Road surface service performance monitoring method and device and related equipment

Abstract

The invention provides a pavement service performance monitoring method and device and related equipment. The method comprises the following steps: acquiring detection basic data; the detection basic data comprises environment data, road surface damage data, road surface load data and / or road surface strain data; establishing a corresponding relation between the detection basic data according to a set rule, generating an input data set, and inputting the input data set into a prediction model to perform pavement decay performance prediction; and outputting the pavement decay performance.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data monitoring, and particularly relates to a road surface service performance monitoring method and device and related equipment. BACKGROUND

[0002] As a core component of modern transportation infrastructure, the service performance of asphalt pavement directly affects road traffic safety, maintenance cost and service life. Traditional pavement performance monitoring mainly relies on manual inspection to patrol the road surface damage, and there are few indexes that can reflect the internal damage of the pavement. There are problems such as poor real-time performance, single data dimension, limited coverage, etc., which are difficult to meet the needs of intelligent transportation for dynamic and high-precision monitoring.

[0003] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those skilled in the art. SUMMARY

[0004] Therefore, the present disclosure provides a road surface service performance monitoring method, device and related equipment to solve or partially solve the above problems.

[0005] To achieve the above object, the present disclosure provides a road surface service performance monitoring method, comprising:

[0006] obtaining detection basic data; the detection basic data includes environmental data, road surface damage data, road surface load data and / or road surface strain data;

[0007] establishing a corresponding relationship between the detection basic data according to a set rule, generating an input data set, and inputting the input data set into a prediction model to predict the road surface degradation performance;

[0008] outputting the road surface degradation performance.

[0009] In some example embodiments, the detection basic data is obtained by:

[0010] The road surface load data and / or the road surface strain data are collected by a self-triggering collection unit embedded in the road surface; wherein the self-triggering collection unit generates a trigger signal through an axle load sensor, and according to the trigger signal, wakes up a stress sensor and / or a strain sensor to collect the road surface load data and / or the road surface strain data.

[0011] In some example embodiments, the corresponding relationship between the detection basic data is established according to a set rule, comprising:

[0012] The different detection basic data are associated by different pile numbers and / or coordinate basic data contained in the detection basic data, so as to establish the correspondence.

[0013] In some example embodiments, the generated input data set comprises:

[0014] The detection basic data after the correspondence is established is subjected to data screening by a density clustering algorithm.

[0015] The detection basic data after the data screening is subjected to missing detection, and the missing part is subjected to data completion.

[0016] In some example embodiments, the prediction model is built by using a long short-term memory neural network model, and a fully connected layer is connected after a long short-term memory network layer; the prediction model uses a mean square error function as a loss function, and uses an adaptive moment estimation algorithm as an optimization function to optimize the random inactivation value generated by the long short-term memory neural network model.

[0017] In some example embodiments, the prediction model is constrained during training by introducing a pavement damage mechanics equation into the training process of the prediction model.

[0018] Based on the same concept, the present disclosure also provides a pavement service performance monitoring device, comprising:

[0019] A first module is configured to acquire detection basic data; the detection basic data comprises environmental data, pavement damage data, pavement load data and / or pavement strain data;

[0020] A second module is configured to establish a correspondence between the detection basic data according to a set rule, generate an input data set, and input the input data set into a prediction model to predict pavement degradation performance;

[0021] A third module is configured to output the pavement degradation performance.

[0022] Based on the same concept, the present disclosure also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of the above.

[0023] Based on the same concept, the present disclosure also provides a non-transitory computer readable storage medium, which stores computer instructions for causing a computer to implement the method according to any one of the above.

[0024] Based on the same concept, the disclosure also provides a computer program product comprising computer program instructions which, when run on a computer, cause the computer to implement the method of any one of the above.

