Wireless brake hose joint state monitoring system and method

Abstract

The invention relates to the technical field of brake system monitoring, and discloses a wireless brake hose connector state monitoring system and method. The system comprises a joint state monitoring terminal and a state characteristic analysis module. The joint state monitoring terminal obtains vibration spectrum parameters and sealing deformation parameters of the brake hose joint, determines working environment parameters based on the parameters, analyzes deformation scene characteristics, collects historical fault data, and generates an abnormal response label group in combination with the deformation scene characteristics and the historical fault data; the state characteristic analysis module is connected with the joint state monitoring terminal, dispatches the material fatigue data and the structure deformation data, analyzes physical deformation characterization corresponding to the material fatigue data, constructs a signal attenuation topology according to the structure deformation data, evaluates the characteristic coupling strength of the signal attenuation topology and the physical deformation characterization, and sends the characteristic coupling strength to the joint state monitoring terminal; a priority sequence of the abnormal response tag groups is determined based on the strength. The system can guarantee safe operation of the brake system.

Description

Technical Field

[0001] This invention relates to the field of brake system monitoring technology, specifically to a wireless brake hose connector status monitoring system and method. Background Technology

[0002] In the automotive, rail transportation, and industrial machinery industries, braking systems are a core component ensuring equipment safety, and their performance stability directly impacts the safety of personnel and equipment. Brake hose connectors, as key connecting parts in the braking system that transmit braking media and braking force, operate under complex conditions for extended periods. They must withstand the periodic pressure shocks generated during braking, as well as the effects of vibration, temperature changes, and media corrosion. With increasing equipment operating time, brake hose connectors are prone to problems such as decreased sealing performance and structural fatigue deformation. Failure to detect and address these issues promptly can lead to brake media leakage, delayed braking response, and in severe cases, even safety accidents. Current methods for monitoring the condition of brake hose joints mostly rely on periodic manual inspections or simple sensor data acquisition. Periodic manual inspections not only require interrupting normal equipment operation, increasing maintenance costs, but are also limited by the experience of the inspectors and the accuracy of the inspection tools, making it difficult to comprehensively capture subtle changes in the joint's condition under dynamic operating conditions, easily overlooking potential faults. Simple sensor data acquisition methods typically only obtain single parameter information, such as pressure and temperature, and cannot achieve comprehensive monitoring of multiple key parameters such as vibration spectrum and seal deformation. Furthermore, existing monitoring technologies lack effective utilization of historical fault data and cannot perform correlation analysis with the current deformation characteristics of the joint, making it difficult to accurately determine the fault type and development trend, resulting in insufficient accuracy and timeliness of fault warnings. In addition, when analyzing multi-dimensional monitoring data, existing technologies cannot effectively assess the intrinsic correlation between material fatigue data and structural deformation data, making it difficult to determine the priority of different abnormal states. This makes it difficult for maintenance personnel to quickly focus on key issues when faced with multiple abnormal signals, affecting fault handling efficiency. With the continuous improvement of equipment automation and intelligence, higher requirements are placed on the real-time performance, accuracy, and intelligence of brake system status monitoring. Existing monitoring technologies can no longer meet the needs of comprehensive monitoring and accurate early warning of brake hose joint status under complex operating conditions. There is an urgent need for a monitoring system that can achieve comprehensive monitoring of multi-dimensional parameters, intelligent analysis combining historical data and scene characteristics, and determination of anomaly priorities, in order to improve the effectiveness of brake hose joint status monitoring and ensure the safe and stable operation of the brake system. Summary of the Invention

[0003] The purpose of this invention is to provide a wireless brake hose connector status monitoring system to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides a wireless brake hose connector status monitoring system, the system comprising: A joint status monitoring terminal is used to acquire the vibration spectrum parameters and sealing deformation parameters of the brake hose joint, determine the working environment parameters of the brake hose joint based on the vibration spectrum parameters and the sealing deformation parameters, analyze the deformation scene characteristics of the brake hose joint based on the working environment parameters, collect historical fault data of the brake hose joint, and generate an abnormal response tag group of the brake hose joint by combining the deformation scene characteristics and the historical fault data. The state feature analysis module, connected to the joint state monitoring terminal, is used to schedule the material fatigue data and structural deformation data of the brake hose joint, analyze the physical deformation characterization corresponding to the material fatigue data, construct the signal attenuation topology of the brake hose joint based on the structural deformation data, evaluate the feature coupling strength between the signal attenuation topology and the physical deformation characterization, and determine the priority sequence of the abnormal response label group based on the feature coupling strength.

[0005] Preferably, the state feature analysis module includes: The deformation feature extraction unit is used to perform feature decomposition on the abnormal response label group to obtain a set of deformation feature factors. The fault classification unit is used to classify the historical fault data and generate a fault type distribution set. The correlation analysis unit is used to calculate the correlation mapping relationship between the set of deformation feature factors and the set of fault type distributions, and based on the correlation mapping relationship, to determine the key deformation features and key fault types of the brake hose connector. The constraint generation unit is used to analyze the monitoring constraints of the brake hose connector based on the key deformation features and the key fault types, and to generate the core monitoring parameters of the brake hose connector based on the monitoring constraints.

[0006] Preferably, the state feature analysis module further includes: The spatial topology optimization unit is used to receive power grid topology data, extract spatial topology features from the power grid topology data, and generate a spatial topology feature encoding matrix. The coupling enhancement unit is used to map the priority sequence to the topological space of the spatial topological feature encoding matrix to generate an optimized priority sequence.

