Method and device for monitoring wear of water-lubricated stern bearing of ship in real time, and electronic equipment
By constructing a real-time multidimensional feature vector and matching it with a set relationship, the wear of the water-lubricated stern bearing can be monitored in real time, solving the problem of untimely maintenance in the existing technology and realizing rapid and accurate wear assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- WUHAN UNIV OF TECH
- Filing Date
- 2026-02-02
- Publication Date
- 2026-06-16
AI Technical Summary
In the existing technology, the wear of water-lubricated stern bearings can only be detected when the ship enters dry dock for maintenance, which leads to untimely maintenance and affects operational safety.
By acquiring real-time sensing signals of the stern bearing lubricated by water in the ship, a real-time multidimensional feature vector is constructed and matched with a pre-defined multidimensional feature vector relationship to determine the target data pair for calculating the real-time wear.
It enables real-time monitoring of wear in water-lubricated stern bearings. The calculation process is simple, the response speed is fast, the monitoring results are highly accurate, and it can provide timely warnings to avoid excessive wear.
Smart Images
Figure CN122220728A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of marine engineering, specifically to a method and device for real-time monitoring of wear of a marine water-lubricated stern bearing, electronic equipment, and computer-readable storage medium. Background Technology
[0002] Stern bearings (also known as sliding stern bearings or stern tube sliding bearings) are key sliding bearing components installed inside the stern tube of a ship. They support the rotation of the stern shaft (propeller shaft), bear radial loads, and reduce friction. They are one of the core components of a ship's propulsion system, directly affecting the safety, stability, and efficiency of ship navigation. Water-lubricated stern bearings use seawater / fresh water as the lubricating medium. They support the rotation of the stern shaft, bear radial loads, and reduce friction. Because they use water as a lubricant, water-lubricated stern bearings are environmentally friendly, vibration-reducing, noise-reducing, and highly efficient.
[0003] In actual operation, even with a lubricating medium, repeated sliding of water-lubricated stern bearings will still cause wear. When the wear exceeds the allowable range, it can lead to increased shaft vibration, increased noise, and even failure. However, in existing technology, the wear of water-lubricated stern bearings is usually only detected during dry-dock maintenance, resulting in untimely maintenance and affecting the operational safety of water-lubricated stern bearings. Summary of the Invention
[0004] In view of this, it is necessary to provide a method and device, electronic equipment and computer-readable storage medium for real-time monitoring of the wear of water-lubricated stern bearings in ships, so as to achieve the technical effect of real-time monitoring of the wear of water-lubricated stern bearings.
[0005] To address the aforementioned technical problems, in a first aspect, this application provides a method for real-time monitoring of wear on a marine water-lubricated stern bearing, comprising:
[0006] Acquire real-time sensing signals of the stern bearing lubricated by water in the ship, and construct a real-time multidimensional feature vector based on the real-time sensing signals; Provide a setting correspondence relationship, which includes multiple setting data pairs, each setting data pair including a mutually corresponding setting multidimensional feature vector and a setting wear amount; Target data pairs are determined based on the real-time multidimensional feature vector and the set correspondence relationship. The target data pairs are the set data pairs where the set multidimensional feature vector and the real-time multidimensional feature vector satisfy the set relationship. The real-time wear of the ship's water-lubricated stern bearing is determined based on the target wear amount, where the target wear amount is the set wear amount in the target data pair.
[0007] In one possible embodiment, constructing the defined correspondence includes: Acquire experimental sensing data of the sample block during the friction experiment, the experimental sensing data including sensing signals and multiple sample wear values of the sample block; The sensing signal is split based on the multiple sampled wear values to obtain multiple sub-signals, and the correspondence between the sub-signals and the sampled wear values is constructed. The set wear amount is obtained based on the sampled wear amount, and multi-dimensional feature extraction is performed on each sub-signal to obtain the set multi-dimensional feature vector.