[0025] As can be seen from the above, the disclosure provides a pavement service performance monitoring method and device and related equipment. The method comprises: acquiring detection basic data; the detection basic data comprises environmental data, pavement damage data, pavement load data and / or pavement strain data; a corresponding relationship between the detection basic data is established according to a set rule to generate an input data set, and the input data set is input into a prediction model for pavement degradation performance prediction; and the pavement degradation performance is output. The disclosure acquires detection basic data through multiple sources of sensors or multiple channels, thereby forming pavement data of multiple different dimensions, so as to simultaneously monitor the multi-dimensional information of the mechanical response, temperature change, roadbed pavement moisture content and surface disease of the pavement. This multi-source data acquisition method overcomes the limitation of single sensor monitoring information, and provides a rich data basis for comprehensive evaluation of the service and degradation performance of the pavement. Then, since the input data adopts multi-dimensional data, part of the data may be time-dimensional data, and another part may be spatial-dimensional data. Therefore, the corresponding relationship between different data can be established first, and then input into the prediction model, so as to comprehensively consider multiple dimensional data factors by using the model, thereby forming a pavement degradation performance prediction result considering multi-dimensional information, improving the accuracy of the prediction result, and more favorably guiding the pavement maintenance scheme. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the disclosure or the related art, brief introductions will be given to the drawings needed to be used in the embodiments or related art descriptions. Obviously, the drawings in the following description are only embodiments of the disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0027] Figure 1 The flowchart of the exemplary method provided by the embodiments of the disclosure is shown.

[0028] Figure 2 The schematic diagram of the self-triggered acquisition unit controlling the sensor to collect data is provided for the embodiments of the disclosure.

[0029] Figure 3 The structural schematic diagram of the exemplary device provided by the embodiments of the disclosure is shown.

[0030] Figure 4 The structural schematic diagram of the electronic device provided by the embodiments of the disclosure is shown. DETAILED DESCRIPTION

[0031] For the purpose, technical solutions and advantages of the present specification to be clearer, the present specification is further described in detail below in combination with specific embodiments and with reference to the drawings.

[0032] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood as the common meanings understood by those skilled in the art to which the embodiments of the present disclosure belong. The terms "first", "second" and similar terms used in the embodiments of the present disclosure do not represent any order, number or importance, but are only used to distinguish different components. The terms "include", "contain" and similar terms mean that the elements, objects or method steps before the terms encompass the elements, objects or method steps listed after the terms and their equivalents, without excluding other elements, objects or method steps. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships can also change accordingly.

[0033] As described in the background section, in the related art, in different structural layers (such as roadbed, base layer, surface layer) of asphalt pavement, according to the structural characteristics of the road and the monitoring requirements, optical fiber strain sensors, optical fiber temperature sensors, humidity sensors and piezoelectric sensors are reasonably arranged. For example, temperature and humidity sensors are buried in each level of the roadbed to monitor the moisture changes of the roadbed and the base layer; piezoelectric sensors and optical fiber strain sensors are arranged at the position of the bottom of the tire track band in the asphalt layer to measure the stress and strain response under the action of vehicle load. Further, by using data mining technology, valuable information and rules can be extracted from massive monitoring data. For example, by using clustering analysis, association rule mining and other methods, the influence rules of different factors (such as temperature, humidity, traffic load, etc.) on the service performance of asphalt pavement can be analyzed.

[0034] However, the embedded sensor scheme (such as optical fiber, piezoelectric sensor): although it can realize high-precision strain and load monitoring, a single physical quantity (such as strain or temperature) cannot fully characterize the complex service state (such as fatigue damage and humidity coupling effect) of asphalt pavement. In the related art, independent sensing systems are mostly used, and there is a lack of deep fusion of cross-modal data.

[0035] In light of the above-mentioned practical situation, this disclosure provides a method for monitoring pavement service performance. This disclosure acquires basic detection data through multiple sources of sensors or multiple channels, thereby forming pavement data with various dimensions. This allows for the simultaneous monitoring of multiple dimensions of information, such as pavement mechanical response, temperature changes, subgrade and pavement moisture content, and surface defects. This multi-source data acquisition method overcomes the limitations of single-sensor monitoring information, providing a rich data foundation for comprehensively evaluating pavement service and degradation performance. Furthermore, since the input data is multi-dimensional, some data may be temporal, while others may be spatial. This allows for the establishment of correspondences between different data types before inputting them into a prediction model. This model comprehensively considers multiple dimensions of data factors, resulting in a pavement degradation performance prediction result that incorporates multi-dimensional information. This improves the accuracy of the prediction result and provides more effective guidance for pavement maintenance plans.

[0036] Figure 1 A flowchart illustrating an exemplary method provided by an embodiment of this disclosure is shown.

