Online comprehensive detection, analysis and evaluation method and system for power equipment bearing

Abstract

The invention provides an online comprehensive detection, analysis and evaluation method and system for a power equipment bearing, and the method comprises the steps: obtaining four-dimensional operation parameters of the bearing in real time, including a temperature and vibration value, an audio frequency spectrum feature, a dynamic maintenance period parameter and a bearing load rate parameter; establishing a correlation model of specific frequency band energy change and vibration value fluctuation in the audio frequency spectrum characteristics through space-time correlation analysis, injecting a dynamic maintenance period parameter as a time domain attenuation factor into the correlation model, and dynamically weighting based on a bearing load rate parameter to generate a health degradation index; when the health degradation index exceeds a dynamic threshold value, generating a pre-maintenance instruction, and outputting a maintenance strategy containing a fault positioning map; a pre-maintenance instruction and a maintenance strategy are packaged according to an industrial communication protocol, and a correlation analysis view and an early warning window are dynamically embedded in a distributed control system interface, so that the accuracy of bearing online monitoring is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of power equipment status monitoring, and in particular to an online comprehensive detection, analysis and evaluation method and system for power equipment bearings. Background Art

[0002] With the continuous improvement of industrial automation, the operating status of power equipment bearings, as key components of rotating machinery, directly affects the safety and reliability of the entire equipment. Bearing failure is one of the most common types of failure in rotating machinery. Effective bearing condition monitoring and fault diagnosis technology is of great significance for preventing sudden equipment failures, reducing unplanned downtime, and lowering maintenance costs.

[0003] Currently, bearing condition monitoring mainly relies on vibration and temperature parameter analysis, resulting in low bearing detection accuracy. Summary of the Invention

[0004] The present invention provides an online comprehensive detection, analysis and evaluation method and system for power equipment bearings, which are used to solve the defect of poor detection accuracy of power equipment bearings in the prior art.

[0005] In a first aspect, the present invention provides a method for online comprehensive detection, analysis and evaluation of power equipment bearings, comprising: Real-time acquisition of four-dimensional operating parameters of the bearing, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; By means of spatiotemporal correlation analysis, a correlation model is established between energy changes in specific frequency bands in the audio spectrum characteristics and fluctuations in the vibration value, and the dynamic maintenance cycle parameter is injected into the correlation model as a time-domain attenuation factor. A health degradation index is generated based on dynamic weighting of the bearing load rate parameter; When the health degradation index exceeds a dynamic threshold, a pre-maintenance instruction is generated, and a maintenance strategy including a fault location map is output; The pre-maintenance instruction and the maintenance strategy are encapsulated according to the industrial communication protocol, and the associated analysis view and the early warning window are dynamically embedded in the distributed control system interface.

[0006] According to the present invention, a method for online comprehensive detection, analysis and evaluation of power equipment bearings is provided, wherein the real-time acquisition of the acoustic spectrum characteristics of the bearings comprises: The sound of bearing operation is collected through a wide-band microphone array; Performing time-frequency transformation on the bearing running sound to extract energy in a predetermined frequency band; Based on the energy of the predetermined frequency band, a three-dimensional characteristic spectrum of sound energy-frequency-time is constructed.

[0007] According to the present invention, a method for online comprehensive detection, analysis and evaluation of power equipment bearings further includes: Calculate the lubricant state attenuation coefficient based on the bearing temperature and load rate parameters; The maintenance cycle parameters are dynamically adjusted based on the lubricant state attenuation coefficient.

[0008] According to a method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, the method establishes a correlation model between energy changes in a specific frequency band in the audio spectrum characteristics and the vibration value fluctuations through spatiotemporal correlation analysis, including: Detecting anomalies in synchronization between a rate of change of energy in a high frequency band of the audio frequency spectrum characteristics and energy in a characteristic frequency band of the vibration value; When the synchronization anomaly meets the preset association conditions, the specific fault mode and location information are marked and an association model is constructed.

[0009] According to a method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, the health degradation index is generated based on the dynamic weighting of the bearing load rate parameter, including: Determine the piecewise function of the bearing load rate as the weight coefficient; Based on the weight coefficient, the vibration value deviation, the sound energy change and the maintenance urgency are weighted and summed to generate a health degradation index.

[0010] According to the method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, before generating the pre-maintenance instruction, the method further includes: Determine statistical boundaries based on historical normal operation data sets; According to the statistical boundary, combined with the fault case library of the same type of equipment, a safe operation interval is generated as a dynamic threshold.

