Artificial Intelligence-Based Method and System for Analyzing Internal Diseases of Road Surfaces

Abstract

The present invention relates to the technical field of road maintenance and management, and in particular to a method and system for analyzing internal diseases of road surfaces based on artificial intelligence, which includes five core processes: real-time data collection through a multi-level sensor network, multi-modal data fusion and deep learning feature extraction, disease prediction and analysis by combining dynamic environments and usage patterns, an intelligent prediction and decision support system, and real-time disease condition assessment and report generation; through these technical means, the present invention achieves the comprehensiveness and timeliness of data collection, the accuracy of disease identification and prediction, the scientific nature of maintenance strategies, and the optimization of resource allocation; the finally generated disease status report provides a detailed disease distribution map, disease type analysis, and disease severity assessment, providing comprehensive, accurate, and timely disease information for maintenance personnel, and significantly improving the efficiency and effectiveness of road surface maintenance and management.

Description

Technical Field

[0001] The present invention relates to the technical field of road maintenance and management, and particularly to a method and system for analyzing internal pavement diseases based on artificial intelligence. Background Art

[0002] With the increase in traffic volume and heavy-duty vehicles, the problem of pavement diseases has become increasingly serious, which not only affects the service life of roads but also poses a potential threat to traffic safety. There are many problems in current pavement disease analysis, mainly including incomplete data collection, single data processing and analysis methods, inaccurate disease prediction and early warning, imperfect decision support, and untimely generation of disease condition assessment and reports. These problems are mainly caused by relying on a single type of sensor, lacking the ability to comprehensively analyze multi-source data, the prediction model lacking the ability of dynamic adjustment, and lacking an effective decision support system.

[0003] The prior art (Chinese invention patent, publication number: CN115755193A, title: Method for Identifying Internal Diseases of Pavement Structure) has the following deficiencies or defects when facing these problems: a single sensor type leads to incomplete data collection; single data processing and analysis methods, unable to make full use of multi-source data; inaccurate disease prediction and early warning, lacking the ability of dynamic adjustment; lacking an effective decision support system, and the assessment of disease impact is not comprehensive; untimely generation of disease condition assessment and reports, and the report content is not detailed and comprehensive enough. These deficiencies and defects limit the comprehensiveness, accuracy, and real-time nature of the prior art solutions in disease identification, prediction, assessment, and decision-making. Summary of the Invention

[0004] In view of the many problems existing in the above prior art, the present invention provides a method and system for analyzing internal pavement diseases based on artificial intelligence. The present invention uses a multi-level sensor network to collect real-time data on the internal and external environments of the pavement, adopts multi-modal data fusion and deep learning technologies for data processing and feature extraction, combines dynamic environment and usage pattern data, and constructs a disease cause model and a disease development trend prediction model; through an intelligent prediction system and a decision support system, it provides real-time disease prediction and maintenance strategies, and generates a detailed report on the current disease situation. By comprehensively using multi-source data, the present invention improves the accuracy and scientific nature of disease identification, prediction, and maintenance strategies, and significantly enhances the efficiency and effect of pavement maintenance and management.

[0005] A method for analyzing internal pavement diseases based on artificial intelligence includes the following steps:

[0006] By applying a sensor network for the internal part of the pavement, collect and preprocess real-time data on the internal structure and external environment of the pavement to generate ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data;

[0007] After synchronizing the time and unifying the formats of the ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, multi-modal data fusion is performed using data-level, feature-level, and decision-level fusion methods, and feature extraction is carried out through a deep learning model to generate fused feature data and disease feature data;

[0008] Combined with the environmental feature data and usage pattern feature data, a disease cause model and a disease development trend prediction model are constructed to analyze the causes, development trends, and impacts of diseases, generating disease cause analysis data, disease trend prediction data, and disease impact assessment data; the usage pattern feature data is generated after synchronizing the time and unifying the formats of traffic flow data, vehicle weight data, and road surface usage frequency data;

[0009] Based on the disease cause analysis data, disease trend prediction data, and disease impact assessment data, an intelligent prediction system and a decision support system are constructed to provide real-time disease prediction and maintenance strategies, generating disease prediction data and maintenance strategy data, and optimizing the intelligent prediction system and decision support system according to the actual maintenance feedback;

[0010] Using the real-time updated disease prediction data and disease feature data, the current disease condition is evaluated to generate a disease status report.

[0011] Preferably, the sensor network includes: ground penetrating radar sensors, piezoelectric sensors, temperature and humidity sensors, and accelerometers, which are arranged at different depths and regions, including:

[0012] By applying ground penetrating radar sensors, electromagnetic wave reflection data of the road surface internal structure is collected;

[0013] Piezoelectric sensors are arranged on the road surface and below to collect vibration and pressure data;

[0014] Temperature and humidity sensors are arranged in the road surface surrounding environment to collect environmental temperature and humidity data;

[0015] Accelerometers are arranged in key areas of the road surface to collect road surface dynamic stress data.

[0016] Preferably, the multi-modal data fusion method includes:

[0017] Data-level fusion: Combining the original data of different sensors at the data level to generate a fused data set;

[0018] Feature-level fusion: Extracting the features of various types of data and fusing the extracted features to generate fused feature data;

[0019] Decision-level fusion: After independently analyzing various types of data, the results are fused to generate comprehensive decision-making data.

[0020] Preferably, the deep learning model includes a convolutional neural network and a graph convolutional network for feature extraction and disease identification, including:

[0021] Using the convolutional neural network to extract features from the fused feature data to generate preliminary disease feature data;

[0022] Using the graph convolutional network to further process the preliminary disease feature data to generate the final disease feature data.

[0023] Preferably, the disease cause model is calculated by the following formula:

[0024] C = f(E, U) = a·E + b·U + c

[0025] Wherein, C represents the disease cause analysis data, E represents the environmental feature data, U represents the usage pattern feature data, f represents the function that converts the environmental feature data and the usage pattern feature data into the disease cause analysis data, a and b are weights, and c is a bias parameter.

[0026] Preferably, the disease development trend prediction model is calculated by the following formula:

[0027] T = g(C, t) = α·C + β·t + γ

[0028] Wherein, T represents the disease trend prediction data, C represents the disease cause analysis data, t represents the time variable, g represents the function that converts the disease cause analysis data and the time variable into the disease trend prediction data, α and β are weights, and γ is a bias parameter.

[0029] Preferably, the intelligent prediction system adopts a reinforcement learning algorithm to continuously optimize the disease prediction and maintenance strategies, including:

[0030] Based on historical disease data and current disease data, training an intelligent prediction model using the reinforcement learning algorithm;

[0031] According to the real-time updated disease data, adjusting and optimizing the parameters of the intelligent prediction model to generate real-time disease prediction data.

[0032] Preferably, the maintenance strategy data includes maintenance time, maintenance resources, and specific operation suggestions, including:

[0033] According to the disease impact assessment data, determining the areas that need to be maintained first and the specific maintenance time;

[0034] According to the disease severity and resource availability, allocating maintenance resources to generate a maintenance resource allocation plan;

[0035] Provide specific operation suggestions, including maintenance tools to be used, operation steps, and safety precautions.

