Method and system for detecting abnormal state of expressway surface based on millimeter wave base station

Abstract

The invention relates to the technical field of road surface abnormal state detection, and provides a millimeter wave base station-based expressway road surface abnormal state detection method and system, and the method comprises the steps: obtaining road surface state detection data, and carrying out the abnormal detection, data fusion and feature extraction of the road surface state detection data through an edge calculation node set by a millimeter wave base station, key detection data features are extracted, and are transmitted to a central data processing platform by using a communication network configured by the millimeter wave base station to carry out abnormal state detection on the expressway surface; adjusting a key data judgment strategy and a transmission rate distribution strategy of the next detection period according to an abnormal state detection result of each detection period, considering a real-time road surface state and a road surface state deterioration condition of each detection road section, and adjusting a key detection data feature quantity and a communication transmission rate of each detection road section in real time; on the basis of reducing the data processing load and improving the detection accuracy, the important attention on the special road section is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal road surface state detection, and in particular to a method and system for detecting abnormal road surface state of a high-speed road surface based on a millimeter wave base station. Background Art

[0002] In modern transportation, highway road safety is an important part of ensuring driving safety and reducing traffic accidents. However, traditional road detection methods, such as manual inspections and low-frequency sensor monitoring, usually have problems such as low detection accuracy, slow response speed, and limited coverage, making it difficult to detect small cracks, subsidence, and other potential dangers on the road in a timely manner.

[0003] At present, several different technologies are used for abnormal road conditions detection on highways. For example, abnormal road conditions detection based on visual detection technology, abnormal road conditions detection based on laser scanning technology, abnormal road conditions detection based on geological radar technology, abnormal road conditions detection based on acceleration sensor and vibration detection, abnormal road conditions detection based on millimeter wave radar technology, and abnormal road conditions detection based on multi-sensor fusion technology. Among them, abnormal road conditions detection based on multi-sensor fusion technology can avoid the influence of single detection data errors and interference, and improve the accuracy and reliability of abnormal road conditions detection, because it integrates the road detection data collected by the above-mentioned multiple sensors for comprehensive detection. However, since multi-sensor fusion technology needs to consider a large amount of data of different categories, in practical applications, how to efficiently process and fuse multi-source data, ensure that key and useful data are adopted, eliminate non-key and useless data, reduce data processing load, and improve detection accuracy is still a technical difficulty. At the same time, multi-sensor data transmission under large data volumes and special scenarios (such as high traffic volume and harsh environment) is also limited by communication bandwidth. How to allocate appropriate communication bandwidth to different detection sections to meet the data transmission requirements of different detection sections and improve the overall highway road detection accuracy has not been considered in existing technologies. Summary of the invention

[0004] The present invention provides a method and system for detecting abnormal state of a high-speed road surface based on a millimeter wave base station, aiming to solve at least one technical problem existing in the above-mentioned prior art.

[0005] The present invention provides a method for detecting abnormal state of a high-speed road surface based on a millimeter wave base station, comprising:

[0006] Acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along the target highway; wherein the road surface state detection data includes a plurality of detection data items;

[0007] By using the edge computing nodes set up at each millimeter wave base station, according to a number of detection data items received by the millimeter wave base station in the current detection period and in accordance with the key data judgment strategy of the current detection period, the key detection data features of each detection section are determined;

[0008] By utilizing the communication network configured by each millimeter wave base station, according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, the key detection data features of each detection section in the current detection period are transmitted to the central data processing platform, and the central data processing platform is driven to perform abnormal state detection of the target highway road surface according to the key detection data features;

[0009] Based on the abnormal state detection results of the target highway, the central data processing platform is driven to feedback strategy adjustment instructions to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy for the next detection cycle according to the received strategy adjustment instructions.

[0010] Optionally, each of the millimeter wave base stations is configured to connect to a sensor array set up in a corresponding detection section for collecting road condition detection data; wherein the sensor array includes a millimeter wave radar sensor, a lidar sensor, a geological radar sensor and an image sensor set in each detection section of the target highway.

[0011] Optionally, using the edge computing node set up by each millimeter wave base station, according to a number of detection data items received by the millimeter wave base station in the current detection period, according to the key data judgment strategy of the current detection period, the key detection data feature steps of each detection section are determined, specifically including:

[0012] Using the edge computing node set up by each millimeter wave base station, a number of detection data items collected and received by the millimeter wave base station in the current detection period are obtained;

[0013] Anomaly detection, data fusion and feature extraction are performed on several detection data items to generate several detection data features, and according to the key data judgment strategy of the current detection cycle, the key detection data features among the several detection data features of each detection section are determined.

