A high-precision water-lubricated bearing wear measuring system and measuring method

Abstract

This invention relates to the field of ship shafting monitoring technology, specifically to a high-precision water-lubricated bearing wear measurement system and method. This invention achieves three-dimensional reconstruction of the shaft center position through a three-sensor spatial triangular layout and geometric inversion algorithm, directly acquiring the bearing's radial wear and shaft tilt angle. Combined with multi-dimensional feature extraction and hybrid intelligent algorithm modeling, it can accurately identify wear states and quantify wear distribution characteristics, effectively improving the accuracy and comprehensiveness of water-lubricated bearing wear measurement. This invention incorporates redundant self-checking and fault isolation mechanisms, along with adaptive filtering, periodic zero-point calibration, and robust algorithm design, effectively ensuring the stability and reliability of measurement data. The non-contact measurement and sealed integrated design are suitable for water-lubricated operating conditions, and the fault-tolerant architecture maintains measurement continuity under single-sensor failure, improving the overall environmental adaptability and operational reliability of the system.

Description

Technical Field

[0001] This invention relates to the field of ship shafting monitoring technology, specifically to a high-precision water-lubricated bearing wear measurement system and method. Background Technology

[0002] Water-lubricated bearings are critical components of marine propulsion systems, relying on a water film between the slats and the shaft for lubrication. Over long-term operation, slat wear thins the water film, leading to increased friction, vibration, and even failure. Traditional wear measurement methods rely on shutdown inspections or indirect parameter estimations (vibration, temperature), which have significant limitations: shutdown inspections are not real-time and are cumbersome; indirect parameters are susceptible to interference and have low accuracy; and there is a lack of comprehensive assessment of wear distribution and shaft tilt. Existing eddy current methods often use a single sensor embedded in the slats to measure journal displacement, which fails to comprehensively reflect wear distribution and is easily affected by the seawater environment (biofilm, surges), resulting in large errors. Indirect estimation methods (vibration, temperature) have a weak correlation with wear amount and cannot meet the requirements for high-precision real-time monitoring.

[0003] Specifically, current water-lubricated bearing wear measurement technology faces the following key bottlenecks: The primary problem is that existing methods generally cannot achieve real-time, online monitoring of wear, and rely heavily on time-consuming and downtime-requiring periodic inspections, resulting in an inability to promptly grasp the bearing's operating status; Secondly, measurement accuracy is difficult to guarantee, especially in the harsh marine environment where ships are located. Traditional sensors are easily affected by factors such as biological attachment, wave impact, and electromagnetic interference, resulting in large fluctuations and significant errors in measurement results. Third, most existing technologies rely on indirect parameters (such as vibration and temperature) to estimate wear, rather than direct measurement. Since these indirect parameters have a weak correlation with the actual wear state of the slats and are easily affected by multiple factors, the estimation results cannot directly and accurately reflect the true wear condition of the slats. Furthermore, existing solutions generally lack the ability to comprehensively assess shaft tilt angle and wear distribution, making it difficult to fully diagnose the health status of bearings (such as potential faults like misalignment and shaft bending). Finally, traditional measurement methods are often cumbersome and complex to operate or have low reliability, failing to meet the high reliability and low maintenance cost requirements of marine propulsion systems. Therefore, there is an urgent need to develop a new wear monitoring system and method that can overcome the above limitations, achieve real-time, high-precision, interference-resistant, direct measurement, and comprehensive assessment of bearing condition. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a high-precision water-lubricated bearing wear measurement system and method, which can realize direct, real-time, and high-precision online monitoring of wear, while having strong environmental anti-interference and fault tolerance capabilities, and can simultaneously assess shaft tilt state and wear trend, comprehensively supporting bearing health management and operation and maintenance decisions.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: I. A high-precision water-lubricated bearing wear measurement system This invention provides a high-precision water-lubricated bearing wear measurement system, which mainly includes: a calibration module 101, a data acquisition module 102, a wireless transmission module 103, a data processing module 104, and a display and interaction module 105; the calibration module 101, the data acquisition module 102, and the wireless transmission module 103 are all integrated and installed in the sealed space of the water-lubricated bearing. The calibration module 101 has a built-in standard reference block for calibrating the zero-point reference of the measurement; the data acquisition module 102 includes three eddy current displacement sensors arranged along the circumference of the shaft system for synchronously acquiring the displacement and tilt angle of the shaft system; the wireless transmission module 103 is used to synchronously upload the acquired raw data to the data processing module 104; the data processing module 104 is used to preprocess the raw data, calculate displacement and tilt angle, model wear amount and dynamically optimize, and output the real-time wear amount and shaft tilt angle; the display and interaction module 105 is used for data visualization, hierarchical early warning prompts and system parameter configuration.