[0011] According to the method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, after generating the pre-maintenance instruction, the method further includes: Fuse the sound source location results with the vibration transmission path analysis to obtain the fault probability; Generate a spatial distribution heat map of the fault probability as a fault location map.

[0012] According to the method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, after obtaining the four-dimensional operating parameters of the bearings in real time, the method further includes: Identify the electromagnetic interference spectrum caused by current harmonics; Detect broadband characteristics of fluid dynamic noise; The electromagnetic interference spectrum and the broadband characteristics are removed from the audio spectrum characteristics.

[0013] According to the method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the present invention, after outputting the maintenance strategy including the fault location map, the method further includes: Establish a failure propagation relationship model for multiple bearings in the same unit; When the health degradation index of a single bearing exceeds the limit, the cascading failure risk value of the associated bearings is calculated using the failure propagation relationship model; A multi-bearing collaborative maintenance sequence and downtime optimization plan are generated based on the cascading failure risk value.

[0014] In a second aspect, the present invention further provides an online comprehensive detection, analysis and evaluation system for power equipment bearings, comprising: An acquisition module is used to obtain the four-dimensional operating parameters of the bearing in real time, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; a correlation module, configured to establish a correlation model between energy changes in a specific frequency band in the audio spectrum characteristics and fluctuations in the vibration value through spatiotemporal correlation analysis, inject the dynamic maintenance cycle parameter into the correlation model as a time-domain attenuation factor, and generate a health degradation index based on dynamic weighting of the bearing load rate parameter; an output module, configured to generate a pre-maintenance instruction when the health degradation index exceeds a dynamic threshold, and output a maintenance strategy including a fault location map; The application module is used to encapsulate the pre-maintenance instruction and the maintenance strategy according to the industrial communication protocol, and dynamically embed the associated analysis view and the early warning window in the distributed control system interface.

[0015] In a third aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for online comprehensive detection, analysis, and evaluation of power equipment bearings as described above is implemented.

[0016] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for online comprehensive detection, analysis and evaluation of power equipment bearings.

[0017] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for online comprehensive detection, analysis and evaluation of power equipment bearings.

[0018] The beneficial effects of the present invention are as follows: by adding bearing sound spectrum acquisition capabilities and detailed data collection such as maintenance and refueling cycles to the existing DCS platform, and using intelligent analysis methods to comprehensively analyze data such as bearing operating temperature, vibration values, sound spectrum, and maintenance and refueling cycles, the necessary data can be provided more objectively and promptly, allowing for early detection of signs of bearing failures, facilitating early preparation and treatment, preventing equipment failures from affecting the normal operation of the unit, and improving equipment reliability and work efficiency. At the same time, the present invention eliminates misjudgments caused by lack of experience and ability in human data collection, thereby improving the objectivity and scientific nature of judgments. Furthermore, by establishing a correlation model between sound spectrum characteristics and vibration value fluctuations, combined with dynamic maintenance cycle parameters and bearing load rate parameters, the bearing health status can be more accurately assessed, achieving precise fault location and predictive maintenance, significantly improving the comprehensiveness and accuracy of bearing operation monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 1 is a flow chart of the on-line comprehensive detection, analysis and evaluation method for power equipment bearings provided in this embodiment; Figure 2 This is a structural diagram of the on-line comprehensive detection, analysis and evaluation system for power equipment bearings provided in this embodiment; Figure 3 Schematic diagram of the structure of the electronic device provided in this embodiment. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0022] Figure 1 It is a flow chart of the on-line comprehensive detection, analysis and evaluation method for power equipment bearings provided in this embodiment.

[0023] like Figure 1 As shown, the method for online comprehensive detection, analysis and evaluation of power equipment bearings provided by the embodiment of the present invention mainly includes the following steps: 101. Real-time acquisition of the four-dimensional operating parameters of the bearing, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters.

[0024] Specifically, temperature and vibration values ​​are collected by temperature sensors and vibration sensors installed on the bearing seat. The temperature sensor collects data at a frequency of 1Hz, and the vibration sensor collects data at a frequency of 10kHz. The audio spectrum characteristics collect the operating sound of the bearing through a wide-band microphone array with a sampling frequency of 48kHz. The dynamic maintenance cycle parameters are determined based on the equipment's operating time, historical maintenance records, and manufacturer recommended values. The bearing load rate parameters are calculated using the motor current, speed, and load torque.