[0007] Preferred, including: The material matching module is used to query the reference sealing material and candidate sealing material of the brake hose connector, and to perform virtual assembly of the brake hose connector by combining the reference sealing material and the candidate sealing material to generate a connector simulation prototype; The assembly testing module is used to collect sealing performance test data and pressure cycle data of the joint simulation prototype, and to analyze the sealing failure characteristics of the joint simulation prototype based on the sealing performance test data.

[0008] Preferably, the assembly testing module includes: The life assessment unit is used to calculate the life prediction equivalent value of the joint simulation prototype based on the pressure cycle data, and to assess the performance degradation of the joint simulation prototype based on the life prediction equivalent value. The spatial adaptation unit is used to determine the assembly position and operating temperature limits of the brake hose connector in the braking system, collect the spatial compatibility parameters of the connector simulation prototype, and calculate the connector spatial adaptability of the connector simulation prototype by combining the assembly position limits, the operating temperature limits and the spatial compatibility parameters.

[0009] Preferably, the system further includes: The fusion processing module is used to perform spatial isomorphic processing on the optimized priority sequence and the connector spatial fit, and generate an optimized connector spatial fit. The cascaded processing unit is used to cascade the sealing failure characteristics, the performance degradation degree, and the optimized joint space fit to generate multi-source fusion monitoring features.

[0010] Preferably, the system further includes: A material selection module is used to select a target sealing material from the benchmark sealing material and the candidate sealing materials based on the multi-source fusion monitoring characteristics; The strategy generation module is used to generate a real-time monitoring strategy for the brake hose connector based on the core monitoring parameters, the optimized priority sequence, and the target sealing material.

[0011] Preferably, the system further includes: The release hysteresis analysis module is used to extract the pressure maintenance duration and deformation recovery time of the tail seal in the brake hose channel during a continuous working cycle, calculate the time difference with the rated pressure release point, and generate seal release hysteresis information. The time period configuration unit is used to filter the channel numbers that have not completed pressure release based on the seal release lag information, and generate a variable pressure control time period table by sorting the channel seals according to their waiting time.

[0012] Preferably, the system further includes: The acceleration response module is used to call the variable pressure control time period table, detect the deformation distance distribution of the seal queue in the real-time cycle, and identify the continuous deformation acceleration time points of adjacent seals. The instruction generation module is used to generate a sealing state control instruction when the continuous deformation acceleration time points are all earlier than the pressure control period preparation switching point.

[0013] Preferably, the present invention also includes a method for monitoring the status of a wireless brake hose connector, comprising all the modules and method flow of the aforementioned wireless brake hose connector status monitoring system.

[0014] Compared with the prior art, the beneficial effects of the present invention are: This wireless brake hose connector status monitoring system comprehensively acquires vibration spectrum parameters and sealing deformation parameters of brake hose connectors through a connector status monitoring terminal. This overcomes the limitations of traditional monitoring technologies that can only collect single parameters, providing a more comprehensive reflection of the connector's true state under dynamic operating conditions. Based on these multi-dimensional parameters, the system determines the working environment parameters and further analyzes deformation scene characteristics. This allows the judgment of the brake hose connector's state to no longer rely on single data points, but rather combine its actual operating environment and deformation performance, better reflecting the connector's actual working conditions and helping to more accurately identify potential anomalies. Simultaneously, the terminal also collects historical fault data and combines it with deformation scene characteristics to generate anomaly response tag groups. This fully utilizes the fault patterns contained in historical data, enabling the association of the current state with past fault cases. This not only enriches the basis for anomaly judgment but also more accurately classifies the possible fault types corresponding to the current anomaly, providing more comprehensive information support for subsequent fault analysis. The inclusion of a state characteristic analysis module further enhances the system's intelligent analysis capabilities. This module processes material fatigue and structural deformation data from brake hose joints, analyzing the physical deformation characteristics corresponding to the material fatigue data. This allows for an understanding of the underlying causes of joint state changes from a material property perspective, avoiding potential biases from relying solely on surface parameters. Constructing a signal attenuation topology based on structural deformation data visually presents the impact of structural deformation on signal transmission, clearly reflecting the correlation between structural state and signal characteristics. By evaluating the characteristic coupling strength between the signal attenuation topology and physical deformation characteristics, the intrinsic connection between the two key factors of material fatigue and structural deformation can be deeply explored, clarifying the degree of influence of different factors on abnormal joint states. Based on this characteristic coupling strength, a priority sequence for abnormal response tag groups is determined. This enables maintenance personnel to quickly understand the urgency and importance of different abnormal states when faced with multiple abnormal tags, eliminating the need to analyze complex abnormal information one by one. They can directly focus on the more impactful and critical abnormal issues, significantly improving the targeting and efficiency of fault handling. This system achieves intelligent processing throughout the entire process, from parameter acquisition and scenario analysis to anomaly priority ranking, overcoming the limitations of traditional manual inspection and simple data collection. In practical applications, it eliminates the need for frequent equipment interruptions for manual inspection, reducing maintenance costs and avoiding potential omissions and errors associated with manual inspection. Through comprehensive monitoring and correlation analysis of multi-dimensional parameters, it can detect potential faults in brake hose joints earlier, providing more sufficient evidence for fault warnings and facilitating proactive maintenance measures to prevent further escalation and more serious safety accidents. Furthermore, the system's clear prioritization of anomalies allows for more rational allocation of maintenance resources, concentrating limited maintenance efforts on critical issues, further improving the efficiency and quality of maintenance work, and ultimately providing stronger guarantees for the safe and stable operation of the braking system. It is applicable to the monitoring needs of brake hose joint status in various fields such as automobiles, rail transportation, and industrial machinery, and has broad application value. Attached Figure Description

