Ship tail shaft seal intelligent leakage early warning coral bionic sensing control method and system

Abstract

The invention relates to the technical field of ship tail shaft seal control, and particularly provides a ship tail shaft seal intelligent leakage early warning coral bionic sensing control method and system, and the method comprises the steps: constructing a bionic micro-motion sensing unit; the probe is composed of a plurality of miniature tentacle-shaped probes and installed around a ship tail shaft seal to generate corresponding electric signal changes. The output multi-channel electric signals of the bionic micro-motion sensing unit are utilized to simulate an information sharing and decision-making mechanism of a coral group, real-time weighted fusion and noise suppression are performed on the multi-probe electric signals, and a special micro-motion characteristic mode of leakage is extracted; distinguishing normal operation vibration from real leakage events; and automatically adjusting sealing parameters of the tail shaft seal according to the level and trend of a preset early warning index in combination with a dynamic control strategy in a micro-motion characteristic mode. The system comprises a sensing unit construction module, a characteristic mode extraction module and a sealing parameter adjustment module. According to the invention, real-time monitoring and self-adaptive regulation and control of ship tail shaft seal leakage are realized.

Description

Technical Field

[0001] This invention relates to the field of ship stern shaft seal control technology, and in particular to a biomimetic sensing control method and system for intelligent early warning of ship stern shaft seal leakage. Background Technology

[0002] The stern shaft seal is a core sealing component of the power transmission system, and its reliability directly affects the safety and environmental performance of ship operation. Traditional stern shaft seals rely on manual inspection or simple threshold alarms, making it difficult to detect initial minute leaks in real time, leading to problems such as grease pollution in the ocean and accelerated bearing wear. Existing sensing technologies are mostly designed for macroscopic leaks and lack sensitivity to seepage stages (such as micro-ruptures of the oil film and slow grease seepage), and lack deep integration of bionics and intelligent algorithms.

[0003] Prior art 1, Chinese patent application number 202310182751.9, discloses a ship stern shaft sealing machine. An end sleeve is interference-fitted to the outer side of the stern shaft, and a stern shaft seal structure is fitted onto the end of the end sleeve. The upper and lower parts of the stern shaft seal structure are threadedly connected to inlet and outlet elbows. An end connecting plate is bolted to the right side of the stern shaft seal structure, and an oil seepage absorber assembly is provided on the right side of the end connecting plate. The oil seepage absorber assembly includes a connecting housing, an oil-absorbing cloth disc placed inside the connecting housing, and a rubber connecting roller at the connection between the connecting housing and the oil-absorbing cloth disc. Although the arrangement of the connecting housing, oil-absorbing cloth disc, and rubber connecting roller facilitates the absorption of seeping lubricating oil, improves the sealing effect, and eliminates the need for wiping by workers, this prior art only absorbs oil stains after a leak occurs, which is a post-event treatment.

[0004] Prior art two, Chinese patent application number 202411912019.3, discloses a lip wear monitoring system for a lip seal on a rotating shaft, including an elastic conductor sheet, an insulating layer, a lip seal, a wire, a measuring module, an indicator light, a rotating shaft, a lower support ring, an upper support ring, and a cavity. The elastic conductor sheet and the wire are connected and conductive, and the wire is connected and conductive to the rotating shaft via a brush. The lip seal isolates the elastic conductor sheet and the rotating shaft. Although the lip wear monitoring system is reliable and can prompt for seal replacement before leakage, preventing bearing damage caused by leakage and gaining valuable preparation time for seal replacement, it is particularly suitable for situations requiring seal wear monitoring, such as tunnel boring machines and ship stern shaft seals. However, it requires direct wear of the conductive sheet on the sealing lip to generate a signal, which can only determine the degree of wear.

[0005] Current technologies 1 and 2 suffer from poor accuracy in identifying leakage characteristics under complex operating conditions. Therefore, this invention provides a biomimetic sensing and control method and system for intelligent early warning of leakage in ship stern shaft seals, based on the principle of coral polyps. Summary of the Invention

[0006] To achieve the above objectives, the present invention adopts the following technical solution: One aspect of the present invention provides a biomimetic sensing and control method for intelligent early warning of leakage of ship stern shaft seals using coral polyps, comprising the following steps: By simulating the microstructural dynamic response characteristics of coral tentacles, a biomimetic micro-motion sensing unit is constructed using flexible polymer materials and microelectromechanical systems. It consists of multiple miniature tentacle-shaped probes, which are installed around the stern shaft seal of a ship and come into contact with the fluid environment. When a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals. By utilizing the multi-channel electrical signals of the output biomimetic micro-motion sensing unit, mimicking the information sharing and decision-making mechanism of coral polyps, the electrical signals from multiple probes are weighted and fused in real time and noise is suppressed to extract the micro-motion characteristic patterns unique to leaks; thus distinguishing between normal operating vibrations and real leak events. Based on the generated micro-motion characteristic pattern and combined with the dynamic control strategy, the sealing parameters of the tail shaft seal are automatically adjusted according to the level and trend of the preset early warning indicators, forming an adaptive control output.

[0007] Another aspect of the present invention provides a biomimetic sensing and control system for intelligent early warning of leakage of ship stern shaft seals, comprising: The sensing unit construction module is used to construct a biomimetic micro-motion sensing unit by simulating the dynamic response characteristics of the microstructure of coral tentacles, using flexible polymer materials and microelectromechanical systems; it consists of multiple micro-tentacle-shaped probes, which are installed around the stern shaft seal of the ship and come into contact with the fluid environment; when a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals; The feature pattern extraction module is used to utilize the multi-channel electrical signals of the output biomimetic micro-motion sensing unit to mimic the information sharing and decision-making mechanism of coral polyps, perform real-time weighted fusion and noise suppression on the electrical signals of multiple probes, and extract the micro-motion feature patterns unique to leakage; and distinguish between normal operating vibrations and real leakage events. The sealing parameter adjustment module is used to automatically adjust the sealing parameters of the tail shaft seal based on the generated micro-motion characteristic pattern and combined with the dynamic control strategy, according to the level and trend of the preset warning indicators, so as to form an adaptive control output.