[0037] like Figure 1 As shown in the embodiments of this disclosure, the road surface service performance monitoring method specifically includes the following steps.

[0038] Step 102: Obtain basic detection data; the basic detection data includes environmental data, road damage data, road load data and / or road strain data.

[0039] In this step, the basic detection data refers to the fundamental data related to pavement performance assessment directly obtained through sensors, third-party channels, etc. In this embodiment, the basic detection data is multi-source or multi-dimensional data, thereby improving the coverage of performance monitoring and ultimately enhancing the accuracy of performance prediction through data from different dimensions.

[0040] In some embodiments, the basic data for detection may include environmental data, such as meteorological data, such as the temperature, humidity, and ultraviolet radiation intensity of the road surface location. This data can be obtained from third parties such as weather stations.

[0041] Subsequently, the basic data for detection can also include road damage data, which can include data on road surface cracks, damage, repairs, etc. Specific data acquisition tools (such as data acquisition vehicles) can be used to periodically collect road surface images and form road damage data.

[0042] Furthermore, the basic data for testing can also include pavement load data and pavement strain data. This data can be collected using sensors embedded within the pavement. For example, fiber optic strain sensors, fiber optic temperature sensors, moisture content sensors, and piezoelectric sensors can be strategically placed. Moisture content sensors can be used to monitor changes in moisture content in the subgrade and base course; piezoelectric sensors and fiber optic strain sensors can be used to measure stress and strain responses under vehicle loads. Ultimately, this generates pavement load data and pavement strain data.

[0043] In some embodiments, to reduce data redundancy and system power consumption, some data in the basic detection data that needs to be acquired through pre-embedded sensors can be controlled by self-triggering acquisition units. These self-triggering acquisition units can control the corresponding sensors to only perform data acquisition when certain conditions are met. For example, acquisition cycles can be set for some sensors, and they will not work outside of the acquisition cycle; acquisition conditions can also be set for some sensors, such as only performing stress and strain detection when a vehicle is detected passing over the road surface. In specific applications, axle load sensors can be used to monitor whether there are vehicles on the road surface. When a vehicle is detected, a trigger signal is generated, which wakes up the stress sensor and / or strain sensor, and then the stress sensor and strain sensor are used to acquire road load data and / or road strain data. That is, in some embodiments, acquiring the basic detection data includes: acquiring the road load data and / or the road strain data through self-triggering acquisition units pre-embedded in the road surface; wherein, the self-triggering acquisition unit generates a trigger signal through the axle load sensor, and wakes up the stress sensor and / or strain sensor according to the trigger signal to acquire the road load data and / or the road strain data.

[0044] In more specific application scenarios, a low-power MCU can be used to control the sensor (i.e., the self-triggering acquisition unit) to control its wake-up and sleep states. Threshold triggering: Sensor data (such as strain) exceeds a preset threshold. This activates the associated pre-embedded stress sensor for acquisition. Subsequently, a flexible micro / nano strain sensor is used: embedded between asphalt layers, to monitor the dynamic strain distribution of the structural layers. Temperature, humidity, and ultraviolet radiation are simultaneously measured via a third-party weather station. This achieves a measurement accuracy of ±3% of the true strain under dynamic loads. Figure 2 As shown, when no vehicle passes by, the MCU controls the sensor to not generate a signal, so that all other sensors are in a sleep state. This is a non-triggered period, during which no valid data is generated (it may not generate any data, or it may generate invalid data, such as all mechanical response values ​​being 0). Therefore, the data during this period can be directly treated as redundant data and automatically filtered out.

[0045] Step 104: Establish the correspondence between the detection basic data according to the set rules, generate the input dataset, and input the input dataset into the prediction model to predict the road surface degradation performance.

[0046] In this step, after acquiring the basic detection data for a certain time period, pavement performance can be predicted based on this data, such as pavement degradation performance. Here, pavement degradation performance can refer to pavement internal damage, degree of damage, remaining bearing capacity, and other pavement monitoring performance characteristics.