[0006] Preferably, of the three eddy current displacement sensors, one is arranged directly above the shaft, and the other two are symmetrically distributed on both sides of the vertical center plane of the shaft system, and the angle between the sensors on both sides and the vertical center plane is 60°; the probes of the eddy current displacement sensors are all set perpendicular to the surface of the shaft system, and a measurement redundancy of 1.5 times the maximum subsidence is reserved between the probes and the surface of the shaft system.

[0007] Preferably, the data acquisition module 102 has a built-in redundant self-checking and fault detection isolation unit, which is used to monitor the output status of the three eddy current displacement sensors in real time: when a single sensor output is abnormal, the current fault channel is automatically isolated, and the least squares method is used to fit and compensate the data of the remaining two normal sensors to maintain the reduced-order operation of the acquisition process.

[0008] Preferably, the data processing module 104 includes a data preprocessing unit 201, a displacement and tilt angle calculation unit 202, a wear amount modeling unit 203, and a dynamic optimization unit 204; The data preprocessing unit 201 is used to perform timestamp alignment, adaptive denoising, data standardization, and multi-dimensional feature extraction of multi-sensor data. The displacement and tilt angle calculation unit 202 is used to reconstruct the real-time position and motion trajectory of the shaft center based on the preprocessed three-way displacement data through a spatial geometric inversion algorithm, and decompose the radial subsidence and tilt angle of the shaft. The wear modeling unit 203 has a built-in preset wear prediction model. By inputting the shaft displacement, shaft tilt angle and multi-dimensional feature parameters into the wear prediction model, and combining historical wear calibration data for pattern matching, the real-time wear of the bearing is calculated and output, and the wear trend is predicted. The dynamic optimization unit 204 is used to perform incremental model learning at fixed intervals, inputting the monitoring data and calibration results of the latest period into the model to update the parameters, so as to continuously ensure the prediction accuracy of the model.

[0009] Preferably, the display and interaction module 105 supports real-time wear curve display and bearing three-dimensional status visualization, and has a built-in three-level early warning mechanism, as well as data storage, report export, parameter configuration and remote upgrade functions. The three-level early warning mechanism includes setting three levels of early warning thresholds: blue, yellow, and red. When the bearing wear exceeds the corresponding threshold, the corresponding level of audio-visual prompts are triggered to distinguish between slight wear, moderate wear, and heavy wear.

[0010] Preferably, the calibration module 101 has a built-in standard reference block for performing zero-point calibration to determine the measurement zero reference and eliminate system deviations caused by temperature drift, sensor aging, and installation tolerances.

[0011] Preferably, the wireless transmission module 103 is used to realize the remote transmission of front-end acquired data. The data acquisition module 102 aligns the original signals of the three eddy current displacement sensors with the calibration reference signals through high-precision timestamps and completes synchronous encapsulation. The encapsulated data is synchronously uploaded to the data processing module 104 through the wireless transmission module 103.

[0012] II. A High-Precision Method for Measuring Wear of Water-Lubricated Bearings Based on the same inventive concept, this invention also provides a high-precision water-lubricated bearing wear measurement method, employing the high-precision water-lubricated bearing wear measurement system described above, including the following steps: Step S1, System Initialization and Zero-Point Calibration: After the sensor installation and deployment are completed, zero-point calibration is performed through the calibration module to determine the measurement zero reference, and the sampling frequency, early warning threshold and system communication parameters are configured simultaneously; Step S2, Multi-channel synchronous data acquisition: Three eddy current displacement sensors synchronously acquire instantaneous displacement signals of the shaft surface at a set frequency, and each displacement signal data is marked with a high-precision timestamp to ensure multi-channel data synchronization; Step S3, Data Preprocessing and Feature Extraction: After encapsulating the three original displacement signals and the calibration reference signal, they are synchronously transmitted to the data processing module via a wireless link. The data preprocessing unit then performs adaptive signal denoising, data standardization, and multi-dimensional feature parameter extraction on the original displacement signals in sequence. Step S4, Calculation of shaft center trajectory and tilt angle: Based on the preprocessed three-way displacement data, the displacement and tilt angle calculation unit reconstructs the real-time position and motion trajectory of the shaft center through a spatial geometric inversion algorithm, and decomposes the displacement vector to calculate the radial settlement and tilt angle of the shaft. Step S5, Wear Calculation and Trend Prediction: By inputting shaft center displacement, shaft tilt angle and multi-dimensional feature parameters into the wear prediction model, and combining historical wear calibration data for pattern matching, the real-time wear of the bearing is calculated and the wear trend is predicted. Step S6, Status Assessment and Graded Early Warning: The system compares the real-time wear amount with the preset three-level early warning threshold to determine the current wear level, and triggers the corresponding level of audible and visual early warning when the wear amount exceeds the corresponding threshold. Step S7, Real-time fault-tolerant self-verification: During system operation, the status of sensors and signal channels is monitored in real time. When a single sensor output is abnormal, the current faulty channel is automatically isolated, and the least squares method is used to fit and compensate the data of the remaining two normal sensors to maintain measurement continuity.