[0025] 102. Through time-space correlation analysis, a correlation model between energy changes in specific frequency bands in the audio spectrum characteristics and vibration value fluctuations is established, and the dynamic maintenance cycle parameters are injected into the correlation model as time-domain attenuation factors. The health degradation index is generated based on the dynamic weighting of the bearing load rate parameters.

[0026] Using spatiotemporal correlation analysis methods, the collected audio signals are analyzed from both temporal and spatial dimensions. Spectral analysis operations such as Fourier transform are performed on the audio signals to convert the time-domain audio signals into the frequency domain, resulting in an audio spectrum. By comparing and studying a large number of bearing audio spectra under normal and different fault conditions, specific frequency bands closely related to the bearing's operating status are identified. Within this frequency band, the energy variation over time is calculated. For example, as bearings gradually develop potential fault hazards such as wear and fatigue, the energy within a specific frequency band may gradually increase or exhibit abnormal fluctuations. Simultaneously, combined with vibration value data collected by vibration sensors, the fluctuation characteristics of the vibration values ​​over time series and their spatial variation patterns (such as vibration differences between different parts of the bearing) are analyzed.

[0027] Based on the analysis of energy changes and vibration fluctuations in specific frequency bands, a correlation model is constructed. Machine learning regression analysis algorithms, such as linear regression and polynomial regression, can be used to identify the mathematical relationship between energy changes and vibration fluctuations in specific frequency bands. Through training and optimization using extensive historical data, the model can accurately reflect the inherent connection between the two. For example, the model might represent a functional relationship, where the energy change value in a specific frequency band is input and the corresponding vibration fluctuation prediction is output.

[0028] The dynamic maintenance cycle parameter reflects the maintenance schedule interval based on the equipment's actual operating conditions. This parameter is injected into the correlation model as a time-domain attenuation factor. The principle is that bearing performance gradually declines as the time since the last maintenance increases, and the impact of various factors in the equipment's operating environment (such as temperature, humidity, and load fluctuations) on the bearing also gradually accumulates. Therefore, a larger dynamic maintenance cycle parameter has a greater impact on the correlation model's predictions, making the model's predicted vibration fluctuations and energy changes in specific frequency bands more significant, reflecting the increased risk of failure due to equipment aging and lack of maintenance.

[0029] The load of power equipment is monitored in real time to calculate the bearing load factor parameters. Different load factors have varying degrees of impact on bearing health. Higher load factors place greater pressure on the bearing, exacerbating wear and increasing the likelihood of failure. When generating the health degradation index, the output of the correlation model is dynamically weighted based on the bearing load factor parameters. For example, when the load factor exceeds a certain threshold, the weighting of energy changes and vibration fluctuations in specific frequency bands in the health degradation index calculation is increased, making the health degradation index more sensitive to the negative impact of high load on bearing health.

[0030] The bearing health degradation index is generated by combining the correlation model results after adjusting the dynamic maintenance cycle parameters and weighting the bearing load factor parameters. This index is a quantitative value, with higher values ​​indicating worse bearing health and a higher likelihood of failure. By setting different health degradation index thresholds, bearings can be classified into different health levels, such as normal, mild warning, moderate warning, and severe failure risk.

[0031] The health degradation index generated through this series of operations can comprehensively, accurately, and dynamically reflect the health status of power equipment bearings. It integrates multiple factors, including sound frequency, vibration, maintenance cycle, and load rate, offering greater accuracy and foresight than maintenance strategies that rely solely on vibration analysis or simple time-based maintenance strategies. For example, in actual applications, it can detect potential bearing failures months or even longer in advance, providing equipment maintenance personnel with ample time to develop maintenance plans and prepare spare parts, thus avoiding equipment downtime caused by sudden bearing failures. This significantly improves the reliability and stability of power equipment operations and reduces equipment maintenance costs and the risk of production losses.

[0032] Alternatively, the system can first detect synchronization anomalies between the energy change rate in the high-frequency band (5kHz-15kHz) of the audio spectrum and the energy in the characteristic frequency band (1kHz-3kHz) of the vibration value. When this synchronization anomaly meets preset correlation conditions, it identifies a specific fault mode and location information, and constructs a correlation model. The preset correlation conditions are: the correlation coefficient between the energy change rate in the high-frequency band of the audio and the energy change in the characteristic frequency band of the vibration is greater than a preset value and persists for a predetermined duration.

