Equipment health assessment method and device, equipment and computer storage medium

Abstract

The invention relates to the technical field of data processing, in particular to an equipment health assessment method and device, equipment and a computer storage medium, and the method comprises the steps: obtaining vibration data; processing and extracting the vibration data to obtain first pure data; the first pure data comprises vibration frequency, vibration amplitude and acceleration; obtaining a health assessment model; and performing evaluation based on the health evaluation model and the first pure data to output a health score. The method and the device have the effect of evaluating the health of the equipment more comprehensively.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device, and computer storage medium for equipment health assessment. Background Technology

[0002] In modern industrial production, equipment health management has always been a key factor affecting production efficiency and cost reduction. Many industrial equipment, such as electric motors, pumps, fans, and compressors, involve rotating parts, and vibration is inevitable during their operation. The vibration level of equipment usually reflects its operating status. When equipment malfunctions, the vibration signal often changes significantly, and these changes can serve as a strong basis for judging the health status of the equipment.

[0003] In related technologies, equipment health assessments often rely on simplified vibration monitoring methods, most of which are limited to a single vibration index. However, single-type index data has limitations and cannot comprehensively reflect the health assessment of the equipment. Summary of the Invention

[0004] In order to conduct a more comprehensive assessment of equipment health, this application provides an equipment health assessment method, apparatus, device, and computer storage medium.

[0005] Firstly, the equipment health assessment method provided in this application adopts the following technical solution: A method for assessing equipment health, comprising: Acquire vibration data; The vibration data is processed and extracted to obtain the first clean data; The first set of clean data includes vibration frequency, vibration amplitude, and acceleration; Obtain a health assessment model; An evaluation is performed based on the health assessment model and the first clean data to output a health score.

[0006] By employing the above technical solution, after acquiring vibration data, the raw vibration data is preprocessed to extract high signal-to-noise ratio (SNR) first-level clean data. This involves removing high-frequency and low-frequency noise, reducing noise interference, and improving data accuracy. The first-level clean data includes vibration frequency, vibration amplitude, and acceleration, encompassing multi-dimensional vibration characteristics. These multi-dimensional characteristics provide a more comprehensive reflection of the vibration status of the device under test. This first-level clean data is then input into a health assessment model to perform an evaluation and analysis of the device under test. After the evaluation and analysis are completed, a health score is output. This health score quantifies the health status of the device under test, allowing users to better understand its condition and enabling efficient health assessment.

[0007] Optionally, the health assessment model includes: Health score calculation formula: ; in, The health score; This refers to the overall deviation. The formula for calculating the overall deviation is: ; in, The standardized deviation of the vibration index is defined as the vibration frequency, vibration amplitude, and acceleration, all of which are vibration indices. For the first The weighting coefficients of the vibration indexes.

[0008] Optionally, the method further includes: The formula for calculating the actual deviation is: ; The formula for calculating the standardized deviation is: ; in, This represents the actual deviation. The vibration index; The standard index corresponding to the vibration index; This represents the maximum deviation corresponding to the aforementioned vibration index.

[0009] Optionally, the method further includes: The weighting coefficients are updated and optimized; The updates and optimizations include: Data accumulation involves acquiring historical data based on a preset period, analyzing the trend of change based on the historical data to obtain the correlation between the vibration index and the occurrence of the fault, and automatically adjusting the weighting coefficient based on the correlation. Monitoring and feedback are conducted to obtain the health score. Based on the health score, the comprehensive deviation of the corresponding vibration index is obtained. The actual impact of the comprehensive deviation on the health score is analyzed. If the actual impact is significant, the weight coefficient of the corresponding vibration index is dynamically increased. Machine learning, combining the historical data and the trend of the health score, dynamically learns the importance of each vibration indicator through weighted regression or decision tree, and maps the vibration level to the weight coefficient.

