Tunnel health monitoring method and system based on edge calculation

Abstract

The invention relates to the technical field of tunnel engineering monitoring, in particular to a tunnel health monitoring method and system based on edge computing, and the method comprises the steps: a data collection module obtains the original state data of a tunnel through a sensor deployment network, carries out the primary processing of the original state data based on edge computing, and obtains the actual state data; during the period, the data acquisition module performs data filtering on the original state data based on a state data threshold value, rejects invalid data in the original state data and marks abnormal data in the valid data according to an anomaly detection algorithm, and the remaining unmarked original state data is the actual state data of the tunnel; and the monitoring cloud platform obtains the actual state data every a preset period, and carries out data summarization, data storage and data analysis processing on all the actual state data. The system has the beneficial effects that part of calculation tasks are issued to the data acquisition module, so that the processing burden of the monitoring cloud platform is reduced, and the real-time performance and effectiveness of monitoring and early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel function monitoring, and in particular to a tunnel health monitoring method and system based on edge computing. Background Art

[0002] Tunnels are the most critical transportation infrastructure, and their structural safety monitoring is extremely important. At present, tunnel health monitoring mainly relies on manual inspections and fixed sensor monitoring, which have obvious limitations. Manual inspections are inefficient and cannot capture tiny structural changes in real time. Although fixed sensors can provide real-time data, they are usually limited to local monitoring and have limited data processing capabilities. In addition, the existing system also has shortcomings in remote access, intelligent analysis, data sharing and collaboration, which makes it difficult for tunnel managers to understand the status of the tunnel in real time, affecting the timeliness and effectiveness of decision-making. At the same time, high-end detection systems are expensive and require regular maintenance. For some small and medium-sized tunnel projects, the cost-effectiveness ratio is not high.

[0003] As tunnels expand in size and monitoring needs increase, existing systems often have difficulty adapting to these changes and lack the necessary flexibility. In addition, existing systems also have limitations in data real-time, processing capabilities, remote monitoring, and intelligent analysis, making it difficult to meet the growing demand for tunnel health monitoring. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a tunnel health monitoring method and system based on edge computing, which solves the technical problem that the existing system has limitations in data real-time, processing capability, remote monitoring, intelligent analysis, etc., and is difficult to meet the growing needs of tunnel health monitoring.

[0006] (II) Technical solution

[0007] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a tunnel health monitoring method based on edge computing, the method is implemented based on a pre-deployed sensor deployment network, and the method includes:

[0009] S11, the data acquisition module obtains the original state data of the tunnel through the sensor deployment network; the original state data includes the data corresponding to the data collected by all sensors in the pre-deployed sensor deployment network;

[0010] S12, the data acquisition module performs preliminary processing on the original status data based on edge computing to obtain actual status data of the tunnel;

[0011] During this period, the data acquisition module filters the raw state data based on a preset state data threshold, removes invalid data from the raw state data, and marks abnormal data in the valid data according to a preset abnormality detection algorithm, and the remaining unmarked raw state data is the actual state data of the tunnel;

[0012] The actual status data includes: target monitoring quantities and characteristic parameters of the tunnel;

[0013] S13. The monitoring cloud platform obtains the actual status data at every preset period, and performs data aggregation, data storage and data analysis on all the actual status data.

[0014] Optionally, the S12 includes:

[0015] S12-1, the data acquisition module pre-processes the received raw state data; the pre-processing includes data cleaning and data sorting;

[0016] S12-2, the data acquisition module compares the pre-processed original state data with the preset state data threshold to determine whether it is valid data;

[0017] If it is invalid data, the data is marked as invalid data and discarded;

[0018] If it is valid data, abnormal data detection is performed;

[0019] S12-3, the data acquisition module marks abnormal data in the valid data according to a preset abnormality detection algorithm;

[0020] During this period, the data acquisition module determines whether the original state data after the invalid data is eliminated is abnormal data according to the filtered valid data and the preset first historical state data, and the preset formula 1, and marks the abnormal data;

[0021] The first historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past first preset time;

[0022] The formula 1 is:

[0023]

[0024] Among them, z is the judgment parameter for judging whether the original state data after invalid data is removed is abnormal data, x is the original state data after invalid data is removed, u is the average value of historical state data, n is the number of historical state data, u i It is historical status data.

[0025] Optionally, the S12-3 further includes:

[0026] When z < 1, the data acquisition module marks the original state data as normal data;

[0027] When 1≤z<2, the data acquisition module marks the original state data as slightly abnormal data;

[0028] When 2≤z<3, the data acquisition module marks the original state data as moderately abnormal data;

[0029] When z≥3, the data acquisition module marks the original state data as severely abnormal data;

[0030] Then the S12 further includes:

[0031] S12-4. The data acquisition module determines the working status of the instrument corresponding to the abnormal data according to the abnormal degree marked by the original status data and the pre-set abnormal diagnosis strategy.

