An AI-based tire repair prediction analysis and diagnosis system

Abstract

The present invention discloses an AI-based tire repair prediction analysis and diagnosis system, which relates to the technical field of tire repair analysis. The acquisition layer obtains repair environment parameters, and the repair environment parameters include the state of the grinding tool and the grinding depth. After standardizing the repair environment parameters, an environmental state vector is generated. The operation behavior parameters are obtained through a real-time perception device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The model construction layer uses the environmental state vector and the operation state vector as input variables and inputs them into a time series neural network to establish a damage evolution dynamic prediction model. The control layer predicts the state of the repair process through the damage evolution dynamic prediction model and dynamically adjusts the repair strategy to control the damage evolution process. This diagnosis system can accurately depict the damage expansion rate, the interface bonding aging amplitude, and the local stress change amplitude, realize the forward-looking prediction of the repair process state, and significantly improve the repair quality and the subsequent service life of the tire.

Description

Technical Field

[0001] The present invention relates to the technical field of tire repair analysis, and particularly relates to an AI-based tire repair prediction analysis and diagnosis system. Background Art

[0002] With the rapid development of the transportation industry, the vehicle ownership continues to grow. As a key component in direct contact with the ground during vehicle operation, the health status of tires is directly related to driving safety and operation efficiency. During long-term use, tires are prone to various factors such as road conditions, driving behaviors, and climate changes, resulting in faults such as wear, bulging, cracking, and air leakage. If these problems cannot be detected and addressed in a timely manner, it will lead to a decline in vehicle performance at best and serious traffic accidents at worst. With the rapid development of artificial intelligence technology, introducing AI into tire health management has become a new technological trend. By intelligently analyzing vehicle sensor data (such as tire pressure, temperature, vibration signals, etc.), historical repair records, and driving environment data, potential faults can be identified in advance, tire life can be predicted, and personalized maintenance plans can be formulated, thus realizing the transformation from passive repair to active prediction and preventive maintenance.

[0003] The existing technologies have the following defects:

[0004] Currently, in the process of tire repair, the understanding of the dynamic process of damage expansion still remains at the stage of empirical summary, lacking a scientific prediction system based on time series characteristics. Diagnostic systems usually use static data modeling and cannot capture the microscopic evolution processes of crack propagation, interface aging, and stress changes during the repair process, resulting in low prediction accuracy for future damage trends, delaying the best intervention time, and easily causing problems such as repair failure and premature tire scrapping.

[0005] Based on this, the present invention proposes an AI-based tire repair prediction analysis and diagnosis system, which can accurately depict the damage expansion rate, interface bonding aging amplitude, and local stress change amplitude, realize the prospective prediction of the repair process state, and significantly improve the repair quality and subsequent tire service life. Summary of the Invention

[0006] The purpose of the present invention is to provide an AI-based tire repair prediction analysis and diagnosis system to solve the deficiencies in the background art.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An AI-based tire repair prediction analysis and diagnosis system, comprising an acquisition layer, a model construction layer, and a control layer;

[0008] The acquisition layer: Obtain maintenance environment parameters and generate an environmental state vector, and obtain operation behavior parameters and generate an operation state vector;

[0009] Model construction layer: Taking the environmental state vector and the operation state vector as input variables, inputting them into a time series neural network to establish a dynamic prediction model for damage evolution;

[0010] Control layer: Predicting the state of the repair process through the dynamic prediction model of damage evolution, and dynamically adjusting the maintenance strategy when the prediction result is abnormal.

[0011] In a preferred embodiment, the time series prediction data output by the dynamic prediction model of damage evolution in the control layer includes the crack propagation amplitude, the interfacial bonding aging amplitude, and the local stress change amplitude. Whether there is an abnormality is predicted based on the crack propagation amplitude, the interfacial bonding aging amplitude, and the local stress change amplitude.

[0012] In a preferred embodiment, the crack propagation amplitude prediction formula: , where is the crack propagation amplitude, represents the crack propagation amplitude at the current moment. If , is the expansion threshold, predicting accelerated crack propagation;

[0013] Bonding aging amplitude prediction formula: , where is the bonding aging amplitude, represents the bonding aging amplitude at the current moment. If , is the aging threshold, predicting a decrease in interfacial stability;

[0014] Local stress change amplitude prediction formula: , where is the local stress change amplitude, represents the local stress value at the current moment, represents the time interval. If , is the change threshold, predicting a potential risk of structural imbalance.

[0015] In a preferred embodiment, when an abnormality is predicted, the adjustment mechanism is:

[0016] Grinding pressure adjustment: , where represents the adjusted grinding pressure, is the current grinding pressure, is the crack propagation amplitude, is the expansion threshold, is the adjustment coefficient;

[0017] Grinding speed adjustment: , where is the adjusted grinding speed, is the current grinding speed, is the bonding aging amplitude, is the aging threshold, is the adjustment coefficient;

[0018] Grinding path correction: , where, is the offset of the corrected grinding trajectory, is the offset of the center line of the current grinding trajectory, is the amplitude of local stress change, is the change threshold, is the adjustment coefficient.