[0013] Preferably, in step S3, the adaptive signal denoising includes: adaptively selecting wavelet filtering or strong tracking Kalman filtering according to the signal noise characteristics to remove high-frequency noise and electromagnetic interference; The data standardization includes: using the Z-score algorithm to unify the scale of the three sensor signal data to eliminate the benchmark deviation caused by individual differences in the sensors; The multi-dimensional feature parameter extraction includes extracting feature parameters from three dimensions: time domain, frequency domain, and time-frequency domain, to provide multi-dimensional data support for subsequent wear calculation.

[0014] Preferably, in step S7, the system automatically starts an incremental learning process every 24 hours, inputting the latest monitoring data and calibration results into the model to update the parameters, so as to continuously ensure the prediction accuracy of the model.

[0015] Compared with the prior art, the present invention has the following main advantages: 1. This invention achieves three-dimensional reconstruction of the shaft center position through a three-sensor spatial triangular layout and geometric inversion algorithm, which can directly obtain the radial wear of the bearing and the shaft tilt angle; combined with multi-dimensional feature extraction and hybrid intelligent algorithm modeling, it can accurately identify the wear state and quantify the wear distribution characteristics, effectively improving the accuracy and comprehensiveness of wear measurement of water-lubricated bearings.

[0016] 2. This invention incorporates a redundant self-checking and fault isolation mechanism, combined with adaptive filtering, periodic zero-point calibration, and robust algorithm design, which can effectively ensure the stability and reliability of measurement data. The non-contact measurement and sealed integrated design are suitable for water lubrication conditions, and the fault-tolerant architecture can maintain measurement continuity under single sensor failure, thereby improving the overall environmental adaptability and operational reliability of the system.

[0017] 3. This invention enables real-time online monitoring of water-lubricated bearing wear throughout the entire period, achieving status perception without downtime. Combined with tiered early warning, trend prediction, and closed-loop data management, it supports comprehensive assessment of bearing health status and optimization of maintenance strategies. With modular design and remote upgrade capabilities, it is easy to install and maintain, adaptable to different ship operating conditions and bearing types, effectively reducing operation and maintenance costs and improving the safety and intelligence level of ship propulsion system operation. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the overall architecture of the high-precision water-lubricated bearing wear measurement system in an embodiment of the present invention; Figure 2 This is a schematic diagram showing the relative arrangement of the three sensors in an embodiment of the present invention; Figure 3 This is a schematic diagram of the data processing module in an embodiment of the present invention; Figure 4 This is a flowchart illustrating the measurement method in an embodiment of the present invention.

[0019] In the diagram: 101-calibration module, 102-data acquisition module, 103-wireless transmission module, 104-data processing module, 105-display and interaction module, 201-data preprocessing unit, 202-displacement and tilt angle calculation unit, 203-wear modeling unit, 204-dynamic optimization unit. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0021] It should be noted that, depending on the implementation needs, the various steps / components described in this application can be broken down into more steps / components, or two or more steps / components or parts of the operation of steps / components can be combined into new steps / components to achieve the purpose of this invention.

[0022] In this invention, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise expressly and specifically limited.

[0023] Example 1: This example provides a high-precision water-lubricated bearing wear measurement system, such as... Figures 1-3 As shown, it mainly includes: a calibration module 101, a data acquisition module 102, a wireless transmission module 103, a data processing module 104, and a display and interaction module 105. Among them, the calibration module 101, the data acquisition module 102, and the wireless transmission module 103 are all installed in the sealed space of the water-lubricated bearing, while the data processing module 104 and the display and interaction module 105 are deployed in the ship's central control room.