[0008] In one possible embodiment, obtaining the set wear amount based on the sampled wear amount includes: Obtain the initial sampling wear amount corresponding to the start time of the sub-signal and the final sampling wear amount corresponding to the end time of the sub-signal; The average of the initial sampling wear amount and the final sampling wear amount is used as the set wear amount.
[0009] In one possible embodiment, determining the target data pair based on the real-time multidimensional feature vector and the established correspondence includes: Calculate the vector distance between the real-time multidimensional feature vector and each of the set multidimensional feature vectors respectively; The set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set conditions is obtained is taken as the target data pair.
[0010] In one possible embodiment, obtaining the set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set condition is the target data pair includes: The set data pair to which the set multidimensional feature vectors whose vector distance is less than a set threshold distance belong is obtained as the target data pair; The determination of the real-time wear of the marine water-lubricated stern bearing based on the target wear amount includes: Obtain the target vector distance corresponding to the target data pair, and determine the target weight corresponding to each target data pair based on the target vector distance; The target wear amount is calculated by weighting the target wear amount based on the target weight to obtain the real-time wear amount.
[0011] In one possible embodiment, obtaining the set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set condition is the target data pair includes: The set data pair corresponding to the minimum value of the vector distance is obtained as the target data pair; The determination of the real-time wear of the marine water-lubricated stern bearing based on the target wear amount includes: The target wear amount of the target data pair is taken as the real-time wear amount.
[0012] In one possible embodiment, constructing a real-time multidimensional feature vector based on the real-time sensing signal includes: Extract the time-domain feature data, frequency-domain feature data, and time-frequency-domain feature data corresponding to the real-time sensing signal; The time-domain feature data includes the mean, variance, and peak factor of the real-time sensing signal; the frequency-domain feature data includes the dominant frequency component, frequency band energy distribution, and power spectral density of the real-time sensing signal; and the time-frequency domain feature data includes the energy distribution characteristics of the real-time sensing signal at different time-frequency resolutions.
[0013] Secondly, this application also provides a real-time monitoring device for the wear of a marine water-lubricated stern bearing, comprising: The signal acquisition module is used to acquire real-time sensing signals of the water-lubricated stern bearing of the ship and construct a real-time multidimensional feature vector based on the real-time sensing signals. A storage module is used to provide a set correspondence relationship, which includes multiple set data pairs, each set data pair including a mutually corresponding set multidimensional feature vector and a set wear amount; A matching module is used to determine target data pairs based on the real-time multidimensional feature vector and the set correspondence relationship. The target data pairs are the set data pairs where the set multidimensional feature vector and the real-time multidimensional feature vector satisfy the set relationship. Wear determination module, which is used to determine the real-time wear of the marine water-lubricated stern bearing based on a target wear amount, wherein the target wear amount is the set wear amount in the target data pair.
[0014] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the real-time monitoring method for wear of marine water-lubricated stern bearings described in any of the above implementations.
[0015] Fourthly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the real-time monitoring method for wear of a marine water-lubricated stern bearing described in any of the above implementations.
[0016] The beneficial effects of this application are: Compared with related technologies, the real-time monitoring method, device, electronic equipment, and computer-readable storage medium for water-lubricated stern bearings provided in this application construct a real-time multi-dimensional feature vector from the real-time sensing signal of the water-lubricated stern bearing. This real-time multi-dimensional feature vector is then matched with a predefined multi-dimensional feature vector in a predefined correspondence to determine a set data pair that satisfies the predefined relationship as a target data pair. Based on the target wear amount in the target data pair, the real-time wear amount of the water-lubricated stern bearing is determined, achieving the technical effect of real-time monitoring of the wear amount of the water-lubricated stern bearing. Furthermore, the real-time wear amount of the water-lubricated stern bearing can be determined simply by matching the real-time multi-dimensional feature vector. The calculation process is simple, the response speed is fast, and the real-time performance is better. Simultaneously, the evaluation of wear amount based on multi-dimensional feature vectors constructed from data of various different modalities allows for a more comprehensive and accurate assessment of wear amount, improving the accuracy of the real-time wear monitoring results. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the real-time monitoring method for the wear of a marine water-lubricated stern bearing provided in an embodiment of this application. Figure 2 This is a schematic diagram of experimental sensor data in the real-time monitoring method for wear of a marine water-lubricated stern bearing provided in the embodiments of this application; Figure 3 This is a schematic diagram of the process for determining target data pairs based on real-time multidimensional feature vectors and set correspondence relationships in the real-time monitoring method for wear of marine water-lubricated stern bearings provided in the embodiments of this application. Figure 4 A schematic diagram of the structure of a real-time monitoring device for the wear of a marine water-lubricated stern bearing provided in another embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation
[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0020] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.