[0019] In a preferred embodiment, the model construction layer concatenates the environmental state vector and the operation state vector to form a unified time series input, and constructs a three-dimensional input tensor from the concatenation results of all time steps;

[0020] Introduce a position encoding mechanism to add time identifiers to the input sequence, obtain the position encoding vector of the th time step, and the constructed input sequence is fed into a time series model based on a time series neural network structure, and the time series model uses the self-attention mechanism to model the dependence relationship between any two time steps;

[0021] From the hidden state of each time step output by the time series neural network encoder, extract the structure to construct a damage evolution prediction model, and finally output the time series prediction of the damage evolution index:

[0022] For each time step construct an objective function to obtain the predicted output vector of the th time step, and output the prediction results of all time steps in chronological order to form a complete dynamic damage evolution trajectory sequence.

[0023] In a preferred embodiment, the model construction layer concatenates the environmental state vector and the operation state vector to form a unified time series input: , and constructs a three-dimensional input tensor from the concatenation results of all time steps: , where, represents the environmental state vector of the th time step, represents the operation state vector of the th time step, represents the fused input vector of the th time step, represents the vector concatenation operation, is the length of the time series, represents the dimension of the environmental state vector, represents the dimension of the operation state vector.

[0024] In a preferred embodiment, the model construction layer introduces a position encoding mechanism to add time identifiers to the input sequence, and the position encoding function is defined as:

[0025] , where, represents the position encoding vector at the -th time step, represents the position encoding dimension index, which is used to control the alternating calculation of sine and cosine, represents the current time step number, is the total vector dimension, represents the dimension of the environmental state vector, represents the dimension of the operation state vector, and the final time-aware input vector is: , represents the final time-aware input vector, represents the -th time step's fused input vector.

[0026] In a preferred embodiment, the model construction layer constructs an objective function for each time step :

[0027] , where, represents the predicted output vector at the -th time step, represents the hidden state vector output by the temporal neural network, which is used to capture historical inputs and long-term dependencies, represents the predicted value of the crack propagation amplitude at the -th time step, represents the predicted value of the interfacial adhesion aging amplitude at the -th time step, the -th time step's local stress change amplitude value, is a non-linear mapping function;

[0028] Output the prediction results of all time steps in chronological order to form a dynamic damage evolution trajectory sequence: , where, represents the prediction sequence matrix of the entire repair process, represents the length of the time series, represents the -th time step's predicted output vector.

[0029] In a preferred embodiment, the acquisition layer synchronously starts the environmental parameter acquisition task, collects real-time data during the grinding process, including the rotational speed of the grinding tool, the degree of tool wear, and the dynamic change of the grinding depth, and performs feature aggregation processing on the standardized grinding tool state data and grinding depth data to form an environmental state vector of a unified dimension for describing the state representation of the current maintenance environment;

[0030] Real-time collect operation behavior parameters, including the grinding path trajectory, grinding angle, force change, tool tilt angle, and operations in the repeated operation area, and obtain the trajectory deviation rate and local over-grinding risk factor for the collected original action sequence, and integrate the operation behavior parameters into an operation state vector.

[0031] In a preferred embodiment, the calculation expression of the trajectory deviation rate is: , where is the trajectory deviation rate, is the total length of the ideal path, is the arc length coordinate along the grinding trajectory, is the spatial position vector of the actual grinding trajectory at parameter s, is the spatial position vector of the ideal grinding trajectory at parameter s, represents the Euclidean norm of the vector;

[0032] The calculation expression of the local over-grinding risk factor is: , where is the local over-grinding risk factor, is the projection range of the grinding action area on the two-dimensional plane, is the grinding depth measured at the position point (x, y), is the grinding depth threshold, represents only the positive residual of the over-grinding area.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0034] The present invention obtains maintenance environment parameters through an acquisition layer. The maintenance environment parameters include the state of the grinding tool and the grinding depth. After standardizing the maintenance environment parameters, an environmental state vector is generated. The operation behavior parameters are obtained through a real-time sensing device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The model construction layer uses the environmental state vector and the operation state vector as input variables and inputs them into a time series neural network to establish a dynamic prediction model for damage evolution. The control layer: predicts the state of the repair process through the dynamic prediction model for damage evolution, sends a warning signal when the prediction result is abnormal, and dynamically adjusts the maintenance strategy to control the damage evolution process. This diagnostic system introduces an acquisition layer, a model construction layer, and a control layer, forming a complete dynamic adaptive closed-loop mechanism, which can accurately depict the damage expansion rate, the interface bonding aging amplitude, and the local stress change amplitude, realize the forward-looking prediction of the repair process state, effectively inhibit the damage deterioration process, and significantly improve the repair quality and the subsequent service life of the tire. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0036] Figure 1 It is a system architecture diagram of the diagnostic system of the present invention.