[0024] Furthermore, the calibration module 101 has a built-in standard reference block for performing zero-point calibration. During initial system installation, periodic maintenance, or significant fluctuations in operating conditions, the system invokes the calibration module 101 to determine the measurement zero-point reference using the standard reference block as a reference, eliminating system deviations caused by temperature drift, sensor aging, and installation tolerances, and ensuring the long-term stability of the measurement reference.

[0025] Furthermore, the data acquisition module 102 is equipped with three eddy current displacement sensors to simultaneously monitor the shaft's displacement and tilt angle. The three sensors are arranged along the upper circumference of the bearing: one sensor is positioned directly above the shaft, and the other two are symmetrically distributed on either side of the vertical center plane of the shaft system, with each sensor making a 60° angle with the vertical center plane. The sensor probes are perpendicular to the shaft surface, and a measurement redundancy of 1.5 times the maximum subsidence is reserved. This triangular layout constitutes a spatial positioning architecture, which can reconstruct the three-dimensional position of the shaft center through geometric inversion of the three displacement signals, achieving synchronous calculation of radial subsidence and shaft tilt angle, while avoiding direct interference from the lubricating water layer and ensuring signal stability.

[0026] Furthermore, this embodiment employs three non-collinearly arranged eddy current displacement sensors instead of two or more. Two sensors can only acquire displacement information in a limited number of directions, making it difficult to simultaneously meet the requirements of shaft center position determination, shaft tilt angle calculation, and measurement result verification. Three non-collinearly arranged sensors can form the minimum geometric constraints required for shaft center position determination. While realizing shaft center position calculation, they can also utilize the redundancy relationship between the three measurement data for anomaly detection and error verification, ensuring measurement accuracy while also considering system simplicity, ease of installation, and low engineering application costs.

[0027] Furthermore, the data acquisition module 102 incorporates a redundant self-checking and fault detection isolation unit to monitor the output status of the three sensors in real time. When a sensor outputs abnormal data due to electromagnetic interference, mechanical vibration, or environmental adhesion, the system automatically identifies and isolates the faulty channel, and uses the least squares method to fit and compensate the remaining two normal data channels, maintaining the continuity of the measurement process and improving the system's fault tolerance.

[0028] Furthermore, the wireless transmission module 103 is used to realize the remote transmission of front-end acquired data. The front-end acquisition unit aligns the three original displacement signals with the calibration reference signal using high-precision timestamps and then completes synchronous encapsulation, with a synchronization accuracy of ±0.1ms. The encapsulated data is synchronously uploaded to the data processing module 104 at the engine room via the communication network, adapting to the communication environment inside the ship.

[0029] Furthermore, the data processing module 104 includes a data preprocessing unit 201, a displacement and tilt angle calculation unit 202, a wear modeling unit 203, and a dynamic optimization unit 204. After receiving the raw data, the data processing module 104 performs the following specific processing steps: 1) Data Preprocessing Unit 201: After receiving the raw data, it first completes the precise alignment of the time dimension, and then adaptively selects wavelet filtering or improved strong tracking Kalman filtering algorithm according to the signal noise characteristics to perform noise removal, such as high-frequency vibration and electromagnetic interference; then it uses the Z-score normalization algorithm to unify the data scale of each sensor to eliminate the deviation caused by individual sensor differences; finally, it extracts feature parameters from the three dimensions of time domain, frequency domain, and time-frequency domain, including time domain features such as mean, variance, and peak value, frequency domain features such as main frequency and frequency band energy, and time-frequency domain features such as wavelet packet decomposition coefficients, to provide high-quality input for subsequent modeling.

[0030] 2) Displacement and tilt angle calculation unit 202: Based on the preprocessed three-way displacement data, the real-time position and motion trajectory of the shaft center are reconstructed through the spatial geometric inversion algorithm, and the radial sinking amount of the shaft and the pitch and yaw tilt angles of the shaft are decomposed to provide direct displacement basis for wear calculation.

[0031] 3) Wear modeling unit 203: Establish a wear calculation model, take shaft displacement, shaft tilt angle and multi-dimensional characteristic parameters as input, and calculate in combination with preset calibration data to obtain the real-time wear amount and circumferential wear distribution of the bearing; the wear calculation model can be established by using a data-driven model, an empirical model or a combination of both, and the parameters can be optimized according to the operating data to improve the accuracy of wear calculation and the adaptability of working conditions.