[0036] Preferably, the disease status report includes a disease distribution map, disease type analysis, and disease severity assessment, and provides detailed information in the form of charts and text descriptions, including:

[0037] Disease distribution map: showing the specific locations and distribution of diseases on the road surface;

[0038] Disease type analysis: classifying and describing different types of diseases and their characteristics;

[0039] Disease severity assessment: quantitatively evaluating the severity of diseases and providing specific scores and suggestions.

[0040] A system for implementing the above-mentioned artificial intelligence-based internal road disease analysis method, including:

[0041] A multi-level sensor network, including a ground penetrating radar sensor, a piezoelectric sensor, a temperature and humidity sensor, and an accelerometer, for real-time collecting and preprocessing data on the internal structure and external environment of the road surface;

[0042] A data processing module, for synchronizing the time and unifying the format of the ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, performing multi-modal data fusion using data-level, feature-level, and decision-level fusion methods, and extracting features through a deep learning model to generate fused feature data and disease feature data;

[0043] An analysis module, for combining environmental feature data and usage pattern feature data to construct a disease cause model and a disease development trend prediction model, analyzing the causes, development trends, and impacts of diseases, and generating disease cause analysis data, disease trend prediction data, and disease impact assessment data, where the usage pattern feature data is generated by synchronizing the time and unifying the format of traffic flow data, vehicle weight data, and road surface usage frequency data;

[0044] An intelligent prediction and decision support module, for constructing an intelligent prediction system and a decision support system based on the disease cause analysis data, disease trend prediction data, and disease impact assessment data, providing real-time disease prediction and maintenance strategies, generating disease prediction data and maintenance strategy data, and optimizing the intelligent prediction system and the decision support system according to actual maintenance feedback;

[0045] A condition assessment and report generation module, for using the real-time updated disease prediction data and disease feature data to evaluate the current disease condition and generate a disease status report.

[0046] Compared with the prior art, the advantages and beneficial effects of the present invention are:

[0047] Through the technical means of a multi-level sensor network, the present invention realizes the comprehensiveness and timeliness of data collection;

[0048] Through the technical means of multi-modal data fusion and deep learning, the present invention realizes the comprehensive analysis of multi-source data and the accuracy of disease identification;

[0049] Through the technical means of a disease prediction model that combines the dynamic environment and usage patterns, the present invention realizes the accuracy and real-time nature of disease prediction and early warning;

[0050] Through the technical means of an intelligent prediction and decision support system, the present invention realizes the scientific nature of maintenance strategies and the optimization of resource allocation;

[0051] Through the technical means of a real-time data analysis and report generation system, the present invention realizes the timeliness and comprehensiveness of disease condition assessment and report generation. Brief Description of the Drawings

[0052] Figure 1 It is a schematic flowchart of the method of the present invention;

[0053] Figure 2 It is a flowchart of multi-modal data fusion in the present invention;

[0054] Figure 3 It is a schematic diagram of a disease cause model and a disease development trend prediction model in the present invention;

[0055] Figure 4 It is an architecture diagram of an intelligent prediction and decision support system in the present invention;

[0056] Figure 5 It is a schematic diagram of a disease status report in the present invention;

[0057] Figure 6 It is a structural block diagram of the system of the present invention. Detailed Embodiments

[0058] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0059] The terms used herein are for describing specific embodiments only and are not intended to limit the present disclosure. Terms such as "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0060] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted to have a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0061] In cases where expressions such as "at least one of A, B, and C, etc." are used, generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.). In cases where expressions such as "at least one of A, B, or C, etc." are used, generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0062] Some block diagrams and / or flowcharts are shown in the drawings. It should be understood that some blocks or combinations of blocks in the block diagrams and / or flowcharts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when executed by the processor, these instructions can create a device for implementing the functions / operations illustrated in these block diagrams and / or flowcharts. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). Additionally, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by or in conjunction with an instruction execution system.

[0063] As Figure 1 shown, an artificial intelligence-based method for analyzing internal pavement diseases includes the following steps:

[0064] By arranging a sensor network for the interior of the pavement, collecting and preprocessing data on the internal structure and external environment of the pavement in real time, and generating ground-penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data;

[0065] Preferably, the sensor network includes: ground penetrating radar sensors, piezoelectric sensors, temperature and humidity sensors, and accelerometers, which are arranged at different depths and regions, including:

[0066] By applying ground penetrating radar sensors, electromagnetic wave reflection data of the road surface internal structure is collected;

[0067] Piezoelectric sensors are arranged on and below the road surface to collect vibration and pressure data;

[0068] Temperature and humidity sensors are arranged in the road surface surrounding environment to collect environmental temperature and humidity data;

[0069] Accelerometers are arranged in key areas of the road surface to collect dynamic stress data of the road surface.

[0070] In the present invention, by arranging a variety of sensors, data of the road surface internal structure and external environment can be comprehensively and accurately collected, providing detailed basic data for the analysis of road surface internal diseases. The ground penetrating radar sensors detect changes in the road surface internal structure by emitting electromagnetic waves and receiving their reflected signals, and the generated ground penetrating radar characteristic data can reflect the hierarchical structure of the road surface and potential disease locations. Piezoelectric sensors utilize the piezoelectric effect. When the road surface is subjected to vehicle loads or other pressures, the generated electrical signals reflect vibration and pressure changes. In this way, piezoelectric sensors can generate vibration characteristic data for monitoring the stress distribution on the road surface. Temperature and humidity sensors are used to collect environmental temperature and humidity data. Environmental conditions have an important impact on the formation and development of road surface diseases, and the data provided by temperature and humidity sensors can help understand the influence of environmental factors on the road surface. Accelerometers are arranged in key areas of the road surface to collect dynamic stress data. When a vehicle passes by, the road surface will generate a dynamic response, and the data of the accelerometers can reflect the dynamic stress change situation of the road surface.

[0071] These sensors are preferably arranged at different depths and regions to ensure comprehensive coverage of the monitoring area and provide high-resolution data. By applying ground penetrating radar sensors, their electromagnetic wave reflection data can penetrate multiple layers of the road surface structure, providing detailed internal structure information. Piezoelectric sensors are arranged both on the road surface and below, and can capture vibration and pressure changes on the surface and inside. Temperature and humidity sensors are arranged in the road surface surrounding environment to ensure accurately reflecting the influence of environmental temperature and humidity changes on the road surface. Accelerometers are arranged in key areas of the road surface, such as sections that are often crushed by heavy-duty vehicles, and can provide dynamic stress data of the key areas.

[0072] Through the above arrangements and data acquisition methods, the present invention can achieve comprehensive monitoring of the internal structure and external environment of the road surface. The real-time acquired data is preprocessed to generate ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, which provide a reliable basis for subsequent multi-modal data fusion and deep feature extraction. Specifically, the ground penetrating radar feature data is used to identify structural anomalies and potential disease locations inside the road surface, the vibration feature data is used to analyze the stress distribution on the road surface, the environmental feature data is used to evaluate the impact of environmental conditions on the road surface, and the stress feature data is used to monitor the response of the road surface under dynamic loads. Through the fusion and deep feature extraction of these multi-modal data, comprehensive feature information is provided for the analysis of disease causes and trend prediction, which helps to achieve accurate identification and prediction of road surface diseases, thereby formulating effective maintenance strategies, extending the service life of the road surface, and ensuring traffic safety.