[0037] Figure 2 It is a timing diagram of the diagnostic system of the present invention.

[0038] Figure 3 It is a flowchart of the operation of the diagnostic system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1: Please refer to Figure 1 - Figure 2 As shown, the present embodiment provides a tire repair prediction and analysis diagnostic system based on AI, including an acquisition layer, a model construction layer, and a control layer;

[0041] Acquisition layer: Obtain maintenance environment parameters through multiple types of sensors. The maintenance environment parameters include the status of the grinding tool and the grinding depth. After standardizing the maintenance environment parameters, an environmental state vector is generated. Obtain operation behavior parameters through a real-time sensing device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The environmental state vector and the operation state vector are sent to the model construction layer;

[0042] Model construction layer: Take the environmental state vector and the operation state vector as input variables, and input them into a temporal neural network (such as Transformer) to establish a dynamic prediction model for damage evolution. The dynamic prediction model for damage evolution is sent to the control layer;

[0043] Control layer: Predict the state of the repair process through the dynamic prediction model for damage evolution. The state of the repair process includes the crack propagation amplitude, the interfacial adhesion aging amplitude, and the local stress change amplitude. When the prediction result is abnormal, a warning signal is sent, and the maintenance strategy is dynamically adjusted to control the damage evolution process.

[0044] In this application, the acquisition layer obtains maintenance environment parameters, including the status of the grinding tool and the grinding depth. After standardizing the maintenance environment parameters, an environmental state vector is generated. Operation behavior parameters are obtained through a real-time sensing device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The model construction layer takes the environmental state vector and the operation state vector as input variables and inputs them into a temporal neural network to establish a dynamic prediction model for damage evolution. The control layer predicts the state of the repair process through the dynamic prediction model for damage evolution. When the prediction result is abnormal, a warning signal is sent, and the maintenance strategy is dynamically adjusted to control the damage evolution process. This diagnostic system introduces an acquisition layer, a model construction layer, and a control layer, forming a complete dynamic adaptive closed-loop mechanism, which can accurately describe the damage expansion rate, the interfacial adhesion aging amplitude, and the local stress change amplitude, realize the forward-looking prediction of the repair process state, effectively inhibit the damage deterioration process, and significantly improve the repair quality and the subsequent service life of the tire.

[0045] Please refer to Figure 3 as shown, the specific working process of the diagnostic system is as follows:

[0046] The diagnostic system obtains the maintenance environment parameters through multiple types of sensors. The maintenance environment parameters include the state of the grinding tool and the grinding depth. After standardizing the maintenance environment parameters, an environmental state vector is generated. The operation behavior parameters are obtained through a real-time sensing device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The environmental state vector and the operation state vector are used as input variables and input into a time series neural network (such as Transformer) to establish a dynamic prediction model for damage evolution. The state of the repair process is predicted through the dynamic prediction model for damage evolution. The state of the repair process includes the crack propagation amplitude, the interfacial adhesion aging amplitude, and the local stress change amplitude. When the prediction result is abnormal, a warning signal is sent, and the maintenance strategy is dynamically adjusted to control the damage evolution process.

[0047] Embodiment 2: The acquisition layer obtains the maintenance environment parameters through multiple types of sensors. The maintenance environment parameters include the state of the grinding tool and the grinding depth. After standardizing the maintenance environment parameters, an environmental state vector is generated. The operation behavior parameters are obtained through a real-time sensing device, and after feature extraction of the operation behavior parameters, an operation state vector is generated. The environmental state vector and the operation state vector are sent to the model construction layer.

[0048] Multiple types of sensor devices are arranged in the tire repair operation area, specifically including grinding tool state monitoring sensors (such as current, voltage, vibration, temperature rise sensors) and grinding depth monitoring sensors (such as laser ranging, ultrasonic thickness measurement sensors), and parameters such as the acquisition frequency, accuracy threshold, and data buffer are initialized and configured.

[0049] After the maintenance operation is started, the acquisition layer synchronously starts the environmental parameter acquisition task to collect real-time data during the grinding process, including but not limited to: multi-dimensional data such as the grinding tool rotation speed, motor load change, temperature change trend, tool wear degree, and dynamic change of the grinding depth.

[0050] Through a sliding time window and normalization processing algorithm (such as z-score normalization, min-max normalization), the originally collected maintenance environment parameter data is standardized to eliminate the data distribution differences brought by different maintenance environments and equipment models, and enhance the generalization ability of subsequent modeling.