[0021] The terms "first," "second," etc., used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.
[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0023] This application provides a method and device for real-time monitoring of wear of a marine water-lubricated stern bearing, an electronic device, and a computer-readable storage medium, which are described below.
[0024] Please refer to Figure 1 The real-time monitoring method for wear of a marine water-lubricated stern bearing provided in this application includes: Step S101: Obtain the real-time sensing signal of the stern bearing lubricated by the ship, and construct a real-time multidimensional feature vector based on the real-time sensing signal.
[0025] In this application, multiple physical sensors are arranged around the water-lubricated stern bearing, including but not limited to different types of sensors such as ultrasonic sensors, eddy current sensors, and fiber Bragg grating sensors. During the operation of the water-lubricated stern bearing, the physical sensors sense relevant operating data of the water-lubricated stern bearing in real time. For example, the ultrasonic sensor senses the ultrasonic signals generated by the operation of the water-lubricated stern bearing in real time; the eddy current sensor continuously emits an alternating magnetic field to the water-lubricated stern bearing to generate eddy currents and detects the magnetic field signals and / or impedance signals generated by the eddy currents in real time; and the fiber Bragg grating sensor senses the reflected light signals generated after the operation of the water-lubricated stern bearing affects the fiber Bragg grating in real time. These ultrasonic signals, magnetic field signals, impedance signals, and reflected light signals together constitute the real-time sensing signals in this application.
[0026] In this step, a real-time multidimensional feature vector is constructed based on the real-time sensing signal, including: extracting time-domain feature data, frequency-domain feature data, and time-frequency-domain feature data corresponding to the real-time sensing signal; the time-domain feature data includes the mean, variance, and peak factor of the real-time sensing signal, the frequency-domain feature data includes the dominant frequency component, frequency band energy distribution, and power spectral density of the real-time sensing signal, and the time-frequency-domain feature data includes the energy distribution characteristics of the real-time sensing signal at different time-frequency resolutions.
[0027] Taking the extraction of time-domain feature data corresponding to real-time sensing signals as an example, the specific steps include: first, denoising the real-time sensing signals, including data processing operations such as removing DC components, eliminating outliers, and simple filtering to obtain denoised sensing signals; then, calculating the basic statistics, dimensionless waveforms, energy, and other time-domain features of the denoised sensing signals; retaining core features according to actual business scenarios, eliminating redundant features, and then encapsulating the obtained effective features into one vector dimension of a real-time multi-dimensional feature vector.
[0028] Step S102: Provide a setting correspondence relationship, which includes multiple setting data pairs. Each setting data pair includes a corresponding setting multidimensional feature vector and a setting wear amount.
[0029] In this step, the correspondence is set as a pre-constructed correspondence based on the experimental data obtained during the friction experiment of the sample block. This correspondence includes multiple set data pairs, which include mutually corresponding set multidimensional feature vectors and set wear amounts.
[0030] Specifically, the sample test block is an experimental test block made of the same material as the water-lubricated stern bearing of a ship. The friction experiment specifically includes: using the sample test block to simulate the operation process of the water-lubricated stern bearing of a ship, rubbing against the lubricant of the water-lubricated stern bearing of a ship, and collecting the sensor signals generated by the sample test block in real time during this process. At the same time, the wear of the sample test block is detected at multiple sampling points during the experiment to obtain the sampled wear amount. The sensor signals and the sampled wear amount are used as experimental sensor data.