[0047] First, feature data required for the prediction model can be extracted based on the basic data. For example, strain kurtosis can be extracted from pavement strain data, and crack skeleton length can be extracted from pavement damage data. In some embodiments, the basic detection data itself can be these feature data, or they can be extracted from the basic data through certain steps as described above. Then, as can be seen from the aforementioned introduction to the basic detection data, this data comes from multiple dimensions, including time and space. Therefore, it is necessary to establish corresponding relationships. In some embodiments, since each basic data generally has its own number, and corresponding pavement station numbers, coordinates, and other information are set for the data collection location, a correspondence between different basic detection data can be established based on this information. That is, in some embodiments, establishing the correspondence between the basic detection data according to set rules includes: associating different basic detection data with station numbers and / or coordinates contained in different basic detection data, thereby establishing the correspondence.

[0048] After determining the corresponding relationships, these basic detection data can then form the input dataset. In some embodiments, the basic detection data may contain outliers that deviate from the overall pattern or are clearly erroneous. Therefore, it may be necessary to perform data filtering or cleaning on the basic detection data. Specifically, density clustering algorithms, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise), can be used for outlier analysis and removal. These algorithms can construct filtering functions based on the characteristics of each relevant dataset, and use these filtering functions to analyze the sample set to remove outlier data.

[0049] Furthermore, since the basic detection data may be missing or incomplete, or data cleaning may cause discontinuities, a missing data check can be performed on the basic detection data after data filtering. If missing data is identified, it can be imputed. It should be noted that for outliers, since they have already been removed through filtering, the imputation process also includes correcting outliers, that is, correcting the removed outliers to normal values ​​or theoretically normal values. Specifically, for imputing missing data, a combination of methods based on the nearest neighbor (KNN), bidirectional RNN, and time series generation can be used to ensure the integrity of the time series data. That is, in some embodiments, generating the input dataset includes: filtering the basic detection data after establishing the correspondence using a density clustering algorithm; performing missing data detection on the filtered basic detection data; and imputing missing data for the missing parts.

[0050] In this embodiment, after generating the input dataset, the prediction model can be used to predict the road surface degradation performance. This prediction model can be a deep learning model combining time and space. During training, a temperature-humidity-mechanical coupling service performance prediction model can be established. A time series data transformation strategy is formulated based on the time granularity characteristics of historical data, transforming the modeling process into a supervised regression problem. Furthermore, given that the input dataset is multivariate and heterogeneous, with each dataset having different numbers of variables, sampling frequencies, and time spans, designing a unified heterogeneous time series is crucial. Specifically, a Long Short-Term Memory (LSTM) neural network model can be used, employing a 1 / 3-layer structure. A fully connected neural network layer can be added after the LSTM unit, using the mean squared error function as the loss function and the Adaptive Moment Estimation (ADAM) algorithm as the optimization function. Overfitting is prevented by continuously optimizing and setting random dropout values. Finally, the ratio of training, validation, and test sets is reasonably set according to the data volume. In the specific training process, the loss function is used to calculate the deviation between the predicted value and the actual value, and the model parameters are continuously corrected and the deviation is reduced through backpropagation and iterative loops. When the deviation calculated by the loss function tends to stabilize, it means that the model has stabilized and the training ends. That is, in some embodiments, the prediction model is built using a long short-term memory neural network model, and a fully connected layer is connected after the long short-term memory network layer; the prediction model uses the mean squared error function as the loss function and the adaptive moment estimation algorithm as the optimization function to optimize the random inactivation values ​​generated by the long short-term memory neural network model.

[0051] In some embodiments, to make the prediction model more closely fit the specific scenario, a pavement damage mechanics equation can be introduced during model training to constrain the physical rationality of crack propagation prediction. For example, the pavement damage mechanics equation could be a rutting prediction equation:

[0052]

[0053] Wherein, R represents the rutting amount (mm) of the asphalt layer; R0, T0, P0, N0, V0, and F0 represent the rutting amount (mm), standard test temperature (e.g., 60℃), standard loading pressure (e.g., 0.7MPa), number of loading cycles, specimen porosity (e.g., 3.0%), and standard loading frequency (e.g., 2.9Hz) of the MTS rutting test under standard conditions, respectively; T, P, N, V, and F represent the temperature (℃), wheel load pressure (MPa), number of wheel load cycles, initial porosity (%) after construction, and loading frequency (Hz) of the asphalt layer, respectively; K represents the asphalt layer thickness influence coefficient; and μ represents the lateral distribution coefficient of wheel tracks on the design lane. That is, in some embodiments, the prediction model is trained by introducing pavement damage mechanics equations to constrain the training process of the prediction model.