[0014] Optionally, performing anomaly detection, data fusion and feature extraction on a plurality of detection data items to generate a plurality of detection data feature steps specifically includes:

[0015] Calling the normal value range of each detection data item, and based on the normal value range, extracting detection data items that fall outside the normal value range from a plurality of detection data items, thereby completing the screening of abnormal detection data items;

[0016] For each abnormal detection data item obtained through screening, a data fusion operation based on data association matching is performed on a plurality of detection data items to obtain a plurality of abnormal detection data item groups; wherein each abnormal detection data item group includes at least one abnormal detection data item and a plurality of non-abnormal detection data items;

[0017] Detection data features of at least one abnormal detection data item and a plurality of non-abnormal detection data items in each abnormal detection data item group are extracted.

[0018] Optionally, according to the key data judgment strategy of the current detection cycle, the step of determining key detection data features among a plurality of detection data features of each detection section specifically includes:

[0019] Based on the similarity between the values ​​of the abnormal detection data item and several non-abnormal detection data items corresponding to each detection data feature and the standard value combination preset at different abnormal levels, the abnormal level of each detection data feature is determined, and the several detection data features are prioritized in descending order of abnormal levels;

[0020] Obtaining a key data judgment strategy for the current detection cycle; wherein the key data judgment strategy is configured as a first preset proportion of detection data features of the key data features in a priority ranking list among a plurality of detection data features;

[0021] According to the key data judgment strategy of the current detection cycle, a first preset proportion of detection data features in the priority sorting list are extracted from a plurality of detection data features of each detection section as key detection data features.

[0022] Optionally, by using the communication network configured by each millimeter wave base station, according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, the key detection data features of each detection section in the current detection period are transmitted to the central data processing platform, driving the central data processing platform to perform abnormal state detection steps of the target highway road surface according to the key detection data features, specifically including:

[0023] Obtaining a transmission rate allocation strategy assigned to each millimeter wave base station in a current detection period; wherein the transmission rate allocation strategy is configured as a transmission rate ratio assigned to each millimeter wave base station in a communication network;

[0024] Calculate the maximum transmission rate of each millimeter wave base station according to the total bandwidth of the communication network and the ratio of the transmission rate allocated to each millimeter wave base station in the current detection period;

[0025] The actual transmission rate of each millimeter wave base station is less than the maximum transmission rate as the first constraint condition, the variance of each element in the ratio of the actual transmission rate of each millimeter wave base station to the ratio of the number of features of the key detection data features of the current detection period is minimized as the second constraint condition, and the actual transmission rate of each millimeter wave base station is calculated with the maximum total transmission rate as the goal;

[0026] Utilizing the communication network configured for each millimeter wave base station, the key detection data features of each detection section in the current detection cycle are transmitted to the central data processing platform according to the actual transmission rate of each millimeter wave base station, driving the central data processing platform to perform abnormal state detection of the target highway road surface based on the key detection data features.

[0027] Optionally, the central data processing platform is driven to perform abnormal state detection steps of the target highway road surface according to the key detection data features, specifically including:

[0028] Acquire abnormal state data of the test highway road surface, extract detection data features and abnormal state detection results in the abnormal state data as training samples, input the training samples into an initial neural network model configured on a central data processing platform for training, and obtain a highway road surface abnormal state detection model obtained when the training times meet the requirements or the training converges;

[0029] The key detection data features are input into the highway road abnormal state detection model for detection, and the highway road abnormal state detection results are obtained and graded to obtain the highway road abnormality level of each detection section in the current detection cycle.

[0030] Optionally, according to the abnormal state detection result of the target highway road surface, the central data processing platform is driven to feedback a strategy adjustment instruction to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and the transmission rate allocation strategy steps of the next detection cycle according to the received strategy adjustment instruction, specifically including:

[0031] According to the highway road abnormality level of each detection section in the target highway road in the current detection cycle, according to the preset conversion relationship between the highway road abnormality level and the first preset ratio number, determine the key data judgment strategy for the next detection cycle;

[0032] The key data judgment strategy of each millimeter wave base station in the current detection cycle is updated to the key data judgment strategy of the next detection cycle, so that each millimeter wave base station performs the action of determining the key detection data characteristics of each detection section in the next detection cycle according to the key data judgment strategy of the next detection cycle.