[0015] Figure 1 This is a timing diagram of the wireless brake hose connector status monitoring system described in this invention. Figure 2 A flowchart detailing the state feature analysis module; Figure 3 A flowchart illustrating the process of material matching and assembly testing; Figure 4 This is a flowchart illustrating the process of fusion processing and cascading processing. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 This invention provides a wireless brake hose connector status monitoring system and method, the system comprising: The system includes a joint condition monitoring terminal and a condition feature analysis module. The joint condition monitoring terminal acquires vibration spectrum parameters and sealing deformation parameters of the brake hose joint through built-in vibration and deformation sensors. Vibration spectrum parameters are analyzed to extract characteristic frequency amplitudes, while sealing deformation parameters are acquired through a microscopic deformation measurement unit. Based on the vibration spectrum parameters and sealing deformation parameters, an environmental parameter analysis algorithm calculates working environment parameters, including temperature gradient, pressure fluctuation range, and mechanical stress distribution. Based on the working environment parameters, a scene feature extraction model analyzes deformation scene characteristics, including high-frequency vibration scenes, steady-state pressure scenes, and transient impact scenes. Simultaneously, historical fault data of the brake hose joint is collected from the system database, including sealing failure records, material fatigue crack data, and connection loosening events. Combining deformation scene characteristics and historical fault data, an anomaly tag generation algorithm generates anomaly response tag groups, including high-frequency vibration anomaly tags, sealing deformation exceeding limits tags, and connection stability tags.

[0018] The condition feature analysis module connects to the joint condition monitoring terminal and schedules material fatigue data and structural deformation data of the brake hose joint through a data interface. Material fatigue data includes the stress-life curve and creep characteristic parameters of the joint material, while structural deformation data includes the geometric deformation vector and strain distribution matrix of the joint. The module analyzes the physical deformation characterization corresponding to the material fatigue data and calculates the cumulative plastic deformation of the material under cyclic loading using a constitutive model. Based on the structural deformation data, a signal attenuation topology is constructed, and graph theory is used to represent the signal transmission path and attenuation coefficient of each monitoring point in the joint. The characteristic coupling strength between the signal attenuation topology and the physical deformation characterization is evaluated, and the correlation coefficient between the deformation of the topology nodes and the signal attenuation is calculated using a coupling analysis algorithm. Based on the characteristic coupling strength, a priority ranking algorithm is used to determine the priority sequence of abnormal response label groups, with abnormal labels with higher coupling strength being processed first.

[0019] Example 1: See Figure 2 The state feature analysis module consists of a deformation feature extraction unit, a fault classification unit, a correlation analysis unit, a constraint generation unit, a spatial topology optimization unit, and a coupling enhancement unit. These units work together to perform in-depth processing and analysis on data from the joint condition monitoring terminal to extract key features, identify fault modes, optimize monitoring priorities, and ultimately improve the decision-making capabilities of the entire monitoring system.

[0020] The deformation feature extraction unit receives anomaly response tag set generated by the joint condition monitoring terminal. This tag set contains anomaly indications in multiple dimensions, such as high-frequency vibration anomaly tags, seal deformation exceeding limits tags, and connection stability tags. The unit first performs standardization preprocessing on these tags to eliminate dimensional differences. Subsequently, it employs feature decomposition technology, specifically principal component analysis, to extract a core set of deformation feature factors from the original tag data. This process transforms high-dimensional, potentially redundant anomaly tag information into low-dimensional feature factors with clear physical meaning. For example, the high-frequency vibration factor represents the degree of vibration energy concentration of the joint within a specific frequency band; the seal deformation gradient factor describes the deformation rate and spatial distribution characteristics of the sealing structure under pressure; and the connection stability factor quantifies the displacement and stress fluctuations of the joint connection points under different operating conditions. These factors together constitute the core feature set describing the health status of the joint.

[0021] The fault classification unit operates in parallel, processing historical fault data accumulated over a long period in the system database. This data contains detailed records of various fault events that have occurred in the brake hose connector, such as seal ring rupture, connector thread wear, and material fatigue cracking. The unit employs an unsupervised clustering algorithm to classify this historical data. Based on attributes such as the fault's manifestation, occurrence conditions, and severity of consequences, the algorithm automatically categorizes similar fault events, thereby generating a structured fault type distribution set. This set may include categories such as "Seal Failure," which is further subdivided into O-ring extrusion failure and lip seal overturning; "Material Fatigue," including creep fracture and stress corrosion; and "Structural Loosening," such as thread loosening and clamp failure. This distribution set systematically summarizes the possible fault modes of the connector.

[0022] The correlation analysis unit acts as a bridge connecting deformation features and fault types. This unit receives a set of deformation feature factors from the deformation feature extraction unit and a set of fault type distributions from the fault classification unit. Its core task is to calculate the quantitative correlation between the two. By executing a correlation analysis algorithm, the statistical correlation strength between each deformation feature factor and each fault type is calculated, generating a correlation mapping matrix. This matrix clearly reveals the intrinsic connection between deformation patterns and specific fault types. Based on this mapping, the unit further employs a feature selection algorithm to identify those features most strongly correlated with high-occurrence or high-severity fault types from all deformation features, defining them as key deformation features. Simultaneously, fault types most closely correlated with key deformation features are identified as critical fault types requiring focused attention. For example, the analysis might reveal a high correlation between high-frequency vibration factors and material fatigue faults, while the sealing deformation gradient factor is strongly correlated with sealing failure faults; these are thus identified as objects requiring focused attention in current monitoring.