[0073] As Figure 2 shown, after synchronizing the time and unifying the format of the ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, multi-modal data fusion is performed using data-level, feature-level, and decision-level fusion methods, and feature extraction is performed through a deep learning model to generate fusion feature data and disease feature data;

[0074] Preferably, the multi-modal data fusion method includes:

[0075] Data-level fusion: Combine the original data of different sensors at the data level to generate a fusion data set;

[0076] Feature-level fusion: Extract the features of various types of data and fuse the extracted features to generate fusion feature data;

[0077] Decision-level fusion: After independently analyzing various types of data, fuse the results to generate comprehensive decision-making data.

[0078] Through time synchronization and format unification, it is ensured that data from different sensors can be compared and analyzed on the same time axis and have the same format, which is convenient for subsequent processing. Time synchronization is achieved by using timestamps or synchronization signals, and format unification is achieved through data normalization processing to convert data with different units and scales into a unified standard format.

[0079] Data-level fusion is to combine the original data of different sensors at the data level to generate a fusion data set. For example, combine the electromagnetic wave reflection data of the ground penetrating radar, the vibration data of the piezoelectric sensor, the environmental data of the temperature and humidity sensor, and the dynamic stress data of the accelerometer into a comprehensive data set. This fusion data set can provide more comprehensive road surface information and help to discover disease features that cannot be detected by a single sensor.

[0080] Feature-level fusion extracts features from various types of data and fuses these features to generate fused feature data. Feature extraction refers to extracting information that can characterize the essence of the data from the original data. For example, extracting reflection intensity features from ground-penetrating radar data, frequency features from vibration data, temperature and humidity change features from environmental data, and stress distribution features from stress data. Fusing these feature data can enhance the ability to identify pavement diseases. For example, by combining reflection intensity features and vibration frequency features, cracks inside the pavement can be identified more accurately.

[0081] Decision-level fusion independently analyzes various types of data and then fuses the analysis results to generate comprehensive decision data. In this process, each type of data is processed through a deep learning model to generate preliminary disease identification results, and then these identification results are comprehensively analyzed. For example, ground-penetrating radar data may identify cavities under the pavement, vibration data may identify cracks on the pavement surface, and environmental data may identify damages caused by temperature and humidity changes. Through decision-level fusion, these identification results are combined to more comprehensively evaluate the health status of the pavement and generate comprehensive disease feature data.

[0082] Through the multi-modal data fusion method, the data advantages of different sensors can be fully utilized, the deficiencies of a single data source can be compensated, and the accuracy and robustness of disease identification can be improved. Combining feature extraction and decision-level fusion with a deep learning model can not only automatically process a large amount of data but also improve the accuracy and reliability of the analysis results. In practical applications, this method can help maintenance personnel promptly discover and handle pavement diseases, extend the service life of the pavement, reduce maintenance costs, and ensure traffic safety. In this way, the present invention realizes a comprehensive, accurate, and intelligent analysis of internal pavement diseases, effectively improving the efficiency of pavement maintenance and management.

[0083] Preferably, the deep learning model includes a convolutional neural network and a graph convolutional network for feature extraction and disease identification, including:

[0084] Using the convolutional neural network to extract features from the fused feature data to generate preliminary disease feature data;

[0085] Using the graph convolutional network to further process the preliminary disease feature data to generate the final disease feature data.

[0086] In the present invention, the deep learning model includes a Convolutional Neural Network (CNN) and a Graph Convolutional Network (GCN) for feature extraction and disease identification. First, the Convolutional Neural Network is used to extract features from the fused feature data to generate preliminary disease feature data; then, the Graph Convolutional Network is used to further process the preliminary disease feature data to generate the final disease feature data.

[0087] The Convolutional Neural Network (CNN) is a deep learning model widely used in the fields of image processing and feature extraction. Its core principle is to process the input data layer by layer through convolutional layers, pooling layers, and fully connected layers to extract high-level features. In the present invention, the CNN is used to process the fused feature data to extract the preliminary disease feature data. For example, when the input data is a dataset fused with ground penetrating radar features, vibration features, environmental features, and stress features, the CNN can extract features related to pavement diseases through convolutional operations, such as the morphology of cracks and abnormal stress distributions. Convolutional operations can effectively capture local features, while pooling operations can reduce the data dimension to prevent overfitting.

[0088] After the preliminary disease feature data is generated, the Graph Convolutional Network (GCN) is used for further processing. The GCN is a deep learning model suitable for processing graph-structured data. Its principle is to perform graph convolution operations to fully utilize the connection relationships between nodes for feature extraction and information propagation. In the present invention, pavement diseases can be regarded as a graph structure, where each node represents feature data at different positions, and the edges between nodes represent the correlations between these positions. For example, there may be correlations between stress data and vibration data at different positions on the pavement, and the GCN can capture these associated information. Through graph convolution operations, the GCN can combine the local features in the preliminary disease feature data with global information to generate more accurate and comprehensive disease feature data.

[0089] Combining the advantages of the CNN and the GCN, the present invention can effectively extract features and identify pavement diseases at different levels. The CNN is good at processing structured grid data, such as image data, and can capture local features; while the GCN can process unstructured graph data and capture complex associated information between nodes. In practical applications, first, the CNN extracts local features related to diseases, and then the GCN further integrates these features to generate the final disease feature data. This method not only improves the accuracy of feature extraction but also enhances the robustness of disease identification.

[0090] In terms of embodiments, for example, when detecting road surface cracks, the fused feature data includes information such as electromagnetic wave reflection intensity, vibration frequency, ambient temperature, and stress distribution. The CNN can initially identify the possible locations and forms of cracks by processing this data. Then, the GCN takes these initially identified feature data as input, combines the correlation information between each location, further confirms the actual situation of the cracks, and identifies the depth, length, and the degree of impact on the road surface of the cracks. The finally generated disease feature data can be provided to maintenance personnel for formulating maintenance plans, timely repairing cracks, and ensuring the safety and durability of the road surface.

[0091] In summary, by combining the convolutional neural network and the graph convolutional network, the present invention can effectively extract and identify road surface disease features, and generate accurate and comprehensive disease feature data. This method not only utilizes the advantages of different types of data, but also can capture complex correlation information, improving the accuracy and reliability of road surface disease analysis, thereby providing strong support for road surface maintenance and management.

[0092] As Figure 3 shown, by combining environmental feature data and usage pattern feature data, a disease cause model and a disease development trend prediction model are constructed to analyze the causes, development trends, and impacts of diseases, and generate disease cause analysis data, disease trend prediction data, and disease impact assessment data; the usage pattern feature data is generated after time synchronization and format unification processing of traffic flow data, vehicle weight data, and road surface usage frequency data;

[0093] The environmental feature data includes environmental factors such as temperature, humidity, and rainfall that affect the road surface condition. These data are collected in real time by temperature and humidity sensors arranged around the road surface, and after data preprocessing steps, standardized environmental feature data is formed. These data are crucial for understanding the impact of environmental changes on road surface diseases. For example, frequent temperature changes may cause the road surface material to expand and contract, resulting in cracks.