[0008] This invention achieves real-time monitoring and adaptive control of stern shaft seal leakage through the system integration of biomimetic principles and intelligent control technology. A tentacle-like microstructure probe constructed from flexible polymer materials converts fluid disturbances into multi-channel electrical signals via a microelectromechanical system (MEMS). This overcomes the limitations of traditional rigid sensors in terms of insufficient sensitivity to microfluidic field changes, enabling dynamic capture of μm-level displacements. Multi-probe signals are fused in the spatiotemporal domain using a group decision-making algorithm, and adaptive weighting coefficients are employed to eliminate environmental noise interference. Based on the leakage feature spectrum extracted by a pattern recognition algorithm, a mapping relationship between vibration signals and leakage states is established, achieving fault identification with a false alarm rate ≤0.5%. The sealing parameter adjustment employs a feedforward-feedback composite control strategy, dynamically adjusting parameters such as the mechanical seal's specific pressure and liquid film stiffness based on the feature pattern recognition results, forming an active compensation mechanism for the sealing gap. The control system response time is <200ms, an improvement of two orders of magnitude compared to traditional methods. This represents a technological leap from passive protection to active early warning of stern shaft seal status, reducing the leakage accident rate under typical operating conditions. Attached Figure Description

[0009] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the biomimetic sensing and control method for intelligent early warning of leakage of ship stern shaft seal provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the construction of the biomimetic micro-motion sensing unit provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram illustrating the principle of extracting the unique micro-motion feature pattern of leakage as provided in Embodiment 4 of the present invention; Figure 4 This is a schematic diagram of the sealing parameters of the automatically adjusted tail shaft seal provided in Embodiment 11 of the present invention; Figure 5 This is a schematic diagram of the intelligent leakage early warning coral polyp biomimetic sensor control system for ship stern shaft seals provided in Embodiment 12 of the present invention. Figure 6 A block diagram of the electronic device provided by the present invention; Figure 7 A block diagram of a computer-readable storage medium provided for this invention; Figure 8 This is a schematic diagram of the structure of the biomimetic micro-motion sensing unit provided by the present invention; Reference numerals: 1. Sensing unit construction module; 2. Feature pattern extraction module; 3. Sealing parameter adjustment module; 4. Central processing unit / microprocessor / main control chip, etc.; 5. Storage medium; 6. Data bus; 7. Input / output bus / external bus / device bus, etc.; 8. Display; 9. Input / output device; 10. Computer-readable instructions; 11. Computer-readable storage medium; 12. Silicon-based flexible polymer material layer; 13. Bionic neural network structure; 14. Probe array and signal interface chip; 15. Support body; 16. Coral polyp tentacles; 17. Hollow fiber structure; 18. Elastomer encapsulation layer; 19. Tail shaft. Detailed Implementation

[0010] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0011] Hereinafter, the terms "first," "second," etc., are used for descriptive convenience 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 with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0012] In this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, "connection" can be a fixed mechanical connection, a detachable mechanical connection, or an integral part; or, "connection" can be a direct connection or an indirect connection through an intermediate medium. Furthermore, unless otherwise explicitly specified and limited, the term "coupling" should be interpreted broadly. For example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components; it can also be understood as an electrical connection between different components in a circuit structure through physical lines capable of transmitting electrical signals, such as copper foil or wires on a printed circuit board (PCB), to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in a non-contact manner, such as an electrical connection between two components using capacitive coupling to transmit electrical signals.

[0013] In this embodiment of the invention, directional terms such as "up," "down," "left," and "right" may be defined relative to the orientation of the components shown in the accompanying drawings. It should be understood that these directional terms can be relative concepts, used for relative description and clarification, and can change accordingly depending on the orientation of the components in the accompanying drawings.

[0014] Example 1: like Figure 1 As shown, this embodiment of the invention provides a biomimetic sensing and control method for intelligent early warning of leakage of ship stern shaft seals using coral polyps, comprising the following steps: Step S100: By simulating the dynamic response characteristics of the microstructure of coral tentacles, a biomimetic micro-motion sensing unit is constructed using flexible polymer materials and microelectromechanical systems; it consists of multiple micro-tentacle-shaped probes, which are installed around the stern shaft seal of the ship and in contact with the fluid environment; when a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals; Step S200: Using the multi-channel electrical signals of the output biomimetic micro-motion sensing unit, the information sharing and decision-making mechanism of coral polyps is imitated to perform real-time weighted fusion and noise suppression on the electrical signals of multiple probes, and extract the micro-motion characteristic patterns unique to leakage; distinguish between normal operating vibration and real leakage events. Step S300: Based on the generated micro-motion characteristic pattern and combined with the dynamic control strategy, the sealing parameters of the tail shaft seal are automatically adjusted according to the level and trend of the preset early warning indicators to form an adaptive control output.

[0015] In the above embodiments, this embodiment achieves real-time monitoring and adaptive control of stern shaft seal leakage through the system integration of biomimetic principles and intelligent control technology. A tentacle-like microstructure probe constructed from flexible polymer materials converts fluid disturbances into multi-channel electrical signals via a microelectromechanical system (MEMS). This overcomes the limitations of traditional rigid sensors in terms of insufficient sensitivity to microfluidic field changes, achieving dynamic capture of μm-level displacements. Multi-probe signals are fused in the spatiotemporal domain using a group decision-making algorithm, and adaptive weighting coefficients are employed to eliminate environmental noise interference. Based on the leakage feature spectrum extracted by a pattern recognition algorithm, a mapping relationship between vibration signals and leakage states is established, achieving fault identification with a false alarm rate ≤0.5%. The sealing parameter adjustment adopts a feedforward-feedback composite control strategy, dynamically adjusting parameters such as the mechanical seal's specific pressure and liquid film stiffness according to the feature pattern recognition results, forming an active compensation mechanism for the sealing gap. The control system response time is <200ms, an improvement of two orders of magnitude compared to traditional methods. This represents a technological leap from passive protection to active early warning of stern shaft seal status, reducing the leakage accident rate under typical operating conditions.