[0023] The constraint generation unit receives key deformation characteristics and key fault types as input. The core function of this unit is to parse out the monitoring conditions that must be met to effectively capture these key characteristics and prevent these key faults. For example, to accurately capture high-frequency vibration factors, a minimum sampling frequency limit for vibration monitoring needs to be specified; to effectively monitor the seal deformation gradient, a threshold range for deformation monitoring needs to be set; considering the attenuation characteristics of the signal transmission in the joint structure, a tolerance range for signal attenuation also needs to be defined. All these conditions together constitute the monitoring constraints for the brake hose joint. Finally, based on these constraints, the unit derives and generates a set of core monitoring parameters that can directly guide sensor configuration and data acquisition through a parametric optimization algorithm, clearly defining the vibration monitoring bandwidth, deformation monitoring accuracy requirements, and minimum signal transmission strength required by the monitoring system.

[0024] The spatial topology optimization unit expands the analytical perspective from the connector itself to the larger system environment in which it resides, particularly the power grid topology. This unit receives power grid topology data describing the connectivity of the entire monitoring network, including the location information of all monitoring nodes and the data transmission paths between them. The unit performs deep processing on this topology data, using graph coding algorithms to extract its inherent spatial topology features, such as the number of connections per node (node ​​degree), the average path length of data packets transmitted between nodes, and network redundancy. These features are then encoded into a spatial topology feature coding matrix. This matrix abstractly represents the connectivity health and communication efficiency of the entire monitoring network.

[0025] The coupling enhancement unit maps and fuses the priority sequence of the anomaly response tag groups initially generated by the state feature analysis module with the network topology space described by the spatial topology feature encoding matrix. Through a spatial mapping algorithm, the processing priority of each anomaly tag is correlated with the importance of nodes and link reliability on its data transmission path. For example, an anomaly tag with initially high priority may have its processing priority adjusted if its data needs to be transmitted through an overloaded or unstable network node to avoid critical data loss due to network congestion. This process generates an optimized priority sequence that is optimized for network environment factors and better reflects the actual system operation, providing a more accurate basis for subsequent resource scheduling and instruction generation.

[0026] Example 2: See Figure 3This involves the collaborative operation of the material matching module and the assembly testing module. The core task of these two modules is to conduct a forward-looking evaluation of the sealing performance of brake hose connectors through material comparison and assembly simulation in a virtual environment. When the material matching module starts working, it accesses a pre-built material database. This database systematically stores data files of various sealing materials that can be used for brake hose connectors, including benchmark sealing materials defined as performance standards, and several candidate sealing materials to be evaluated. Each material file details the material's mechanical properties, such as elastic modulus, tensile strength, compression set, and hardness; chemical properties, such as resistance to hydraulic oil, brake fluid, ozone, and high and low temperatures; and physical properties, such as coefficient of friction and coefficient of thermal expansion. The module queries and retrieves these material datasets from the database based on the current connector's design specifications and application conditions.

[0027] The module enters the virtual assembly stage, using the acquired parameter sets of the baseline and candidate sealing materials to construct a precise digital twin model of the brake hose connector in a computer-aided engineering environment. This model not only includes the connector's metal structural components, such as the connector core, nut, and sleeve, but also meticulously includes the geometry and material properties of the seals (such as O-rings and gaskets). Using finite element analysis software, the module virtually "assembles" seals of different materials into the connector model, applying realistic assembly preload and working boundary conditions. This process generates an independent connector simulation prototype for each evaluated sealing material, incorporating its unique material properties. Each prototype fully reflects the contact relationships, stress distribution, and potential micro-deformation of the connector components under those material properties.

[0028] The assembly and testing module is responsible for performing a series of virtual performance tests on these generated joint simulation prototypes. This module first collects sealing performance data. It simulates the flow of high-pressure brake fluid inside the joint by performing computational fluid dynamics simulations. During the simulation, the system precisely applies cyclic loads at the working pressure and monitors the fluid leakage path and rate at the sealing contact interface. Simultaneously, the simulation calculations also output the magnitude and distribution cloud map of the sealing contact pressure, a key indicator for evaluating seal effectiveness. Sufficiently high and uniformly distributed contact pressure is essential to ensure seal reliability; any area with excessively low local pressure could become a potential leak point. Based on this sealing performance data, the module further analyzes the sealing failure characteristics of each joint simulation prototype. Using failure mode and effects analysis (FMEA), it identifies the most likely locations and forms of seal failure under different pressure levels and temperature conditions. For example, the analysis might reveal that a certain candidate material experiences a decrease in elasticity at low temperatures, leading to a significant reduction in contact pressure and instantaneous leakage under pressure shock; while another material might undergo excessive creep deformation at high temperatures, resulting in permanent compression deformation and loss of resilience, thus failing to restore a sealed state after pressure unloading.

[0029] The assembly testing module also collects pressure cycle data, simulating the repeated pressurization and depressurization processes experienced by the braking system in actual operation. The module applies tens of thousands, even millions, of pressure cycle loads to the simulated joint prototype, with the load amplitude and frequency set according to actual driving conditions. Throughout the pressure cycle simulation, the system continuously monitors and records the changes in sealing contact pressure, the strain response of the seal, and any possible stress relaxation phenomena. This pressure cycle data is crucial, as it records the dynamic response and evolution trend of the joint's sealing performance under long-term alternating loads, providing raw data for predicting the joint's durability and reliability.