[0010] By adopting the above technical solutions and dynamically updating and optimizing the weighting coefficients, the accuracy of the results can be improved during model calculation, resulting in a more accurate health score that accurately reflects the health status of the device under test. Data accumulation enables dynamic adjustment of the weighting coefficients, ensuring they better reflect the actual conditions of the device under test and automatically calibrating long-term relationships. If the deviation of an indicator has a significant impact on the actual health score, its weight is dynamically increased to address the issue of fixed weights potentially ignoring key anomalies, ensuring that important fault signals are prioritized, improving the sensitivity of such vibration indicators, and dynamically responding to anomaly impacts. Machine learning automatically identifies key fault characteristics without requiring manual weight presets, adapting to different equipment types or operating conditions. After long-term operation, the model can learn more complex nonlinear relationships, improving the generalization ability of the assessment.

[0011] Optionally, the method further includes: Obtain the dynamic threshold range; The health status is determined based on the health score and the dynamic threshold range; If the stated health status is good, then no action is taken; If the health status is normal, then the first warning signal is output; If the health status is at risk, then the first alarm signal will be output.

[0012] By adopting the above technical solution, the normal fluctuation range under different operating conditions can vary greatly, and the dynamic threshold can more accurately reflect the true health baseline of the current equipment. Based on the comparison between the health score and the dynamic threshold, the health status of the equipment under test is divided into: good, average, and risky. In the average state, the equipment under test has a minor abnormality, so an initial warning signal is needed to prompt the user to perform maintenance or increase attention to reduce unnecessary downtime. In the risky state, the equipment under test has a serious abnormality, at which point an initial alarm signal is output to ensure that the user takes timely action to prevent complete damage to the equipment under test. Users can take different actions according to different situations, optimizing the allocation of operation and maintenance resources.

[0013] Optionally, obtaining the dynamic threshold range includes: Obtain the operating status of the device under test; Based on the operating status, obtain the operating change trend of the device under test; A first correction value is mapped based on the aforementioned operational change trend; The dynamic threshold range is adjusted based on the first correction value; Also includes: Obtain the historical health score of the device under test; Analyze health change trends based on the historical health scores; A second correction value is mapped based on the aforementioned operational change trend; The dynamic threshold range is adjusted based on the second correction value.

[0014] By adopting the above technical solution, the scientific nature, accuracy, and adaptability of threshold setting in equipment health assessment are significantly improved by comprehensively considering the changing trends of the operating status and historical health scores of the equipment under test, and mapping first and second correction values ​​respectively. The vibration characteristics and health benchmark range of the equipment differ under different operating conditions. By correcting the threshold based on operating status and trends, the assessment standard is made more closely aligned with actual working conditions, avoiding misjudgments caused by fixed thresholds under special conditions. The health status of the equipment under test is often a gradual process. By analyzing historical health score trends, long-term change patterns such as equipment aging and performance degradation can be identified, thereby adjusting the threshold to adapt to this gradual change and avoiding false alarms or missed alarms caused by short-term fluctuations. Trend analysis based on historical data can predict the possible direction of changes in the equipment's health status in advance, so that the dynamic threshold range not only reflects the current state but also adapts to potential future changes, enhancing the system's predictive maintenance capabilities. The first correction value enables the dynamic threshold to quickly respond to changes in the current operating status of the equipment, while the second correction value ensures that the threshold adapts to the long-term health change trend of the equipment, taking into account both short-term fluctuations and long-term trends. With dual correction, the dynamic threshold range can be automatically adjusted under different working conditions and time periods, preventing misjudgments due to short-term abnormal fluctuations and loss of sensitivity due to long-term health degradation, thereby improving the stability and reliability of health assessment.

[0015] Optionally, when the health status is at risk, it further includes: The corresponding vibration index is obtained based on the operational change trend and the health change trend. Determine whether the vibration index meets the preset requirements; If the vibration index does not meet the preset requirements, then the vibration index that does not meet the preset requirements is obtained and the obtained vibration index is regarded as an abnormal index. An optimization report is generated based on the aforementioned anomaly indicators.