[0033] Optionally, according to the abnormal state detection result of the target highway road surface, the central data processing platform is driven to feedback a strategy adjustment instruction to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and the transmission rate allocation strategy steps of the next detection cycle according to the received strategy adjustment instruction, specifically including:

[0034] According to the highway abnormality level of each detection section in the target highway in the past N detection cycles, the maximum level difference of the highway abnormality level of each detection section in the past N detection cycles is calculated, and the levels are sorted according to the level difference;

[0035] According to the ranking difference sorting result, the target ratio of the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked last in the ranking in the communication network is added to the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked first in the ranking in the communication network, and so on, to generate the transmission rate ratio assigned to each millimeter wave base station in the communication network in the next detection cycle;

[0036] The transmission rate allocation strategy of each millimeter wave base station in the current detection cycle is updated to the transmission rate allocation strategy of the next detection cycle, so that each millimeter wave base station performs abnormal state detection actions for each detection section of the next detection cycle according to the transmission rate allocation strategy of the next detection cycle.

[0037] The present invention also provides a high-speed road abnormal state detection system based on a millimeter wave base station, the system comprising:

[0038] An acquisition module, used to acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along the target highway road surface; wherein the road surface state detection data includes a plurality of detection data items;

[0039] A determination module is used to use the edge computing node set by each millimeter wave base station to determine the key detection data characteristics of each detection section according to the key data judgment strategy of the current detection period based on a number of detection data items received by the millimeter wave base station in the current detection period;

[0040] A detection module is used to utilize the communication network configured by each millimeter wave base station and transmit the key detection data features of each detection section in the current detection period to the central data processing platform according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, so as to drive the central data processing platform to perform abnormal state detection of the target highway road surface according to the key detection data features;

[0041] The update module is used to drive the central data processing platform to feedback strategy adjustment instructions to each millimeter wave base station based on the abnormal state detection results of the target highway road surface, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy of the next detection cycle according to the received strategy adjustment instructions.

[0042] The beneficial effects of the present invention are as follows: a method and system for detecting abnormal state of a highway road surface based on a millimeter wave base station are proposed, by acquiring road surface state detection data transmitted by several millimeter wave base stations set up along the target highway road surface, using the edge computing nodes set up by each millimeter wave base station to perform abnormal detection, data fusion and feature extraction on several detection data items in the road surface state detection data, extracting key detection data features according to the key data judgment strategy, and then using the communication network configured by each millimeter wave base station, according to the transmission rate allocation strategy, transmitting the key detection data features to the central data processing platform for abnormal state detection of the highway road surface, finally, according to the abnormal state detection result of each detection cycle, adjusting the key data judgment strategy and transmission rate allocation strategy of the next detection cycle, considering the real-time road surface state and road surface state deterioration of each detection section, to adjust the number of key detection data features and the communication transmission rate of each detection section in real time, on the basis of reducing the data processing load and improving the detection accuracy, increasing the focus on special sections, and improving the detection accuracy of the overall highway road surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the structure of the method for detecting abnormal state of a highway road surface based on a millimeter wave base station provided in this embodiment.

[0044] Figure 2 A schematic flow chart of a method for detecting abnormal highway road conditions based on a millimeter wave base station provided in this embodiment.

[0045] Reference numerals:

[0046] 10 - acquisition module; 20 - determination module; 30 - detection module; 40 - update module. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Embodiment 1:

[0049] like Figure 1As shown, a method for detecting abnormal state of a high-speed road surface based on a millimeter wave base station includes:

[0050] S1: Acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along a target highway; wherein the road surface state detection data includes a plurality of detection data items;

[0051] S2: using the edge computing node set up by each millimeter wave base station, according to a number of detection data items received by the millimeter wave base station in the current detection period, and in accordance with the key data judgment strategy of the current detection period, determine the key detection data features of each detection section;

[0052] S3: utilizing the communication network configured by each millimeter wave base station and transmitting the key detection data features of each detection section in the current detection period to the central data processing platform according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, so as to drive the central data processing platform to perform abnormal state detection of the target highway road surface according to the key detection data features;

[0053] S4: Based on the abnormal state detection results of the target highway road, the central data processing platform is driven to feedback strategy adjustment instructions to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy of the next detection cycle according to the received strategy adjustment instructions.