[0033] The dynamic maintenance cycle parameters are converted into a time-domain attenuation factor. The calculation formula is: attenuation factor = 1-(current operating time / recommended maintenance cycle). The attenuation factor decreases with increasing operating time, reflecting the natural attenuation of bearing performance over time.

[0034] A piecewise function of the bearing load factor is used as the weighting factor. Specifically, when the load factor is less than 30%, the weighting factor is 0.8; when the load factor is between 30% and 70%, the weighting factor is 1.0; and when the load factor is greater than 70%, the weighting factor is 1.5. Based on the weighting factor, the vibration value deviation, acoustic energy change, and maintenance urgency are weighted and summed to generate the health degradation index. The calculation formula is: Health Degradation Index = Weighting Factor × (0.4 × Vibration Value Deviation + 0.4 × Acoustic Energy Change + 0.2 × Maintenance Urgency).

[0035] 103. When the health degradation index exceeds the dynamic threshold, a pre-maintenance instruction is generated and a maintenance strategy including a fault location map is output.

[0036] Specifically, the online monitoring system for power equipment bearings continuously monitors changes in the health degradation index in real time. The dynamic threshold setting is not static but is adjusted dynamically based on a variety of factors. First, a large amount of historical data is collected from bearings at different operating stages (such as the initial installation, normal operation, and nearing the end of their service life) to analyze the patterns of changes in the health degradation index during these stages. For example, the health degradation index of a new bearing changes relatively slowly during initial operation, but accelerates as it ages and approaches failure. Second, the actual operating conditions of power equipment are considered, including frequent load changes and fluctuations in ambient temperature and humidity. For example, in high-temperature and high-humidity environments, bearing wear may accelerate, causing the health degradation index to rise more rapidly. In these cases, the dynamic threshold needs to be adjusted to be more sensitive. Machine learning algorithms, such as the ARIMA model used in time series analysis, learn and predict historical and real-time operating data to determine the appropriate dynamic threshold.

[0037] When the health degradation index exceeds the dynamic threshold, the system immediately triggers the pre-maintenance instruction generation mechanism. The system's logic judgment module quickly captures the signal that the health degradation index has exceeded the threshold and subsequently activates the instruction generation program. This program generates a pre-maintenance instruction containing rich information according to pre-set format and content requirements. The instruction clearly specifies the power equipment number and specific location of the bearing (such as a motor bearing on a production line), as well as the current health degradation index value and the degree to which it exceeds the threshold. For example: "Power equipment No. 005, a motor bearing located in the middle of the production line, has a health degradation index of 85, exceeding the current dynamic threshold of 70. Pre-maintenance must be arranged immediately." This detailed information allows maintenance personnel to immediately identify the problematic equipment and the severity of the problem.

[0038] Leveraging previously collected audio and vibration signals and analysis results from correlation models, combined with advanced data analysis techniques, a fault location map is generated. First, an in-depth retrospective analysis is conducted on energy changes and vibration fluctuations in specific frequency bands of the audio signals. For example, if an abnormally high energy level in a specific frequency band is accompanied by vibration fluctuations far exceeding the normal range in a certain direction, the potential fault location can be preliminarily determined by the correlation between spatial location and sensor layout. Next, using a fault tree analysis (FTA) method, starting with an abnormal health degradation index as the top event, the system analyzes the various possible intermediate and fundamental events leading to this event, such as bearing inner ring wear, outer ring fatigue, and rolling element damage. The logical relationships between these events are presented in a tree-like structure within the map. The map also uses color coding and graphical indicators to visually display the level of fault probability. For example, red indicates a very high probability of failure, yellow indicates a moderate probability, and green indicates normal operation. This fault location map allows maintenance personnel to clearly visualize the fault risk status of each bearing component.

[0039] Generate targeted maintenance strategies based on the fault location map and the operating history and maintenance records of the power equipment. If the fault location map shows a high probability of bearing inner ring failure, and the equipment has previously experienced downtime due to inner ring wear, the maintenance strategy may recommend immediate replacement of the inner ring and a comprehensive inspection and cleaning of the relevant lubrication system to ensure good lubrication and prevent the new inner ring from wearing out rapidly again. For areas with minor fault signs, such as minor scratches on the rolling element surface, the maintenance strategy may be to strengthen monitoring during this pre-maintenance, record the development of the scratches, and adjust operating parameters, such as appropriately reducing the load or increasing the lubrication frequency, to delay the development of the fault, and focus on this area during the next maintenance cycle. The maintenance strategy will also include detailed information such as a list of tools required for maintenance, a list of spare parts, and an estimated maintenance time, providing comprehensive guidance for maintenance personnel.