[0094] The usage pattern feature data refers to the usage conditions of the road, including traffic flow data, vehicle weight data, and road surface usage frequency data. These data are collected in real time by sensors arranged on the road surface and generated after time synchronization and format unification processing. For example, traffic flow data can be obtained through traffic monitoring cameras and flow meters installed at the road entrance, vehicle weight data can be obtained through weighing sensors installed on the road surface, and road surface usage frequency data is obtained through vehicle passing times statistics. These data can reflect the load conditions of the road surface under different usage conditions and have a direct impact on the formation and development of diseases.

[0095] The disease cause model is used to analyze the influence of environmental characteristic data and usage pattern characteristic data on the formation of road surface diseases. This model is trained by machine learning algorithms and uses historical data to establish the relationship between the environment, usage patterns, and diseases. For example, through methods such as linear regression models and multi-layer perceptrons (MLPs), the influence degree of factors such as environmental temperature, humidity change, and traffic flow on road surface diseases such as cracks and settlements can be trained. The disease cause analysis data generated by the disease cause model can help maintenance personnel understand which factors are the main disease causes, so as to take targeted preventive measures.

[0096] The disease development trend prediction model is used to predict the development trend of diseases in the future for a period of time. This model combines the disease cause analysis data and time variables, and through time series analysis methods (such as LSTM, ARIMA, etc.), predicts the development trajectory of diseases. For example, in the case of existing cracks, the model can predict the expansion speed and range of the cracks in the next few months, providing a scientific basis for the maintenance plan. Through the disease development trend prediction data, maintenance personnel can formulate repair plans in advance to avoid the further deterioration of diseases.

[0097] The disease impact assessment data is used to evaluate the impact of diseases on the road surface structure and traffic safety. This assessment combines the disease cause analysis data and the disease trend prediction data, and uses simulation technologies such as finite element analysis (FEA) to evaluate the impact of diseases on the load-bearing capacity and service life of the road surface structure. For example, by simulating the stress conditions of the road surface in different disease states, the degree of weakening of the overall strength of the road surface by cracks and the impact on the safety of heavy vehicle traffic can be evaluated.

[0098] In practical applications, assume that on a certain highway, the environmental characteristic data shows that there has been frequent rainfall and large temperature changes recently, and the usage pattern characteristic data indicates that the traffic flow on this section is large and there are many heavy vehicles. Through the disease cause model, it can be analyzed that rainfall and temperature changes cause fatigue of road surface materials, and heavy vehicles further exacerbate the formation of cracks. Using the disease development trend prediction model, it can be predicted to what extent the cracks will expand in the next few months. Finally, through the disease impact assessment, it can be evaluated that if not repaired in time, the crack may lead to a decrease in the load-bearing capacity of the road surface and potential safety hazards. These analysis results provide a scientific basis for the highway management department to help it formulate timely maintenance and repair plans.

[0099] To sum up, the present invention combines environmental characteristic data and usage pattern characteristic data, constructs a disease cause model and a disease development trend prediction model, realizes a comprehensive analysis of the causes, development trends, and impacts of road surface diseases, and provides important data support and decision-making basis for road surface maintenance and management.

[0100] Preferably, the disease cause model is calculated by the following formula:

[0101] C = f(E, u) = a·E + b·U + c

[0102] Where C represents the data for analyzing the causes of diseases, E represents the environmental characteristic data, U represents the usage pattern characteristic data, f represents the function that converts the environmental characteristic data and the usage pattern characteristic data into the data for analyzing the causes of diseases, a and b are weights, and c is a bias parameter.

[0103] The environmental characteristic data (E) includes environmental factors affecting the road surface conditions, such as temperature, humidity, rainfall, etc. These data are collected in real time by temperature and humidity sensors arranged around the road surface, and after data preprocessing steps, standardized environmental characteristic data are formed. The environmental characteristic data reflects the impact of the natural environment on the road surface. For example, frequent temperature changes may cause the road surface materials to expand and contract, resulting in cracks.

[0104] The usage pattern characteristic data (U) reflects the usage conditions of the road, including traffic flow data, vehicle weight data, and road surface usage frequency data. These data are collected in real time by sensors arranged on the road surface, and are generated after time synchronization and format unification processing. The traffic flow data can be obtained through traffic monitoring cameras and flow meters installed at the road entrance, the vehicle weight data can be obtained through weighing sensors installed on the road surface, and the road surface usage frequency data is obtained through counting the number of vehicle passages. The usage pattern characteristic data can show the load conditions of the road surface under different usage conditions, and has a direct impact on the formation and development of diseases.

[0105] The disease cause model converts the environmental characteristic data and the usage pattern characteristic data into the data for analyzing the causes of diseases (C) through the above formula. In this formula, a and b are weights, representing the influence degrees of environmental factors and usage patterns on the causes of diseases, and c is a bias term, which is used to adjust the accuracy of the model output. This model is trained through machine learning algorithms, and uses historical data to establish the relationship between the environment, usage patterns, and diseases. For example, the model can train the influence degrees of factors such as temperature, humidity changes, and traffic flow on diseases such as road surface cracks and settlements through methods such as linear regression, decision trees, or multi-layer perceptrons.

[0106] The core of the disease cause model lies in using a large amount of historical data to find the relationship between environmental characteristics, usage pattern characteristics, and the causes of diseases through machine learning algorithms. Through this model, it is possible to accurately predict the types and severity of diseases that may occur on the road surface under the current environment and usage patterns. Specifically, assuming that a certain road has experienced frequent rainfall and a large number of heavy-duty vehicles passing through in the past few months, the model can analyze the cumulative impact of these factors on the road surface and predict the most likely disease types, such as crack expansion or road surface settlement.

[0107] For example, on a certain highway, the environmental characteristic data (E) shows frequent recent rainfall and large temperature variations, while the usage pattern characteristic data (U) indicates heavy traffic flow and a large number of heavy-duty vehicles on this section. Through the disease cause model, it can be analyzed that rainfall and temperature changes lead to pavement material fatigue, and heavy-duty vehicles further exacerbate the formation of cracks. The model will use historical data to determine the values of a, b, and c, so that the formula can accurately calculate the disease cause analysis data (C) under such environmental and usage patterns. This kind of analysis can help highway management departments identify potential pavement diseases in advance and take corresponding preventive measures, such as timely repairing cracks or strengthening the pavement, to extend the service life of the pavement and ensure driving safety.

[0108] In summary, the disease cause model generates disease cause analysis data by comprehensively analyzing environmental characteristic data and usage pattern characteristic data and using machine learning algorithms to establish the relationship between disease causes and these factors. This method not only improves the accuracy of disease identification but also provides targeted preventive measures, significantly enhancing the efficiency and effectiveness of pavement maintenance and management.

[0109] Preferably, the disease development trend prediction model is calculated by the following formula:

[0110] T = g(C, t) = α·C + β·t + γ

[0111] Where, T represents the disease trend prediction data, C represents the disease cause analysis data, t represents the time variable, g represents the function that converts the disease cause analysis data and the time variable into the disease trend prediction data, α and β are weights, and γ is the bias parameter.