[0032] 4) Dynamic Optimization Unit 204: The system automatically initiates an incremental learning process every 24 hours, inputting the latest monitoring data and calibration results into the model to update parameters, adapting to changes in operating conditions and sensor performance drift, and continuously ensuring the model's predictive accuracy. Analysis results include real-time wear calculation, tilt angle monitoring, and wear trend prediction, ultimately generating a complete report containing current condition assessment and maintenance recommendations.

[0033] Furthermore, the display and interaction module 105 is used to provide users with an intuitive operating interface and rich visualization functions, specifically including: 1) Real-time data display: The main interface uses dynamic curves to display the wear changes of each measuring point in real time, supplemented by three-dimensional graphics to intuitively present the overall condition of the bearing, and supports multi-window comparison display of data for different time periods.

[0034] 2) Three-level early warning mechanism: Set three-level early warning thresholds: blue, yellow and red. When the wear exceeds the corresponding threshold, the corresponding level of sound and light prompts are triggered to distinguish between slight wear, moderate wear and heavy wear.

[0035] 3) Data storage and export: All monitoring data is automatically stored in a relational database and backed up to the cloud regularly. Users can export reports in preset formats as needed.

[0036] 4) Interactive functions: It provides a complete parameter configuration interface, allowing users to adjust parameters such as sampling frequency and alarm threshold, and make maintenance decisions as needed. It can also perform system health checks through built-in diagnostic tools to ensure the continuous and stable operation of the measurement system.

[0037] The modules interact with each other through standardized interfaces, forming a complete closed loop from data acquisition to status assessment. Adopting a modular design concept, each functional module can be upgraded independently, and the system supports OTA remote updates, allowing software upgrades and maintenance to be completed without system downtime, significantly improving system availability and maintenance convenience. This innovative design scheme ensures both measurement accuracy and engineering practicality, providing reliable technical support for the intelligent monitoring of marine water-lubricated bearings.

[0038] In practice, the system can adjust the sensor sampling frequency and data processing algorithm according to the actual operating conditions of the ship. For example, for high-speed ships, the sensor sampling frequency can be set higher to capture more subtle vibrations and pressure changes; for different types of water-lubricated bearings, the system can select the most suitable feature extraction method and machine learning algorithm to improve the accuracy of monitoring and prediction.

[0039] Example 2: This example provides a high-precision water-lubricated bearing wear measurement system, the working principle of which is as follows: 1. Sensor data acquisition Sensor Arrangement and Measurement: Three eddy current sensors are arranged along the circumference on the upper part of the bearing. Since a single sensor can only reflect displacement changes in a single direction, it cannot accurately capture the three-dimensional sinking trajectory (axial, radial, and tilt angle) of the water-lubricated bearing under complex working conditions. This application forms a triangular positioning system by arranging three sensors, which can construct a spatial coordinate system and realize the vector decomposition and synthesis of the bearing sinking, effectively eliminating single-point measurement deviations caused by installation errors or environmental disturbances.

[0040] Furthermore, the three sensors are equipped with a redundancy self-checking mechanism: when one sensor generates abnormal data due to electromagnetic interference or mechanical vibration, the system can dynamically compensate using data from the remaining two sensors (in this embodiment, least squares fitting is used) to ensure the continuity and stability of the measurement results; this design is particularly suitable for corrosive environments such as high humidity and high salt spray for water-lubricated bearings.

[0041] Specifically, three high-precision eddy current displacement sensors are placed circumferentially in the upper space of the water-lubricated bearing. One sensor is positioned directly above the shaft, while the other two sensors are symmetrically distributed along the central plane (vertical direction) of the shaft system. The angle between the two side sensors and the central plane (vertical direction) of the shaft system is controlled at 60°. The sensor probes are kept perpendicular to the shaft surface and a measurement redundancy of 1.5 times the maximum subsidence is reserved. This layout achieves dynamic measurement of the three-dimensional subsidence through geometric inversion of the three sensor signals. Combined with a redundancy check algorithm, single-point errors are eliminated, while avoiding interference from the lubricating water environment, ensuring signal stability and measurement accuracy, and meeting the real-time monitoring requirements under complex working conditions.

[0042] Furthermore, the eddy current sensor non-contactly measures the instantaneous change in the inner diameter surface of the bearing relative to the sensor probe, i.e., the displacement signal. The sinking trajectory data measured by three displacement sensors can accurately reconstruct the position of the bearing center, which serves as the basis for calculating the wear amount.