[0032] Optionally, the S12 further includes:

[0033] S12-0, the data acquisition module stores the acquired original state data in a preset local database;

[0034] S12-5, the data acquisition module stores the actual state data after preliminary processing in a local database, and establishes a corresponding relationship between the actual state data and the original state data;

[0035] S12-6. The data acquisition module sends the actual status data obtained within the period to the monitoring cloud platform through the 4G / 5G smart gateway or wired network at preset intervals.

[0036] The local database includes: a MySQL database, a MongoDB database, or a Solr database.

[0037] Optionally, the S12 further includes:

[0038] At every second preset time, the data acquisition module compresses the actual status data obtained during the period based on the compressed sensing principle, and sends the compressed actual status data to the monitoring cloud platform.

[0039] Optionally, the S13 includes:

[0040] S13-1, the monitoring cloud platform acquires and stores the actual status data at every preset period;

[0041] S13-2, the monitoring cloud platform obtains the data change value of the detection object corresponding to each sensor in the sensor deployment network according to the actual status data obtained in the preset period and the preset second historical status data;

[0042] The second historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past third preset time;

[0043] S13-3. The monitoring cloud platform evaluates the health and risk status of the tunnel according to the data change value of the detection object corresponding to each sensor in the sensor deployment network and the pre-set warning value of each detection object.

[0044] Optionally, the S13-1 includes:

[0045] The monitoring cloud platform obtains actual status data at every preset period and obtains the signal-to-noise ratio of the actual status data;

[0046] The monitoring cloud platform selects the corresponding denoising process based on the signal-to-noise ratio of the actual state data and the preset signal-to-noise ratio gradient threshold, and denoises the actual state data; the denoising process includes: moving average filtering, weighted average filtering, stop filtering, Wiener filtering and wavelet threshold denoising;

[0047] The monitoring cloud platform eliminates dispersion, fills in missing values, and normalizes the actual status data after denoising;

[0048] The monitoring cloud platform reduces the dimension of the actual state data after dispersion elimination, missing value filling and normalization processing according to a preset dimensionality reduction algorithm; the dimensionality reduction algorithm includes principal component analysis, t-distribution neighborhood embedding algorithm or isometric mapping method;

[0049] The monitoring cloud platform stores the actual status data after dimensionality reduction in a pre-set cloud database.

[0050] Optionally, S13 further includes:

[0051] The monitoring cloud platform establishes a data visualization interface based on the actual status data after aggregation, data storage and data analysis, so that managers can detect the tunnel status in real time and generate real-time reports and data statistics;

[0052] The visualization interface includes real-time maps, charts, and reports.

[0053] In a second aspect, an embodiment of the present invention provides a tunnel health monitoring system based on edge computing, including:

[0054] Sensor deployment network, data acquisition modules and monitoring cloud platform;

[0055] The sensor deployment network is set at a designated location in the tunnel, and includes a tilt sensor, a strain sensor, a temperature sensor, a vibration sensor, and a displacement sensor;

[0056] The sensor deployment network is used to monitor various data in the tunnel, that is, the original state data of the tunnel, and send the original state data of the tunnel to the data acquisition module;

[0057] The data acquisition module is used to perform preliminary processing on the original status data based on edge computing to obtain actual status data of the tunnel;

[0058] The monitoring cloud platform is used to obtain the actual status data at every preset period, and perform data aggregation, data storage and data analysis processing on all the actual status data.

[0059] Optionally, the data acquisition module includes: a data acquisition unit, an edge computing unit and a data storage unit;

[0060] The data collection unit is used to receive the original state data of the tunnel in real time and send it to the edge computing unit and the data storage unit;

[0061] The edge computing unit is used to filter the original state data based on a preset state data threshold, remove invalid data in the original state data, and mark abnormal data in the valid data according to a preset abnormality detection algorithm. The remaining unmarked original state data is the actual state data of the tunnel, and the data processing unit sends the actual state data to the data storage unit;

[0062] The data storage unit is used to store the acquired original state data in a preset local database when original state data is received; and to store the actual state data in the local database when actual state data is received, and to establish a corresponding relationship between the actual state data and the original state data.