[0051] The standardized grinding tool state data and grinding depth data are subjected to feature aggregation processing, and a dimension fusion technology (such as principal component analysis PCA or convolutional feature compression network) is used to form an environmental state vector with a unified dimension to describe the state representation of the current maintenance environment. The relevant code example is as follows:

[0052] import_torch

[0053] import_torch.nn_as_nn

[0054] import torch.nn.functional as F

[0055] class FeatureCompressor(nn.Module):

[0056] def __init__(self):

[0057] super(FeatureCompressor, self).__init__()

[0058] # Tool status convolution channels

[0059] self.conv_tool = nn.Sequential(

[0060] nn.Conv1d(in_channels=8, out_channels=16, kernel_size=3, padding=1),

[0061] nn.ReLU(),

[0062] nn.Conv1d(in_channels=16, out_channels=16, kernel_size=3, padding=1),

[0063] nn.ReLU() )

[0065] # Polishing depth convolution channels

[0066] self.conv_depth = nn.Sequential(

[0067] nn.Conv1d(in_channels=4, out_channels=16, kernel_size=3, padding=1),

[0068] nn.ReLU(),

[0069] nn.Conv1d(in_channels=16, out_channels=16, kernel_size=3, padding=1),

[0070] nn.ReLU() )

[0072] # Aggregation + compression to a unified vector dimension

[0073] self.pool = nn.AdaptiveAvgPool1d(output_size = 1) # Aggregate the time dimension

[0074] self.fc = nn.Linear(in_features = 32, out_features = 32) # Unify the dimensions

[0075] def forward(self, tool_input, depth_input):

[0076] # Input shape: (batch_size, T, feature_dim)

[0077] tool_input = tool_input.permute(0, 2, 1) # Convert to (batch_size, feature_dim, T)

[0078] depth_input = depth_input.permute(0, 2, 1)

[0079] tool_feat = self.conv_tool(tool_input) # Shape: (batch_size, 16, T)

[0080] depth_feat = self.conv_depth(depth_input) # Shape: (batch_size, 16, T)

[0081] fused = torch.cat([tool_feat, depth_feat], dim = 1) # Shape: (batch_size, 32, T)

[0082] pooled = self.pool(fused) # Shape: (batch_size, 32, 1)

[0083] pooled = pooled.squeeze(-1) # Shape: (batch_size, 32)

[0084] output = self.fc(pooled).unsqueeze(1) # Shape: (batch_size, 1, 32)

[0085] return output

[0086] Usage example:

[0087] model = FeatureCompressor()

[0088] tool_data = torch.randn(16, 50, 8) # batch_size = 16, time steps = 50, tool features = 8

[0089] depth_data = torch.randn(16, 50, 4) # batch_size = 16, time steps = 50, depth features = 4

[0090] env_vector = model(tool_data, depth_data) # output shape: [16, 1, 32]

[0091] print(env_vector.shape)

[0092] In the above code example, the shape of the grinding tool state data is [batch_size, T, 8], indicating that the time series length is T and contains 8 state dimensions; the shape of the grinding depth data is [batch_size, T, 4], indicating that the time series length is T and contains 4 depth-related dimensions; the output unified environmental state vector dimension is [batch_size, 1, 32], which extracts local patterns of the time series through convolutional layers; AdaptiveAvgPool1d compresses different time series lengths into a fixed length; the fully connected layer compresses to the target dimension; the output is a unified environmental state vector, which is convenient for subsequent input into model building layers such as Transformer.

[0093] By using an inertial measurement unit (IMU), motion capture system, or machine vision module installed on the maintenance tool, the motion characteristics of the operator are collected in real time, including operation behavior information such as the grinding path trajectory, grinding angle, force change, tool tilt angle, and repeated operation area. Feature extraction is performed on the collected original motion sequence, such as the trajectory deviation rate and local over-grinding risk factor. The above-mentioned extracted operation behavior characteristics are integrated into an operation state vector in a unified format, which is used as a multi-dimensional state description vector of the maintenance behavior to characterize the operation quality and potential error risk.

[0094] The trajectory deviation rate measures the geometric deviation between the operation trajectory and the ideal grinding path, and its calculation expression is: , where is the trajectory deviation rate, is the total length of the ideal path, is the arc length coordinate along the grinding trajectory, is the spatial position vector of the actual grinding trajectory at parameter s is the spatial position vector of the ideal grinding trajectory at parameter s, represents the Euclidean norm (i.e., distance) of the vector.

[0095] The local over-grinding risk factor measures the degree of over-grinding of the grinding depth in a certain area per unit area relative to the preset depth threshold, and the expression is:

[0096] , where is the local over-grinding risk factor, is the projection range of the grinding action area on the two-dimensional plane, is the measured grinding depth at the position point (x, y), is the grinding depth threshold, that is, the maximum safe grinding depth allowed by the material, represents only counting the positive residuals of the "over-grinding" area (the part exceeding the threshold).

[0097] Through the data bus or the edge computing module, the generated environmental state vector and operation state vector are merged and packaged in time series and sent to the model construction layer for further damage evolution modeling and prediction analysis.