[0016] By adopting the above technical solution, when the equipment health status is determined to be at risk, a mechanism for identifying and generating optimization reports based on abnormal vibration indicators and health change trends is further introduced. This achieves a closed loop from problem discovery to root cause location and then to guiding optimization, demonstrating significant technical value and practical effects. It is no longer limited to a comprehensive conclusion based on low health scores, but accurately identifies which vibration indicators led to the risky state, greatly improving the accuracy of fault location. The operational change trends assist in determining the source of abnormal indicators, making diagnosis more accurate. Not all abnormal vibration indicators mean high risk; screening based on preset requirements avoids invalid warnings or information overload. It ensures focus on the marked abnormal indicators, providing precise targets for subsequent optimization. Clearly defined problem indicators provide strong direction and support root cause analysis and decision-making.

[0017] Secondly, the equipment health assessment device provided in this application adopts the following technical solution: A device for assessing device health includes: The first acquisition module is used to acquire vibration data; The processing and extraction module is used to process and extract the vibration data to obtain first clean data; the first clean data includes vibration frequency, vibration amplitude, and acceleration. The second acquisition module is used to acquire the health assessment model; An evaluation output module is used to perform an evaluation based on the health evaluation model and the first clean data to output a health score.

[0018] Thirdly, the electronic device provided in this application adopts the following technical solution: An electronic device includes a processor coupled to a memory; the processor is configured to execute a computer program stored in the memory such that the electronic device performs the method as described in the first aspect.

[0019] Fourthly, the computer-readable storage medium provided in this application adopts the following technical solution: A computer-readable storage medium includes a computer program or instructions that, when executed on a computer, cause the computer to perform the method as described in the first aspect.

[0020] In summary, this application includes at least one of the following beneficial technical effects: After acquiring vibration data, the raw vibration data is preprocessed to extract high signal-to-noise ratio (SNR) first-level clean data, which removes high-frequency and low-frequency noise, reducing noise interference and improving data accuracy. The first-level clean data includes vibration frequency, vibration amplitude, and acceleration, encompassing multi-dimensional vibration characteristics. These multi-dimensional characteristics provide a more comprehensive reflection of the vibration status of the device under test. This first-level clean data is then input into a health assessment model to perform an assessment and analysis of the device under test. After the assessment and analysis, a health score is output, quantifying the health status of the device under test. This allows users to better understand the device's condition and enables efficient health assessment. By comprehensively considering the changing trends of the operating status and historical health scores of the equipment under test (DUT), and mapping them to first and second correction values ​​respectively, the threshold range is dynamically adjusted, significantly improving the scientific rigor, accuracy, and adaptability of threshold setting in equipment health assessment. The vibration characteristics and health baseline range of equipment differ under different operating conditions. By correcting the threshold based on operating status and trends, the assessment standard better reflects actual working conditions, avoiding misjudgments caused by fixed thresholds under special conditions. The health status of DUT is often a gradual process. By analyzing historical health score trends, long-term patterns such as equipment aging and performance degradation can be identified, allowing for threshold adjustments to adapt to this gradual change and preventing false alarms or missed alarms due to short-term fluctuations. Trend analysis based on historical data can predict the possible direction of changes in equipment health status in advance, ensuring that the dynamic threshold range not only reflects the current state but also adapts to potential future changes, enhancing the system's predictive maintenance capabilities. The first correction value enables the dynamic threshold to quickly respond to changes in the current operating status of the equipment, while the second correction value ensures that the threshold adapts to the long-term health change trend of the equipment, taking into account both short-term fluctuations and long-term trends. With dual correction, the dynamic threshold range can be automatically adjusted under different working conditions and time periods. It will not cause misjudgment due to short-term abnormal fluctuations, nor will it lose sensitivity due to long-term health degradation, thereby improving the stability and reliability of the entire health assessment. Attached Figure Description

[0021] Figure 1 This is a flowchart of the device health assessment method according to an embodiment of this application.