[0063] (III) Beneficial effects

[0064] The beneficial effects of the present invention are as follows: a tunnel health monitoring method based on edge computing of the present invention collects various data in the tunnel in real time through a sensor deployment network, and delegates some computing tasks to the data acquisition module. Compared with the prior art, it effectively reduces the processing burden of the monitoring cloud platform, alleviates the pressure of the data transmission process, reduces the processing and transmission delays, and improves the real-time and effectiveness of monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flow chart of a tunnel health monitoring method based on edge computing;

[0066] Figure 2 This is a schematic diagram of the structure of a tunnel health monitoring system based on edge computing;

[0067] Figure 3 Schematic diagram of the network deployment for sensor deployment;

[0068] Figure 4 This is a schematic diagram of the monitoring cloud platform structure. DETAILED DESCRIPTION

[0069] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0070] A tunnel health monitoring method based on edge computing proposed in an embodiment of the present invention collects various data in the tunnel in real time through a sensor deployment network, and delegates some computing tasks to a data acquisition module. Compared with the existing technology, it effectively reduces the processing burden of the monitoring cloud platform, alleviates the pressure of the data transmission process, reduces the processing and transmission delays, and improves the real-time and effectiveness of monitoring and early warning.

[0071] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0072] Example 1

[0073] This embodiment proposes a tunnel health monitoring method based on edge computing. The method is implemented based on a pre-deployed sensor deployment network. The sensor deployment network includes: tilt sensors (including fixed inclinometers, MEMS inclinometers), strain sensors, temperature sensors (including thermometers and fiber grating thermometers), vibration sensors and displacement sensors, etc.; each sensor is set at a specified position in the tunnel.

[0074] The process of the method is as follows Figure 1 As shown, including:

[0075] S11. The data acquisition module acquires original state data of the tunnel through the sensor deployment network; the original state data includes data corresponding to and collected by all sensors in the pre-deployed sensor deployment network.

[0076] S12, the data acquisition module performs preliminary processing on the original status data based on edge computing to obtain actual status data of the tunnel;

[0077] During this period, the data acquisition module filters the original state data based on a preset state data threshold, removes invalid data in the original state data, and marks abnormal data in the valid data according to a preset abnormality detection algorithm. The remaining unmarked original state data is the actual state data of the tunnel; the actual state data includes: the target monitoring quantity and characteristic parameters of the tunnel; specifically includes:

[0078] S12-0, the data acquisition module stores the acquired original state data in a preset local database;

[0079] S12-1, the data acquisition module pre-processes the received raw state data; the pre-processing includes data cleaning and data sorting;

[0080] S12-2, the data acquisition module compares the pre-processed original state data with the preset state data threshold to determine whether it is valid data;

[0081] If it is invalid data, the data is marked as invalid data and discarded;

[0082] If it is valid data, abnormal data detection is performed;

[0083] S12-3, the data acquisition module marks abnormal data in the valid data according to a preset abnormality detection algorithm;

[0084] During this period, the data acquisition module determines whether the original state data after the invalid data is eliminated is abnormal data according to the filtered valid data and the preset first historical state data, and the preset formula 1, and marks the abnormal data;

[0085] The first historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past first preset time;

[0086] The formula 1 is:

[0087]

[0088] Among them, z is the judgment parameter for judging whether the original state data after invalid data is removed is abnormal data, x is the original state data after invalid data is removed, u is the average value of historical state data, n is the number of historical state data, u i For historical status data;

[0089] When z < 1, the data acquisition module marks the original state data as normal data;

[0090] When 1≤z<2, the data acquisition module marks the original state data as slightly abnormal data;

[0091] When 2≤z<3, the data acquisition module marks the original state data as moderately abnormal data;

[0092] When z≥3, the data acquisition module marks the original state data as severely abnormal data;

[0093] S12-4. The data acquisition module determines the working status of the instrument corresponding to the abnormal data according to the abnormal degree marked by the original status data and the pre-set abnormal diagnosis strategy.

[0094] S12-5, the data acquisition module stores the actual state data after preliminary processing in a local database, and establishes a corresponding relationship between the actual state data and the original state data;

[0095] S12-6. The data acquisition module sends the actual status data obtained within the period to the monitoring cloud platform through the 4G / 5G smart gateway or wired network at preset intervals.

[0096] The local database includes: a MySQL database or a MongoDB database or a Solr database;

[0097] At every second preset time, the data acquisition module compresses the actual status data obtained during the period based on the compressed sensing principle, and sends the compressed actual status data to the monitoring cloud platform.

[0098] S13, the monitoring cloud platform obtains the actual status data at every preset period, and performs data aggregation, data storage and data analysis on all the actual status data; specifically including:

[0099] S13-1, the monitoring cloud platform obtains actual status data at every preset period, and obtains the signal-to-noise ratio of the actual status data;

[0100] The monitoring cloud platform selects the corresponding denoising process based on the signal-to-noise ratio of the actual state data and the preset signal-to-noise ratio gradient threshold, and denoises the actual state data; the denoising process includes: moving average filtering, weighted average filtering, stop filtering, Wiener filtering and wavelet threshold denoising;

[0101] The monitoring cloud platform eliminates dispersion, fills in missing values, and normalizes the actual status data after denoising;