[0030] The material matching module transforms material properties into concrete, quantifiable structural models through virtual assembly, while the assembly testing module reveals the performance and potential defects of these models under simulated real-world conditions through rigorous simulation testing. This process avoids the high costs and long cycles of the traditional "design-prototype-testing" cycle, enabling in-depth, data-driven comparisons and analyses of the sealing performance and failure risks of various material options before physical prototype manufacturing. The output sealing performance test data, pressure cycle data, and sealing failure characteristic analysis results provide a solid and detailed basis for subsequent material selection and joint design optimization, significantly improving the relevance and efficiency of the development process.

[0031] Example 3: Focusing on the detailed operation of the life assessment unit and the spatial adaptation unit in the assembly testing module, these two units jointly complete the durability prediction and system integration compatibility assessment of the simulated joint prototype generated by the virtual assembly. The entire process is driven by simulation data, quantitatively analyzing the performance evolution of the joint under long-term service environment and its matching degree with the braking system. The core task of the life assessment unit is to predict the service life trend of the simulated joint prototype based on the pressure cycle data collected by the assembly testing module. The pressure cycle data comes from dynamic load simulation, which accurately reproduces the periodic pressure load experienced by the braking system during actual operation. The data records the complete history of the pressure applied to the joint sealing interface over time throughout the entire simulation cycle, i.e., the pressure-time curve. At the same time, the simulation also records the stress and strain response data of key parts of the seal (such as the O-ring lip contact area and the gasket compression area). The unit first extracts the characteristic parameters of each pressure cycle from these data, including peak pressure, valley pressure, pressure holding time, pressure increase rate, and pressure decrease rate. Among these, the most critical is to calculate the alternating stress amplitude borne by the sealing material in each cycle. The stress amplitude reflects the mechanical fatigue strength of the material under cyclic loading. The element then inputs these cyclic characteristic parameters into a life prediction model based on the theory of material fatigue damage accumulation. This model considers the material's SN curve (stress-life curve) characteristics, mean stress effect, and possible nonlinear damage accumulation behavior. The core calculation process of the model involves integrating and summing the minute damage caused by each cycle, ultimately outputting a quantitative index characterizing the overall durability of the joint—the life prediction equivalent value. This equivalent value is not an absolute life hour, but a relative value or equivalent cycle number, used for horizontal comparison of the durability of different materials or design schemes. Its calculation formula can be expressed as: ; in: Lifetime prediction equivalent value (dimensionless or equivalent cycle number). : The amplitude of alternating stress (in MPa) borne by critical parts of the sealing material during each pressure cycle. The fatigue strength coefficient (unit: MPa) of a material under a specific mean stress is obtained by fitting material fatigue test data. The fatigue index of a material reflects its sensitivity to alternating stress amplitude and is also determined by experimental data. The total number of pressure cycles in the simulation. : The derivative of the number of iterations.

[0032] Based on the calculated lifetime prediction equivalent value, the unit further evaluates the performance degradation rate of the simulated joint prototype. Performance degradation rate is an indicator reflecting the decreasing trend of sealing performance with increasing cycle count. The unit analyzes the curves of sealing performance parameters recorded in the pressure cycling data as a function of cycle count. Combining the lifetime prediction equivalent value, the rate or gradient of the sealing performance degradation from the initial state to a certain critical failure level is quantified using a degradation rate calculation algorithm. The performance degradation rate is ultimately expressed as a numerical value, the magnitude of which directly reflects the strength of the joint's ability to maintain sealing performance after long-term use; a larger value indicates a faster performance degradation.

[0033] The spatial adaptation unit focuses on evaluating the physical integration feasibility and environmental adaptability of the connector prototype in a real braking system. This unit first needs to clarify the specific assembly location and operating temperature limits of the brake hose connector within the target braking system. Assembly location limits are obtained from the 3D design model or installation specifications of the braking system, detailing geometric constraints such as the maximum allowable length of the connector installation space, the minimum allowable bending radius, interference distances from surrounding components, and spatial angle requirements for the connection ports. Operating temperature limits describe the minimum ambient temperature, maximum fluid temperature, and temperature variation range that the connector may experience under extreme operating conditions.

[0034] The unit then collects spatial compatibility parameters from the joint simulation prototype. These parameters describe the joint's geometric tolerance range and the thermophysical properties of the materials. The spatial compatibility parameters are derived from the joint's design drawings and material database.

[0035] The core calculation of the spatial adaptation unit combines the three sets of inputs mentioned above: assembly position constraints, operating temperature constraints, and spatial compatibility parameters, to calculate the spatial adaptation degree of the joint simulation prototype. This calculation is a multi-factor comprehensive evaluation process. Geometric fit calculation: The dimensional parameters of the simulated joint prototype are compared with the spatial constraints defined by the assembly position. For example, it calculates whether the maximum possible length of the joint within the tolerance range is less than the maximum allowable length of the installation space; and whether the minimum possible bending radius of the joint within the tolerance range is greater than the minimum bending radius required by the system. It assesses whether there are potential geometric interference risks. Based on the degree to which all geometric constraints are met, a geometric fit score is calculated.