[0043] Furthermore, zero-point calibration and error elimination: The system has a built-in standard module containing a standard block for performing zero-point calibration. At the start of a measurement or during a predetermined maintenance cycle, the system uses this standard block as a reference for calibration to determine the zero-point reference. This calibration process effectively eliminates temperature drift caused by changes in ambient temperature and systematic errors resulting from sensor aging or long-term operation, ensuring the long-term stability and accuracy of the measurement reference.

[0044] 2. Wireless transmission Data encapsulation: The front-end acquisition module synchronously encapsulates the three original displacement signals and the calibration reference signal.

[0045] Wireless transmission: The built-in wireless transmission module synchronously uploads the raw data to the data processing module via the communication network for subsequent data processing.

[0046] 3. Data Processing Initial signal processing: The acquired raw displacement signal enters the data preprocessing unit of the data processing module. This unit preprocesses the signal, including denoising, amplification, quantization, etc., to provide high-quality input data for subsequent calculations.

[0047] Core Algorithm and Data Optimization: The system employs an improved strong-tracking Kalman filter algorithm to extract minute, effective information reflecting bearing wear trends from displacement signals containing significant noise and interference. This algorithm can quickly and accurately track bearing wear, a slowly changing state variable, and respond rapidly even to sudden changes in wear trends.

[0048] System reliability assurance mechanism: The system integrates a fault detection and isolation (FDI) module to continuously monitor the operating status of the three eddy current sensors and signal channels. Once an eddy current sensor outputs abnormal data or an erroneous signal, the module will immediately identify and isolate it; at the same time, the system will activate a degraded operation mode to continue estimating wear using the remaining normal sensor data; thereby greatly improving the system's fault tolerance and reliability, and ensuring measurement continuity at critical moments.

[0049] Example 3: Based on the same inventive concept, this example also provides a high-precision water-lubricated bearing wear measurement method, employing the high-precision water-lubricated bearing wear measurement system described above, such as... Figure 4 As shown, it includes the following steps: Step S1, System Initialization and Zero-Point Calibration: After the sensor installation and deployment are completed, the system is powered on and initialized. The standard reference block of the calibration module is called to perform zero-point calibration, determine the measurement zero reference, and eliminate temperature drift, installation error and sensor initial deviation; the sampling frequency, early warning threshold and communication parameters are configured synchronously.

[0050] Step S2, Multi-channel synchronous data acquisition: The data acquisition module sends a synchronous acquisition command to the three eddy current displacement sensors to synchronously acquire the instantaneous displacement signal of the journal surface at a preset sampling frequency; each data channel is marked with a high-precision timestamp to ensure that the time synchronization accuracy of the three signals is not less than ±0.1ms; after the acquisition is completed, the raw data and timestamp are packaged and sent to the wireless transmission module.

[0051] Step S3, Data Preprocessing and Feature Extraction: The three original displacement signals and the calibration reference signal are encapsulated into a unified data frame and synchronously transmitted to the data processing module via a wireless link. The data preprocessing unit then performs three levels of processing. Signal denoising: Analyze the noise characteristics of the signal and adaptively select wavelet filtering or strong tracking Kalman filtering to remove noise components such as high-frequency vibration and electromagnetic interference; Data standardization: The Z-score algorithm is used to unify the scale of the three data streams, eliminating the baseline bias caused by individual differences in the sensors; Feature extraction: Feature parameters are extracted from three dimensions: time domain, frequency domain, and time-frequency domain, providing multi-dimensional data support for subsequent wear calculation.

[0052] Step S4, Calculation of shaft center trajectory and tilt angle: The displacement and tilt angle calculation unit reconstructs the spatial position and motion trajectory of the shaft center based on three displacement signals through a triangulation positioning geometric inversion algorithm; the displacement vector is decomposed to calculate the total radial sinking of the shaft and the pitch and yaw tilt angles of the shaft; during the process, an abnormal single-point data is eliminated through a redundancy verification algorithm to eliminate measurement deviations caused by installation errors and environmental disturbances; if a single-channel sensor failure is detected, it automatically switches to the dual-sensor fitting calculation mode to ensure uninterrupted measurement.

[0053] Step S5, Wear Calculation and Trend Prediction: Input the acquired multi-dimensional feature parameters, axis trajectory parameters and tilt angle data into the wear modeling unit, perform pattern matching in combination with historical wear calibration data, and output the real-time wear amount and circumferential wear distribution results; at the same time, predict the wear development trend in the future based on the historical data sequence.