[0102] The monitoring cloud platform reduces the dimension of the actual state data after dispersion elimination, missing value filling and normalization processing according to a preset dimensionality reduction algorithm; the dimensionality reduction algorithm includes principal component analysis, t-distribution neighborhood embedding algorithm or isometric mapping method;

[0103] The monitoring cloud platform stores the actual status data after dimensionality reduction in a pre-set cloud database;

[0104] S13-2, the monitoring cloud platform obtains the data change value of the detection object corresponding to each sensor in the sensor deployment network according to the actual status data obtained in the preset period and the preset second historical status data;

[0105] The second historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past third preset time;

[0106] S13-3, the monitoring cloud platform evaluates the health and risk status of the tunnel according to the data change value of the detection object corresponding to each sensor in the sensor deployment network and the pre-set warning value of each detection object;

[0107] The monitoring cloud platform establishes a data visualization interface based on the actual status data after aggregation, data storage and data analysis, so that managers can detect the tunnel status in real time and generate real-time reports and data statistics;

[0108] The visualization interface includes real-time maps, charts, and reports.

[0109] The present embodiment provides a tunnel health monitoring method based on edge computing, which realizes data collection, edge computing, cloud platform data processing and analysis, prediction and decision support, and real-time monitoring and response through pre-set sensors, significantly improving the management efficiency and safety of the tunnel operation and maintenance process. By delegating part of the data processing process to the data collection module, edge computing is realized, and edge computing is used for preliminary processing, the processing burden of the monitoring cloud platform is effectively reduced, the pressure of the data transmission process is alleviated, the processing and transmission delays are reduced, and the real-time and effectiveness of monitoring and early warning are improved. After the preliminary processing, the data is processed again through the monitoring cloud platform to effectively predict potential equipment failures. The above approach not only reduces the failure rate of equipment and extends the service life of equipment, but also significantly improves the operation and maintenance efficiency and overall reliability.

[0110] Example 2

[0111] This embodiment provides a tunnel health monitoring method based on edge computing, including:

[0112] The data acquisition module obtains the original state data of the tunnel through the sensor deployment network; the original state data includes the corresponding data collected by all sensors in the pre-deployed sensor deployment network, and the original state data is cleaned and sorted to screen, convert and correct the original state data, and then deal with errors, missing, abnormalities or duplications in the data. Among them, common data cleaning methods include: missing value processing, abnormal value processing, noise data processing, data deduplication, data normalization (normalization and standardization, etc.); common data sorting methods include: data format conversion, data integration, data aggregation, data encoding and feature extraction. In general, the original state data is a data set, including the corresponding data collected by all sensors in the sensor deployment network.

[0113] The data acquisition module compares the pre-processed raw state data with the pre-set state data threshold to determine whether the raw state is valid data; wherein the state data threshold is a state threshold set one-to-one with all sensors in the sensor deployment network, and each state data threshold includes an upper limit and a lower limit, which are used to preliminarily determine whether the data is valid;

[0114] If it is invalid data, the data will be marked as invalid data and removed. The invalid data after removal will be saved in the preset data cache area accordingly, and the invalid data in the data cache area will be periodically cleared.

[0115] Furthermore, the data acquisition module judges the pre-processed original state data in real time based on the state data threshold. When the original state data corresponding to any sensor contains continuous invalid data, or the original state data corresponding to the sensor contains invalid data for multiple times (preset times) within a period of time, it is judged that the sensor may be abnormal; all data corresponding to the sensor filtered out within this period of time are recovered, and an abnormal file is generated; the abnormal file includes the acquisition time corresponding to each data, the data value, and the judgment result of whether it is invalid data, and is saved in the local database to facilitate subsequent fault type troubleshooting.

[0116] If it is valid data, further abnormal data monitoring is performed to determine whether the valid data is abnormal data. Data anomaly detection is usually implemented based on the set anomaly detection algorithm. Common data anomaly detection algorithms include: mean-variance method and box plot method based on statistics, vector machine (SVM) anomaly detection model based on machine learning, clustering algorithm (such as K-means and DBSCAN, etc.) and isolation forest, simple exponential smoothing based on time series and ARIMA model.

[0117] This embodiment uses the preset first historical state data and the preset formula 1 to determine whether the original state data after the invalid data is removed is abnormal data, and marks the abnormal data;

[0118] The first historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past first preset time;

[0119] The formula 1 is:

[0120]

[0121] Among them, z is the judgment parameter for judging whether the original state data after invalid data is removed is abnormal data, x is the original state data after invalid data is removed, u is the average value of historical state data, n is the number of historical state data, u i It is historical status data.