[0036] Thermal compatibility calculation: This focuses on the compatibility of thermal deformation under the operating temperature limit. Based on the material's coefficient of thermal expansion and the temperature range specified in the operating temperature limit, the theoretical dimensional changes of the joint in the cold (minimum temperature) and hot (maximum temperature) states are calculated. This dimensional change is then compared with the thermal expansion gap or dynamic tolerance range specified in the assembly position. Simultaneously, it assesses whether the changes in the hardness, elastic modulus, and other properties of the joint material (especially the seal) remain within acceptable limits under extreme temperatures, ensuring the sealing function. Based on the compatibility assessment results of thermal deformation and material property changes, a thermal compatibility score is calculated.

[0037] Comprehensive fit calculation: The geometric matching score and thermal matching score are weighted and fused according to predefined weights (reflecting the relative importance of geometric and thermal factors to overall fit) to generate a comprehensive joint spatial fit index. This index is a normalized value (e.g., between 0 and 1). The higher the value, the stronger the physical integration and environmental adaptability of the joint simulation prototype in the target braking system, and the lower the risk of installation difficulties, spatial interference, or thermal failure.

[0038] Example 4: See Figure 4This involves the collaborative operation of a fusion processing module, a cascaded processing unit, a material screening module, and a strategy generation module. These modules work together to fuse, analyze, and make decisions based on the multi-dimensional data generated in the early stages, ultimately generating a customized real-time monitoring strategy for brake hose connectors. The fusion processing module first receives an optimized priority sequence from the state feature analysis module and connector spatial fit from the assembly testing module. The optimized priority sequence is a list of anomaly label processing orders adjusted by network topology weights; for example, its content might be: [Label ID: A007, Priority: 0.95], [Label ID: B212, Priority: 0.88], [Label ID: C041, Priority: 0.82]... The connector spatial fit is a scalar value, such as 0.87, representing the degree of physical compatibility between the connector prototype and the braking system. The module's task is to perform spatial isomorphic processing on these two heterogeneous data sets, aiming to dynamically weight the independent indicator of spatial fit according to the urgency (priority) of anomaly processing, making it more reflective of the adaptation requirements under the current system state. This processing is implemented using a spatial mapping algorithm. The algorithm maps each label in the optimized priority sequence to a virtual "attention" spatial dimension, with higher-priority labels receiving greater weights in that spatial dimension. Simultaneously, the connector spatial fit is projected onto this multi-dimensional space composed of multiple label priority weights, and its calculation is adjusted based on the weights of each dimension. The output is no longer a single scalar, but an optimized connector spatial fit associated with the current anomalous state. For example, if the current high-frequency vibration anomaly (label A007) has the highest priority, and this anomaly is related to the vibration amplification effect of the connector in a confined space, the algorithm might appropriately lower the spatial fit score in this scenario to highlight this risk, potentially resulting in an optimized value of 0.84.

[0039] The cascaded processing unit then performs feature cascading operations. It receives sealing failure characteristics and performance degradation from the assembly test module, and optimized joint space fit from the fusion processing module. The sealing failure characteristics are a set of descriptive data detailing the failure modes, critical pressure thresholds, and failure location coordinates exhibited by the joint in the simulation. The performance degradation is a numerical value quantifying the rate of decrease in sealing performance with each pressure cycle. The optimized joint space fit is another adjusted numerical value. The unit's task is to fuse these three feature vectors from different sources and with varying properties into a unified multi-dimensional feature vector—the multi-source fusion monitoring feature. This process is not a simple data concatenation; instead, each feature is first standardized and normalized to eliminate differences in dimensions and numerical ranges. Subsequently, a feature fusion algorithm is used to assign appropriate weights to different types of features and combine them according to the data structure into a new, high-dimensional feature vector. This multi-source fusion monitoring feature vector comprehensively characterizes the sealing performance reliability, long-term durability, and integration adaptability with the vehicle environment of the joint prototype, providing a comprehensive data view for subsequent final decisions.

[0040] The material selection module operates based on multi-source fusion monitoring features generated by the cascaded processing unit. The core task of this module is to select the target sealing material with the best overall performance from a pre-determined benchmark sealing material and several candidate sealing materials. The module has a pre-set set of multi-objective decision rules, which define how to evaluate the quality of materials based on the various components of the multi-source fusion monitoring features. For example, the rules may assign a high weight to the critical pressure threshold in the sealing failure characteristics, while also considering the numerical value of performance degradation and the optimized joint space fit. The module inputs the multi-source fusion monitoring features corresponding to each material into this decision rule for evaluation and scoring, as shown in Table 1.

[0041] Table 1: Summary of evaluation of candidate sealing materials

[0042]

[0043] The module iterates through all candidate materials, calculates the comprehensive score for each material, and finally selects the material with the highest comprehensive score as the target sealing material. For example, based on the simulation data in the table above, candidate material C (M-89) is selected as the target sealing material because of its excellent resistance to attenuation and spatial adaptability, although its critical pressure threshold is slightly lower than that of material A, it has the highest comprehensive score.

[0044] The strategy generation module is the final output of the entire process. It receives three key inputs: core monitoring parameters determined by the state characteristic analysis module, an optimized priority sequence, and the target sealing material selected by the material selection module. The module's task is to integrate this information to generate an executable, personalized real-time monitoring strategy. This strategy is a structured document or configuration file covering multiple aspects. In the monitoring parameter configuration section, the strategy specifies in detail the sensor sampling frequency, data filtering parameters, and alarm thresholds for each monitoring parameter for this specific joint (these thresholds are fine-tuned based on material characteristics such as fatigue limits and creep properties). In the anomaly handling process section, the strategy directly defines the response mechanisms and processing order for different levels of anomalies based on the optimized priority sequence, clarifying which anomalies require immediate alarms, which require recording and observation, and the corresponding diagnostic command flow. In the maintenance plan section, the strategy, considering the characteristics of the target sealing material (such as its expected aging cycle and sensitivity to specific contaminants), recommends preventative maintenance inspection cycles and key inspection items. The final real-time monitoring strategy is a highly customized solution that ensures that the resource allocation and response logic of the monitoring system are closely matched with the actual material properties and operational risks of the joint, thereby improving the accuracy and efficiency of monitoring.