[0031] Please refer to Figure 2 When constructing and setting the correspondence, firstly based on n Individual wear measurement h 1 、h 2 、h 3 ……h n The sensing signal is split into multiple sub-signals. During this process, a correspondence is established between the sub-signals and the sampled wear amount. For example, constructing (…). Q 1， h 1) 、 ( Q 2， h 2) 、 ( Q 3， h 3) …… ( Q n， h n The correspondence between the two signals is determined; then, the set wear amount is obtained based on the sampled wear amount, and multi-dimensional feature extraction is performed on each sub-signal to obtain the set multi-dimensional feature vector.
[0032] The process of obtaining the set wear amount based on the sampled wear amount includes: acquiring the initial sampled wear amount corresponding to the start time of the sub-signal and the final sampled wear amount corresponding to the end time of the sub-signal; and using the average of the initial sampled wear amount and the final sampled wear amount as the set wear amount. For example... Figure 2 sub-signals in Q 2. The initial sampling wear amount corresponding to its starting time is h 1 、 The terminal sampling wear amount corresponding to the final time is h 2. Based on this, the average value ( h 1 +h 2) / 2 as a sub-signal Q 1 corresponds to the set wear amount.
[0033] It is understood that the aforementioned use of the average of the initial and final sampling wear amounts as the set wear amount is merely a specific example of the set wear amount in this embodiment. In some embodiments of this application, the sampling wear amount corresponding to the sub-signal can also be directly used as the set wear amount. For example, for the sub-signal... Q 2. The corresponding sampled wear amount h 2 is used as the set wear amount.
[0034] It is understandable that the types of vector dimensions used in the multidimensional feature vectors set in this step are the same as those used in the real-time multidimensional feature vectors in the previous steps. Specifically, the feature extraction method used in this step to extract multidimensional features from each sub-signal is the same as the feature extraction method used in the previous steps to construct real-time multidimensional feature vectors based on real-time sensing signals. For example, both the multidimensional feature vectors and the real-time multidimensional feature vectors can be set to be time-domain feature data, frequency-domain feature data, and time-frequency-domain feature data extracted from ultrasonic signals, or both can be set to be time-domain feature data, frequency-domain feature data, and time-frequency-domain feature data extracted from reflected light signals, etc.
[0035] Step S103: Determine the target data pair based on the real-time multidimensional feature vector and the set correspondence. The target data pair is the set data pair where the set multidimensional feature vector and the real-time multidimensional feature vector satisfy the set relationship.
[0036] In this step, please refer to Figure 3 The target data pairs are determined based on real-time multidimensional feature vectors and established correspondences, specifically including: Step S301: Calculate the vector distance between the real-time multidimensional feature vector and each set multidimensional feature vector.
[0037] In this step, the Euclidean distance between the real-time multidimensional feature vector and each set multidimensional feature vector is calculated as the vector distance. The real-time multidimensional feature vector... V real With each set multidimensional feature vector V 1 、V 2 、V All three are three-dimensional feature vectors. V= [ x 1 ，x 2 ，x 3], x 1 ，x 2 ，x 3 represent three-dimensional feature vectors. V The corresponding time domain, frequency domain, and time-frequency domain characteristics.
[0038] by V 1 = [ 0.5，5，50 ], V2 = [ 1.5，50，80 ], V 3 = [ 2.5，75，150 ], V real = [1.0 ，50，75 For example, real-time multidimensional feature vectors V real With each set multidimensional feature vector V 1 、V 2 、V Euclidean distance between 3 D 1 、D 2 、D 3 Specifically: .
[0039] Step S302: Obtain the set data pairs to which the set multidimensional feature vectors whose vector distance satisfies the set conditions as target data pairs.