[0054] Finally, the road surface degradation performance is obtained by using a prediction model to predict the input dataset.

[0055] Step 106: Output the road surface degradation performance.

[0056] In this step, the pavement degradation performance can be output, for example, displayed on a corresponding device to provide feedback to the operator. Of course, in other embodiments, the output method for pavement degradation performance is not limited to display; it can also be used to store, display, use, or reprocess the pavement degradation performance. The specific output method for pavement degradation performance can be flexibly selected according to different application scenarios and implementation needs.

[0057] Specifically, for example, in the application scenario where the method of this embodiment is executed on a single device, the road surface degradation performance can be directly output on the display component (monitor, projector, etc.) of the current device, so that the operator of the current device can directly see the content of the road surface degradation performance on the display component.

[0058] For example, in application scenarios where the method of this embodiment is executed on a system composed of multiple devices, the road surface degradation performance can be transmitted to other preset devices within the system, i.e., synchronization terminals, as receivers, via any data communication method (wired connection, NFC, Bluetooth, Wi-Fi, cellular network, etc.), so that the synchronization terminals can perform subsequent processing. Optionally, the synchronization terminal can be a preset server, which is generally located in the cloud and serves as a data processing and storage center, capable of storing and distributing the road surface degradation performance; wherein, the receivers of the distribution are terminal devices, and the owners or operators of these terminal devices can be managers, supervisors, maintenance personnel, etc., of the road-related systems.

[0059] For example, in the application scenario where the method of this embodiment is executed on a system composed of multiple devices, the road surface degradation performance can be directly sent to a preset terminal device through any data communication method. The terminal device can be one or more of the devices listed in the preceding paragraphs.

[0060] As can be seen from the above embodiments, this disclosure provides a method for monitoring pavement service performance. The method includes: acquiring basic detection data; the basic detection data includes environmental data, pavement damage data, pavement load data, and / or pavement strain data; establishing a correspondence between the basic detection data according to set rules, generating an input dataset, inputting the input dataset into a prediction model to predict pavement degradation performance; and outputting the pavement degradation performance. This disclosure acquires basic detection data through multiple sources of sensors or multiple channels, thereby forming pavement data of various dimensions, which can simultaneously monitor multiple dimensions of information such as pavement mechanical response, temperature change, subgrade and pavement moisture content, and surface defects. This multi-source data acquisition method overcomes the limitations of single-sensor monitoring information and provides a rich data foundation for comprehensively evaluating the service and degradation performance of pavements. Subsequently, since the input data uses multi-dimensional data, some of the data may be in the time dimension and others may be in the spatial dimension. This allows us to first establish the correspondence between different data and then input it into the prediction model. The model can then take into account multiple dimensions of data factors to form a pavement degradation performance prediction result that considers multi-dimensional information, thereby improving the accuracy of the prediction result and providing more effective guidance for pavement maintenance plans.

[0061] In specific application scenarios, the embodiments of this disclosure not only employ multi-source data acquisition methods to overcome the limitations of single-sensor monitoring information, but also utilize efficient wireless communication technology and cloud computing platforms to transmit sensor-collected data to the cloud in real time for rapid processing and analysis. Operators can view the road surface's service status in real time via computer clients or mobile terminals, promptly grasping trends in road performance changes and avoiding delays in maintenance decisions due to data lag. Subsequently, the accumulated massive monitoring data provides rich material for big data analysis. Through the mining and analysis of historical data, the service performance change patterns of different regions and road types can be summarized, providing valuable experience and reference for future road design, construction, and maintenance.

[0062] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this disclosure embodiment can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0063] It should be noted that the above description describes specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] Based on the same concept, corresponding to any of the above embodiments, this disclosure also provides a road surface service performance monitoring device.

[0065] refer to Figure 3 The road surface service performance monitoring device includes:

[0066] The first module 310 is used to acquire basic detection data; the basic detection data includes environmental data, road damage data, road load data and / or road strain data.

[0067] The second module 320 is used to establish the correspondence between the detection basic data according to the set rules, generate an input dataset, and input the input dataset into the prediction model to predict the road surface degradation performance.