[0045] Example 5: When the release hysteresis analysis module starts working, it first monitors the hose channel within the braking system for a continuous working cycle. This module uses pressure sensor arrays and deformation sensor arrays deployed at key locations in the channel to collect real-time dynamic data of the tail seal during the braking cycle. Within a single working cycle, the module accurately records the time points and corresponding physical states of the braking pressure application phase, pressure maintenance phase, and pressure release phase. The pressure release phase is of particular focus: the module extracts the pressure maintenance duration data of the tail seal during the process from the start of pressure decrease to complete unloading. This duration reflects the time required for the pressure to drop from the rated value to below the safety threshold. Simultaneously, the module captures the deformation recovery behavior of the seal after pressure unloading using high-precision deformation sensors, identifying and recording its deformation recovery time point, i.e., the precise moment when the seal recovers from a compressed deformation state to a free state (or near-free state). The core calculation of the module lies in comparing the time difference between the deformation recovery time point and the rated pressure release point set by the system. The rated pressure release point is a preset theoretical time point, representing the moment when the seal should complete deformation recovery under ideal, hysteresis-free conditions. By calculating the time difference between the actual deformation recovery time and the rated pressure release point within each working cycle, the module generates seal release hysteresis information. This information includes two key quantitative indicators: hysteresis duration, i.e., the specific time length by which the actual recovery time lags behind the rated release point; and recovery delay, i.e., the degree of delay relative to the rated recovery rate. This information clearly reveals the delay characteristics of the tail seal of a specific channel in its pressure release response.

[0046] The time-slot configuration unit performs subsequent processing based on the seal release hysteresis information provided by the release hysteresis analysis module. The core task of this unit is to identify channels in the system with a risk of incomplete pressure release. It analyzes the hysteresis duration and recovery delay in the seal release hysteresis information and sets a judgment threshold. For channels with a hysteresis duration exceeding this threshold or an abnormal recovery delay, the unit determines that there is a risk of incomplete pressure release, meaning the pressure from the previous braking cycle was not fully released in time, which may affect the response of the next braking cycle or lead to increased fatigue of the seal. The unit filters out all channel numbers that meet this condition, forming a list of channels to be processed. Subsequently, the unit sorts these risky channels. The sorting is based on the waiting time of each channel's seal, i.e., the length of time the seal has been in a "waiting for complete release" state from the rated pressure release point to the current moment. The longer the waiting time, the higher the risk of residual pressure in the channel, requiring priority intervention. Based on this sorting result, the unit generates a variable pressure control time slot table. This time slot table is a structured time series plan that allocates a pressure control time window for each channel with a risk of release hysteresis. For example, the seal with the longest waiting time in channel CH-05 is scheduled for adjustment in the earliest time slot before the start of the next braking cycle; while channel CH-12, with a shorter waiting time, is scheduled for a slightly later time slot. The time slot schedule specifies in detail the start time and duration of pressure regulation operations for each channel.

[0047] The accelerated response module is activated during the system's real-time operating cycle. This module uses the variable pressure control time schedule generated by the time-slot configuration unit as its base plan. Its core function is to monitor the actual physical state changes of all seals in the control queue during the current real-time cycle. It detects and acquires the deformation distance data of each seal in real time through a network of deformation sensors distributed around the seal queue. Deformation distance refers to the displacement of a seal relative to its free state (or reference position). The module analyzes this real-time deformation distance data to calculate the deformation distance distribution of the entire seal queue, such as the deformation differences between adjacent seals and the changing trend of the deformation gradient. Based on continuous deformation distance time-series data, the module uses time-series analysis techniques to identify whether there is an accelerated phenomenon in the deformation state changes between adjacent seals. Specifically, it detects whether the deformation recovery rate of adjacent seals shows a synchronous and significant increase at a specific time point; this time point is called the continuous deformation acceleration time point. This time point marks the beginning of the collective accelerated deformation recovery of the seal queue, indicating that the pressure release process may be entering an accelerated phase.

[0048] The instruction generation module continuously receives identification results from the acceleration response module, namely, continuous deformation acceleration time point data, and compares them with the preset pressure control period preparation switching point for each channel in the variable pressure control period table. The pressure control period preparation switching point is a preparation moment set in the period table before the planned start time for performing pressure control operation on that channel. The judgment logic of the instruction generation module is: if, during real-time operation, the identified continuous deformation acceleration time points for a certain channel (or a group of channels) are all earlier than the pressure control period preparation switching point assigned to it by the period table, this indicates that the seal queue itself has begun to accelerate recovery, and its actual recovery process is faster than the preset control plan. In this case, the module determines that it can follow this natural acceleration trend and advance or adjust the control action. Therefore, the module generates a seal state control instruction. This instruction contains specific control parameters, such as: adjusting the pressure release rate curve of the channel to match the detected deformation acceleration trend; or fine-tuning the initial pressure setpoint of the channel in subsequent braking cycles to compensate for possible residual pressure effects; or even including coordinated control parameters for adjacent channels to optimize the pressure balance of the entire pipeline system. Commands are sent to the corresponding actuators, such as proportional pressure valves or dedicated deformation compensation devices, via the system control bus to achieve dynamic and responsive control of the seal's condition. The entire implementation process establishes a closed loop of perception-analysis-decision-execution. By accurately monitoring the seal's release hysteresis characteristics and actively responding to the natural recovery acceleration trend, the timing and parameters of pressure regulation are dynamically optimized, aiming to improve the seal's operational reliability and extend its service life.