[0016] Example 2: like Figure 2As shown, based on Example 1, the process of constructing the biomimetic micro-motion sensing unit in step S100 of this embodiment of the invention includes the following steps: Step S101: Using the high flexibility and dynamic responsiveness of coral tentacles as a biological model, a silicon-based flexible polymer material is used as the matrix; the silicon-based flexible polymer material is modified with molecular chains and doped with nanoparticles; through a micro-nano scale molding process, the silicon-based flexible polymer material is shaped into a hollow fiber structure with a micron-scale diameter and containing a biomimetic neural network. Step S102: The hollow fiber structure of the prepared biomimetic neural network is used as the core sensing unit and integrated into a multi-channel probe array inspired by the distributed layout of coral tentacles; each fiber is an independent sensing unit, and its bottom is connected to a signal interface chip based on microelectromechanical systems technology; an independent electrical transmission path is established for each fiber. Step S103: The obtained distributed tentacle-shaped probe array is embedded into the inert elastomer encapsulation layer using a secondary injection molding process according to the geometric contour of the ship's stern shaft seal; forming a biomimetic micro-motion sensing unit that is integrated with the stern shaft seal structure and in contact with the fluid environment.

[0017] The structure of the above embodiments can be referred to in the appendix. Figure 8 (Appendix) Figure 8This is only a specific embodiment, and adjustments should be made according to actual conditions in practical applications. It includes a silicon-based flexible polymer material layer 12, a biomimetic neural network structure 13, and a hollow fiber structure 17 composed of the silicon-based flexible polymer material layer 12 and the biomimetic neural network structure 13. The silicon-based flexible polymer material layer 12 and the biomimetic neural network structure 13 are mounted on a substrate via a support 15. A probe array composed of coral tentacle clusters 16 is connected to a signal interface chip 14. Both the signal interface chip 14 and the hollow fiber structure 17 are connected to a hygroscopic elastomer encapsulation layer 18. The hygroscopic elastomer encapsulation layer 18 and the tail shaft 19 are integrated into a single design. In this embodiment, through molecular chain modification and nanoparticle doping of the silicon-based flexible polymer material, the optimal matching of Young's modulus and elongation at break of the matrix material is achieved. Combined with the hollow fiber structure formed by micro-nano molding technology, the unit possesses both the low stiffness and high-frequency dynamic response characteristics of coral tentacles. The biomimetic neural network cavity fiber achieves independent electrical paths for each unit through a MEMS signal interface chip, forming a distributed capacitive-resistive hybrid sensing network. This enables the probe array to simultaneously capture three types of physical quantities: fluid pressure fluctuations, surface shear forces, and contact deformation. An inert elastomer encapsulation layer achieves mechanical coupling with the probe array through a secondary injection molding process, providing IP68 protection and chemical inertness while maintaining the fiber's degrees of freedom. The overall structure, through the piezoresistive-capacitive coupling effect of the biomimetic neural network cavity, achieves spatiotemporal resolution of fluid boundary layer disturbances in the tail shaft seal, with signal transmission efficiency superior to traditional discrete sensor layouts.

[0018] In summary, this embodiment forms an embedded monitoring system with bio-like sensing characteristics. Its core innovation lies in transforming bionic principles into an engineerable micro-motion sensing solution through the collaborative design of materials, structure, and process.

[0019] Example 3: Based on Example 2, the process of molding the silicon-based flexible polymer material into a hollow fiber structure with a micron-scale diameter and containing a biomimetic neural network in step S101 provided in this embodiment of the invention includes the following steps: Step S1011: Using the fractal topology of the neural network inside the coral tentacles used to transmit stimuli as a geometric blueprint, a negative mold containing an interconnected microchannel network is processed by using high-temperature glass material through a combination of laser ablation and selective chemical etching; the microchannel structure of the negative mold is completely complementary to the neural network cavity fiber structure of the target fiber, and the inner wall of the microchannel structure has extremely low surface energy. Step S1012: Utilizing the rheological properties of silicon-based flexible polymer materials, a negative template is filled and cured; the silicon-based flexible polymer material, after molecular chain modification and nanoparticle doping treatment, is injected into the prepared negative mold microchannels under viscous conditions; by applying external negative pressure, the silicon-based flexible polymer material is driven to completely fill the microchannel network; through controllable thermocatalysis, the silicon-based flexible polymer material is cross-linked and cured in situ within the mold, and its molecular chain network combines with the microchannel morphology of the mold to form a composite material preform; Step S1013: Peel the cured composite material preform from the negative mold. After peeling, the composite material preform retains the mirror structure of the microchannel of the negative mold, that is, it contains a continuous and interconnected hollow network inside. Perform surface oxygen plasma treatment on the composite material preform to activate the outer surface and give it a specific polarity. A hollow fiber structure with a micron-scale diameter, external adhesion activity and internal biomimetic neural network is obtained.

[0020] Among them, the high-temperature glass material can be borosilicate glass; the silicon-based flexible polymer material is a polydimethylsiloxane composite material doped with carbon nanotubes; the viscosity conditions are specifically controlled within the range of 4000 to 6000 mPa·s (centipoise); the thermal catalysis can be carried out at a temperature of 80 degrees Celsius for 4 hours; the surface oxygen plasma treatment is carried out at a power of 100 watts, using an oxygen flow rate of 100 sccm (standard milliliters per minute), in a vacuum chamber of 50 Pa for 60 seconds; the above process conditions are for illustrative purposes only and can be adjusted according to actual conditions. The focus of this embodiment is not the process.