[0122] Based on the value of the judgment parameter z, the abnormality of the original state data after the invalid data is removed is judged and a corresponding mark is given:

[0123] When z < 1, the data acquisition module marks the original state data as normal data;

[0124] When 1≤z<2, the data acquisition module marks the original state data as slightly abnormal data;

[0125] When 2≤z<3, the data acquisition module marks the original state data as moderately abnormal data;

[0126] When z≥3, the data acquisition module marks the original state data as severely abnormal data.

[0127] The data acquisition module determines the working status of the instrument and equipment corresponding to the abnormal data based on the abnormal degree marked by the original status data and the pre-set abnormal diagnosis strategy.

[0128] After receiving the raw state data collected by all sensors in the sensor deployment network, the data acquisition module stores the acquired raw state data in a pre-set local database, classifies the raw state data based on its data source, and marks the corresponding collection time for all raw state data;

[0129] The data collection module stores the actual state data after preliminary processing in the local database, and establishes a corresponding relationship between the actual state data and the original state data before processing, so as to facilitate subsequent viewing and comparative analysis. Generally, the local database includes a MySQL database, a MongoDB database, or a Solr database.

[0130] The data acquisition module periodically sends the actual status data stored in the local database to the monitoring cloud platform. Before sending the actual status data, the data needs to be compressed to reduce possible IO congestion and improve data transmission efficiency.

[0131] Therefore, the compressed sensing algorithm is used to compress the actual state data. Common compressed sensing algorithms include coefficient representation algorithm, OMP algorithm, L1 norm minimization algorithm and wavelet transform algorithm.

[0132] This embodiment compresses data in the following manner:

[0133] The data collection module classifies all actual status data between one data sending node and another data sending node according to the corresponding sensor. The data sending node is the time point when the data collection module regularly sends the actual status data stored in the local database to the monitoring cloud platform. For the actual status data corresponding to a sensor, all data from the first moment to the tth moment are compressed, and the perception data obtained after the tth moment is Wherein, P is the sensor number, and all data sets corresponding to sensor P from the first moment to the tth moment are actual state data.

[0134] First, X p The sparsity of the collected sensory data is analyzed to determine whether the collected data is compressible. In general, the discrete cosine transform can be used to analyze the sparsity of the collected data. When the sensory data can be compressed, some time points can be selected through the row vectors in the observation matrix. The weighted measurement value of the collected sensory data multiplied by the corresponding element in the observation matrix at the selected time point is generated on the edge server. The test paper of sensor P can be expressed as in is the preset collection coefficient.

[0135] During the compression process, all actual status data of the data acquisition module is the weighted sum of the perception data at all perception moments, rather than simply superimposing all the perception data. By compressing the data in this way, the amount of data transmitted to the monitoring cloud platform can be reduced. In this process, the observation matrix usually selects a Gaussian random matrix. At different perception moments, t* different acquisition coefficients are used to weight the perception data collected at the current moment to form t* observation values ​​for storage. After that, t* observation values ​​are formed each time a perception moment passes, and are added to the observation values ​​stored at the previous moment to become new t* observation values, until the last t* observation values ​​are formed at the moment when the data needs to be sent, and then the entire data is compressed.

[0136] The observation value corresponding to a single sensor collected is The sensed data x1 collected at time t1 is multiplied by the collection coefficient Then the data is sent to time t2; at time t2, the observed value at time t1 is added to the sensed data x2 collected at time t2 multiplied by the collection coefficient The sum of the weighted values is sent to the next time until the data within the sensing time is collected. After t* observations, for the observed value formed by P at time t* where t* << t. That is, data compression is performed.

[0137] The monitoring cloud platform needs to use the inverse application of the compressive sensing algorithm to reconstruct, recover, and store the compressed actual state data after receiving it.

[0138] The monitoring cloud platform obtains the data change values of the detection objects corresponding to the sensors in the sensor deployment network according to the actual state data obtained at a preset period and the pre-set second historical state data;

[0139] The second historical state data is the effective non-abnormal data of the tunnel obtained by the sensor deployment network in the past third preset time;

[0140] The monitoring cloud platform evaluates the tunnel health and risk status according to the data change values of the detection objects corresponding to the sensors in the sensor deployment network and the pre-set warning values of each detection object.

[0141] Before storing the data, the monitoring cloud platform needs to process the received actual state data, including: obtaining the signal-to-noise ratio of the actual state data; based on the signal-to-noise ratio of the actual state data and the pre-set signal-to-noise ratio gradient threshold, screening the corresponding denoising process to denoise the actual state data; the denoising process includes: moving average filtering, weighted average filtering, median filtering, Wiener filtering, and wavelet threshold denoising;

[0142] The monitoring cloud platform performs dispersion elimination, missing value filling, and normalization processing on the denoised actual state data;

[0143] The monitoring cloud platform performs dimensionality reduction on the actual state data after dispersion elimination, missing value filling, and normalization processing according to the pre-set dimensionality reduction algorithm; the dimensionality reduction algorithm includes principal component analysis, t-distributed neighborhood embedding algorithm, or isometric mapping method;

[0144] The monitoring cloud platform stores the dimensionally reduced actual state data in the pre-set cloud database.