[0022] Figure 2 This is a block diagram of the device health assessment apparatus according to an embodiment of this application.

[0023] Figure 3 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] This specific embodiment is merely an explanation of this application and is not intended to limit it. Users skilled in the art can make modifications to this embodiment without contributing any inventive step after reading this specification, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by users of ordinary skills in the art without creative effort are within the scope of protection of this application.

[0026] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0027] This application discloses a device health assessment method. This device health assessment method can be performed by an electronic device. The electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, desktop computer, etc., but is not limited to these.

[0028] This application discloses a method for assessing equipment health. (Refer to...) Figure 1 The main processes of a device health assessment method are described below (S100~S400): Step S100: Acquire vibration data; Step S200: Process and extract the vibration data to obtain the first clean data; the first clean data includes vibration frequency, vibration amplitude, and acceleration; Step S300: Obtain the health assessment model; Step S400: An evaluation is performed based on the health assessment model and the first clean data to output a health score.

[0029] The electronic device acquires vibration data, which is the raw data. Therefore, the electronic device processes and extracts this vibration data, essentially cleaning it to remove interference and obtain first-level clean data. This first-level clean data includes, but is not limited to, vibration frequency, vibration amplitude, and acceleration. The electronic device then acquires a health assessment model and evaluates the device under test based on this model and the first-level clean data. Specifically, the first-level clean data is input into the health assessment model to obtain a health score. The health assessment of the device under test utilizes multi-dimensional data. This comprehensive evaluation based on multi-dimensional data provides a more complete picture of the device's condition and better reflects its actual health status. Furthermore, by quantifying the health status of the device under test, users can more intuitively understand its condition and assess its health.

[0030] Specifically, the health assessment model includes: the formula for calculating the health score. ;in, Health score; This refers to the overall deviation; the formula for calculating the overall deviation is: ;in, The standardized deviation of vibration indices, including vibration frequency, vibration amplitude, and acceleration, is used. For the first The weighting coefficients of each vibration index.

[0031] The health score is a quantitative value representing the health status of the device under test (DUT), reflecting its operational condition. First, the standardized deviation of the vibration index is calculated. Then, the overall deviation is calculated using the corresponding weighting coefficients and the standardized deviation. The health score is then calculated from the overall deviation. Different vibration indices correspond to different weighting coefficients because different indices reflect different aspects of the DUT's health. Therefore, setting different and appropriate weighting coefficients can make the health score more accurate.

[0032] For vibration indices, vibration frequency is one vibration index, vibration amplitude is another vibration index, and acceleration is also a vibration index.

[0033] Specifically, the method also includes: the formula for calculating the actual deviation is: The formula for calculating the standardized deviation is: ;in, This represents the actual deviation. Vibration index; The standard index corresponding to the vibration index; This represents the maximum deviation of the corresponding vibration index.

[0034] For example, let's say we obtain vibration frequency data (A), vibration amplitude data (B), and acceleration data (C). We also obtain standard indices for vibration frequency, vibration amplitude, and acceleration. Substituting these into the formula, we can calculate the actual deviation corresponding to each of the three vibration indices. Then, obtain the maximum deviation corresponding to the three vibration indicators, substitute it into the formula, and the standardized deviation can be calculated. Because the three vibration indicators have different dimensions, the actual deviation cannot be used uniformly. Therefore, it is necessary to use the formula for standardization, that is, to calculate the standardized deviation.

[0035] As an optional implementation of this application, the method further includes: updating and optimizing the weighting coefficients; the updating and optimization includes: Data accumulation involves acquiring historical data based on a preset cycle, analyzing trends based on historical data to determine the correlation between vibration indicators and fault occurrence, and automatically adjusting weighting coefficients based on the correlation. Monitoring and feedback are conducted to obtain a health score. Based on the health score, the comprehensive deviation of the corresponding vibration index is obtained. The actual impact of the comprehensive deviation on the health score is analyzed. If the actual impact is significant, the weight coefficient of the corresponding vibration index is dynamically increased. Machine learning combines historical data and health score trends to dynamically learn the importance of each vibration indicator through weighted regression or decision trees, mapping the vibration level to weight coefficients.