[0021] In the above embodiments, the glass negative mold processed by laser ablation and chemical etching achieves the micron-level structural transfer of the fractal topology of coral neural networks. The low surface energy of the mold surface ensures the integrity of demolding. The process combination enables the geometric fidelity of the complex three-dimensional hollow network to meet biomimetic requirements. The combination of negative pressure filling process based on the rheological properties of silicon-based polymers and thermocatalytic in-situ curing achieves uniform distribution of nano-doped phases in the microchannels while avoiding phase separation defects. Oxygen plasma treatment generates surface-active groups, creating a gradient distribution of polarity on the outer surface of the fiber and non-polarity in the inner cavity. This characteristic simultaneously meets the interface bonding requirements during subsequent integration and the fluid wetting control of the internal cavity. The final hollow fiber structure possesses: ① a multi-level fractal flow channel in the form of neural network biomimetic, realizing the distributed transmission of stress / chemical signals; ② piezoresistive-dielectric dual-response characteristics introduced by nanoparticle doping; ③ environmental coupling capability imparted by the outer surface active layer. This process chain, through the three-level synergy of precision mold manufacturing, controllable material forming, and surface functionalization, transforms the structure-function coupling mechanism of organisms into an engineering solution that can be mass-produced.

[0022] Example 4: like Figure 3 As shown, based on Example 1, the process of extracting the micro-motion characteristic pattern unique to leakage in step S200 of this embodiment of the invention includes the following steps: Step S201: Treat the electrical signal as a distributed sensing group; based on the mechanism of local information exchange between individual corals through physical contact, calculate the dynamic cross-correlation coefficient of each pair of probe signals in the time domain to form a real-time updated spatial correlation matrix; the spatial correlation matrix characterizes the distribution of the cooperative response intensity between probes caused by fluid disturbance events. Step S202: The spatial correlation matrix is ​​used as a quantitative indicator of the group consensus. The overall correlation strength between each probe and other probes in the spatial correlation matrix is ​​converted into the weight value of the probe signal in the fusion process. At the same time, the vibration noise generated during normal ship operation forms a background field in the circumferential direction of the entire tail shaft seal, and outputs a purified fusion signal that represents the group consensus. Step S203: Extract dynamic features of the fused signal based on time windows, mimicking the ability of coral reefs to recognize specific stimulus patterns, and focusing on the morphological features of the fused signal waveform; the combination of morphological features constitutes the micro-motion characteristic pattern unique to the leak, which can be distinguished from the vibration of normal ship operation.

[0023] In the above embodiments, this embodiment forms a fluid leakage detection method system based on distributed collaborative sensing. Dynamic coupling analysis of the probe network is achieved through a spatial correlation matrix, transforming traditional single-point signal detection into group collaborative response pattern recognition. This matrix also possesses noise suppression capabilities, and its dynamic cross-correlation coefficient calculation effectively separates local disturbance events from global background vibrations. The dual function of the spatial correlation matrix is ​​manifested in two aspects: firstly, it serves as a basis for weight allocation to optimize the fusion of probe signals; secondly, it achieves common-mode noise cancellation through circumferential background field modeling. This mechanism ensures that the fused signal retains spatially correlated disturbance characteristics while suppressing ship system vibrations unrelated to leakage. The temporal dynamic analysis of the fused signal and the preceding spatial collaborative detection form a cascaded processing: the spatiotemporal dimensions correspond to the spatial correlation of disturbance propagation and the temporal representation of the leakage transient process, respectively; the combined extraction of morphological features achieves a complete mathematical description of the micro-motion pattern, and its discriminative ability stems from the essential distinction between the non-stationary transient process unique to fluid leakage and steady-state ship vibration.

[0024] In summary, this embodiment transforms the collaborative perception principle of biological swarm intelligence into signal processing. Through dynamic calculation of the spatial correlation matrix, online generation of adaptive fusion weights, and joint extraction of temporal morphological features, a leak detection feature space with physical interpretability is constructed. It breaks through the dependence of traditional threshold detection on absolute signal amplitude and instead detects the collaborative response mode of the probe network, significantly improving the micro-leakage recognition rate under strong background noise.

[0025] Example 5: Based on Example 4, the process of constructing a real-time updated spatial correlation matrix in step S201 provided in this embodiment of the invention includes the following steps: Step S2011: Using the multi-channel electrical signals of the output biomimetic micro-motion sensing unit, it is regarded as a distributed sensing group; based on the instantaneous and local nature of contact sensing between individual coral polyps, the signal of each probe in the latest preset very short time segment is intercepted to form a signal sensing segment; the signal sensing segments of all probes are aligned in time to form a multi-channel signal slice. Step S2012: Using the obtained multi-channel signal slices, based on the principle that the efficiency of information transmission between two individuals in a coral colony through contact is related to the distance between them and the state of the medium, calculate the normalized cross-correlation coefficient of the two signal sensing segments in a very short time segment; by traversing all probe pair combinations, obtain a set of dynamic cross-correlation values ​​that reflect the strength of the consistency of response between each probe pair under the current instantaneous conditions. Step S2013: Fill the corresponding element positions of a symmetric matrix with the cross-correlation values ​​according to their corresponding probe numbers. The row and column indices represent probe numbers, and the diagonal elements are fixed to the maximum value, indicating the complete correlation of the probes themselves. This forms a real-time updated spatial correlation matrix, which quantitatively describes the distribution of the coordinated response intensity among the sensing units in the group caused by the fluid disturbance event at the current moment, and implies the possible spatial location information of the leakage source.