[0054] It should be noted that the road abnormality detection based on multi-sensor fusion technology can avoid the impact of single detection data errors and interference and improve the accuracy and reliability of road abnormality detection because it integrates road detection data collected by multiple sensors for comprehensive detection. However, since multi-sensor fusion technology needs to consider a large amount of data of different categories, in practical applications, how to efficiently process and fuse multi-source data, ensure that key and useful data are adopted, eliminate non-key and useless data, reduce data processing load, and improve detection accuracy is still a technical difficulty. At the same time, multi-sensor data transmission under large data volumes and special scenarios (such as high traffic volume and harsh environment) is also limited by communication bandwidth. How to allocate appropriate communication bandwidth for different detection sections to meet the data transmission requirements of different detection sections and improve the overall detection accuracy of high-speed roads has not been considered in existing technologies.

[0055] In order to solve the above problems, this embodiment obtains road surface condition detection data transmitted by several millimeter wave base stations set up along the target highway, and uses the edge computing nodes set up by each millimeter wave base station to perform anomaly detection, data fusion and feature extraction on several detection data items in the road surface condition detection data, and extracts key detection data features according to the key data judgment strategy. Then, the communication network configured by each millimeter wave base station is used to transmit the key detection data features to the central data processing platform according to the transmission rate allocation strategy for abnormal state detection of the highway. Finally, the key data judgment strategy and transmission rate allocation strategy of the next detection cycle are adjusted according to the abnormal state detection results of each detection cycle. The real-time road surface state and road surface state deterioration of each detection section are considered to adjust the number of key detection data features and the communication transmission rate of each detection section in real time. On the basis of reducing the data processing load and improving the detection accuracy, the focus on special sections is increased, thereby improving the detection accuracy of the overall highway road surface.

[0056] In a preferred embodiment, each of the millimeter wave base stations is configured to connect to a sensor array set up in a corresponding detection section for collecting road condition detection data; wherein the sensor array includes a millimeter wave radar sensor, a lidar sensor, a geological radar sensor and an image sensor set up in each detection section of the target highway road surface.

[0057] Furthermore, by using the edge computing node set up in each millimeter wave base station, according to a number of detection data items received by the millimeter wave base station in the current detection period, according to the key data judgment strategy of the current detection period, the key detection data feature steps of each detection section are determined, specifically including:

[0058] S21: using the edge computing node set by each millimeter wave base station, obtaining a number of detection data items collected and received by the millimeter wave base station in the current detection period;

[0059] S22: performing anomaly detection, data fusion and feature extraction on a plurality of detection data items, generating a plurality of detection data features, and determining a key detection data feature among a plurality of detection data features of each detection section according to a key data judgment strategy of a current detection cycle.

[0060] Furthermore, anomaly detection, data fusion and feature extraction are performed on several detection data items to generate several detection data feature steps, specifically including:

[0061] S221: calling the normal value range of each detection data item, and based on the normal value range, extracting detection data items that fall outside the normal value range from a plurality of detection data items, thereby completing the screening of abnormal detection data items;

[0062] S222: performing a data fusion operation based on data association matching on each abnormal detection data item obtained through screening among a plurality of detection data items to obtain a plurality of abnormal detection data item groups; wherein each abnormal detection data item group includes at least one abnormal detection data item and a plurality of non-abnormal detection data items;

[0063] S223: Extracting detection data features of at least one abnormal detection data item and a plurality of non-abnormal detection data items in each abnormal detection data item group.

[0064] Furthermore, according to the key data judgment strategy of the current detection cycle, the key detection data feature steps among the several detection data features of each detection section are determined, specifically including:

[0065] S224: determining the abnormality level of each detection data feature based on the similarity between the values ​​of the abnormal detection data item and the plurality of non-abnormal detection data items corresponding to each detection data feature and the preset standard value combinations of different abnormality levels, and prioritizing the plurality of detection data features in descending order of the abnormality levels;

[0066] S225: Acquire a key data judgment strategy for the current detection cycle; wherein the key data judgment strategy is configured as a first preset proportion of detection data features of the key data features in a priority ranking list among a plurality of detection data features;

[0067] S226: According to the key data judgment strategy of the current detection cycle, a first preset proportion of detection data features in the priority sorting list are extracted from a plurality of detection data features of each detection section as key detection data features.