[0040] By generating pre-maintenance instructions when the health degradation index exceeds a dynamic threshold and outputting a maintenance strategy including a fault location map, the maintenance efficiency and operational reliability of power equipment bearings can be significantly improved. In terms of maintenance efficiency, maintenance personnel no longer need to spend a large amount of time troubleshooting faulty equipment and analyzing the cause of the failure. Pre-maintenance instructions and fault location maps directly point them in the right direction, greatly shortening fault diagnosis time. For example, troubleshooting time that could have taken hours or even days can be reduced to tens of minutes. From the perspective of equipment operational reliability, issuing pre-maintenance instructions based on abnormal health degradation indices in advance avoids further deterioration of bearing failures and effectively reduces the probability of sudden equipment downtime.

[0041] Before generating a preventive maintenance instruction, a statistical boundary is determined based on a historical normal operation dataset. The normal fluctuation range of vibration and acoustic energy is calculated using the 3σ principle. Based on this statistical boundary and incorporating a database of similar equipment failure cases, a safe operating range is generated, which serves as a dynamic threshold. The dynamic threshold adjusts with equipment operating time and load. The calculation formula is: Dynamic Threshold = Baseline Threshold × (1 + 0.2 × Load Factor) × (1 + 0.1 × Operating Time Ratio).

[0042] After generating the predictive maintenance instructions, the system integrates the sound source location results with the vibration transmission path analysis to determine the fault probability. A heat map of the spatial distribution of the fault probability is then generated as a fault location map. The fault location map is based on the bearing structure and uses color to indicate the fault probability of different locations, with red indicating a high probability and blue indicating a low probability.

[0043] 104. Encapsulate the preventive maintenance instructions and maintenance strategies according to the industrial communication protocol, and dynamically embed the associated analysis view and early warning window in the distributed control system interface.

[0044] Specifically, in the online bearing inspection system for power equipment, after pre-maintenance instructions and maintenance strategies are generated, they must be encapsulated according to industrial communication protocols. When selecting industrial communication protocols, the industrial environment and system compatibility of the power equipment must be fully considered, such as commonly used protocols like Modbus and OPC UA. First, the pre-maintenance instructions and maintenance strategies are structured and broken down into distinct data fields, such as device identification, fault description, maintenance steps, and spare parts list. Using the Modbus protocol as an example, each field is assigned a specific register address, and the text information in the instructions and strategies is converted into binary or hexadecimal data formats that comply with the protocol specifications. For complex maintenance strategies, packet transmission is used to ensure data integrity and accuracy. During the encapsulation process, necessary checksums, such as cyclic redundancy check (CRC), are added to allow the receiving end to verify data errors during transmission, ensuring reliable transmission of instructions and strategies within industrial networks.

[0045] As the core platform for monitoring and managing power equipment operations, the distributed control system (DCS) requires the dynamic embedding of packaged preventive maintenance instructions and maintenance strategies. First, system developers use interfaces provided by the DCS (such as APIs or SDKs) to reserve display areas within the appropriate locations within the DCS interface. For example, information related to preventive maintenance instructions and maintenance strategies can be displayed in a sidebar or pop-up window on the main monitoring interface. For correlation analysis views, previously generated correlation analysis results, such as fault location maps and health degradation index trends, are optimized using data visualization technology and converted into charts and graphs suitable for display within the DCS interface. For example, the fault location map can be presented as an interactive map, allowing users to click on different areas to view detailed fault information. The processed correlation analysis view and packaged preventive maintenance instructions and maintenance strategy data are then transmitted to the interface display area via the DCS's communication mechanisms for dynamic loading. Whenever new preventive maintenance instructions or maintenance strategies are generated, the system automatically updates the interface content to ensure operators have the latest information.