[0054] Step S6, Status Assessment and Graded Early Warning: The system compares the real-time wear amount with the preset three-level early warning threshold to determine the current wear level; when the wear amount exceeds the corresponding threshold, it triggers the corresponding level of audible and visual early warning and generates a status assessment report containing the current wear amount, tilt angle, wear trend and maintenance suggestions; the report and real-time data are synchronously pushed to the display and interaction module for visualization.

[0055] Step S7, Real-time fault-tolerant self-verification: The system monitors the status of sensors and signal channels in real time throughout the entire operation process. When a single abnormality is detected, the faulty channel is automatically isolated, and the remaining two data channels are used to complete the wear estimation through a fitting algorithm to maintain measurement continuity.

[0056] Furthermore, all parts of this application that are not described in detail are the same as or implemented using existing technology.

[0057] In summary: 1. This invention achieves three-dimensional reconstruction of the shaft center position through a three-sensor spatial triangular layout and geometric inversion algorithm, which can directly obtain the radial wear of the bearing and the shaft tilt angle; combined with multi-dimensional feature extraction and hybrid intelligent algorithm modeling, it can accurately identify the wear state and quantify the wear distribution characteristics, effectively improving the accuracy and comprehensiveness of wear measurement of water-lubricated bearings.

[0058] 2. This invention incorporates a redundant self-checking and fault isolation mechanism, combined with adaptive filtering, periodic zero-point calibration, and robust algorithm design, which can effectively ensure the stability and reliability of measurement data. The non-contact measurement and sealed integrated design are suitable for water lubrication conditions, and the fault-tolerant architecture can maintain measurement continuity under single sensor failure, thereby improving the overall environmental adaptability and operational reliability of the system.

[0059] 3. This invention enables real-time online monitoring of water-lubricated bearing wear throughout the entire period, achieving status perception without downtime. Combined with tiered early warning, trend prediction, and closed-loop data management, it supports comprehensive assessment of bearing health status and optimization of maintenance strategies. With modular design and remote upgrade capabilities, it is easy to install and maintain, adaptable to different ship operating conditions and bearing types, effectively reducing operation and maintenance costs and improving the safety and intelligence level of ship propulsion system operation.

[0060] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0062] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A high-precision water-lubricated bearing wear measurement system, characterized in that: It includes a calibration module (101), a data acquisition module (102), a wireless transmission module (103), a data processing module (104), and a display and interaction module (105); the calibration module (101), the data acquisition module (102), and the wireless transmission module (103) are all integrated and installed in the sealed space of the water-lubricated bearing; The calibration module (101) has a built-in standard reference block for calibrating the zero-point reference of the measurement; the data acquisition module (102) includes three eddy current displacement sensors arranged along the circumference of the shaft system for synchronously acquiring the displacement and tilt angle of the shaft system; the wireless transmission module (103) is used to synchronously upload the acquired raw data to the data processing module (104); the data processing module (104) is used to preprocess the raw data, calculate displacement and tilt angle, model wear amount and dynamically optimize, and output the real-time wear amount and shaft tilt angle; the display and interaction module (105) is used for data visualization, hierarchical early warning prompts and system parameter configuration.

2. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, Of the three eddy current displacement sensors, one is positioned directly above the shaft, and the other two are symmetrically distributed on both sides of the vertical center plane of the shaft system, with the angle between the sensors on both sides and the vertical center plane being 60°. The probes of the eddy current displacement sensors are all set perpendicular to the surface of the shaft system, and a measurement redundancy of 1.5 times the maximum subsidence is reserved between the probes and the surface of the shaft system.

3. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, The data acquisition module (102) has a built-in redundant self-verification and fault detection isolation unit, which is used to monitor the output status of the three eddy current displacement sensors in real time: when a single sensor output is abnormal, the current fault channel is automatically isolated, and the least squares method is used to fit and compensate the data of the remaining two normal sensors to maintain the reduced-order operation of the acquisition process.

4. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, The data processing module (104) includes a data preprocessing unit (201), a displacement and tilt angle calculation unit (202), a wear amount modeling unit (203), and a dynamic optimization unit (204). The data preprocessing unit (201) is used to perform timestamp alignment, adaptive denoising, data standardization and multi-dimensional feature extraction of multi-sensor data; The displacement and tilt angle calculation unit (202) is used to reconstruct the real-time position and motion trajectory of the shaft center based on the preprocessed three-way displacement data through a spatial geometric inversion algorithm, and decompose the radial subsidence and tilt angle of the shaft. The wear modeling unit (203) has a built-in preset wear prediction model. By inputting the shaft center displacement, shaft tilt angle and multi-dimensional feature parameters into the wear prediction model, and combining historical wear calibration data for pattern matching, the real-time wear of the bearing is calculated and the wear trend is predicted. The dynamic optimization unit (204) is used to perform incremental model learning at fixed intervals, inputting the monitoring data and calibration results in the latest period into the model to update the parameters, so as to continuously ensure the prediction accuracy of the model.

5. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, The display and interaction module (105) supports real-time wear curve display and bearing three-dimensional status visualization, and has a built-in three-level early warning mechanism. It also has data storage, report export, parameter configuration and remote upgrade functions. The three-level early warning mechanism includes setting three levels of early warning thresholds: blue, yellow, and red. When the bearing wear exceeds the corresponding threshold, the corresponding level of audio-visual prompts are triggered to distinguish between slight wear, moderate wear, and heavy wear.

6. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, The calibration module (101) has a built-in standard reference block for performing zero-point calibration to determine the measurement zero reference and eliminate system deviations caused by temperature drift, sensor aging and installation tolerances.

7. The high-precision water-lubricated bearing wear measurement system according to claim 1, characterized in that, The wireless transmission module (103) is used to realize the remote transmission of front-end collected data. The data acquisition module (102) aligns the original signals of the three eddy current displacement sensors with the calibration reference signals through high-precision timestamps and completes synchronous encapsulation. The encapsulated data is synchronously uploaded to the data processing module (104) through the wireless transmission module (103).

8. A high-precision method for measuring the wear of water-lubricated bearings, employing the high-precision water-lubricated bearing wear measurement system as described in any one of claims 1 to 7, characterized in that, Includes the following steps: S1, System Initialization and Zero-Point Calibration: After the sensor installation and deployment are completed, zero-point calibration is performed through the calibration module to determine the measurement zero reference, and the sampling frequency, early warning threshold and system communication parameters are configured simultaneously; S2, Multi-channel synchronous data acquisition: Three eddy current displacement sensors synchronously acquire instantaneous displacement signals of the shaft surface at a set frequency, and each displacement signal data is marked with a high-precision timestamp to ensure multi-channel data synchronization; S3, Data Preprocessing and Feature Extraction: After encapsulating the three original displacement signals and the calibration reference signal, the data is synchronously transmitted to the data processing module via a wireless link. The data preprocessing unit then performs adaptive signal denoising, data standardization, and multi-dimensional feature parameter extraction on the original displacement signals in sequence. S4, Calculation of shaft center trajectory and tilt angle: The displacement and tilt angle calculation unit reconstructs the real-time position and motion trajectory of the shaft center based on the pre-processed three-way displacement data through a spatial geometric inversion algorithm, and decomposes the displacement vector to calculate the radial settlement and tilt angle of the shaft. S5, Wear Calculation and Trend Prediction: By inputting shaft displacement, shaft tilt angle and multi-dimensional characteristic parameters into the wear prediction model, and combining historical wear calibration data for pattern matching, the real-time wear of the bearing is calculated and the wear trend is predicted. S6, Status Assessment and Graded Early Warning: The system compares the real-time wear amount with the preset three-level early warning threshold to determine the current wear level, and triggers the corresponding level of audible and visual early warning when the wear amount exceeds the corresponding threshold. S7, Real-time fault-tolerant self-checking: During system operation, the status of sensors and signal channels is monitored in real time. When a single sensor output is abnormal, the current faulty channel is automatically isolated, and the least squares method is used to fit and compensate the data of the remaining two normal sensors to maintain measurement continuity.

9. A high-precision method for measuring the wear of water-lubricated bearings according to claim 8, characterized in that... In step S3, the adaptive signal denoising includes: adaptively selecting wavelet filtering or strong tracking Kalman filtering according to the signal noise characteristics to remove high-frequency noise and electromagnetic interference; The data standardization includes: using the Z-score algorithm to unify the scale of the three sensor signal data to eliminate the benchmark deviation caused by individual differences in the sensors; The multi-dimensional feature parameter extraction includes extracting feature parameters from three dimensions: time domain, frequency domain, and time-frequency domain, to provide multi-dimensional data support for subsequent wear calculation.

10. A high-precision method for measuring the wear of water-lubricated bearings according to claim 8, characterized in that... In step S7, the system automatically starts an incremental learning process every 24 hours, inputting the latest monitoring data and calibration results into the model to update the parameters, so as to continuously ensure the prediction accuracy of the model.

Images