[0068] In this embodiment, after each millimeter wave base station receives the road state detection data collected by the sensor array, the edge computing node set by each millimeter wave base station is used to extract several detection data items, and then perform abnormal detection, data fusion and feature extraction, and determine the abnormal detection data items by comparing with the normal value range of each detection data item, and then perform data matching and fusion by combining common data items to generate an abnormal detection data item group consisting of at least one abnormal detection data item and several non-abnormal detection data items, and finally extract the detection data features from the abnormal detection data item group. After that, according to the similarity between each detection data feature and the standard data combination, the abnormal level is determined and the priority is sorted, and then the key data judgment strategy of the current detection cycle is called to extract the detection data features from the first preset ratio before the priority sorting, and construct the key detection data features. Therefore, through the construction of the key detection data features, it is ensured that the key and useful data are adopted, and the non-key and useless data are eliminated, so that the multi-source data can be efficiently processed and fused, the data processing load can be reduced, and the detection accuracy can be improved.

[0069] In a preferred embodiment, the communication network configured by each millimeter wave base station is used to transmit the key detection data features of each detection section in the current detection period to the central data processing platform according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, so as to drive the central data processing platform to perform abnormal state detection steps of the target highway road surface according to the key detection data features, specifically including:

[0070] S31: Obtaining a transmission rate allocation strategy assigned to each millimeter wave base station in a current detection period; wherein the transmission rate allocation strategy is configured as a transmission rate ratio assigned to each millimeter wave base station in a communication network;

[0071] S32: Calculate the maximum transmission rate of each millimeter wave base station according to the total bandwidth of the communication network and the ratio of the transmission rate allocated to each millimeter wave base station in the current detection period;

[0072] S33: Taking the actual transmission rate of each millimeter wave base station as the first constraint condition being less than the maximum transmission rate, taking the variance of each element in the ratio of the actual transmission rate of each millimeter wave base station to the ratio of the number of features of the key detection data features of the current detection period as the minimum as the second constraint condition, and taking the maximum total transmission rate as the goal, the actual transmission rate of each millimeter wave base station is obtained;

[0073] S34: Utilizing the communication network configured for each millimeter wave base station, the key detection data features of each detection section in the current detection cycle are transmitted to the central data processing platform according to the actual transmission rate of each millimeter wave base station, driving the central data processing platform to perform abnormal state detection of the target highway road surface according to the key detection data features.

[0074] On this basis, the central data processing platform is driven to perform abnormal state detection steps of the target highway road surface according to the key detection data characteristics, including:

[0075] S35: Acquire abnormal state data of the test highway, extract detection data features and abnormal state detection results in the abnormal state data as training samples, input the training samples into an initial neural network model configured on a central data processing platform for training, and obtain a highway abnormal state detection model obtained when the training times meet the requirements or the training converges;

[0076] S36: Inputting the key detection data features into the highway road abnormal state detection model for detection, obtaining the highway road abnormal state detection results and performing classification, and obtaining the highway road abnormality level of each detection section in the current detection cycle.

[0077] In this embodiment, after extracting the key detection data features constructed for each detection section, the communication network configured for each millimeter wave base station is used to transmit the key detection data features of each detection section in the current detection cycle to the central data processing platform in accordance with the transmission rate allocation strategy assigned to the millimeter wave base station in the current detection cycle. Then, the central data processing platform uses a pre-trained highway road abnormal state detection model to perform highway road abnormal state detection and grade the detection results. Among them, when each detection section transmits the key detection data features to the central data processing platform, the transmission rate allocation strategy assigned to each millimeter wave base station in the current detection cycle is first obtained, and the maximum transmission rate of each millimeter wave base station is calculated according to the transmission rate allocation strategy and the total bandwidth of the communication network. Then, the actual transmission rate of each millimeter wave base station is less than the maximum transmission rate as the first constraint condition (that is, each millimeter wave base station cannot transmit at a rate exceeding the maximum transmission rate), and the variance of each element in the ratio of the actual transmission rate of each millimeter wave base station to the number of features of the key detection data features of the current detection cycle is minimized as the second constraint condition (that is, the ratio of the actual transmission rate of each millimeter wave base station to the data volume of the key detection data features is the most suitable), and the actual transmission rate of each millimeter wave base station is obtained with the maximum total transmission rate as the goal (that is, the maximum usage of the total bandwidth). According to the actual transmission rate, each detection section transmits the key detection data features to the central data processing platform. Under large data volumes and special scenarios (such as high traffic volume and harsh environment), appropriate communication bandwidths are reasonably allocated to different detection sections to meet the data transmission requirements of different detection sections and improve the overall detection accuracy of the highway road surface.