[0046] A dedicated early warning window is set up in the DCS interface to highlight preventive maintenance instructions and important maintenance reminders. The triggering mechanism of the early warning window is linked to the health degradation index out-of-bounds signal. When the health degradation index exceeds the dynamic threshold, the system generates a preventive maintenance instruction and immediately activates the early warning window. The early warning window uses eye-catching colors (such as a red background), flashing effects, and sound prompts to attract the attention of operators. The window not only displays key information about the preventive maintenance instruction, such as the equipment name and the urgency of the fault, but also provides quick links. Operators can click to jump directly to the detailed maintenance strategy page and the associated analysis view, allowing them to quickly understand the fault situation and treatment measures. At the same time, the early warning window has memory and filtering functions, which can record historical warning information. Operators can query and filter according to conditions such as time and equipment type, facilitating the statistics and analysis of equipment failures.

[0047] By encapsulating preventive maintenance instructions and maintenance strategies according to industrial communication protocols and dynamically embedding correlation analysis views and early warning windows in the distributed control system interface, significant results have been achieved in many aspects of online testing of power equipment bearings. In terms of information transmission, this ensures that preventive maintenance instructions and maintenance strategies can be accurately and efficiently transmitted within the industrial network environment, avoiding information loss or misunderstanding due to incompatible data formats or transmission errors, and enabling maintenance personnel and operators to obtain accurate equipment maintenance information in a timely manner. In terms of operational convenience, the correlation analysis view and early warning window are integrated into the DCS interface. Operators can intuitively understand the bearing's fault status, health trends, and corresponding maintenance measures without switching between multiple systems or interfaces, greatly improving fault handling efficiency.

[0048] Furthermore, based on the above embodiment, the present embodiment obtains the audio spectrum characteristics of the bearing in real time, including: collecting the bearing operation sound through a wide-band microphone array, where the microphone array is composed of multiple omnidirectional microphones distributed in a ring shape and a certain distance from the outer surface of the bearing; performing time-frequency transformation on the bearing operation sound to extract the energy of a predetermined frequency band, and using short-time Fourier transform to extract the energy distribution of the target frequency band; and constructing a three-dimensional characteristic map of sound energy-frequency-time based on the energy of the predetermined frequency band.

[0049] Furthermore, this embodiment also includes calculating a lubricant state attenuation coefficient according to the temperature and load rate parameters of the bearing; and dynamically adjusting maintenance cycle parameters based on the lubricant state attenuation coefficient.

[0050] Specifically, the lubricant state attenuation coefficient is calculated as: Attenuation coefficient = 1 + 0.05 × (T - T0) / 10 + 0.03 × (L - L0) / 10, where T is the current bearing temperature, T0 is the reference temperature (typically 40°C), L is the current load factor, and L0 is the reference load factor (typically 50%). As the temperature or load increases, the lubricant state attenuation coefficient increases, indicating a faster rate of lubricant performance degradation.

[0051] The maintenance interval is dynamically adjusted based on the lubricant attenuation coefficient. The adjustment formula is: Adjusted maintenance interval = Original maintenance interval / Lubricant attenuation coefficient. For example, if the attenuation coefficient is 1.2 and the original maintenance interval is 3000 hours, the adjusted maintenance interval is 2500 hours.

[0052] Furthermore, in this embodiment, after obtaining the four-dimensional operating parameters of the bearing in real time, it also includes: identifying the electromagnetic interference spectrum caused by current harmonics, extracting the frequency components of integer multiples of 50Hz or 60Hz by analyzing the motor current waveform, and establishing an electromagnetic interference spectrum template; detecting the broadband characteristics of fluid dynamic noise, and identifying the broadband noise characteristics generated by fluid flow by analyzing the background noise during the operation of the cooling system; eliminating the electromagnetic interference spectrum and broadband characteristics from the audio spectrum characteristics, and using an adaptive filtering algorithm to retain the characteristic frequency bands related to the bearing fault.

[0053] Furthermore, after outputting the maintenance strategy including the fault location map, this embodiment also includes: establishing a failure propagation relationship model for multiple bearings in the same unit, and constructing a fault propagation network based on the mechanical connection relationship, load transfer path and vibration transfer characteristics between the bearings; when the health degradation index of a single bearing exceeds the limit, the cascading failure risk value of the associated bearings is calculated through the failure propagation relationship model, and the risk value calculation takes into account the distance between the bearings, the degree of load sharing and the vibration transfer coefficient; based on the cascading failure risk value, a multi-bearing collaborative maintenance sequence and a downtime optimization plan are generated, and the collaborative maintenance sequence is sorted from high to low according to the risk value, and the downtime optimization plan takes into account the production plan, spare parts inventory and the availability of maintenance personnel.