[0068] The third module 330 is used to output the road surface degradation performance.

[0069] In some exemplary embodiments, the first module 310 is further configured to:

[0070] The road load data and / or road strain data are collected by a self-triggered acquisition unit embedded in the road surface; wherein, the self-triggered acquisition unit generates a trigger signal through an axle load sensor, and wakes up the stress sensor and / or strain sensor according to the trigger signal to collect the road load data and / or road strain data.

[0071] In some exemplary embodiments, the second module 320 is further configured to:

[0072] By associating different detection base data with different station numbers and / or coordinate base data, the corresponding relationship is established.

[0073] In some exemplary embodiments, the second module 320 is further configured to:

[0074] The detection data after establishing the aforementioned correspondence is filtered using a density clustering algorithm.

[0075] Missing data is detected in the basic detection data after data filtering, and missing data is filled in.

[0076] In some exemplary embodiments, the prediction model is constructed using a long short-term memory neural network model, and a fully connected layer is connected after the long short-term memory network layer; the prediction model uses the mean squared error function as the loss function and the adaptive moment estimation algorithm as the optimization function to optimize the random inactivation values ​​generated by the long short-term memory neural network model.

[0077] In some exemplary embodiments, the training process of the prediction model is constrained by introducing a road damage mechanics equation.

[0078] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing the embodiments of this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0079] The apparatus described above is used to implement the corresponding pavement service performance monitoring method in the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0080] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the road service performance monitoring method as described in any of the above embodiments.

[0081] Figure 4 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0082] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0083] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0084] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0085] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0086] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0087] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0088] The electronic devices described above are used to implement the corresponding road surface service performance monitoring methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0089] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the road service performance monitoring method as described in any of the above embodiments.

[0090] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. 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, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0091] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the road service performance monitoring method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0092] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to perform the road surface service performance monitoring method. Corresponding to the execution entity for each step in each embodiment of the road surface service performance monitoring method, the processor executing the corresponding step can belong to the corresponding execution entity.

[0093] The computer program product of the above embodiments is used to cause the computer and / or the processor to execute the road service performance monitoring method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0094] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0095] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuitry) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0096] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0097] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for monitoring the service performance of road surfaces, characterized in that, include: Obtain basic detection data; The basic data for the detection includes environmental data, pavement damage data, pavement load data, and / or pavement strain data; Establish the correspondence between the detection base data according to the set rules, generate the input dataset, and input the input dataset into the prediction model to predict the road surface degradation performance. Output the road surface degradation performance.

2. The method according to claim 1, characterized in that, The acquisition of basic detection data includes: The road load data and / or road strain data are collected by a self-triggered acquisition unit embedded in the road surface; wherein, the self-triggered acquisition unit generates a trigger signal through an axle load sensor, and wakes up the stress sensor and / or strain sensor according to the trigger signal to collect the road load data and / or road strain data.

3. The method according to claim 1, characterized in that, The step of establishing the correspondence between the basic detection data according to the set rules includes: By associating different detection base data with different station numbers and / or coordinate base data, the corresponding relationship is established.

4. The method according to claim 1, characterized in that, The generated input dataset includes: The detection data after establishing the aforementioned correspondence is filtered using a density clustering algorithm. Missing data is detected in the basic detection data after data filtering, and missing data is filled in.

5. The method according to claim 1, characterized in that, The prediction model is constructed using a long short-term memory neural network model, and a fully connected layer is added after the long short-term memory network layer. The prediction model uses the mean squared error function as the loss function and the adaptive moment estimation algorithm as the optimization function to optimize the random inactivation values ​​generated by the long short-term memory neural network model.

6. The method according to claim 5, characterized in that, During training, the prediction model is constrained by introducing a road damage mechanics equation.

7. A road surface service performance monitoring device, characterized in that, include: The first module is used to acquire basic detection data; The basic data for the detection includes environmental data, pavement damage data, pavement load data, and / or pavement strain data; The second module is used to establish the correspondence between the detection basic data according to the set rules, generate an input dataset, and input the input dataset into the prediction model to predict the road surface degradation performance. The third module is used to output the road surface degradation performance.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer program instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 6.

Images