[0026] In the above embodiments, this embodiment achieves spatiotemporal synchronous capture capability of fluid disturbance events by constructing multi-channel electrical signals into a time-aligned slice structure. This architecture simulates the local sensing mechanism of coral polyps, preserving the spatial distribution characteristics of sensing units at the hardware level, providing a raw data basis for subsequent correlation calculations. Based on the calculation of normalized cross-correlation coefficients, a non-contact method for measuring the consistency of response between probes is established. This model quantifies the signal coupling strength caused by disturbance propagation in the fluid medium by traversing all probe pair combinations, and its calculation process implicitly considers the influence of medium transmission characteristics on the signal. By constructing a symmetric matrix, the temporal signal correlation is mapped to a spatial correlation topology; the off-diagonal elements of the matrix reflect the cooperative response patterns between probes at different spatial locations, while the diagonal elements provide a signal self-consistency benchmark, forming an overall quantitative characterization of the fluid disturbance propagation field that can be updated in real time.

[0027] In summary, this embodiment achieves the following detection capabilities for fluid disturbance events: by indirectly characterizing the location characteristics of the disturbance source through the spatial distribution pattern of multi-probe signal coupling strength, by utilizing the dynamic update characteristics of matrix elements to capture the instantaneous state of disturbance propagation in the fluid medium, and by providing feature input parameters based on collective perception consistency for subsequent localization algorithms; and by establishing a reverse analytical framework for the fluid disturbance propagation field based on signal spatial correlation, the technical advantage of which lies in improving detection reliability through collective response pattern analysis rather than relying on the sensitivity of a single probe.

[0028] Example 6: Based on Example 4, the process in which the combination of morphological features in step S203 of this embodiment of the invention constitutes a micro-motion feature pattern unique to leakage includes the following steps: Step S2031: Utilize the fusion signal representing the consensus of the group and regard it as the overall response of the entire perceptual group to the current environmental stimulus; take the biological phenomenon that when a threat initially appears in a coral reef, the response spreads rapidly outward from a local point but is not uniform and synchronous as a model; within a sliding time window, perform multi-scale analysis on the fusion signal, and extract parameters that purely describe the morphology, such as the local fluctuation density of the fusion signal waveform, the amplitude ratio between adjacent fluctuations, and the duration distribution of fluctuation clusters, to jointly constitute a set of morphological indicators describing the local fine structure of the signal; Step S2032: Inspired by the characteristics of coral reefs forming specific spatial response patterns under continuous stimulation, the time-varying indicators are mapped to evolutionary trajectories; the stability coefficient, slope of the change trend, and deviation from the background baseline of the evolutionary trajectory within the time window are calculated; the parameters together constitute another set of dynamic indicators describing the global consistency and stability of the response. The process of calculating the normalized cross-correlation coefficient of two signal sensing segments within a very short time segment is as follows: Based on the principle that the information transmission efficiency between corals is affected by distance, the mean of the signal sensing segments of the two probes within the same time segment is first removed. Then, the sum of the products of their corresponding data points is calculated, and this result is normalized by dividing it by the product of the standard deviations of the two signals. In this process, the initial correlation coefficient is multiplied by an attenuation coefficient related to the physical distance between the two probes, and finally a dynamic cross-correlation value that reflects both the similarity of the signal waveforms and their spatial position relationship is obtained. Step S2033: Perform feature concatenation and fusion of the morphological index set and the dynamic index set, and aggregate them according to their contribution to the characterization of the leakage event to form a feature vector; the feature vector is the micro-motion feature pattern unique to leakage, and its inherent numerical combination and distribution are distinguishable from the signal pattern generated by the vibration of normal ship operation.

[0029] In the above embodiments, this embodiment achieves cross-scale feature coverage from microscopic morphology to macroscopic dynamics by analyzing local waveforms within a sliding time window, fluctuation density, amplitude ratio, duration distribution, and global evolution trajectory, as well as stability coefficient, trend slope, and baseline deviation, thus forming a complete characterization of the spatiotemporal characteristics of the leakage signal. Mimicking the biological principle of coral reef response diffusion, a two-layer feature extraction framework is constructed, combining local non-uniform response and global pattern formation, enhancing the detection sensitivity to weak signals in the early stages of leakage and the ongoing evolution process. The high-dimensional feature vector generated through feature cascading and weighted aggregation exhibits the following distinguishing characteristics in its parameter combination distribution pattern in mathematical space: the morphological index set captures local nonlinear fluctuations of transient signals, while the dynamic index set reflects the temporal evolution law of the system response; their synergistic effect allows the leakage mode and normal vibration mode in the feature space to form a separable hyperplane boundary. The introduction of the stability coefficient and baseline deviation parameters suppresses random fluctuation interference caused by environmental noise; while the joint constraint of the amplitude ratio and trend slope eliminates periodic mechanical vibration interference unrelated to leakage.

[0030] In summary, this embodiment constructs a physically interpretable high-dimensional feature space through bio-inspired feature engineering, achieving nonlinear separability from conventional operating condition vibration modes while preserving the essential characteristics of the leakage signal.

[0031] Example 7: Based on Example 6, the process of forming a feature vector in step S2033 provided in this embodiment of the invention includes the following steps: Step S20331: Using the morphological index set and the kinetic index set, based on the mechanism by which each individual in the coral colony contributes weight according to the intensity of the stimulus it perceives and its location in the environment, assign a dynamic weight coefficient to each feature parameter in the morphological index set and the kinetic index set; the dynamic weight coefficient is determined according to the statistical distribution of the feature parameter under historical normal conditions; the greater the contribution as a basis for leakage judgment, the greater the contribution. Step S20332: Using dynamic weighting coefficients, synthesize all feature parameters by multiplying their original values ​​by the weighting coefficients to form a feature vector; each dimension value in the feature vector is a fusion result weighted by contribution, and simultaneously contains local morphological anomaly information and global dynamic behavior anomaly information of the electrical signal. Step S20333: The weighted composite feature vector is used as the output, which is the micro-motion feature pattern unique to leakage; it is a comprehensive measure that embeds the relative importance relationship between features, and its overall numerical distribution pattern has an essential and distinguishable difference from the feature vector distribution pattern generated under normal ship operation vibration.