[0036] The weighting coefficients are not fixed values, but are dynamically updated and optimized in different ways to make the calculated health score more consistent with the actual health status of the device under test.

[0037] As an optional implementation of this application, the method further includes: obtaining a dynamic threshold range; determining the health status based on the health score and the dynamic threshold range; if the health status is good, no action is taken; if the health status is average, a first warning signal is output; if the health status is at risk, a first alarm signal is output.

[0038] Depending on the assessment criteria, the electronic device outputs different signals. Users can understand the status of the device under test (DUT) based on these signals. For example, when the electronic device determines the DUT is in a normal state, it outputs a first warning signal, serving as a preliminary warning to the user. This indicates a minor anomaly, requiring the user to pay closer attention and perform maintenance to eliminate the anomaly and avoid unnecessary downtime. When the electronic device determines the DUT is at risk, it outputs a first alarm signal. This indicates a serious anomaly, requiring immediate action from the user to prevent complete damage and greater losses. Users can rationally allocate and manage maintenance resources according to different situations.

[0039] As an optional implementation of this application, obtaining the dynamic threshold range includes: obtaining the operating status of the device under test; obtaining the operating change trend of the device under test based on the operating status; mapping a first correction value based on the operating change trend; correcting the dynamic threshold range based on the first correction value; and further includes: obtaining the historical health score of the device under test; analyzing the health change trend based on the historical health score; mapping a second correction value based on the operating change trend; and correcting the dynamic threshold range based on the second correction value.

[0040] Electronic equipment acquires operational trends based on the device under test's (DUT) operating status, maps these trends to a first correction value, and adjusts the dynamic threshold range accordingly. By adjusting the threshold based on both operating status and trends, the evaluation criteria better reflect actual operating conditions, avoiding misjudgments caused by fixed thresholds under special circumstances. The health status of the DUT typically undergoes a long-term, gradual change. By analyzing historical health score trends, long-term patterns such as equipment aging and performance degradation can be identified, allowing for threshold adjustments to adapt to these gradual changes and preventing false alarms or missed alarms due to short-term fluctuations. Balancing short-term fluctuations with long-term trends improves the stability and reliability of health assessments. As an optional implementation of this application, when the health status is at risk, the method further includes: obtaining the corresponding vibration index based on the operation change trend and the health change trend; determining whether the vibration index meets the preset requirements; if the vibration index does not meet the preset requirements, obtaining the vibration index that does not meet the preset requirements and using the obtained vibration index as an abnormal index; and generating an optimization report based on the abnormal index.

[0041] The abnormal vibration index identification and optimization report generation mechanism based on operational and health change trends achieves a closed loop from problem discovery to root cause location and optimization guidance. It moves beyond a simple conclusion based solely on low health scores, accurately identifying which vibration indicators led to the risk state, significantly improving the accuracy of fault location. It ensures focus on tagged abnormal indicators, providing precise targets for subsequent optimization. Clearly defined problem indicators provide strong direction, supporting root cause analysis and decision-making.

[0042] Figure 2 A structural block diagram of a device health assessment apparatus 500 provided in this application embodiment is shown below. Figure 2 As shown, the device health assessment apparatus 500 includes: The first acquisition module 501 is used to acquire vibration data; The processing and extraction module 502 is used to process and extract vibration data to obtain first clean data; the first clean data includes vibration frequency, vibration amplitude, and acceleration. The second acquisition module 503 is used to acquire the health assessment model; The assessment output module 504 is used to perform an assessment based on the health assessment model and the first clean data to output a health score.