[0098] The model construction layer takes the environmental state vector and operation state vector as input variables and inputs them into a time series neural network (such as Transformer) to establish a damage evolution dynamic prediction model, and the damage evolution dynamic prediction model is sent to the control layer.

[0099] The core work of the model construction layer is first to receive and fuse two types of input information from the acquisition layer, namely the standardized environmental state vector and operation state vector, which respectively represent multi-dimensional features related to operation behaviors such as the state of the maintenance tool, grinding depth, and tool vibration frequency. Since there are significant differences in dimension, time series characteristics, and semantics between these two types of vectors, feature dimension alignment and fusion must be carried out first.

[0100] Assume: represents the environmental state vector at the -th time step (including sensor parameters such as the state of the grinding tool (such as rotational speed, temperature rise), grinding depth, and environmental humidity): represents the operation state vector at the -th time step (reflecting maintenance behavior characteristics such as hand trajectory, grinding trajectory angle, and contact force); the two are concatenated to form a unified time series input: , represents the fused input vector at the -th time step, represents the vector concatenation operation, and the concatenation results of all time steps form a three-dimensional input tensor: , this fused input retains the temporal structure, forming a complete input sequence as the input basis for the Transformer.

[0101] Since the temporal neural network is essentially a fully connected model based on the self-attention mechanism and its structure does not have natural temporal perception ability, a position encoding mechanism needs to be introduced to add time identifiers to the input sequence, enabling the temporal neural network to understand the evolution trend of events over time.

[0102] Let the input at the -th time step be , then the position encoding function is defined as:

[0103] , where represents the position encoding vector at the -th time step, represents the position encoding dimension index, used to control the alternating calculation of sine and cosine, represents the current time step number, is the total vector dimension, represents the dimension of the environmental state vector, represents the dimension of the operation state vector. The final time-aware input vector is: . The addition of time identifiers enables the model to capture the dynamic laws of damage over time during learning, such as how stress concentration points migrate with grinding time and the fatigue accumulation trend of the adhesive layer.

[0104] The constructed input sequence is fed into the temporal model based on the Transformer structure. The core mechanism in the Transformer is the self-attention mechanism, which can model the dependency relationship between any two time steps, thereby uncovering the delayed and non-linear correlation between the grinding behavior and the damage behavior. The attention mechanism is defined as follows:

[0105] , where: represents the Query matrix, which is obtained by linearly mapping the input vector, represents the Key matrix, which is also linearly transformed from the input vector, represents the Value matrix, containing information representing values; is the dimension of the key; is the length of the time series (i.e., the discrete number of steps of the maintenance process duration), is the dimension of the Key vector, is the dimension of the Value vector, and softmax is used to normalize the importance weights at each time step. By stacking multiple Transformer encoder layers, the model can capture multi-level semantic interactions. For example, whether the fluctuations in the tool vibration frequency trigger crack propagation in the bonding area after multiple time steps.

[0106] From the hidden state at each time step output by the Transformer encoder extract key structures to build the final output of the damage evolution prediction model, which is the time series prediction of the following three key damage evolution indicators:

[0107] Crack propagation amplitude: Measures the crack growth amount per unit time;

[0108] Interface bonding aging amplitude: Measures the trend of the bonding layer strength deterioration;

[0109] Local stress change amplitude: Measures the stress change amplitude in a specific area.

[0110] For each time step Construct the objective function: , where represents the predicted output vector at the -th time step, containing the damage evolution prediction indicators in three dimensions. represents the hidden state vector (high-dimensional feature) output by the Transformer, used to capture historical inputs and long-term dependencies. represents the predicted value of the crack propagation amplitude at the -th time step (the crack length growth rate per unit time). represents the predicted value of the interface bonding aging amplitude at the -th time step. The -th time step's local stress change amplitude value, representing the stress concentration evolution trend, is a non-linear mapping function, which can be implemented by a feedforward neural network.

[0111] Finally, the prediction results of all time steps are output in chronological order to form a complete dynamic damage evolution trajectory sequence, which is used as the input reference for the control layer:

[0112] , where represents the prediction sequence matrix for the entire repair process, and each row is the predicted value of the damage state at a time step, represents the length of the time series, represents the The predicted values of the three - dimensional damage evolution index for each time step. This sequence can not only be used to identify local abnormal states (such as the rapid growth of cracks over a certain period of time), but also evaluate the impact of overall maintenance operations on the tire structure stability through continuous trends, achieving: prospective modeling of the future damage development trajectory; quantitative feedback on the impact results of maintenance operation behaviors; real - time warning of potential risk points (such as local stress anomalies).

[0113] The design of the model construction layer realizes the deep integration of environment and behavior + dynamic tracking of multi - dimensional damage + deep learning of time - series evolution trends. Compared with traditional empirical rules or single - variable prediction methods, it has the following technical advantages: being able to adapt to complex and variable maintenance environments and different workers' operating habits; effectively modeling the delay response and non - linear damage mechanism during the maintenance process; realizing real - time prediction and early intervention of damage expansion during the maintenance process; supporting the dynamic adaptation and real - time optimization of maintenance control strategies in the time dimension.