[0112] The disease cause analysis data (C) comes from the aforementioned disease cause model and is generated by analyzing environmental characteristic data and usage pattern characteristic data. The disease cause analysis data reflects the formation situation of pavement diseases under the current environment and usage conditions, including information such as disease types, locations, and their severity. The time variable (t) represents the predicted time range, which can be several days, weeks, or even months in the future.

[0113] The core of the disease development trend prediction model lies in using the disease cause analysis data and the time variable to predict the future development trajectory of diseases. The model is trained through machine learning algorithms and establishes the relationship between disease development and time by combining historical data. α and β in the formula are weights, indicating the influence degree of the disease cause analysis data and the time variable on the disease development trend, and γ is the bias term, which is used to adjust the accuracy of the model output.

[0114] The disease development trend prediction model can provide future predictions of pavement diseases, helping managers formulate preventive maintenance plans. For example, when the model inputs the current disease cause analysis data and the future time range, the model can output disease trend prediction data, showing the possible development status of diseases at a certain future time point. Such predictions can identify potential risk areas in advance, perform maintenance and repairs in a timely manner, and avoid the further spread of diseases.

[0115] For example, assume that the current disease cause analysis data (C) of a certain road shows multiple cracks, and the usage pattern feature data indicates that the traffic flow on this section is large and there are many heavy-duty vehicles. Through the disease development trend prediction model, the development trend of these cracks in the next few months can be predicted. The model may show that under the current conditions, the cracks will expand to a larger range in the next few months and may affect the overall structure of the road surface. The prediction result (T) can help the highway management department formulate a repair plan in advance, fill the cracks in a timely manner, and prevent the disease from deteriorating further.

[0116] In practical applications, the disease development trend prediction model can be optimized by combining multiple machine learning algorithms. For example, time series analysis methods such as Long Short-Term Memory Networks (LSTM) and Autoregressive Integrated Moving Average models (ARIMA) can be used to capture the time dependence and periodic changes in disease development. In addition, regression algorithms such as decision trees and random forests can also be used for modeling to handle complex non-linear relationships. By combining these algorithms, the disease development trend prediction model can provide more accurate and reliable prediction results.

[0117] In summary, the disease development trend prediction model establishes the relationship between disease development and time by comprehensively considering disease cause analysis data and time variables, training with machine learning algorithms, and generating disease trend prediction data. This method can not only predict the future development trend of diseases, but also provide a scientific basis for pavement maintenance and management, help managers formulate maintenance plans in advance, prevent the further spread of diseases, and ensure the safety and durability of the road surface.

[0118] As Figure 4 shown, based on disease cause analysis data, disease trend prediction data, and disease impact assessment data, an intelligent prediction system and a decision support system are constructed to provide real-time disease predictions and maintenance strategies, generate disease prediction data and maintenance strategy data, and optimize the intelligent prediction system and the decision support system according to the actual maintenance feedback;

[0119] The data for analyzing the causes of diseases is generated by a disease cause model, which reflects the impact of environmental characteristic data and usage pattern characteristic data on the formation of road diseases. The data for predicting disease trends is generated by a disease development trend prediction model, which predicts the development trajectory of diseases over a period of time in the future. The data for evaluating the impact of diseases assesses the impact of diseases on road structure and traffic safety, and is usually obtained through simulation technologies such as finite element analysis (FEA).

[0120] The intelligent prediction system comprehensively analyzes this data to predict the future development of road diseases in real time. The system uses machine learning and artificial intelligence algorithms, combines historical data and real-time data, and dynamically predicts road diseases. For example, using regression analysis, time series analysis or deep learning models, the intelligent prediction system can predict the development trends of road diseases in the next few days, weeks or even months.

[0121] Based on the output of the intelligent prediction system, the decision support system provides specific maintenance strategies. The system combines the data for analyzing the causes of diseases, the data for predicting disease trends and the data for evaluating the impact of diseases, and provides scientific decision support for maintenance personnel. For example, the decision support system can recommend maintaining a certain section of the road within a specific time period to prevent the diseases from deteriorating further; or recommend using specific repair materials and methods to extend the service life of the road surface.

[0122] Through the collaborative work of the intelligent prediction system and the decision support system, specific disease prediction data and maintenance strategy data can be generated. The disease prediction data includes the prediction results of disease types, locations, severities and their future developments. The maintenance strategy data includes maintenance time, maintenance resource allocation, specific operation suggestions, etc. These data can help highway management departments take preventive maintenance measures in a timely manner, reduce the impact of diseases on traffic safety, and lower maintenance costs.

[0123] In practical applications, the optimization of the intelligent prediction system and the decision support system depends on actual maintenance feedback. By regularly collecting and analyzing maintenance result data, the accuracy and effectiveness of predictions and decisions can be evaluated. For example, if a certain section of the road surface is repaired according to the recommended maintenance strategy but the diseases still spread, it indicates that there may be deficiencies in the system's predictions and decisions. By adjusting and optimizing model parameters, the intelligent prediction system and the decision support system can continuously improve their accuracy and reliability.

[0124] For example, cracks appear in multiple locations on a certain highway. Through the analysis of the disease cause model, it is found that frequent temperature changes and heavy-duty vehicles are the main causes. The intelligent prediction system uses the disease trend prediction data to predict that the cracks will further expand in the next few months. The decision support system recommends repairs before the cracks expand and provides specific repair times and methods. After the actual maintenance, the management department feedbacks that the repair effect is good, and the system uses this feedback to optimize the model and improve the accuracy of future predictions and decisions.

[0125] In summary, by constructing an intelligent prediction system and a decision support system, the present invention can provide disease predictions and maintenance strategies in real time, generate specific disease prediction data and maintenance strategy data, and continuously optimize the system according to the actual maintenance feedback. This method not only improves the accuracy of pavement disease prediction but also enhances the scientific nature of maintenance decisions, effectively extends the service life of the pavement, and ensures traffic safety.

[0126] Preferably, the intelligent prediction system adopts a reinforcement learning algorithm to continuously optimize disease predictions and maintenance strategies, including:

[0127] Based on historical disease data and current disease data, use the reinforcement learning algorithm to train an intelligent prediction model;

[0128] According to the real-time updated disease data, adjust and optimize the parameters of the intelligent prediction model to generate real-time disease prediction data.

[0129] The intelligent prediction system trains an intelligent prediction model based on historical disease data and current disease data. Historical disease data includes past pavement disease conditions and their corresponding environmental and usage pattern feature data, which provide a large number of learning samples for the model. Current disease data is the pavement disease condition collected in real time, including the latest ground-penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data.

[0130] During the training process of the reinforcement learning algorithm, the interaction process between the environment (i.e., the pavement disease condition) and the agent (i.e., the prediction model) is represented as a Markov decision process (MDP). At each time step, the agent observes the current state (such as the current disease cause analysis data and environmental feature data), selects an action (such as predicting future disease development or recommending a maintenance strategy), and then updates the strategy according to the feedback of the environment (such as the actual disease development situation) to maximize the cumulative reward (such as the accuracy of disease prediction or the effectiveness of the maintenance strategy).