[0049] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0050] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A wireless brake hose connector status monitoring system, characterized in that, include: A joint status monitoring terminal is used to acquire the vibration spectrum parameters and sealing deformation parameters of the brake hose joint, determine the working environment parameters of the brake hose joint based on the vibration spectrum parameters and the sealing deformation parameters, analyze the deformation scene characteristics of the brake hose joint based on the working environment parameters, collect historical fault data of the brake hose joint, and generate an abnormal response tag group of the brake hose joint by combining the deformation scene characteristics and the historical fault data. The state feature analysis module, connected to the joint state monitoring terminal, is used to schedule the material fatigue data and structural deformation data of the brake hose joint, analyze the physical deformation characterization corresponding to the material fatigue data, construct the signal attenuation topology of the brake hose joint based on the structural deformation data, evaluate the feature coupling strength between the signal attenuation topology and the physical deformation characterization, and determine the priority sequence of the abnormal response label group based on the feature coupling strength.

2. The wireless brake hose connector status monitoring system as described in claim 1, characterized in that, The state feature analysis module includes: The deformation feature extraction unit is used to perform feature decomposition on the abnormal response label group to obtain a set of deformation feature factors. The fault classification unit is used to classify the historical fault data and generate a fault type distribution set. The correlation analysis unit is used to calculate the correlation mapping relationship between the set of deformation feature factors and the set of fault type distributions, and based on the correlation mapping relationship, to determine the key deformation features and key fault types of the brake hose connector. The constraint generation unit is used to analyze the monitoring constraints of the brake hose connector based on the key deformation features and the key fault types, and to generate the core monitoring parameters of the brake hose connector based on the monitoring constraints.

3. The wireless brake hose connector status monitoring system as described in claim 2, characterized in that, The state feature analysis module also includes: The spatial topology optimization unit is used to receive power grid topology data, extract spatial topology features from the power grid topology data, and generate a spatial topology feature encoding matrix. The coupling enhancement unit is used to map the priority sequence to the topological space of the spatial topological feature encoding matrix to generate an optimized priority sequence.

4. The wireless brake hose connector status monitoring system as described in claim 3, characterized in that, include: The material matching module is used to query the reference sealing material and candidate sealing material of the brake hose connector, and to perform virtual assembly of the brake hose connector by combining the reference sealing material and the candidate sealing material to generate a connector simulation prototype; The assembly testing module is used to collect sealing performance test data and pressure cycle data of the joint simulation prototype, and to analyze the sealing failure characteristics of the joint simulation prototype based on the sealing performance test data.

5. The wireless brake hose connector status monitoring system as described in claim 4, characterized in that, The assembly testing module includes: The life assessment unit is used to calculate the life prediction equivalent value of the joint simulation prototype based on the pressure cycle data, and to assess the performance degradation of the joint simulation prototype based on the life prediction equivalent value. The spatial adaptation unit is used to determine the assembly position and operating temperature limits of the brake hose connector in the braking system, collect the spatial compatibility parameters of the connector simulation prototype, and calculate the connector spatial adaptability of the connector simulation prototype by combining the assembly position limits, the operating temperature limits and the spatial compatibility parameters.

6. The wireless brake hose connector status monitoring system as described in claim 5, characterized in that, Also includes: The fusion processing module is used to perform spatial isomorphic processing on the optimized priority sequence and the connector spatial fit, and generate an optimized connector spatial fit. The cascaded processing unit is used to cascade the sealing failure characteristics, the performance degradation degree, and the optimized joint space fit to generate multi-source fusion monitoring features.

7. The wireless brake hose connector status monitoring system as described in claim 6, characterized in that, Also includes: A material selection module is used to select a target sealing material from the benchmark sealing material and the candidate sealing materials based on the multi-source fusion monitoring characteristics; The strategy generation module is used to generate a real-time monitoring strategy for the brake hose connector based on the core monitoring parameters, the optimized priority sequence, and the target sealing material.

8. The wireless brake hose connector status monitoring system as described in claim 7, characterized in that, Also includes: The release hysteresis analysis module is used to extract the pressure maintenance duration and deformation recovery time of the tail seal in the brake hose channel during a continuous working cycle, calculate the time difference with the rated pressure release point, and generate seal release hysteresis information. The time period configuration unit is used to filter the channel numbers that have not completed pressure release based on the seal release lag information, and generate a variable pressure control time period table by sorting the channel seals according to their waiting time.

9. The wireless brake hose connector status monitoring system as described in claim 8, characterized in that, Also includes: The acceleration response module is used to call the variable pressure control time period table, detect the deformation distance distribution of the seal queue in the real-time cycle, and identify the continuous deformation acceleration time points of adjacent seals. The instruction generation module is used to generate a sealing state control instruction when the continuous deformation acceleration time points are all earlier than the pressure control period preparation switching point.

10. A method for monitoring the status of a wireless brake hose connector, characterized in that, It includes all modules and method flows of the wireless brake hose connector status monitoring system according to any one of claims 1 to 9.

Images