[0114] This model can be widely applied to scenarios such as tire defect repair, maintenance of military heavy - duty tires, intelligent maintenance robots, etc. It is the key support for the deep integration of AI and the physical behavior of tire structures.

[0115] The control layer predicts the state of the repair process through the damage evolution dynamic prediction model. The state of the repair process includes the crack propagation amplitude, the interface bonding aging amplitude, and the local stress change amplitude. When abnormal prediction results occur, it sends warning signals and dynamically adjusts the maintenance strategy to control the damage evolution process.

[0116] In the AI - based tire repair prediction and analysis system, the control layer undertakes the key decision - making scheduling and dynamic intervention tasks. Its core goal is: based on the "damage evolution dynamic prediction results" output by the model construction layer, to real - time perceive, abnormally identify, and intervene and adjust the risk states such as crack evolution, bonding aging, and local stress distribution during the tire repair process, so as to improve the repair accuracy, reduce the secondary risk of repair, and extend the service life of the tire.

[0117] The entire control process is divided into three major stages: (1) receiving and evaluating the damage state prediction results, (2) abnormal identification and prediction, (3) dynamic control and feedback optimization of the maintenance strategy.

[0118] The time - series prediction data output by the system damage evolution dynamic prediction model focuses on the trends of the following three physical indicators:

[0119] Crack - Propagation - Rate: It represents the crack propagation speed per unit time and reflects the severity of material damage expansion in the tire structure during the repair and grinding process.

[0120] Adhesive-Interface-Aging-Rate: Measures the rate of performance degradation at the interface between the adhesive layer or patch and the original tire structure, determining the durability and reliability of the repair bond.

[0121] Local-Stress-Variation-Trend: Monitors local stress fluctuations in the repair area caused by excessive grinding or abnormal load distribution, reflecting the structural mechanical stability.

[0122] To ensure that the repair process always remains within a safe and stable dynamic balance range, the system sets the following prediction formulas for trend monitoring.

[0123] (1) Crack Propagation Amplitude Prediction Formula: , where is the crack propagation amplitude, represents the crack propagation amplitude at the current moment, represents the time interval, the sampling period between adjacent moments, calculates the change slope of crack propagation per unit time with the differential concept, and predicts whether the current crack is accelerating. If , is the expansion threshold, it is considered that the crack propagation is accelerating and in a dangerous state.

[0124] (2) Adhesive Aging Amplitude Prediction Formula: , where is the adhesive aging amplitude, represents the adhesive aging amplitude at the current moment, represents the time interval, the sampling period between adjacent moments, represents the degradation rate of the adhesive performance per unit time, and identifies interface aging caused by grinding heat, interface contamination, etc. If , is the aging threshold, the interface stability decreases, indicating that the glue joint may fail.

[0125] (3) Local Stress Variation Amplitude Prediction Formula: , where is the local stress variation amplitude, represents the local stress value at the current moment, represents the time interval, the sampling period between adjacent moments, evaluates the non-uniform change degree of the local stress field, and captures whether there is instability caused by excessive grinding during manual operation or unrelieved residual stress of the material. If , is the change threshold, there is a hidden danger of structural imbalance.

[0126] When the prediction result exceeds the safety threshold, the system will actively adjust the grinding parameters to inhibit the further expansion of damage. The adjustment mechanism is as follows:

[0127] (1) Grinding pressure adjustment model: , where represents the adjusted grinding pressure, is the current grinding pressure, is the crack propagation amplitude, is the expansion threshold. To reduce the excessive crack propagation rate, when the crack propagates too fast, the grinding pressure is automatically reduced. The adjustment coefficient represents the sensitivity of the system to abnormal crack propagation, and its usual value range is .

[0128] (2) Grinding speed adjustment model: , where is the adjusted grinding speed, is the current grinding speed, is the bonding aging amplitude, is the aging threshold. To reduce the bonding interface aging caused by too fast grinding, by reducing the operation time, the heat conduction and the accumulation of interface shear stress are controlled. The adjustment coefficient represents the control aging sensitivity, and the recommended value range is .

[0129] (3) Grinding path correction formula: , where is the offset of the corrected grinding trajectory, is the offset of the current grinding trajectory center line, is the local stress change amplitude, is the change threshold. To correct the local stress concentration caused by path deviation or repeated grinding, the path adjustment amount is proportional to the local stress change amplitude. The adjustment coefficient represents that it can be set based on the tire material or the repair position to control the degree of path deviation correction.