[0131] In practical applications, the intelligent prediction system will be optimized through the following steps:

[0132] Initialize the model: Based on the initial historical disease data, initialize the parameters of the intelligent prediction model and the reinforcement learning algorithm.

[0133] Train the model: The intelligent prediction model learns the optimal strategy by continuously interacting with the environment. For example, the model may try different disease prediction methods or maintenance strategies, observe their effects, and update the strategy according to the reward signal (such as prediction accuracy or maintenance effect). The training process may include multiple rounds of iteration until the model converges.

[0134] Real-time optimization: When new disease data is updated in real time, the intelligent prediction system adjusts and optimizes the model parameters according to this data. The reinforcement learning algorithm uses the new data for online learning, enabling the model to adapt to new environmental changes and improving the accuracy of prediction and decision-making.

[0135] For example, the management department of a certain highway uses an intelligent prediction system to monitor and maintain the road surface. When the system detects cracks in a certain section of the road surface, it will predict the expansion trend of the cracks based on the current disease data and historical data, and recommend maintenance strategies. The reinforcement learning algorithm plays a key role in this process: the system will simulate different maintenance strategies (such as immediate repair or delayed repair), evaluate the effects of each strategy, and then select the optimal strategy and implement it. If the actual maintenance effect is not good, the system will further adjust the strategy according to the feedback data to continuously optimize the model.

[0136] In this way, the intelligent prediction system can generate real-time disease prediction data and maintenance strategy data. These data include disease types, locations, severities, and prediction results of their future development, as well as specific maintenance times, resource allocations, and operation suggestions. The real-time disease prediction data helps the management department identify potential risk areas in advance, and the maintenance strategy data provides a scientific basis for decision-making to ensure that the maintenance work is timely and effective.

[0137] In summary, the present invention constructs an intelligent prediction system by adopting a reinforcement learning algorithm, enabling it to continuously optimize disease prediction and maintenance strategies based on historical and current data. Through reinforcement learning, the intelligent prediction system not only improves the accuracy of disease prediction but also enhances the scientific nature of maintenance decisions, effectively extending the service life of the road surface and ensuring traffic safety.

[0138] Preferably, the maintenance strategy data includes maintenance time, maintenance resources, and specific operation suggestions, including:

[0139] Determine the areas that need to be preferentially maintained and the specific maintenance time according to the disease impact assessment data;

[0140] Allocate maintenance resources according to the disease severity and resource availability, and generate a maintenance resource allocation plan;

[0141] Provide specific operation suggestions, including maintenance tools to be used, operation steps, and safety precautions.

[0142] Based on the disease impact assessment data, determine the areas that need to be prioritized for maintenance and the specific maintenance time. The disease impact assessment data is generated from the aforementioned disease cause analysis and disease trend prediction, and includes the type, location, severity of the disease, and its potential impact on the road surface structure and traffic safety. By analyzing this data, the system can identify the areas with the most severe diseases and the greatest impact on traffic, and formulate a detailed maintenance schedule according to the development trend of the diseases and the actual road surface usage. For example, if a section of the road surface has severe cracks and the cracks are expanding rapidly, the system will prioritize the emergency repair of this section of the road surface and formulate the corresponding maintenance time to minimize the interference to traffic.

[0143] Next, allocate maintenance resources according to the disease severity and resource availability to generate a maintenance resource allocation plan. The disease severity is evaluated through the disease cause model and the disease development trend prediction model, and the resource availability is determined according to the actual situation of the current maintenance equipment, personnel, and material inventory, etc. The system will reasonably allocate maintenance resources according to the severity and urgency of different diseases. For example, for minor road surface damage, regular maintenance equipment and personnel can be arranged; for severe diseases, more resources may need to be allocated, including heavy machinery and professional maintenance personnel. The resource allocation plan should not only consider the urgency of the diseases, but also the optimal utilization of maintenance resources to avoid resource waste and duplication of maintenance work.

[0144] Finally, provide specific operation suggestions, including maintenance tools to be used, operation steps, and safety precautions. The generation of specific operation suggestions is based on the maintenance strategy data and historical maintenance records. The system will combine the disease type and severity to recommend the most suitable maintenance tools and methods. For example, for crack repair, the system may recommend using a specific type of caulking material and construction equipment, and provide detailed operation steps, including crack cleaning, preparation of caulking materials, and construction process. At the same time, the system will also provide safety precautions to ensure the safety of maintenance work. For example, when repairing asphalt road surfaces in high-temperature weather, attention needs to be paid to preventing equipment overheating and heatstroke of construction workers; when constructing at night, sufficient lighting and warning signs need to be set up to ensure construction safety.

[0145] For example, the management department of a certain highway, through an intelligent prediction system and a decision support system, identifies that there are serious cracks in a certain section of the road surface and may expand to a larger area in the next few weeks. Based on the disease impact assessment data, the system determines that this section of the road surface needs to be maintained as a priority and recommends arranging emergency repair work within the next week. According to the severity of the disease and the availability of resources, the system generates a maintenance resource allocation plan, allocates sufficient maintenance equipment and professional personnel. At the same time, the system provides detailed operation suggestions, recommends using a certain efficient crack filling material, and provides specific construction steps and safety precautions. During the actual construction process, the maintenance team operates according to the suggestions provided by the system, successfully repairs the road surface cracks, avoids the further expansion of the disease, and ensures traffic safety and road surface durability.

[0146] Through the above steps, the generation and optimization of maintenance strategy data can effectively improve the efficiency and safety of road surface maintenance work. The present invention, through an intelligent prediction and decision support system, not only provides scientific disease prediction and maintenance strategies, but also ensures the efficient execution and safe operation of actual maintenance work. This method significantly improves the overall level of road surface maintenance and management, extends the service life of the road surface, reduces maintenance costs, and ensures the safety and smoothness of the road.

[0147] As Figure 5 shown, using the real-time updated disease prediction data and disease characteristic data, the current disease condition is evaluated, and a disease current situation report is generated.

[0148] Preferably, the disease current situation report includes a disease distribution map, disease type analysis, and disease severity assessment, and provides detailed information in the form of charts and text descriptions, including:

[0149] Disease distribution map: showing the specific location and distribution of diseases on the road surface;

[0150] Disease type analysis: classifying and describing different types of diseases and their characteristics;

[0151] Disease severity assessment: quantitatively evaluating the severity of the disease, providing specific scores and suggestions.

[0152] The disease prediction data is generated by an intelligent prediction system, and based on historical disease data, current disease data, and reinforcement learning algorithms, it predicts the future development trend of diseases in real time. The disease characteristic data is extracted by multi-modal data fusion and deep learning models, and contains specific characteristics of road surface diseases, such as the width, depth, and length of cracks, as well as information such as surface deformation and stress distribution.

[0153] Using these real-time updated data, the system can comprehensively evaluate the current disease condition and generate a detailed disease current situation report. The disease current situation report includes the following core parts:

[0154] Disease distribution map: The disease distribution map shows the specific locations and distribution of diseases on the road surface. By combining the characteristic data of ground-penetrating radar, vibration characteristics, environmental characteristics, and stress characteristics, the system can draw an accurate disease distribution map. For example, through ground-penetrating radar data, voids and cracks inside the road surface can be identified, and through vibration data, surface cracks and deformations can be identified. After these data are fused and processed, the generated disease distribution map can intuitively show the specific locations and scopes of diseases, helping maintenance personnel quickly locate the areas that need to be repaired.