[0032] In the above embodiments, this embodiment determines the dynamic weight coefficients based on the statistical distribution of historical normal states, making the contribution measurement of feature parameters more consistent with the actual leakage detection needs. The weight allocation simulates the local response mechanism of coral communities, enhancing the sensitivity to abnormal signals while suppressing redundant feature interference under normal operating conditions. Morphological indicators (local waveform anomalies) and dynamic indicators (global behavioral anomalies) are synthesized through dynamic weighting to form a hybrid feature expression that can capture both transient distortions and characterize long-term evolution trends. The weighted product operation retains the original numerical physical meaning while highlighting the weight ratio of highly discriminative features. Each dimension of the feature vector is a fusion result weighted by contribution, nonlinearly amplifying the distribution difference between leakage modes and normal vibration modes in high-dimensional space. The dynamic adjustment mechanism of the weight coefficients can adapt to different sensor characteristics or environmental noise levels, improving feature robustness. The feature vector generation process explicitly associates signal morphology with system dynamic behavior, avoiding the loss of physical meaning caused by black-box feature extraction. The weight coefficients directly reflect the actual contribution of each parameter to leakage discrimination, facilitating subsequent model decision analysis.

[0033] In summary, this embodiment constructs a leakage feature representation with strong discriminativeness, high robustness, and physical interpretability through dynamic weight allocation and multi-dimensional feature fusion, providing an input space for separability optimization for subsequent pattern classification.

[0034] Example 8: Based on Example 7, the process of assigning a dynamic weight coefficient to each feature parameter in the morphological index set and the dynamic index set in step S20331 of this embodiment of the invention includes the following steps: Step S203311: Using historical data accumulated during the long-term normal operation of the ship, perform statistical learning on each feature parameter in the morphological index set and the dynamic index set; using the collective memory of coral polyps of the normal state of their environment as a blueprint, calculate the mean and standard deviation of each feature parameter on the historical dataset, and establish a statistical baseline model for each feature parameter to describe its normal fluctuation range. Step S203312: Using a statistical baseline model, the dynamic weight coefficient of each feature parameter is calculated based on the degree of deviation of the individual coral polyp's judgment of the stimulus intensity from the normal background. The coefficient is inversely proportional to the historical normal standard deviation of the feature parameter. Step S203313: Form a set of dynamic weight coefficients corresponding to the feature parameters and dynamic weight coefficients, and quantify the importance of each feature parameter in the leakage detection at the current time.

[0035] In the above embodiments, this embodiment calculates the mean and standard deviation of feature parameters based on historical normal data to establish a benchmark model that quantifies their normal fluctuation range. The model covers typical ship operating conditions through long-term data accumulation, avoiding baseline drift caused by transient interference. The dynamic weight coefficient is inversely proportional to the historical standard deviation of the feature parameters, giving higher weights to parameters with smaller fluctuation ranges (more sensitive to anomalies). The weight allocation mechanism is equivalent to applying nonlinear gain to low-noise features, improving the detection probability of weak leakage signals. The dynamic weight coefficient set explicitly correlates the statistical characteristics and discriminative contributions of the feature parameters, and the weight update process does not require the introduction of external hyperparameters. The weight coefficients are dynamically adjusted with historical data, adapting to long-term changes such as sensor degradation or gradual environmental changes. The statistical baseline model only needs to store the mean and standard deviation, and the weight calculation is a linear operation, meeting real-time requirements. Model updates can be achieved through incremental learning, avoiding repeated processing of the entire dataset.

[0036] In summary, this embodiment transforms the physical properties of feature parameters into calculable weight coefficients through statistical learning, forming a data-driven feature selection mechanism that balances sensitivity and stability, providing normalized and discriminative inputs for subsequent fusion.

[0037] Example 9: Based on Example 8, the process in step S203312 of this embodiment of the invention, which uses the individual coral's judgment of the intensity of stimulation based on its degree of deviation from the normal background, includes the following steps: Step S2033121: Using the historical normal standard deviation of each feature parameter in the established statistical baseline model, the reciprocal of the historical normal standard deviation is used as the basis for calculating the dynamic weight coefficient. Step S2033122: Input the basis for calculating the dynamic weight coefficients into a custom nonlinear transformation program to maintain the balance and robustness of the overall decision-making system; through nonlinear mapping, output a standardized dynamic weight coefficient for each feature parameter. Step S2033123: The obtained dynamic weight coefficients are inversely proportional to the historical standard deviation of the feature parameters, quantifying the relative importance of each feature parameter in identifying leakage events at the current moment.

[0038] In the above embodiments, this embodiment constructs an adaptive feature importance allocation method through nonlinear normalization transformation of statistics, which, while preserving the data-driven characteristics, forces the weight system to have physical interpretability and algorithmic robustness.

[0039] Example 10: Based on Example 9, the nonlinear mapping process provided in this embodiment of the invention includes the following steps: Step S20331221: Use the reciprocal of the historical normal standard deviation corresponding to each feature parameter obtained by calculation as the input value; substitute the input value into an exponential function with the natural constant e as the base for transformation, and the output value is constrained between zero and a positive upper limit value; Step S20331222: Perform a linear scaling process on the output value to calibrate its output range to a preset weight value range; output a standardized dynamic weight coefficient for each feature parameter; Step S20331223: The resulting standardized dynamic weight coefficients.

[0040] In the above embodiments, this embodiment constructs a weight generation mechanism that combines nonlinear discrimination enhancement and numerical stability through the cascaded operation of exponential transformation and linear scaling, providing standardized and physically meaningful weight inputs for the fusion of multi-source heterogeneous features.