[0040] In this step, the specific condition is that the vector distance is less than a set threshold distance. The set threshold distance is a pre-defined critical value used as a reference for judging whether the actual distance meets the set condition. Based on this, obtaining the set data pairs to which the set multidimensional feature vectors whose vector distance meets the set condition belongs as target data pairs specifically involves obtaining the set data pairs to which the set multidimensional feature vectors whose vector distance is less than the set threshold distance belongs. For example, if the set threshold distance is 60, then the corresponding selection is Euclidean distance. D 1 、D 2 、D 3 D 1 、D The corresponding multidimensional feature vector for 2 V 1 、V The set data pair to which 2 belongs is used as the target data pair.
[0041] It is understood that setting the condition specifically as a vector distance less than a set threshold distance is merely an example of one specific scheme for setting the condition in this application. In some other embodiments of this application, the setting condition can also be the minimum value of the vector distance. Based on this, obtaining the set data pairs to which the set multidimensional feature vectors whose vector distance satisfies the set condition are designated as target data pairs includes: obtaining the set data pairs corresponding to the minimum value of the vector distance as target data pairs. The corresponding selection is Euclidean distance. D 1 、D 2 、D Minimum value in 3 D The corresponding multidimensional feature vector for 2 V The set data pair to which 2 belongs is used as the target data pair.
[0042] Step S104: Determine the real-time wear amount of the marine water-lubricated stern bearing based on the target wear amount, where the target wear amount is the set wear amount in the target data pair.
[0043] In this step, the real-time wear of the marine water-lubricated stern bearing is determined based on the target wear amount. The specific determination method is selected according to the target data.
[0044] For example, corresponding to the condition set in the aforementioned steps, specifically that the vector distance is less than a set threshold distance, the Euclidean distance is selected. D 1 、D 2 、D 3 D 1 、D The corresponding multidimensional feature vector for 2 V 1 、V If the set data pair to be 2 is used as the target data pair, then the real-time wear of the marine water-lubricated stern bearing is determined based on the target wear amount, which specifically includes: obtaining the target vector distance corresponding to the target data pair, determining the target weight corresponding to each target data pair based on the target vector distance, and performing a weighted calculation on the target wear amount based on the target weight to obtain the real-time wear amount.
[0045] The specific formula for determining the target weights of each target data pair based on the target vector distance is expressed as follows: ,in, ω 1 ω 2. To define the multidimensional feature vectors respectively V 1 、V The target weight corresponding to 2.
[0046] Furthermore, the target wear amount is weighted and calculated based on the target weight, resulting in the following formula for the real-time wear amount: ,in, W To define multidimensional feature vectors V 1 、V The set wear amount corresponding to 2.
[0047] For example, the condition set in the aforementioned steps could also be the minimum value of the vector distance, corresponding to the choice of Euclidean distance. D 1 、D 2 、D Minimum value in 3 D The corresponding multidimensional feature vector for 2 V Using the set data pair as the target data pair, determining the real-time wear of the marine water-lubricated stern bearing based on the target wear amount specifically includes: setting a multi-dimensional feature vector. VThe target wear amount corresponding to the target data pair is used as the real-time wear amount.
[0048] Compared with related technologies, the real-time wear monitoring method for water-lubricated stern bearings provided in this embodiment constructs a real-time multi-dimensional feature vector using real-time sensing signals from the water-lubricated stern bearing. This real-time multi-dimensional feature vector is then matched with a predefined multi-dimensional feature vector in a set correspondence to determine a set data pair that satisfies the predefined relationship as a target data pair. Based on the target wear amount in the target data pair, the real-time wear amount of the water-lubricated stern bearing is determined, achieving the technical effect of real-time monitoring of the wear amount of the water-lubricated stern bearing. Furthermore, the real-time wear amount of the water-lubricated stern bearing can be determined simply by matching the real-time multi-dimensional feature vector. This process is simple, has a fast response speed, and better real-time performance. Simultaneously, the evaluation of wear amount based on multi-dimensional feature vectors constructed from data of various modalities allows for a more comprehensive and accurate assessment of wear amount, improving the accuracy of real-time wear monitoring results.