[0155] Disease type analysis: Disease type analysis classifies and describes different types of diseases and explains their characteristics in detail. For example, the system can identify and classify different types of cracks (such as longitudinal cracks, transverse cracks, and reticular cracks), potholes, settlements, and surface wear, etc. The characteristics of each disease type are described in detail, including its formation reasons, development processes, and impacts on the road surface structure. Through this classification and analysis, maintenance personnel can better understand the nature and causes of diseases, and thus formulate targeted maintenance strategies.

[0156] Disease severity assessment: Disease severity assessment quantitatively evaluates the severity of diseases and provides specific scores and suggestions. The system combines disease characteristic data and prediction data, and adopts specific assessment criteria and algorithms to quantitatively evaluate the severity of each disease. For example, by evaluating the width, depth, and length of cracks, the severity score of the cracks can be calculated; by analyzing the amplitude and scope of road surface settlement, the impact of settlement on traffic safety can be evaluated. The assessment results are presented in the form of scores and accompanied by specific maintenance suggestions, such as immediate repair, regular monitoring, or further investigation.

[0157] Through the generated disease status report, maintenance personnel can comprehensively understand the current health status of the road surface and accordingly formulate a scientific maintenance plan. The charts and written descriptions in the report are intuitive in form and easy to understand and apply. For example, on a certain highway, the disease distribution map generated by the system shows the specific locations of multiple severe cracks; the disease type analysis further explains the types and formation reasons of these cracks; the disease severity assessment provides the severity scores and specific maintenance suggestions for each crack, such as some cracks need to be repaired immediately, while others can be monitored regularly. Based on these detailed information, the maintenance team can quickly take actions to repair severe diseases, prevent potential risks, and ensure the safety and durability of the road surface.

[0158] In summary, the present invention generates a detailed disease status report, including a disease distribution map, disease type analysis, and disease severity assessment, by utilizing real-time updated disease prediction data and disease feature data. This report provides comprehensive and accurate disease information for maintenance personnel, helping them formulate and implement effective maintenance strategies, and significantly improving the efficiency and effectiveness of pavement maintenance and management.

[0159] As Figure 6 shown, a system for implementing the above artificial intelligence-based pavement internal disease analysis method includes:

[0160] A multi-level sensor network, including arranged ground penetrating radar sensors, piezoelectric sensors, temperature and humidity sensors, and accelerometers, for real-time collecting and preprocessing pavement internal structure and external environment data;

[0161] The multi-level sensor network includes arranged ground penetrating radar sensors, piezoelectric sensors, temperature and humidity sensors, and accelerometers. The ground penetrating radar sensor detects changes in the pavement internal structure by emitting electromagnetic waves and receiving their reflected signals, generating ground penetrating radar feature data. The piezoelectric sensor utilizes the piezoelectric effect to collect vibration and pressure data, generating vibration feature data. The temperature and humidity sensor collects environmental temperature and humidity data, generating environmental feature data. The accelerometer collects pavement dynamic stress data, generating stress feature data. These sensors are arranged at different depths and regions to ensure full coverage of the monitoring area and provide high-resolution data.

[0162] A data processing module, for synchronizing the time and unifying the format of the ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, performing multi-modal data fusion using data-level, feature-level, and decision-level fusion methods, and extracting features through a deep learning model to generate fused feature data and disease feature data;

[0163] The data processing module is used to synchronize the time and unify the format of the ground penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data. Time synchronization is achieved by using timestamps or synchronization signals, and format unification is achieved through data normalization processing to convert data with different units and scales into a unified standard format. Then, multi-modal data fusion is performed using data-level, feature-level, and decision-level fusion methods. Data-level fusion combines the raw data of different sensors at the data level, feature-level fusion extracts and fuses the features of various types of data, and decision-level fusion independently analyzes various types of data and then fuses the results. Feature extraction is performed through a deep learning model to generate fused feature data and disease feature data. The deep learning model includes a convolutional neural network (CNN) and a graph convolutional network (GCN), which are used for local feature extraction and global information integration respectively.

[0164] An analysis module is used to combine environmental characteristic data and usage pattern characteristic data to construct a disease cause model and a disease development trend prediction model, analyze the causes, development trends and impacts of diseases, and generate disease cause analysis data, disease trend prediction data and disease impact assessment data. The usage pattern characteristic data is generated after performing time synchronization and format unification processing on traffic flow data, vehicle weight data and road surface usage frequency data.

[0165] The analysis module combines environmental characteristic data and usage pattern characteristic data to construct a disease cause model and a disease development trend prediction model. The environmental characteristic data includes factors such as temperature, humidity, and rainfall that affect the road surface condition. The usage pattern characteristic data is generated after performing time synchronization and format unification processing on traffic flow data, vehicle weight data and road surface usage frequency data. The disease cause model analyzes the impacts of environmental characteristic data and usage pattern characteristic data on the formation of road surface diseases and generates disease cause analysis data. The disease development trend prediction model combines the disease cause analysis data and time variables to predict the future development trajectory of diseases and generate disease trend prediction data and disease impact assessment data.

[0166] An intelligent prediction and decision support module is used to construct an intelligent prediction system and a decision support system based on the disease cause analysis data, disease trend prediction data and disease impact assessment data, provide real-time disease predictions and maintenance strategies, generate disease prediction data and maintenance strategy data, and optimize the intelligent prediction system and decision support system according to the actual maintenance feedback.

[0167] The intelligent prediction and decision support module constructs an intelligent prediction system and a decision support system based on the disease cause analysis data, disease trend prediction data and disease impact assessment data. The intelligent prediction system uses a reinforcement learning algorithm to continuously learn the best strategy through interaction with the environment to maximize the cumulative reward. The system performs model training and real-time optimization based on historical disease data and current disease data to generate real-time disease prediction data. The decision support system combines the disease prediction data and impact assessment data to provide detailed maintenance strategies, including maintenance time, maintenance resource allocation and specific operation suggestions, and optimizes the intelligent prediction system and decision support system according to the actual maintenance feedback.

[0168] A condition assessment and report generation module is used to evaluate the current disease condition using the real-time updated disease prediction data and disease characteristic data and generate a disease current situation report.

[0169] The condition assessment and report generation module utilizes the real-time updated disease prediction data and disease characteristic data to assess the current disease condition and generate a disease status report. The disease status report includes a disease distribution map, an analysis of disease types, and an assessment of disease severity. The disease distribution map shows the specific locations and distribution of diseases on the road surface; the analysis of disease types classifies and describes different types of diseases and their characteristics; the assessment of disease severity quantitatively evaluates the severity of the diseases, providing specific scores and suggestions.

