Dangerous rock mass crack monitoring system and method based on Zigbee technology

Abstract

The invention provides a dangerous rock mass crack monitoring system and method based on the Zigbee technology, and belongs to the technical field of geological disaster monitoring, and the system comprises a plurality of terminal nodes, at least one coordinator node, an edge computing device and a remote monitoring center. The plurality of terminal nodes comprise a crack data acquisition module for acquiring crack data of crack widths, depths and change rates of a plurality of monitoring points of the dangerous rock mass in real time; the Zigbee wireless communication module is used for wireless transmission; the self-adaptive control module is used for adjusting the data acquisition frequency and the transmission interval according to the crack change rate of the monitoring point; the coordinator node is used for receiving crack data of a plurality of monitoring points; the edge computing device is used for analyzing a danger signal in the crack data by adopting the trained machine learning model and generating a real-time early warning signal; and the remote monitoring center is used for receiving, displaying and storing the analysis result and the early warning signal. According to the method, low-power-consumption and long-distance dangerous rock mass crack monitoring can be achieved, and long-term and stable operation is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to a method for monitoring cracks in dangerous rock bodies based on Zigbee technology. Background Art

[0002] In the field of geological disaster monitoring, real-time monitoring of cracks in dangerous rock masses plays an important role in preventing disasters such as landslides and collapses. Currently, crack monitoring systems usually use wired sensor networks or traditional wireless sensor networks. These technologies have met the needs of monitoring crack changes to a certain extent, but in practical applications, especially in remote mountainous areas, areas with complex terrain or limited power resources, existing technologies still have some limitations.

[0003] First, the deployment cost of wired sensor networks is high and the installation is complex, especially in mountainous environments with complex terrain. Cabling is difficult and the maintenance cost is high. Cables are easily affected by the external environment and suffer physical damage, which increases the workload of equipment maintenance. At the same time, the flexibility of wired systems is poor. Once the layout is completed, it is difficult to adjust according to actual needs.

[0004] Secondly, although traditional wireless sensor networks are more flexible in deployment than wired systems, most of them use communication technologies such as Wi-Fi and cellular networks. These communication technologies have high power consumption, and terminal devices often need to replace batteries frequently, making it difficult to achieve long-term and stable monitoring. Especially in remote areas or areas with insufficient power supply, maintaining the long-term normal operation of equipment has become a major challenge. In addition, existing wireless communication technologies are also limited in coverage and communication distance, making it difficult to adapt to large-scale monitoring areas.

[0005] Furthermore, many existing monitoring systems transmit the collected data to remote servers for centralized processing. Although this model can perform large-scale data analysis, it relies on remote servers and has problems such as data transmission delays and network instability, which cannot meet the requirements of real-time and response speed in geological disaster monitoring. At the same time, the monitoring parameters of existing systems are usually fixed and difficult to adjust adaptively according to environmental changes, which may miss key data or generate too much unnecessary monitoring information in some cases.

[0006] In summary, the existing dangerous rock mass crack monitoring system has the problems of short data transmission distance and high power consumption. Summary of the invention

[0007] To solve the above problems, the present invention provides a dangerous rock crack monitoring method based on Zigbee technology, which can realize low-power and long-distance dangerous rock crack monitoring and achieve long-term and stable operation.

[0008] To achieve the above object, the present invention provides the following technical solutions.

[0009] A method for monitoring cracks in dangerous rock mass based on Zigbee technology comprises the following steps:

[0010] A plurality of terminal nodes are respectively arranged at a plurality of monitoring points in the dangerous rock mass monitoring area; the terminal nodes include a crack data acquisition module, a Zigbee wireless communication module and an adaptive control module; the crack data acquisition module acquires crack data of crack width, depth and change rate of a plurality of monitoring points of the dangerous rock mass in real time; the Zigbee wireless communication module wirelessly transmits the crack data of a plurality of monitoring points; the adaptive control module adjusts the data acquisition frequency of the crack monitoring sensor and the transmission interval of the Zigbee wireless communication module according to the crack change rate of the monitoring point;

[0011] at least one coordinator node, connected in communication with the plurality of terminal nodes, for receiving crack data of a plurality of monitoring points;

[0012] At least one edge computing device, in communication with the coordinator node, configured to analyze dangerous signals in the crack data using a trained machine learning model and generate a real-time warning signal;

[0013] A remote monitoring center is connected to the edge computing device for receiving, displaying and storing analysis results and warning signals.