[0145] The monitoring cloud platform establishes a data visualization interface based on the actual status data after aggregation, data storage and data analysis, so that managers can detect the tunnel status in real time and generate real-time reports and data statistics;

[0146] The visualization interface includes real-time maps, charts, and reports.

[0147] This embodiment collects various data in the tunnel in real time through a sensor deployment network, and delegates some computing tasks to the data acquisition module. Compared with the existing technology, it effectively reduces the processing burden of the monitoring cloud platform, alleviates the pressure of the data transmission process, reduces the processing and transmission delays, and improves the real-time and effectiveness of monitoring and early warning.

[0148] Example 3

[0149] This embodiment provides a tunnel health monitoring system based on edge computing, whose structure is as follows: Figure 2 As shown, including:

[0150] A monitoring cloud platform and at least one sensor deployment network, and a data acquisition module corresponding to each sensor deployment network. Each sensor deployment network is in communication connection with its corresponding data acquisition module, and all data acquisition modules are in communication connection with the monitoring cloud platform. All sensor deployment networks are distributed at different locations in the tunnel, and each sensor deployment network includes: a tilt sensor, a strain sensor, a temperature sensor, a vibration sensor, and a displacement sensor; wherein the tilt sensor includes a fixed inclinometer and a MEMS inclinometer, and the tilt sensor is used to measure the tilt angle of the tunnel. The change in the tilt angle can reflect the deformation of the tunnel, thereby judging the structural health of the tunnel. The strain sensor includes a vibrating string strain gauge, a vibrating string surface strain gauge, a fiber Bragg grating surface strain gauge, a vibrating string embedded strain gauge, and a fiber Bragg grating embedded strain gauge. The strain sensor is used to measure the strain of the tunnel structure. By monitoring the strain change of the tunnel structure, the structural health of the tunnel can be judged, and maintenance measures can be taken in time. The temperature sensor includes a thermometer and a fiber Bragg grating thermometer, and the temperature sensor is used to measure the temperature change of the tunnel. The temperature change of the tunnel can affect the stability of the tunnel structure. Therefore, the monitoring of the temperature sensor is very important for judging the health of the tunnel. Vibration sensors are used to monitor the vibration of tunnel structures. The vibration changes of tunnel structures can reflect the structural health of the tunnel. If abnormal vibration is found in time, corresponding maintenance measures can be taken. Displacement sensors include vibrating string displacement meters, vibrating string embedded joint meters, vibrating string surface joint meters, and potentiometer-type large-range displacement meters. All sensors in any sensor deployment network are connected to the data acquisition module corresponding to the sensor deployment network. The sensor deployment network deployment diagram is shown in the figure below. Figure 3 shown.

[0151] The data acquisition module integrates 4G / 5G smart gateway, CAN bus interface and other data transmission interfaces. The data acquisition module can realize functions such as data acquisition, edge computing and data transmission, that is, data collection from various sensors, and after preliminary processing of the data, the data is output to the monitoring cloud platform through 4G wireless network or wired network.

[0152] The data acquisition module includes: a data acquisition unit, an edge computing unit and a data storage unit;

[0153] The data collection unit is used to receive the original state data of the tunnel in real time and send it to the edge computing unit and the data storage unit;

[0154] The edge computing unit is used to filter the original state data based on a preset state data threshold, remove invalid data in the original state data, and mark abnormal data in the valid data according to a preset abnormality detection algorithm. The remaining unmarked original state data is the actual state data of the tunnel, and the data processing unit sends the actual state data to the data storage unit;

[0155] The data storage unit is used to store the acquired original state data in a preset local database when original state data is received; and to store the actual state data in the local database when actual state data is received, and to establish a corresponding relationship between the actual state data and the original state data.

[0156] That is, the data acquisition module usually also includes a data acquisition workstation located at the tunnel site. The data acquisition workstation uses different conditioning methods to condition the signals of various types of sensors, and processes and converts the conditioned sensor signals to finally form digital signals that can be transmitted remotely. On this basis, according to the different signal input methods and monitored physical quantities, the collected signals are divided into digital signals, analog signals and optical signals, and processed by pre-set digital signal data acquisition software, analog signal data acquisition software and optical signal data acquisition software. The three software have similar business functions, but different algorithms for processing data and different hardware devices they rely on, so they will be developed separately.

[0157] The edge computing unit is also used to clean and organize the original status data, diagnose the working status of the instrument and equipment based on the abnormal phenomena of the original status data, and then calculate the target monitoring quantity and characteristic parameters, and send them to the data storage unit.