[0130] Example 3: In the above Example 2, the processing logic of the model construction layer is given, that is, the detailed steps of establishing a dynamic damage evolution prediction model by taking the environmental state vector and the operation state vector as input variables and inputting them into a temporal neural network (such as Transformer). In this example, an example of the establishment steps of the dynamic damage evolution prediction model is given, as follows:

[0131] Purpose: Convert multi-source heterogeneous sensor data and behavioral parameters into a unified time series structure as the basic input of the model.

[0132] Collect raw data: Grinding tool status: including tool rotation speed (rpm), temperature rise (°C), vibration value, etc. Grinding depth: obtained by laser ranging or structured light scanning. Trajectory deviation rate: obtained by calculating the geometric difference between the actual trajectory and the ideal trajectory. Local over-grinding risk factor: obtained based on grinding intensity, time, and remaining material thickness.

[0133] All data is aligned by timestamp and sampled at equal intervals (e.g., every second) to construct a series of time-step data Use the z-score or min-max method to normalize each parameter to prevent model bias caused by inconsistent numerical dimensions, and construct the input vector: , where, represents the step grinding tool status (such as rotation speed or temperature rise). represents the step grinding depth. represents the trajectory deviation rate. represents the local over-grinding risk factor.

[0134] Concatenate the environmental state vector and the operation state vector to form a unified input sequence:

[0135] , construct a sequence for the entire time period: , introduce positional encoding and send it into the Transformer encoder. Since the Transformer lacks temporal perception ability, positional encoding needs to be added: , where: represents the th time-step positional encoding vector. The overall input is sent into the Transformer-Encoder: .

[0136] Define the output for each time step as: , and the model training objective is to make the output predict the evolution of the damage state, including: Crack-Growth-Rate: predicting the growth rate of the crack length in the current state. Adhesion-Aging: predicting the degradation trend of the bonding interface. Local stress change amplitude: predicting the evolution of stress concentration that may cause fatigue damage.

[0137] For example, the input raw data (assuming the unit is the normalized value) is as follows: Grinding tool status (wear rate): 0.75; Grinding depth: 1.20; Trajectory deviation rate: 0.35; Grinding factor at the same position: 0.40.

[0138] We fuse these features into two vectors:

[0139] Environmental state vector ;

[0140] Operation state vector ;

[0141] Combine into a joint vector sequence for model input (assuming the current time window is :

[0142] ;

[0143] Damage evolution dynamic prediction model (Transformer):

[0144] Feature embedding transformation (Linear -projection): Transform the input vector:

[0145]

[0146] Let:

[0147] ;

[0148] ;

[0149] Calculate:

[0150] ;

[0151] ;

[0152] ;

[0153] Obtain the embedding vector: ;

[0154] This part is processed by the encoder for time - series data (we only process single - step examples here), and the predicted damage state is output:

[0155] Prediction targets: crack propagation amplitude, bonding aging amplitude, local stress change;

[0156] Assume that the trained Transformer maps the embedding vector to the following function (simplified simulation):

[0157] ;

[0158] Substitute into the calculation:

[0159] ;

[0160] ;

[0161] .

[0162] The real-time prediction of the damage evolution trend during maintenance is realized through the damage evolution dynamic prediction model; it supports dynamically adjusting the grinding path or repair method according to the results; it improves the service life and safety stability of the tire; it can be extended to a multi-time-step prediction model for dynamic monitoring of the whole maintenance process.

[0163] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0164] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not elaborate all the details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the relevant technical fields can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An AI-based tire maintenance prediction analysis and diagnosis system, characterized in that: It includes a collection layer, a model construction layer, and a control layer; Collection layer: Obtain maintenance environment parameters and generate an environmental state vector, obtain operation behavior parameters and generate an operation state vector. The environmental state vector includes the standardized grinding tool speed, tool wear degree, and dynamic change of grinding depth. The operation state vector includes the trajectory deviation rate and the local over-grinding risk factor; Model construction layer: Use the environmental state vector and the operation state vector as input variables and input them into a temporal neural network to establish a dynamic prediction model for damage evolution; Control layer: Predict the state of the repair process through the dynamic prediction model of damage evolution, and dynamically adjust the maintenance strategy when the prediction result is abnormal; The time series prediction data output by the dynamic prediction model of damage evolution in the control layer includes the crack propagation amplitude, the interfacial adhesion aging amplitude, and the local stress change amplitude. Whether there is an abnormality is predicted based on the crack propagation amplitude, the interfacial adhesion aging amplitude, and the local stress change amplitude.

2. The tire repair prediction analysis and diagnosis system based on AI according to claim 1, characterized in that: Crack propagation amplitude prediction formula: , where is the crack propagation amplitude, represents the crack propagation amplitude at the current moment. If , is the expansion threshold, predicting crack propagation acceleration; Adhesive aging amplitude prediction formula: , where is the adhesive aging amplitude,[[]] represents the adhesive aging amplitude at the current moment. If , is the aging threshold, predicting a decrease in interface stability; Prediction formula for the amplitude of local stress change: , where is the amplitude of local stress change, represents the local stress value at the current moment, represents the time interval. If , is the change threshold, it is predicted that there is a potential hidden danger of structural imbalance.