[0041] Example 11: like Figure 4 As shown, based on Example 1, the process of automatically adjusting the sealing parameters of the tail seal in step S300 of this embodiment of the invention includes the following steps: Step S301: Utilize the micro-motion characteristic pattern unique to the generated leakage to analyze its multi-dimensional feature vector; establish a nonlinear mapping relationship between each dimension of the feature vector and different sealing parameters of the tail shaft seal to form a feature-parameter mapping relationship library; Step S302: Input the real-time acquired micro-motion feature patterns into the feature-parameter mapping relationship library, and output a preliminary sealing parameter adjustment scheme through multi-dimensional feature weighted matching; when the feature patterns tend to stabilize to a standard, adopt a maintenance adjustment strategy to finally generate a parameter adjustment strategy sequence; Step S303: The parameter adjustment strategy sequence is sent to the execution unit of the tail seal system. Through the biomimetic distributed control architecture, multiple sealing parameters are adjusted synchronously. Different execution units cooperate to complete the coordinated adjustment of multiple parameters such as sealing ring pressure and compensation fluid flow according to the requirements of the strategy sequence, forming an adaptive control output.

[0042] In the above embodiments, this embodiment constructs a closed-loop control system from anomaly detection to parameter optimization through feature-driven parameter mapping, dynamic strategy generation, and distributed collaborative execution, thereby achieving autonomous maintenance and recovery of the tail shaft seal sealing performance.

[0043] Example 12: like Figure 5 As shown, based on Embodiments 1-11, the intelligent leak warning coral polyp biomimetic sensing control system for ship stern shaft seals provided in this embodiment of the invention includes: Sensing unit construction module 1 is used to construct a biomimetic micro-motion sensing unit by simulating the microstructure dynamic response characteristics of coral tentacles, using flexible polymer materials and microelectromechanical systems; it consists of multiple micro tentacle-shaped probes, which are installed around the stern shaft seal of the ship and in contact with the fluid environment; when a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals; Feature pattern extraction module 2 is used to utilize the multi-channel electrical signals of the output biomimetic micro-motion sensing unit to mimic the information sharing and decision-making mechanism of coral polyps, perform real-time weighted fusion and noise suppression on the electrical signals of multiple probes, and extract the micro-motion feature patterns unique to leakage; distinguishing between normal operating vibrations and real leakage events. The sealing parameter adjustment module 3 is used to automatically adjust the sealing parameters of the tail shaft seal based on the generated micro-motion characteristic pattern and combined with the dynamic control strategy, according to the level and trend of the preset warning indicators, so as to form an adaptive control output.

[0044] In the above embodiments, this embodiment achieves intelligent monitoring and closed-loop control of ship stern shaft seal leakage through modular design. The sensing unit construction module provides high-sensitivity micro-disturbance detection capability and realizes response to minute changes in the fluid environment through biomimetic microstructure design; the feature pattern extraction module establishes a multi-source information fusion processing mechanism to effectively distinguish between real leakage signals and background noise interference; the sealing parameter adjustment module realizes closed-loop feedback control and dynamically optimizes the sealing working state according to leakage characteristics.

[0045] In summary, this embodiment achieves full-process automation from physical signal acquisition to control output, overcoming the limitations of traditional single-point detection. It establishes a distributed sensor network, forming an intelligent decision-making mechanism based on feature recognition, and achieving the adaptive adjustment function of the sealing system. This significantly improves the reliability and response speed of stern shaft seal condition monitoring, providing a new technical guarantee for the safe operation of marine power plants.

[0046] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0047] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; and a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer-executable instructions therein for performing the steps of various methods of embodiments of the present invention when executed by the processor.

[0048] The central processing unit / microprocessor / main control chip, etc., can include, but are not limited to, one or more processors or microprocessors.

[0049] Storage medium 5 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CDROM, DVDROM, Blu-ray disc, etc.).

[0050] In addition, the electronic device may also include (but is not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (e.g., keyboard, mouse, speaker, etc.).

[0051] The central processing unit / microprocessor / main control chip, etc. 4 can communicate with external devices (8, 9, etc.) via I / O bus 7 through wired or wireless network (not shown).

[0052] The storage medium 5 may also store at least one computer-executable instruction for performing the steps of various functions and / or methods in the embodiments described herein when the central processing unit / microprocessor / main control chip, etc., 4 is running.

[0053] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0054] Figure 7 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0055] like Figure 7 As shown, the non-transitory computer-readable storage medium 11 stores instructions, such as computer-readable instructions 10. When the computer-readable instructions 10 are executed by a processor, the various methods described above can be performed. The non-transitory computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0056] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0057] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0058] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0059] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods of the various embodiments of this invention through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0060] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A biomimetic sensing and control method for intelligent early warning of leakage of ship stern shaft seals using coral polyps, characterized in that, Includes the following steps: By utilizing the multi-channel electrical signals of the output biomimetic micro-motion sensing unit, mimicking the information sharing and decision-making mechanism of coral colonies, the electrical signals from multiple probes are weighted and fused in real time and noise suppressed to extract the micro-motion characteristic patterns unique to leaks; thus distinguishing between normal operating vibrations and real leak events.

2. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 1, characterized in that, The process of extracting the unique micro-motion feature patterns of a leak includes the following steps: The electrical signal is regarded as a distributed sensing group; based on the mechanism of local information exchange between individual corals through physical contact, the dynamic cross-correlation coefficient of each pair of probe signals in the time domain is calculated to form a real-time updated spatial correlation matrix; the spatial correlation matrix describes the distribution of the cooperative response intensity between probes caused by fluid disturbance events. The spatial correlation matrix is ​​used as a quantitative indicator of the degree of group consensus. The overall correlation strength between each probe and other probes in the spatial correlation matrix is ​​converted into the weight value of the probe signal in the fusion process. At the same time, the vibration noise generated during normal ship operation forms a background field in the circumferential direction of the entire tail shaft seal, and outputs a purified fusion signal that represents the group consensus. For the fused signal, dynamic features are extracted based on time windows to mimic the ability of coral reefs to recognize stimulus patterns, focusing on the morphological features of the fused signal waveform; the combination of morphological features constitutes the micro-motion characteristic pattern unique to leakage, which can be distinguished from the vibration of normal ship operation.

3. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 2, characterized in that, The process by which the combination of morphological features together constitutes the unique micro-motion characteristic pattern of a leak includes the following steps: Using the fusion signal representing group consensus, and taking the biological phenomena of response when a threat first appears in a coral reef as a model, the fusion signal is analyzed at multiple scales within a sliding time window. The parameters describing the morphology of the fusion signal waveform, such as the local undulation density, the amplitude ratio between adjacent undulations, and the duration distribution of undulation clusters, are extracted and together constitute a set of morphological indicators describing the local fine structure of the signal. Inspired by the characteristics of coral reefs forming spatial response patterns under continuous stimulation, time-varying indicators are mapped to evolutionary trajectories. The stability coefficient, slope of the change trend, and deviation parameters of the evolutionary trajectory from the background baseline within the time window are calculated. These parameters together constitute another set of dynamic indicators describing the global consistency and stability of the response. The morphological and dynamic indices are concatenated and fused, and then weighted and aggregated according to their contribution to the characterization of the leakage event to form a feature vector. The feature vector is the micro-motion characteristic pattern unique to leakage, and its inherent numerical combination and distribution are distinguishable from the signal patterns generated by vibrations during normal ship operation.

4. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 3, characterized in that, The process of forming a feature vector includes the following steps: Using morphological and kinetic index sets, and based on the mechanism by which each individual in a coral colony contributes weight based on the intensity of the stimulus it perceives and its location in the environment, a dynamic weight coefficient is assigned to each feature parameter in the morphological and kinetic index sets. Using dynamic weighting coefficients, all feature parameters are synthesized by multiplying their original values ​​by their weighting coefficients, forming a feature vector; Each dimension value in the vector is a fusion result weighted by contribution, which contains both local morphological anomaly information and global dynamic behavior anomaly information of the electrical signal. The weighted composite feature vector is used as the output, which is the micro-motion feature pattern unique to leakage. It is a comprehensive measure that embeds the relative importance relationship between features. Its overall numerical distribution pattern has an essential and distinguishable difference from the feature vector distribution pattern generated under normal ship operation vibration.

5. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 4, characterized in that, The process of assigning a dynamic weight coefficient to each feature parameter in the morphological and dynamic indices sets includes the following steps: Using historical data accumulated during long-term normal operation of ships, statistical learning is performed on each feature parameter in the morphological and dynamic indicator sets. Based on the collective memory of coral polyps of their normal environmental conditions, the mean and standard deviation of each feature parameter on the historical dataset are calculated, and a statistical baseline model describing the normal fluctuation range of each feature parameter is established. Using a statistical baseline model, the dynamic weighting coefficient of each feature parameter is calculated based on the degree of deviation of the individual coral polyp from the normal background, and is inversely proportional to the historical normal standard deviation of the feature parameter. A set of dynamic weight coefficients corresponding to feature parameters and dynamic weight coefficients is formed, which is an index set that quantifies the importance of each feature parameter in the leakage detection at the current moment.

6. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 5, characterized in that, The process of basing an individual coral's perception of stimulus intensity on its deviation from the normal background includes the following steps: Using the historical normal standard deviation of each feature parameter in the established statistical baseline model, the reciprocal of the historical normal standard deviation is used as the basis for calculating the dynamic weight coefficient. The basis for calculating the dynamic weight coefficients is input into a custom nonlinear transformation program to maintain the balance and robustness of the overall decision-making system. Through nonlinear mapping, a standardized dynamic weight coefficient is output for each feature parameter; The resulting dynamic weight coefficients are inversely proportional to the historical standard deviation of the feature parameters, quantifying the relative importance of each feature parameter in identifying leakage events at the current moment.

7. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 6, characterized in that, The nonlinear mapping process includes the following steps: The inverse of the historical normal standard deviation corresponding to each feature parameter is used as the input value; the input value is substituted into an exponential function with the natural constant e as the base for transformation, and the output value is constrained between zero and a positive upper limit value. The output value is linearly scaled to calibrate its output range to a preset weight value range; a standardized dynamic weight coefficient is output for each feature parameter. The resulting standardized dynamic weight coefficients.

8. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 1, characterized in that, It also includes a biomimetic micro-motion sensing unit constructed by simulating the microstructure dynamic response characteristics of coral tentacles, using flexible polymer materials and microelectromechanical systems; composed of multiple miniature tentacle-shaped probes, installed around the stern shaft seal of a ship, in contact with the fluid environment; when a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals.

9. The intelligent leakage early warning coral polyp biomimetic sensing control method for ship stern shaft seal as described in claim 1, characterized in that, It also includes a micro-motion characteristic pattern based on the generated data, combined with a dynamic control strategy, which automatically adjusts the sealing parameters of the tail shaft seal according to the level and trend of the preset warning indicators, forming an adaptive control output.

10. A biomimetic sensing control system for intelligent early warning of leakage from a ship's stern shaft seal, implementing the biomimetic sensing control method for intelligent early warning of leakage from a ship's stern shaft seal as described in any one of claims 1 to 9, characterized in that, include: The sensing unit construction module is used to construct a biomimetic micro-motion sensing unit by simulating the dynamic response characteristics of the microstructure of coral tentacles, using flexible polymer materials and microelectromechanical systems; it consists of multiple micro-tentacle-shaped probes, which are installed around the stern shaft seal of the ship and come into contact with the fluid environment; when a leak occurs, the fluid disturbance causes the probes to move slightly, generating corresponding changes in electrical signals; The feature pattern extraction module is used to utilize the multi-channel electrical signals of the output biomimetic micro-motion sensing unit to mimic the information sharing and decision-making mechanism of coral polyps, perform real-time weighted fusion and noise suppression on the electrical signals of multiple probes, and extract the micro-motion feature patterns unique to leakage; and distinguish between normal operating vibrations and real leakage events. The sealing parameter adjustment module is used to automatically adjust the sealing parameters of the tail shaft seal based on the generated micro-motion characteristic pattern and combined with the dynamic control strategy, according to the level and trend of the preset warning indicators, so as to form an adaptive control output.

Images