[0158] Furthermore, the monitoring cloud platform uses the powerful computing and storage capabilities of the cloud computing platform to process and store the collected data in real time. The monitoring cloud platform is based on cloud computing and Internet of Things technology to provide effective, reliable and convenient data monitoring services to obtain relevant monitoring data and alarm information in the first time, thereby realizing the safety monitoring of various engineering projects. The main functions include data collection, data warning, data viewing, report printing, and information aggregation. The monitoring cloud platform supports browser versions: IE9 and above, Firefox11 and above, Chrome10 and above.

[0159] Monitoring cloud platform, its structure is as follows Figure 4 As shown, it is generally divided into: data persistence layer, basic support layer, business layer, and presentation layer.

[0160] The data persistence layer is the bottom layer of the entire platform. It obtains data through scheduled task applications, determines the data preprocessing steps based on the actual data quality, and stores the collected data persistently. That is, it determines how to proceed with the noise reduction process based on the signal-to-noise ratio of the actual state data received.

[0161] The basic support layer is the general basic support function of the software system, which is an abstract function independent of the business field. Establishing a perfect basic support layer lays a solid foundation for system development, debugging and maintenance, making time controllable and quality reliable.

[0162] In the business layer, various sensor devices are managed to implement specific business operations, and business modules are customized and developed in combination with the actual management needs of tunnel health monitoring. In the business layer, prediction models can be set up, including time series analysis models, regression analysis models, neural network prediction models, decision trees, etc., to analyze actual status data and predict future tunnel conditions.

[0163] In the presentation layer, in order to meet the needs of business management, comprehensive management of various businesses is realized, as well as data interaction, business linkage and comprehensive analysis and decision-making between multiple business units. There are mainly Web applications and mobile applications.

[0164] Furthermore, the system also includes a user end. The user end includes a device control panel, a data center, an alarm center, a measurement point management, an enterprise engineering management, and a report management. The purpose is to develop a user-friendly interface so that tunnel managers can access the cloud platform through the Internet and view the tunnel health status and analysis reports in real time.

[0165] This embodiment provides a tunnel health monitoring system based on edge computing. On the basis of edge computing, a prediction model is set on the monitoring cloud platform to predict future tunnel conditions based on the actual status data received, thereby reducing accidental risks, while the user-side settings enhance the convenience during use.

[0166] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0167] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like 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 mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0168] In the present invention, unless otherwise clearly specified and limited, when a first feature is “on” or “below” a second feature, it may be that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Moreover, when a first feature is “above”, “above” or “above” a second feature, it may be that the first feature is directly above or obliquely above the second feature, or it may simply mean that the first feature is higher in level than the second feature. When a first feature is “below”, “below” or “below” a second feature, it may be that the first feature is directly below or obliquely below the second feature, or it may simply mean that the first feature is lower in level than the second feature.

[0169] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0170] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may alter, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A tunnel health monitoring method based on edge computing, the method is implemented based on a pre-deployed sensor deployment network, characterized in that: The method comprises: S11, the data acquisition module obtains the original state data of the tunnel through the sensor deployment network; the original state data includes the data corresponding to the data collected by all sensors in the pre-deployed sensor deployment network; S12, the data acquisition module performs preliminary processing on the original status data based on edge computing to obtain actual status data of the tunnel; During this period, the data acquisition module filters the raw state data based on a preset state data threshold, removes invalid data from the raw state data, and marks abnormal data in the valid data according to a preset abnormality detection algorithm, and the remaining unmarked raw state data is the actual state data of the tunnel; The actual status data includes: target monitoring quantities and characteristic parameters of the tunnel; S13. The monitoring cloud platform obtains the actual status data at every preset period, and performs data aggregation, data storage and data analysis on all the actual status data.

2. The tunnel health monitoring method based on edge computing according to claim 1 is characterized in that: The S12 includes: S12-1, the data acquisition module pre-processes the received raw state data; the pre-processing includes data cleaning and data sorting; S12-2, the data acquisition module compares the pre-processed original state data with the preset state data threshold to determine whether it is valid data; If it is invalid data, the data is marked as invalid data and discarded; If it is valid data, abnormal data detection is performed; S12-3, the data acquisition module marks abnormal data in the valid data according to a preset abnormality detection algorithm; During this period, the data acquisition module determines whether the original state data after eliminating the invalid data is abnormal data based on the filtered valid data and the preset first historical state data, and the preset formula 1, and marks the abnormal data; The first historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past first preset time; The formula 1 is: Among them, z is the judgment parameter for judging whether the original state data after invalid data is removed is abnormal data, x is the original state data after invalid data is removed, u is the average value of historical state data, n is the number of historical state data, u i It is historical status data.