3. The tire repair prediction analysis and diagnosis system based on AI according to claim 2, wherein: When the prediction is abnormal, the adjustment mechanism is as follows: Polishing pressure adjustment: , where represents the adjusted polishing pressure, is the current polishing pressure, is the crack propagation amplitude, is the expansion threshold, is the adjustment coefficient; Polishing speed adjustment: , where is the adjusted polishing speed, is the current polishing speed, is the bonding aging amplitude, is the aging threshold, is the adjustment coefficient; Grinding path correction: , where is the offset of the corrected grinding trajectory, is the offset of the center line of the current grinding trajectory, is the amplitude of local stress change, is the change threshold, is the adjustment coefficient.

4. The tire repair prediction analysis and diagnosis system based on AI according to claim 3, wherein: The model construction layer concatenates the environmental state vector and the operation state vector to form a unified time series input, and forms a three-dimensional input tensor with the concatenation results of all time steps; Introduce a positional encoding mechanism to add time identifiers to the input sequence, obtain the positional encoding vector at the th time step, and construct the input sequence which is fed into a temporal model based on a temporal neural network structure. The temporal model uses the self-attention mechanism to model the dependence relationship between any two time steps; From the hidden state at each time step output by the spiking neural network encoder extract the structure to construct a damage evolution prediction model, and finally output the time series prediction of the damage evolution index: For each time step Construct the objective function, obtain the predicted output vector at the -th time step, and output the prediction results of all time steps in chronological order to form a complete dynamic damage evolution trajectory sequence.

5. The tire repair prediction analysis and diagnosis system based on AI according to claim 4, characterized in that: The model construction layer concatenates the environmental state vector and the operation state vector to form a unified time series input: , and forms a three-dimensional input tensor from the concatenation results of all time steps: , where represents the environmental state vector at the -th time step, represents the operation state vector at the -th time step, represents the fused input vector at the -th time step, represents the vector concatenation operation, is the length of the time series, represents the dimension of the environmental state vector, represents the dimension of the operation state vector.

6. The AI-based tire repair prediction analysis and diagnosis system according to claim 5, wherein: The model construction layer introduces a positional encoding mechanism to add time identifiers to the input sequence, and the positional encoding function is defined as: , where represents the position encoding vector at the -th time step, represents the position encoding dimension index, which is used to control the alternating calculation of sine and cosine, represents the current time step number, is the total vector dimension, represents the dimension of the environmental state vector, represents the dimension of the operation state vector, and the final time-aware input vector is: , represents the final time-aware input vector, represents the fused input vector at the -th time step.

7. The tire repair prediction analysis and diagnosis system based on AI according to claim 6, characterized in that: The model construction layer for each time step Construct the objective function: , where represents the predicted output vector at the -th time step, represents the hidden state vector output by the temporal neural network, which is used to capture historical inputs and long-term dependencies, represents the predicted value of the crack growth amplitude at the -th time step, represents the predicted value of the interfacial adhesion aging amplitude at the -th time step, represents the local stress change amplitude at the -th time step, is a non-linear mapping function; Output the prediction results of all time steps in chronological order to form a dynamic damage evolution trajectory sequence: , where represents the prediction sequence matrix of the entire repair process, represents the length of the time series, represents the prediction output vector at the 8. An AI-based tire repair prediction analysis and diagnosis system according to claim 7, characterized in that: The collection layer synchronously starts the environmental parameter collection task, collects real-time data during the grinding process, including the grinding tool speed, tool wear degree, and dynamic change of grinding depth, performs feature aggregation processing on the standardized grinding tool state data and grinding depth data to form an environmental state vector with a unified dimension, which is used to describe the state representation of the current maintenance environment; Real-time collect operation behavior parameters, including the grinding path trajectory, grinding angle, force change, tool tilt angle, and operation in the repeated operation area, obtain the trajectory deviation rate and the local over-grinding risk factor from the collected original action sequence, and integrate the operation behavior parameters into an operation state vector.

9. An AI-based tire repair prediction analysis and diagnosis system according to claim 8, characterized in that: The calculation expression of the trajectory deviation rate is as follows: , where is the trajectory deviation rate, is the total length of the ideal path, is the arc length coordinate along the grinding trajectory, is the spatial position vector of the actual grinding trajectory at the parameter s, is the spatial position vector of the ideal grinding trajectory at the parameter s, represents the Euclidean norm of the vector; The calculation expression of the local over-polishing risk factor is as follows: , where is the local over-polishing risk factor, is the projection range of the polishing action area on the two-dimensional plane, is the polishing depth measured at the position point (x, y), is the polishing depth threshold, represents only counting the positive residuals of the over-polished area.

Images