[0049] Based on the real-time monitoring method for wear of water-lubricated stern bearings in ships, the corresponding method is as follows: Figure 4 As shown in the embodiment of this application, a real-time monitoring device for the wear of a marine water-lubricated stern bearing is also provided, comprising: The signal acquisition module 401 is used to acquire real-time sensing signals of the water-lubricated stern bearing of the ship and construct a real-time multidimensional feature vector based on the real-time sensing signals. Storage module 402 is used to provide a setting correspondence relationship, which includes multiple setting data pairs. Each setting data pair includes a corresponding setting multidimensional feature vector and a setting wear amount. Matching module 403 is used to determine target data pairs based on real-time multidimensional feature vectors and set correspondence relationships. The target data pairs are set data pairs where the set multidimensional feature vectors and real-time multidimensional feature vectors satisfy the set relationship. Wear determination module 404 is used to determine the real-time wear of the marine water-lubricated stern bearing based on the target wear amount, where the target wear amount is the set wear amount in the target data pair.
[0050] The real-time monitoring device for the wear of a water-lubricated stern bearing provided in the above embodiments can realize the technical solution described in the embodiments of the real-time monitoring method for the wear of a water-lubricated stern bearing. The specific implementation principle of each module or unit can be found in the corresponding content in the embodiments of the real-time monitoring method for the wear of a water-lubricated stern bearing, which will not be repeated here.
[0051] Please refer to Figure 5 This application also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502, and a display 503. Figure 5Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
[0052] In some embodiments, processor 501 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 502 or process data, such as the real-time monitoring method for wear of a ship's water-lubricated stern bearing in this application.
[0053] In some embodiments, processor 501 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 501 may be local or remote. In some embodiments, processor 501 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, or any combination thereof.
[0054] In some embodiments, memory 502 may be an internal storage unit of electronic device 500, such as a hard disk or memory of electronic device 500. In other embodiments, memory 502 may also be an external storage device of electronic device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 500.
[0055] Furthermore, the memory 502 may include both internal storage units of the electronic device 500 and external storage devices. The memory 502 is used to store application software and various types of data installed on the electronic device 500.
[0056] In some embodiments, display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 503 is used to display information from electronic device 500 and to display a visual user interface. Components 501-503 of electronic device 500 communicate with each other via a system bus.
[0057] In one embodiment, when processor 501 executes the real-time monitoring program for the wear of the ship's water-lubricated stern bearing stored in memory 502, the following steps can be implemented: Acquire real-time sensing signals of the stern bearing lubricated by water in the ship, and construct a real-time multidimensional feature vector based on the real-time sensing signals; It provides a setting correspondence relationship, which includes multiple setting data pairs. Each setting data pair includes a corresponding setting multidimensional feature vector and a setting wear amount. Target data pairs are determined based on real-time multidimensional feature vectors and a set correspondence. The target data pairs are set data pairs where the set multidimensional feature vectors and real-time multidimensional feature vectors satisfy a set relationship. The real-time wear of the marine water-lubricated stern bearing is determined based on the target wear amount, which is the set wear amount in the target data pair.
[0058] It should be understood that when the processor 501 executes the real-time monitoring program for the wear of the ship's water-lubricated stern bearing in the memory 502, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.
[0059] Furthermore, this application does not specifically limit the type of electronic device 500 mentioned in the embodiments. Electronic device 500 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic devices. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of this application, electronic device 500 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0060] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the real-time monitoring method for the wear of a marine water-lubricated stern bearing provided in the above-described method embodiments.
[0061] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.
[0062] The above provides a detailed description of the method, device, electronic equipment, and storage medium for real-time monitoring of wear of marine water-lubricated stern bearings. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for real-time monitoring of wear on a marine water-lubricated stern bearing, characterized in that, include: Acquire real-time sensing signals of the stern bearing lubricated by water in the ship, and construct a real-time multidimensional feature vector based on the real-time sensing signals; Provide a setting correspondence relationship, which includes multiple setting data pairs, each setting data pair including a mutually corresponding setting multidimensional feature vector and a setting wear amount; Target data pairs are determined based on the real-time multidimensional feature vector and the set correspondence relationship. The target data pairs are the set data pairs where the set multidimensional feature vector and the real-time multidimensional feature vector satisfy the set relationship. The real-time wear of the ship's water-lubricated stern bearing is determined based on the target wear amount, where the target wear amount is the set wear amount in the target data pair.
2. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 1, characterized in that, Constructing the specified correspondence includes: Acquire experimental sensing data of the sample block during the friction experiment, the experimental sensing data including sensing signals and multiple sample wear values of the sample block; The sensing signal is split based on the multiple sampled wear values to obtain multiple sub-signals, and the correspondence between the sub-signals and the sampled wear values is constructed. The set wear amount is obtained based on the sampled wear amount, and multi-dimensional feature extraction is performed on each sub-signal to obtain the set multi-dimensional feature vector.
3. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 2, characterized in that, The step of obtaining the set wear amount based on the sampled wear amount includes: Obtain the initial sampling wear amount corresponding to the start time of the sub-signal and the final sampling wear amount corresponding to the end time of the sub-signal; The average of the initial sampling wear amount and the final sampling wear amount is used as the set wear amount.
4. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 1, characterized in that, The determination of target data pairs based on the real-time multidimensional feature vector and the established correspondence includes: Calculate the vector distance between the real-time multidimensional feature vector and each of the set multidimensional feature vectors respectively; The set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set conditions is obtained is taken as the target data pair.
5. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 4, characterized in that, The step of obtaining the set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set conditions are used as the target data pair includes: The set data pair to which the set multidimensional feature vectors whose vector distance is less than a set threshold distance belong is obtained as the target data pair; The determination of the real-time wear of the marine water-lubricated stern bearing based on the target wear amount includes: Obtain the target vector distance corresponding to the target data pair, and determine the target weight corresponding to each target data pair based on the target vector distance; The target wear amount is calculated by weighting the target wear amount based on the target weight to obtain the real-time wear amount.
6. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 4, characterized in that, The step of obtaining the set data pair to which the set multidimensional feature vectors whose vector distance satisfies the set conditions are used as the target data pair includes: The set data pair corresponding to the minimum value of the vector distance is obtained as the target data pair; The determination of the real-time wear of the marine water-lubricated stern bearing based on the target wear amount includes: The target wear amount of the target data pair is taken as the real-time wear amount.
7. The method for real-time monitoring of wear of a marine water-lubricated stern bearing according to claim 1, characterized in that, The step of constructing a real-time multidimensional feature vector based on the real-time sensing signal includes: Extract the time-domain feature data, frequency-domain feature data, and time-frequency-domain feature data corresponding to the real-time sensing signal; The time-domain feature data includes the mean, variance, and peak factor of the real-time sensing signal; the frequency-domain feature data includes the dominant frequency component, frequency band energy distribution, and power spectral density of the real-time sensing signal; and the time-frequency domain feature data includes the energy distribution characteristics of the real-time sensing signal at different time-frequency resolutions.
8. A device for real-time monitoring of wear of a marine water-lubricated stern bearing, characterized in that, include: The signal acquisition module is used to acquire real-time sensing signals of the water-lubricated stern bearing of the ship and construct a real-time multidimensional feature vector based on the real-time sensing signals. A storage module is used to provide a set correspondence relationship, which includes multiple set data pairs, each set data pair including a mutually corresponding set multidimensional feature vector and a set wear amount; A matching module is used to determine target data pairs based on the real-time multidimensional feature vector and the set correspondence relationship. The target data pairs are the set data pairs where the set multidimensional feature vector and the real-time multidimensional feature vector satisfy the set relationship. Wear determination module, which is used to determine the real-time wear of the marine water-lubricated stern bearing based on a target wear amount, wherein the target wear amount is the set wear amount in the target data pair.
9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the real-time monitoring method for wear of a marine water-lubricated stern bearing as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the real-time monitoring method for wear of a marine water-lubricated stern bearing as described in any one of claims 1 to 7.