3. The tunnel health monitoring method based on edge computing according to claim 2 is characterized in that: The S12-3 also includes: When z < 1, the data acquisition module marks the original state data as normal data; When 1≤z<2, the data acquisition module marks the original state data as slightly abnormal data; When 2≤z<3, the data acquisition module marks the original state data as moderately abnormal data; When z≥3, the data acquisition module marks the original state data as severely abnormal data; Then the S12 further includes: S12-4. The data acquisition module determines the working status of the instrument corresponding to the abnormal data according to the abnormal degree marked by the original status data and the pre-set abnormal diagnosis strategy.

4. The tunnel health monitoring method based on edge computing according to claim 2 is characterized in that: The S12 further includes: S12-0, the data acquisition module stores the acquired original state data in a preset local database; S12-5, the data acquisition module stores the actual state data after preliminary processing in a local database, and establishes a corresponding relationship between the actual state data and the original state data; S12-6. The data acquisition module sends the actual status data obtained within the period to the monitoring cloud platform through the 4G / 5G smart gateway or wired network at preset intervals. The local database includes: a MySQL database, a MongoDB database, or a Solr database.

5. The tunnel health monitoring method based on edge computing according to claim 1 is characterized in that: The S12 further includes: At every second preset time, the data acquisition module compresses the actual status data obtained during the period based on the compressed sensing principle, and sends the compressed actual status data to the monitoring cloud platform.

6. The tunnel health monitoring method based on edge computing according to claim 1 is characterized in that: The S13 includes: S13-1, the monitoring cloud platform acquires and stores the actual status data at every preset period; S13-2, the monitoring cloud platform obtains the data change value of the detection object corresponding to each sensor in the sensor deployment network according to the actual status data obtained in the preset period and the preset second historical status data; The second historical status data is valid non-abnormal data of the tunnel acquired by the sensor deployment network within the past third preset time; S13-3. The monitoring cloud platform evaluates the health and risk status of the tunnel according to the data change value of the detection object corresponding to each sensor in the sensor deployment network and the pre-set warning value of each detection object.

7. The tunnel health monitoring method based on edge computing according to claim 6 is characterized in that: The S13-1 includes: The monitoring cloud platform obtains actual status data at every preset period and obtains the signal-to-noise ratio of the actual status data; The monitoring cloud platform selects the corresponding denoising process based on the signal-to-noise ratio of the actual state data and the preset signal-to-noise ratio gradient threshold, and denoises the actual state data; the denoising process includes: moving average filtering, weighted average filtering, stop filtering, Wiener filtering and wavelet threshold denoising; The monitoring cloud platform eliminates dispersion, fills in missing values, and normalizes the actual status data after denoising; The monitoring cloud platform reduces the dimension of the actual state data after dispersion elimination, missing value filling and normalization processing according to a preset dimensionality reduction algorithm; the dimensionality reduction algorithm includes principal component analysis, t-distribution neighborhood embedding algorithm or isometric mapping method; The monitoring cloud platform stores the actual status data after dimensionality reduction in a pre-set cloud database.

8. The tunnel health monitoring method based on edge computing according to claim 1 is characterized in that: The S13 also includes: The monitoring cloud platform establishes a data visualization interface based on the actual status data after aggregation, data storage and data analysis, so that managers can detect the tunnel status in real time and generate real-time reports and data statistics; The visualization interface includes real-time maps, charts, and reports.

9. A tunnel health monitoring system based on edge computing, characterized in that: include: Sensor deployment network, data acquisition modules and monitoring cloud platform; The sensor deployment network is set at a designated location in the tunnel, and includes a tilt sensor, a strain sensor, a temperature sensor, a vibration sensor, and a displacement sensor; The sensor deployment network is used to monitor various data in the tunnel, that is, the original state data of the tunnel, and send the original state data of the tunnel to the data acquisition module; The data acquisition module is used to perform preliminary processing on the original status data based on edge computing to obtain actual status data of the tunnel; The monitoring cloud platform is used to obtain the actual status data at every preset period, and perform data aggregation, data storage and data analysis processing on all the actual status data.

10. The tunnel health monitoring system based on edge computing according to claim 9, characterized in that: The data acquisition module includes: a data acquisition unit, an edge computing unit and a data storage unit; The data collection unit is used to receive the original state data of the tunnel in real time and send it to the edge computing unit and the data storage unit; The edge computing unit is used to filter the original state data based on a preset state data threshold, remove invalid data in the original state data, and mark abnormal data in the valid data according to a preset abnormality detection algorithm. The remaining unmarked original state data is the actual state data of the tunnel, and the data processing unit sends the actual state data to the data storage unit; The data storage unit is used to store the acquired original state data in a preset local database when original state data is received; and to store the actual state data in the local database when actual state data is received, and to establish a corresponding relationship between the actual state data and the original state data.

Images