[0170] Through the collaborative work of the above modules, the present invention realizes the comprehensive, real-time, and accurate analysis of internal road diseases and the formulation of maintenance strategies. The multi-level sensor network ensures the comprehensiveness and timeliness of data collection; the data processing module improves the accuracy of disease identification through multi-modal data fusion and deep feature extraction; the analysis module combines environmental and usage pattern data to construct a disease cause and trend prediction model, realizing the accuracy and real-time of disease prediction and early warning; the intelligent prediction and decision support module optimizes the maintenance strategy and resource allocation through reinforcement learning algorithms; the condition assessment and report generation module provides detailed disease information, providing a scientific basis for maintenance and management. The overall effect significantly improves the efficiency and effectiveness of road maintenance and management, ensuring the safety and durability of the road.

[0171] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0173] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one or more of the procedures Figure 1 one or more of the procedures and / or blocks Figure 1 specified in one or more of the blocks.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the procedures Figure 1 one or more of the procedures and / or blocks Figure 1 specified in one or more of the blocks.

[0175] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0176] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0177] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0178] It should also be noted that the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0179] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An artificial intelligence-based method for analyzing internal diseases of road surfaces, characterized in that, Including the following steps: By arranging a sensor network for the interior of the road surface, real-time collecting and preprocessing the data of the interior structure and external environment of the road surface, generating ground-penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data; After time synchronization and format unification of the ground-penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, multi-modal data fusion is carried out using data-level, feature-level, and decision-level fusion methods, and feature extraction is performed through a deep learning model to generate fusion feature data and disease feature data; Combining environmental feature data and usage pattern feature data, constructing a disease cause model and a disease development trend prediction model, analyzing the causes, development trends, and impacts of diseases, generating disease cause analysis data, disease trend prediction data, and disease impact assessment data; the usage pattern feature data is generated after time synchronization and format unification processing of traffic flow data, vehicle weight data, and road surface usage frequency data; The disease development trend prediction model is trained using a machine learning algorithm by comprehensively considering disease cause analysis data and time variables, establishing the relationship between disease development and time, generating disease trend prediction data, and the disease trend prediction data is used to predict the development trajectory of diseases in the future for a period of time; The disease development trend prediction model generates disease trend prediction data through the following formula: T = g(C, t) = α·C + β·t + γ Where, T represents the disease trend prediction data, C represents the disease cause analysis data, t represents the time variable, g represents the function that converts the disease cause analysis data and time variable into disease trend prediction data, α and β are weights, and γ is a bias parameter; Based on the disease cause analysis data, disease trend prediction data, and disease impact assessment data, constructing an intelligent prediction system and a decision support system: The intelligent prediction system, based on historical disease data, current disease data, and reinforcement learning algorithms, real-time predicts the development trend of future diseases, generating disease prediction data, and the disease prediction data includes disease types, locations, severities, and prediction results of their future development; The decision support system combines disease prediction data and disease impact assessment data to generate maintenance strategy data including maintenance time, maintenance resource allocation, and specific operation suggestions; And optimizing the intelligent prediction system and the decision support system according to the actual maintenance feedback; Using the real-time updated disease prediction data and disease feature data to evaluate the current disease condition and generate a disease status report.

2. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 1, wherein The sensor network includes: ground-penetrating radar sensors, piezoelectric sensors, temperature and humidity sensors, and accelerometers, which are arranged at different depths and regions, including: By applying ground-penetrating radar sensors to collect the electromagnetic wave reflection data of the road surface interior structure; Piezoelectric sensors are arranged on the road surface and below to collect vibration and pressure data; Temperature and humidity sensors are arranged in the surrounding environment of the road surface to collect environmental temperature and humidity data; Accelerometers are arranged in key areas of the road surface to collect road surface dynamic stress data.

3. The method for analyzing internal diseases of road surface based on artificial intelligence according to claim 1, wherein, The multi-modal data fusion method includes: Data-level fusion: Combine the raw data from different sensors at the data level to generate a fused dataset; Feature-level fusion: Extract the features of various types of data and fuse the extracted features to generate fused feature data; Decision-level fusion: After independently analyzing various types of data, fuse the results to generate comprehensive decision-making data.

4. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 3, characterized in that, The deep learning model includes a convolutional neural network and a graph convolutional network for feature extraction and disease identification, including: Use the convolutional neural network to extract features from the fused feature data to generate preliminary disease feature data; Use the graph convolutional network to further process the preliminary disease feature data to generate the final disease feature data.

5. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 1, characterized in that, The disease cause model is calculated by the following formula: C = f(E, U) = a·E + b·U + c Where, C represents the disease cause analysis data, E represents the environmental feature data, U represents the usage pattern feature data, f represents the function that converts the environmental feature data and the usage pattern feature data into the disease cause analysis data, a and b are weights, and c is the bias parameter.

6. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 1, wherein The intelligent prediction system adopts a reinforcement learning algorithm to continuously optimize the disease prediction and maintenance strategies, including: Based on historical disease data and current disease data, train the intelligent prediction model using the reinforcement learning algorithm; According to the real-time updated disease data, adjust and optimize the parameters of the intelligent prediction model to generate real-time disease prediction data.

7. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 1, characterized in that The maintenance strategy data includes maintenance time, maintenance resources, and specific operation suggestions, including: Based on the disease impact assessment data, determine the areas that need to be maintained first and the specific maintenance time; According to the disease severity and resource availability, allocate maintenance resources to generate a maintenance resource allocation plan; Provide specific operation suggestions, including the maintenance tools to be used, operation steps, and safety precautions.

8. The method for analyzing internal pavement diseases based on artificial intelligence according to claim 1, characterized in that The disease status report includes a disease distribution map, disease type analysis, and disease severity assessment, and provides detailed information in the form of charts and text descriptions, including: Disease distribution map: Displays the specific locations and distribution of diseases on the road surface; Disease type analysis: Classifies and describes different types of diseases and their characteristics; Disease severity assessment: Quantitatively assesses the severity of the disease and provides specific scores and suggestions.

9. A system for implementing the artificial intelligence-based method for analyzing internal pavement diseases according to any one of claims 1 to 8, characterized in that, Including: A multi-level sensor network, including a ground-penetrating radar sensor, a piezoelectric sensor, a temperature and humidity sensor, and an accelerometer, for real-time collecting and preprocessing the road surface internal structure and external environment data; A data processing module for synchronizing the time and unifying the format of the ground-penetrating radar feature data, vibration feature data, environmental feature data, and stress feature data, performing multi-modal data fusion using data-level, feature-level, and decision-level fusion methods, and extracting features through a deep learning model to generate fused feature data and disease feature data; An analysis module, which is used to combine environmental feature data and usage pattern feature data to construct a disease cause model and a disease development trend prediction model, analyze the causes, development trends and impacts of diseases, and generate disease cause analysis data, disease trend prediction data and disease impact assessment data. The usage pattern feature data is generated after performing time synchronization and format unification processing on traffic flow data, vehicle weight data and road surface usage frequency data; An intelligent prediction and decision support module, which is used to construct an intelligent prediction system and a decision support system based on disease cause analysis data, disease trend prediction data and disease impact assessment data, provide real-time disease prediction and maintenance strategies, generate disease prediction data and maintenance strategy data, and optimize the intelligent prediction system and the decision support system according to actual maintenance feedback; A condition assessment and report generation module, which is used to utilize real-time updated disease prediction data and disease feature data to evaluate the current disease condition and generate a disease status report.

Images