[0043] Specifically, the second acquisition module 503 includes: The first calculation module is used to calculate the health score. The formula for calculating the health score is as follows: ;in, Health score; This refers to the overall deviation. The second calculation module is used to calculate the overall deviation. The formula for calculating the overall deviation is: ;in, The standardized deviation of vibration indices, including vibration frequency, vibration amplitude, and acceleration, is used. For the first The weighting coefficients of each vibration index.

[0044] In this optional embodiment, the device health assessment apparatus 500 further includes: The third calculation module is used to calculate the actual deviation. The formula for calculating the actual deviation is: ; The fourth calculation module is used to calculate the standardized deviation. The formula for calculating the standardized deviation is: ;in, This represents the actual deviation. Vibration index; The standard index corresponding to the vibration index; This represents the maximum deviation of the corresponding vibration index.

[0045] In this optional embodiment, the device health assessment apparatus 500 further includes: The update and optimization submodule is used to update and optimize the weight coefficients. The update and optimization include: data accumulation (acquiring historical data based on a preset period, analyzing trends based on historical data to obtain the correlation between vibration indicators and fault occurrence, and automatically adjusting weight coefficients based on the correlation); monitoring and feedback (obtaining a health score, obtaining the comprehensive deviation of the corresponding vibration indicators based on the health score, analyzing the actual impact of the comprehensive deviation on the health score, and dynamically increasing the weight coefficient of the corresponding vibration indicator if the actual impact is significant); and machine learning (combining historical data and health score trends, dynamically learning the importance of each vibration indicator through weighted regression or decision trees, and mapping the vibration level to weight coefficients).

[0046] In this optional embodiment, the device health assessment apparatus 500 further includes: The first acquisition submodule is used to acquire the dynamic threshold range; The first judgment submodule is used to determine the health status based on the health score and dynamic threshold range; if the health status is good, no action is taken; if the health status is average, the first warning signal is output; if the health status is at risk, the first alarm signal is output.

[0047] Specifically, the first acquisition submodule includes: The second acquisition submodule is used to acquire the operating status of the device under test; The third acquisition submodule is used to acquire the operating change trend of the device under test based on its operating status. The first mapping submodule is used to map the first correction value based on the running change trend; The first correction submodule is used to correct the dynamic threshold range based on the first correction value; The first acquisition submodule also includes: The fourth acquisition submodule is used to acquire the historical health score of the device under test; The first analysis submodule is used to analyze health change trends based on historical health scores; The second mapping submodule is used to map a second correction value based on the trend of change in operation; The second correction submodule is used to correct the dynamic threshold range based on the second correction value.

[0048] In this optional embodiment, the device health assessment apparatus 500 further includes: The fifth acquisition submodule is used to acquire the corresponding vibration index based on the operational change trend and the health change trend when the health status is at risk. The second judgment submodule is used to determine whether the vibration index meets the preset requirements; if the vibration index does not meet the preset requirements, the vibration index that does not meet the preset requirements is obtained and the obtained vibration index is regarded as an abnormal index. The generation submodule is used to generate optimization reports based on abnormal indicators.

[0049] Figure 3 This is a structural block diagram of an electronic device 600 provided in an embodiment of this application. The electronic device 600 can be a mobile phone, tablet computer, PC, server, or other device. Figure 3 As shown, the electronic device 600 includes a memory 601, a processor 602, and a communication bus 603; the memory and the processor 602 are connected via the communication bus 603. The memory 601 stores a computer program that can be loaded by the processor 602 and executed as described in the above embodiments for the device health assessment method.

[0050] The memory 601 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 601 may include a stored program area and a stored managed data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the device health assessment method provided in the above embodiments, etc.; the stored managed data area may store managed data involved in the device health assessment method provided in the above embodiments, etc.

[0051] Processor 602 may include one or more processing cores. Processor 602 executes instructions, programs, code sets, or instruction sets stored in memory 601, and calls managed data stored in memory 601 to perform various functions of this application and process managed data. Processor 602 may be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 602 may also be other types, and this application embodiment does not specifically limit the specific devices used.