[0078] In a preferred embodiment, according to the abnormal state detection result of the target highway road, the central data processing platform is driven to feedback the strategy adjustment instruction to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy of the next detection cycle according to the received strategy adjustment instruction, specifically including:

[0079] S41: determining a key data judgment strategy for the next detection cycle according to the highway road abnormality level of each detection section in the target highway road in the current detection cycle and according to a preset conversion relationship between the highway road abnormality level and the first preset ratio number;

[0080] S42: Update the key data judgment strategy of each millimeter wave base station in the current detection cycle to the key data judgment strategy of the next detection cycle, so that each millimeter wave base station performs the action of determining the key detection data characteristics of each detection section in the next detection cycle according to the key data judgment strategy of the next detection cycle.

[0081] Furthermore, according to the abnormal state detection result of the target highway road, the central data processing platform is driven to feedback the strategy adjustment instruction to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy steps of the next detection cycle according to the received strategy adjustment instruction, specifically including:

[0082] S43: according to the highway abnormality level of each detection section in the target highway in the past N detection cycles, calculating the maximum level difference of the highway abnormality level of each detection section in the past N detection cycles, and sorting according to the level difference;

[0083] S44: according to the result of the ranking difference sorting, the target ratio of the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked last in the ranking in the communication network is added to the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked first in the ranking in the communication network, and so on, to generate the transmission rate ratio assigned to each millimeter wave base station in the communication network in the next detection cycle;

[0084] S45: Update the transmission rate allocation strategy of each millimeter wave base station in the current detection cycle to the transmission rate allocation strategy of the next detection cycle, so that each millimeter wave base station performs abnormal state detection actions for each detection section of the next detection cycle according to the transmission rate allocation strategy of the next detection cycle.

[0085] In this embodiment, the key data judgment strategy and transmission rate allocation strategy of the next detection cycle are adjusted according to the abnormal state detection results of each detection cycle. The real-time road surface state and road surface state deterioration of each detection section are taken into consideration to adjust the number of key detection data features and the communication transmission rate of each detection section in real time. On the basis of reducing the data processing load and improving the detection accuracy, the focus on special sections is increased, thereby improving the detection accuracy of the overall high-speed road surface.

[0086] Embodiment 2:

[0087] Reference Figure 2 , Figure 2 A schematic structural diagram of a high-speed road abnormal state detection system based on a millimeter wave base station provided in an embodiment of the present invention.

[0088] like Figure 2 As shown, a high-speed road abnormal state detection system based on millimeter wave base stations is used in the high-speed road abnormal state detection method based on millimeter wave base stations as described above, comprising:

[0089] An acquisition module 10 is used to acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along a target highway road surface; wherein the road surface state detection data includes a plurality of detection data items;

[0090] The determination module 20 is used to use the edge computing node set by each millimeter wave base station to determine the key detection data characteristics of each detection section according to the key data judgment strategy of the current detection period based on a number of detection data items received by the millimeter wave base station in the current detection period;

[0091] The detection module 30 is used to utilize the communication network configured by each millimeter wave base station and transmit the key detection data features of each detection section in the current detection period to the central data processing platform according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, so as to drive the central data processing platform to perform abnormal state detection of the target highway road surface according to the key detection data features;

[0092] The update module 40 is used to drive the central data processing platform to feedback strategy adjustment instructions to each millimeter wave base station based on the abnormal state detection results of the target highway road surface, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy of the next detection cycle according to the received strategy adjustment instructions.

[0093] The specific implementation of the method for detecting abnormal state of a high-speed road surface based on a millimeter wave base station in the present application is basically the same as the above-mentioned embodiment of the method for detecting abnormal state of a high-speed road surface based on a millimeter wave base station, and will not be repeated here.

[0094] In the description of the embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "center", "top", "bottom", "top", "bottom", "inside", "outside", "inner side", "outer side" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Among them, "inside" refers to an internal or enclosed area or space. "Periphery" refers to the area surrounding a specific component or a specific area.

