time is determined based on the vibration signal data and a first mapping relationship; wherein, the first mapping relationship is used to characterize the correspondence between the vibration signal data and the risk level. Based on the third evaluation attribute, the measurement point location information, and the transmission relationship between the measurement points, the fourth evaluation attribute of the point to be detected at each acquisition time is determined; The fourth evaluation attribute is processed by exponential weighted moving average to obtain the fifth evaluation attribute of the point to be detected at each acquisition time. The anomaly assessment attribute of the measuring point is determined based on the fifth assessment attribute of at least one measuring point at each acquisition time.

4. The method according to claim 3, characterized in that, The determination of the fourth evaluation attribute of the point to be detected at each acquisition time, based on the third evaluation attribute, the measurement point location information, and the transmission relationship between the measurement points, includes: Based on at least one third evaluation attribute of the point to be tested, the location information of the measuring point, and the transmission relationship between the measuring points, the measuring point topology diagram of the device to be tested is determined; For any target measurement point in the measurement point topology map, determine at least one neighboring measurement point associated with the target measurement point and the neighborhood average evaluation attribute; wherein, the neighborhood average evaluation attribute is determined by weighted averaging of the third evaluation attributes of the at least one neighboring measurement point; Based on the third evaluation attribute and the neighborhood average evaluation attribute of the target measurement point, the fourth evaluation attribute is determined.

5. The method according to claim 1, characterized in that, The associated evaluation attribute related to the trend verification dimension is the equipment fault evaluation attribute. The equipment fault evaluation attribute is validated to obtain the validation result under the trend verification dimension, including: Based on the first evaluation attribute at multiple collection times, determine the rate of change of the first attribute within a second preset time period and the rate of change of the second attribute within a third preset time period; wherein, the second preset time period and the third preset time period are both partial durations within the first preset time period, and the second preset time period is longer than the third preset time period; Degradation trend factor is determined based on the rate of change of the first attribute and the rate of change of the second attribute; The degradation trend factor is determined as the verification result under the change trend verification dimension.

6. The method according to claim 1, characterized in that, The associated evaluation attributes related to the consistency verification dimension include: equipment failure evaluation attributes, measurement point anomaly evaluation attributes, and equipment lifespan evaluation attributes. The equipment failure evaluation attributes, measurement point anomaly evaluation attributes, and equipment lifespan evaluation attributes are validated to obtain the validation results under the consistency verification dimension, including: The consistency of the equipment fault assessment attribute, the measurement point anomaly assessment attribute, and the equipment life assessment attribute is verified to determine the first conflict information; Based on the first conflict information, the verification result under the consistency verification dimension is determined.

7. The method according to claim 1, characterized in that, The associated evaluation attribute related to the confidence level verification dimension is the equipment lifespan evaluation attribute. The equipment lifespan evaluation attribute is validated to obtain the validation results under the confidence level verification dimension, including: The equipment maintenance data and equipment operating condition data corresponding to the equipment life assessment attributes are subjected to quality verification to obtain the first verification sub-result; The confidence level of the equipment life assessment attributes is verified to obtain a second verification result. Determine the historical lifespan assessment attributes of the device under test within a preset historical time period; The historical life assessment attributes and the equipment life assessment attributes are subjected to trend verification processing to determine the third verification sub-result; The first verification result, the second verification result, and the third verification result are weighted and summed to determine the verification result corresponding to the confidence verification dimension.

8. The method according to claim 1, characterized in that, The step of processing the equipment fault assessment attribute, the measuring point anomaly assessment attribute, and the equipment life assessment attribute based on at least one of the verification results to obtain the target health status of the equipment under test includes: Based on at least one of the verification results, determine the weight coefficient correction information; Based on the weight coefficient correction information, the original weight information is adjusted to obtain the first weight coefficient corresponding to the equipment failure assessment attribute, the second weight coefficient corresponding to the measurement point anomaly assessment attribute, and the third weight coefficient corresponding to the equipment life assessment attribute. The target health is determined based on the equipment fault assessment attribute, the first weight coefficient, the measurement point anomaly assessment attribute, the second weight coefficient, the equipment life assessment attribute, and the third weight coefficient.

9. The method according to claim 8, characterized in that, The determination of target health based on the equipment fault assessment attribute, the first weighting coefficient, the measurement point anomaly assessment attribute, the second weighting coefficient, the equipment life assessment attribute, and the third weighting coefficient includes: Based on the equipment fault assessment attributes and the first weighting coefficient, the adjusted fault assessment attributes are determined. Based on the anomaly assessment attribute of the measurement point and the second weighting coefficient, the adjusted measurement point assessment attribute is determined; Based on the equipment life assessment attributes and the third weighting coefficient, the adjusted life assessment attributes are determined; The target health level is determined based on the adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted lifespan assessment attributes.

10. The method according to claim 9, characterized in that, The determination of the target health level based on the adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted lifespan assessment attributes includes: The adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted lifespan assessment attributes are summed to obtain the initial health level. The adjusted fault assessment attributes, the adjusted measurement point assessment attributes, and the adjusted life assessment attributes are subjected to consistency verification to determine the second conflict information; Based on the second conflict information, determine the adjustment parameters; The initial health level is adjusted based on the adjustment parameters to obtain the target health level.

Images