[0052] The communication bus 603 may include a path for transmitting information between the aforementioned components. The communication bus 603 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 603 can be divided into an address bus, a managed data bus, a control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double arrow, but this does not mean that there is only one bus or one type of bus.

[0053] This application provides a computer storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for device health assessment.

[0054] In this embodiment, the computer storage medium can be a tangible device that holds and stores instructions used by the instruction execution device. The computer storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), speaker random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0055] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A method for assessing equipment health, characterized in that, include: Acquire vibration data; The vibration data is processed and extracted to obtain the first clean data; The first set of clean data includes vibration frequency, vibration amplitude, and acceleration; Obtain a health assessment model; An evaluation is performed based on the health assessment model and the first clean data to output a health score.

2. The equipment health assessment method according to claim 1, characterized in that, The health assessment model includes: Health score calculation formula: ; in, The health score; This refers to the overall deviation. The formula for calculating the overall deviation is: ; in, The standardized deviation of the vibration index is defined as the vibration frequency, vibration amplitude, and acceleration, all of which are vibration indices. For the first The weighting coefficients of the vibration indexes.

3. The equipment health assessment method according to claim 2, characterized in that, The method further includes: The formula for calculating the actual deviation is: ; The formula for calculating the standardized deviation is: ; in, This represents the actual deviation. The vibration index; The standard index corresponding to the vibration index; This represents the maximum deviation corresponding to the aforementioned vibration index.

4. The equipment health assessment method according to claim 2, characterized in that, The method further includes: The weighting coefficients are updated and optimized; The updates and optimizations include: Data accumulation involves acquiring historical data based on a preset period, analyzing the trend of change based on the historical data to obtain the correlation between the vibration index and the occurrence of the fault, and automatically adjusting the weighting coefficient based on the correlation. Monitoring and feedback are conducted to obtain the health score. Based on the health score, the comprehensive deviation of the corresponding vibration index is obtained. The actual impact of the comprehensive deviation on the health score is analyzed. If the actual impact is significant, the weight coefficient of the corresponding vibration index is dynamically increased. Machine learning, combining the historical data and the trend of the health score, dynamically learns the importance of each vibration indicator through weighted regression or decision tree, and maps the vibration level to the weight coefficient.

5. The equipment health assessment method according to claim 1, characterized in that, The method further includes: Obtain the dynamic threshold range; The health status is determined based on the health score and the dynamic threshold range; If the stated health status is good, then no action is taken; If the health status is normal, then the first warning signal is output; If the health status is at risk, then the first alarm signal will be output.

6. The equipment health assessment method according to claim 5, characterized in that, The process of obtaining the dynamic threshold range includes: Obtain the operating status of the device under test; Based on the operating status, obtain the operating change trend of the device under test; A first correction value is mapped based on the aforementioned operational change trend; The dynamic threshold range is adjusted based on the first correction value; Also includes: Obtain the historical health score of the device under test; Analyze health change trends based on the historical health scores; A second correction value is mapped based on the aforementioned operational change trend; The dynamic threshold range is adjusted based on the second correction value.

7. The equipment health assessment method according to claim 6, characterized in that, When the health status is at risk, it also includes: The corresponding vibration index is obtained based on the operational change trend and the health change trend. Determine whether the vibration index meets the preset requirements; If the vibration index does not meet the preset requirements, then the vibration index that does not meet the preset requirements is obtained and the obtained vibration index is regarded as an abnormal index. An optimization report is generated based on the aforementioned anomaly indicators.

8. A device for assessing equipment health, characterized in that, include: The first acquisition module is used to acquire vibration data; The processing and extraction module is used to process and extract the vibration data to obtain the first clean data; The first set of clean data includes vibration frequency, vibration amplitude, and acceleration; The second acquisition module is used to acquire the health assessment model; An evaluation output module is used to perform an evaluation based on the health evaluation model and the first clean data to output a health score.

9. An electronic device, characterized in that, The device includes a processor coupled to a memory; the processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images