[0095] In the description of the embodiments of the present invention, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", and "fourth" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0096] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", and "assemble" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0097] In the description of the embodiments of the present invention, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0098] In the description of the embodiments of the present invention, it should be understood that "-" and "~" represent a range between two values, and the range includes the endpoints. For example: "AB" represents a range greater than or equal to A and less than or equal to B. "A~B" represents a range greater than or equal to A and less than or equal to B.

[0099] In the description of the embodiments of the present invention, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the associated objects before and after are in an "or" relationship.

[0100] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting abnormal state of high-speed road surface based on millimeter wave base station, characterized in that: include: Acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along the target highway; wherein the road surface state detection data includes a plurality of detection data items; By using the edge computing nodes set up at each millimeter wave base station, according to a number of detection data items received by the millimeter wave base station in the current detection period and in accordance with the key data judgment strategy of the current detection period, the key detection data features of each detection section are determined; By utilizing the communication network configured by each millimeter wave base station, according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, the key detection data features of each detection section in the current detection period are transmitted to the central data processing platform, and the central data processing platform is driven to perform abnormal state detection of the target highway road surface according to the key detection data features; Based on the abnormal state detection results of the target highway, the central data processing platform is driven to feedback strategy adjustment instructions to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy for the next detection cycle according to the received strategy adjustment instructions.

2. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 1, characterized in that: Each of the millimeter wave base stations is configured to connect to a sensor array set up on a corresponding detection section for collecting road condition detection data; wherein the sensor array includes a millimeter wave radar sensor, a lidar sensor, a geological radar sensor and an image sensor set on each detection section of the target highway road surface.

3. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 1, characterized in that: Using the edge computing node set up by each millimeter wave base station, according to the several detection data items received by the millimeter wave base station in the current detection cycle, according to the key data judgment strategy of the current detection cycle, the key detection data feature steps of each detection section are determined, specifically including: Using the edge computing node set up by each millimeter wave base station, a number of detection data items collected and received by the millimeter wave base station in the current detection period are obtained; Anomaly detection, data fusion and feature extraction are performed on several detection data items to generate several detection data features, and according to the key data judgment strategy of the current detection cycle, the key detection data features among the several detection data features of each detection section are determined.

4. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 3 is characterized in that: Perform anomaly detection, data fusion and feature extraction on several detection data items to generate several detection data feature steps, including: Calling the normal value range of each detection data item, and based on the normal value range, extracting detection data items that fall outside the normal value range from a plurality of detection data items, thereby completing the screening of abnormal detection data items; For each abnormal detection data item obtained through screening, a data fusion operation based on data association matching is performed on a plurality of detection data items to obtain a plurality of abnormal detection data item groups; wherein each abnormal detection data item group includes at least one abnormal detection data item and a plurality of non-abnormal detection data items; Detection data features of at least one abnormal detection data item and a plurality of non-abnormal detection data items in each abnormal detection data item group are extracted.

5. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 1, characterized in that: According to the key data judgment strategy of the current detection cycle, the key detection data feature steps among several detection data features of each detection section are determined, specifically including: Based on the similarity between the values ​​of the abnormal detection data item and several non-abnormal detection data items corresponding to each detection data feature and the standard value combination preset at different abnormal levels, the abnormal level of each detection data feature is determined, and the several detection data features are prioritized in descending order of abnormal levels; Obtaining a key data judgment strategy for the current detection cycle; wherein the key data judgment strategy is configured as a first preset proportion of detection data features of the key data features in a priority ranking list among a plurality of detection data features; According to the key data judgment strategy of the current detection cycle, a first preset proportion of detection data features in the priority sorting list are extracted from a plurality of detection data features of each detection section as key detection data features.

6. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 5, characterized in that: By using the communication network configured by each millimeter wave base station, according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection cycle, the key detection data features of each detection section in the current detection cycle are transmitted to the central data processing platform, driving the central data processing platform to perform abnormal state detection steps of the target highway road surface according to the key detection data features, specifically including: Obtaining a transmission rate allocation strategy assigned to each millimeter wave base station in a current detection period; wherein the transmission rate allocation strategy is configured as a transmission rate ratio assigned to each millimeter wave base station in a communication network; Calculate the maximum transmission rate of each millimeter wave base station according to the total bandwidth of the communication network and the ratio of the transmission rate allocated to each millimeter wave base station in the current detection period; The actual transmission rate of each millimeter wave base station is less than the maximum transmission rate as the first constraint condition, the variance of each element in the ratio of the actual transmission rate of each millimeter wave base station to the ratio of the number of features of the key detection data features of the current detection period is minimized as the second constraint condition, and the actual transmission rate of each millimeter wave base station is calculated with the maximum total transmission rate as the goal; Utilizing the communication network configured for each millimeter wave base station, the key detection data features of each detection section in the current detection cycle are transmitted to the central data processing platform according to the actual transmission rate of each millimeter wave base station, driving the central data processing platform to perform abnormal state detection of the target highway road surface based on the key detection data features.

7. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 6, characterized in that: The central data processing platform is driven to perform abnormal state detection steps of the target highway road surface according to key detection data features, including: Acquire abnormal state data of the test highway road surface, extract detection data features and abnormal state detection results in the abnormal state data as training samples, input the training samples into an initial neural network model configured on a central data processing platform for training, and obtain a highway road surface abnormal state detection model obtained when the training times meet the requirements or the training converges; The key detection data features are input into the highway road abnormal state detection model for detection, and the highway road abnormal state detection results are obtained and graded to obtain the highway road abnormality level of each detection section in the current detection cycle.

8. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 7, characterized in that: According to the abnormal state detection results of the target highway road, the central data processing platform is driven to feedback the strategy adjustment instructions to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy steps of the next detection cycle according to the received strategy adjustment instructions, specifically including: According to the highway road abnormality level of each detection section in the target highway road in the current detection cycle, according to the preset conversion relationship between the highway road abnormality level and the first preset ratio number, determine the key data judgment strategy for the next detection cycle; The key data judgment strategy of each millimeter wave base station in the current detection cycle is updated to the key data judgment strategy of the next detection cycle, so that each millimeter wave base station performs the action of determining the key detection data characteristics of each detection section in the next detection cycle according to the key data judgment strategy of the next detection cycle.

9. The method for detecting abnormal state of high-speed road surface based on millimeter wave base station according to claim 8, characterized in that: According to the abnormal state detection results of the target highway road, the central data processing platform is driven to feedback the strategy adjustment instructions to each millimeter wave base station, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy steps of the next detection cycle according to the received strategy adjustment instructions, specifically including: According to the highway abnormality level of each detection section in the target highway in the past N detection cycles, the maximum level difference of the highway abnormality level of each detection section in the past N detection cycles is calculated, and the levels are sorted according to the level difference; According to the ranking difference sorting result, the target ratio of the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked last in the ranking in the communication network is added to the transmission rate ratio assigned to the millimeter wave base station of the detection section ranked first in the ranking in the communication network, and so on, to generate the transmission rate ratio assigned to each millimeter wave base station in the communication network in the next detection cycle; The transmission rate allocation strategy of each millimeter wave base station in the current detection cycle is updated to the transmission rate allocation strategy of the next detection cycle, so that each millimeter wave base station performs abnormal state detection actions for each detection section of the next detection cycle according to the transmission rate allocation strategy of the next detection cycle.

10. A high-speed road abnormal state detection system based on millimeter wave base station, characterized in that: The system comprises: An acquisition module, used to acquire road surface state detection data transmitted by a plurality of millimeter wave base stations arranged along the target highway road surface; wherein the road surface state detection data includes a plurality of detection data items; A determination module is used to use the edge computing node set by each millimeter wave base station to determine the key detection data characteristics of each detection section according to the key data judgment strategy of the current detection period based on a number of detection data items received by the millimeter wave base station in the current detection period; A detection module is used to utilize the communication network configured by each millimeter wave base station and transmit the key detection data features of each detection section in the current detection period to the central data processing platform according to the transmission rate allocation strategy allocated to the millimeter wave base station in the current detection period, so as to drive the central data processing platform to perform abnormal state detection of the target highway road surface according to the key detection data features; The update module is used to drive the central data processing platform to feedback strategy adjustment instructions to each millimeter wave base station based on the abnormal state detection results of the target highway road surface, so that each millimeter wave base station updates the key data judgment strategy and transmission rate allocation strategy of the next detection cycle according to the received strategy adjustment instructions.

Images