[0054] Based on the same general inventive concept, the present invention also protects an online comprehensive detection, analysis and evaluation system for power equipment bearings. The online comprehensive detection, analysis and evaluation system for power equipment bearings described below and the online comprehensive detection, analysis and evaluation method for power equipment bearings described above can refer to each other.

[0055] Figure 2 It is a structural diagram of the on-line comprehensive detection, analysis and evaluation system for power equipment bearings provided in this embodiment.

[0056] like Figure 2 As shown, the power equipment bearing online comprehensive detection, analysis and evaluation system provided in this embodiment includes: Acquisition module 201, for acquiring four-dimensional operating parameters of the bearing in real time, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; Correlation module 202 is configured to establish a correlation model between energy changes in a specific frequency band in the audio spectrum characteristics and fluctuations in the vibration value through spatiotemporal correlation analysis, inject the dynamic maintenance cycle parameter as a time-domain attenuation factor into the correlation model, and generate a health degradation index based on dynamic weighting of the bearing load rate parameter; Output module 203, configured to generate a pre-maintenance instruction when the health degradation index exceeds a dynamic threshold, and output a maintenance strategy including a fault location map; The application module 204 is used to encapsulate the pre-maintenance instruction and the maintenance strategy according to the industrial communication protocol, and dynamically embed the correlation analysis view and the warning window in the distributed control system interface.

[0057] Figure 3 Schematic diagram of the structure of the electronic device provided in this embodiment.

[0058] like Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communications bus 340. The processor 310, the communications interface 320, and the memory 330 communicate with each other via the communications bus 340. The processor 310 may invoke logic instructions in the memory 330 to execute an online comprehensive detection, analysis, and evaluation method for power equipment bearings. The method includes: acquiring four-dimensional operating parameters of the bearing in real time, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; establishing a correlation model between energy changes in specific frequency bands in the audio spectrum characteristics and fluctuations in the vibration values ​​through spatiotemporal correlation analysis; injecting the dynamic maintenance cycle parameters into the correlation model as time-domain attenuation factors; and generating a health degradation index based on dynamic weighting of the bearing load rate parameters; generating a pre-maintenance instruction when the health degradation index exceeds a dynamic threshold, and outputting a maintenance strategy including a fault location map; encapsulating the pre-maintenance instruction and the maintenance strategy according to an industrial communication protocol, and dynamically embedding the correlation analysis view and warning window in the distributed control system interface.

[0059] Furthermore, the logic instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0060] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the online comprehensive detection, analysis and evaluation method for power equipment bearings provided by the above methods. The method includes: real-time acquisition of four-dimensional operating parameters of the bearing, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters and bearing load rate parameters; through spatiotemporal correlation analysis, establishing a correlation model between energy changes in specific frequency bands in the audio spectrum characteristics and fluctuations in the vibration values, and injecting the dynamic maintenance cycle parameters into the correlation model as time-domain attenuation factors, and generating a health degradation index based on dynamic weighting of the bearing load rate parameters; when the health degradation index exceeds a dynamic threshold, generating a pre-maintenance instruction, and outputting a maintenance strategy including a fault location map; encapsulating the pre-maintenance instruction and the maintenance strategy according to the industrial communication protocol, and dynamically embedding the correlation analysis view and early warning window in the distributed control system interface.

[0061] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the online comprehensive detection, analysis and evaluation method for power equipment bearings provided by the above-mentioned methods, the method comprising: obtaining the four-dimensional operating parameters of the bearing in real time, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters and bearing load rate parameters; establishing a correlation model between the energy changes in a specific frequency band in the audio spectrum characteristics and the fluctuations in the vibration values ​​through spatiotemporal correlation analysis, injecting the dynamic maintenance cycle parameters into the correlation model as time-domain attenuation factors, and generating a health degradation index based on dynamic weighting of the bearing load rate parameters; generating a pre-maintenance instruction when the health degradation index exceeds a dynamic threshold, and outputting a maintenance strategy including a fault location map; encapsulating the pre-maintenance instruction and the maintenance strategy according to the industrial communication protocol, and dynamically embedding the correlation analysis view and early warning window in the distributed control system interface.

[0062] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0063] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for online comprehensive detection, analysis and evaluation of power equipment bearings, characterized in that: include: Real-time acquisition of four-dimensional operating parameters of the bearing, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; By means of spatiotemporal correlation analysis, a correlation model is established between energy changes in specific frequency bands in the audio spectrum characteristics and fluctuations in the vibration value, and the dynamic maintenance cycle parameter is injected into the correlation model as a time-domain attenuation factor. A health degradation index is generated based on dynamic weighting of the bearing load rate parameter; When the health degradation index exceeds a dynamic threshold, a pre-maintenance instruction is generated, and a maintenance strategy including a fault location map is output; The pre-maintenance instruction and the maintenance strategy are encapsulated according to the industrial communication protocol, and the associated analysis view and the early warning window are dynamically embedded in the distributed control system interface.

2. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 1 is characterized in that: The real-time acquisition of the acoustic frequency spectrum characteristics of the bearing includes: The sound of bearing operation is collected through a wide-band microphone array; Performing time-frequency transformation on the bearing running sound to extract energy in a predetermined frequency band; Based on the energy of the predetermined frequency band, a three-dimensional characteristic spectrum of sound energy-frequency-time is constructed.

3. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 1 is characterized in that: Also includes: Calculate the lubricant state attenuation coefficient based on the bearing temperature and load rate parameters; The maintenance cycle parameters are dynamically adjusted based on the lubricant state attenuation coefficient.

4. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 1 is characterized in that: The establishment of a correlation model between energy changes in a specific frequency band in the audio spectrum characteristics and fluctuations in the vibration value through spatiotemporal correlation analysis includes: Detecting anomalies in synchronization between a rate of change of energy in a high frequency band of the audio frequency spectrum characteristics and energy in a characteristic frequency band of the vibration value; When the synchronization anomaly meets the preset association conditions, the specific fault mode and location information are marked and an association model is constructed.

5. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 1 is characterized in that: Generating a health degradation index based on the dynamic weighting of the bearing load rate parameter includes: Determine the piecewise function of the bearing load rate as the weight coefficient; Based on the weight coefficient, the vibration value deviation, the sound energy change and the maintenance urgency are weighted and summed to generate a health degradation index.

6. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 1 is characterized in that: Before generating the pre-maintenance instruction, the method further includes: Determine statistical boundaries based on historical normal operation data sets; According to the statistical boundary, combined with the fault case library of the same type of equipment, a safe operation interval is generated as a dynamic threshold.

7. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to claim 6 is characterized in that: After the pre-maintenance instruction is generated, the method further includes: Fuse the sound source location results with the vibration transmission path analysis to obtain the fault probability; Generate a spatial distribution heat map of the fault probability as a fault location map.

8. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to any one of claims 1 to 7, characterized in that: After the four-dimensional operating parameters of the bearing are acquired in real time, the method further includes: Identify the electromagnetic interference spectrum caused by current harmonics; Detect broadband characteristics of fluid dynamic noise; The electromagnetic interference spectrum and the broadband characteristics are removed from the audio spectrum characteristics.

9. The method for online comprehensive detection, analysis and evaluation of power equipment bearings according to any one of claims 1 to 7, characterized in that: The output includes the maintenance strategy of the fault location map, and further includes: Establish a failure propagation relationship model for multiple bearings in the same unit; When the health degradation index of a single bearing exceeds the limit, the cascading failure risk value of the associated bearings is calculated using the failure propagation relationship model; A multi-bearing collaborative maintenance sequence and downtime optimization plan are generated based on the cascading failure risk value.

10. An online comprehensive detection, analysis and evaluation system for power equipment bearings, characterized in that: include: An acquisition module is used to obtain the four-dimensional operating parameters of the bearing in real time, including temperature and vibration values, audio spectrum characteristics, dynamic maintenance cycle parameters, and bearing load rate parameters; a correlation module, configured to establish a correlation model between energy changes in a specific frequency band in the audio spectrum characteristics and fluctuations in the vibration value through spatiotemporal correlation analysis, inject the dynamic maintenance cycle parameter into the correlation model as a time-domain attenuation factor, and generate a health degradation index based on dynamic weighting of the bearing load rate parameter; an output module, configured to generate a pre-maintenance instruction when the health degradation index exceeds a dynamic threshold, and output a maintenance strategy including a fault location map; The application module is used to encapsulate the pre-maintenance instruction and the maintenance strategy according to the industrial communication protocol, and dynamically embed the associated analysis view and the early warning window in the distributed control system interface.

Images