[0014] Preferably, the crack data acquisition module includes a sensor and a microprocessor;

[0015] The sensor is a crack monitoring sensor based on the principle of resistance change, which obtains crack data of crack width, depth and change rate at multiple monitoring points; the sensor is electrically connected to the analog input terminal of the microprocessor, and the microprocessor digitizes the signal and sends it to the Zigbee wireless communication module through the serial interface.

[0016] Preferably, the Zigbee wireless communication module is also used to automatically adjust the transmission power according to geographical conditions or signal strength.

[0017] Preferably, the terminal node also includes multiple types of environmental parameter sensors; the multiple types of environmental parameter sensors are used to monitor external environmental data including temperature, humidity and pressure, and transmit the external environmental data and crack monitoring data to the edge computing device through the Zigbee wireless communication module.

[0018] Preferably, the edge computing device is used to pre-process the received external environment data and crack monitoring data; the pre-processing includes data cleaning, normalization and feature extraction;

[0019] The edge computing device is also used to predict the crack monitoring data after data processing through a pre-trained machine learning recognition model to obtain crack development trend analysis results;

[0020] The edge computing device is used to automatically adjust the warning threshold according to the crack monitoring data and the external environment data through a pre-trained machine learning threshold adjustment model. When the prediction result exceeds the warning threshold, a warning signal is generated and transmitted to the remote monitoring center.

[0021] Preferably, the edge computing device is a Raspberry Pi.

[0022] Preferably, the terminal node further comprises a power management unit; the power management unit comprises an electrically connected solar charging circuit and a solar charging battery.

[0023] Preferably, it also includes a high-speed storage device; the high-speed storage device is electrically connected to the remote monitoring system, and the high-speed storage device is used to store all external environment data and crack monitoring data, as well as crack development trend analysis results;

[0024] The edge computing device also includes a local storage module; the local storage module is used to store historical crack monitoring data and upload the historical crack monitoring data to the remote monitoring center when necessary.

[0025] Preferably, the remote monitoring system is also used to access its data through a mobile device or computer and adjust monitoring parameters, including sampling frequency, sensor sensitivity and data transmission interval.

[0026] A method for monitoring cracks in dangerous rock mass based on Zigbee technology comprises the following steps:

[0027] Collect crack data of crack width, depth and change rate at multiple monitoring points in dangerous rock mass in real time;

[0028] The crack data of multiple monitoring points are wirelessly transmitted through Zigbee wireless communication; wherein the collection frequency of the crack data and the transmission interval of the Zigbee wireless communication are adjusted according to the crack change rate of the monitoring point;

[0029] The trained machine learning model is used to analyze the dangerous signals in the crack data and generate real-time warning signals. The analysis results and warning signals are then displayed and stored.

[0030] Beneficial effects of the present invention:

[0031] The present invention proposes a dangerous rock crack monitoring system and method based on Zigbee technology. The system uses Zigbee wireless communication technology to adjust the data acquisition frequency of the crack monitoring sensor and the transmission interval of the Zigbee wireless communication module through the crack change rate of the monitoring point, thereby achieving low power consumption and long-distance crack data transmission, which is particularly suitable for long-term monitoring in remote areas and complex terrains. Compared with traditional Wi-Fi or cellular networks, Zigbee technology has significant advantages in power consumption, stability and coverage. The system automatically adjusts the acquisition frequency and transmission interval to minimize power consumption and extend the battery life of the equipment while ensuring monitoring accuracy, making it suitable for long-term unattended monitoring scenarios.

[0032] This system uses edge computing devices to apply machine learning algorithms to real-time analysis of crack monitoring data, which can quickly respond to data changes, identify potential dangerous situations and generate warnings, avoiding the delay problem caused by traditional monitoring systems relying on remote server processing. In addition, edge computing devices can dynamically adjust warning thresholds based on real-time and historical data to further improve the accuracy of warnings.

[0033] The system adopts a modular design, and the terminal nodes, coordinator nodes and edge computing devices can be flexibly configured according to the scale and complexity of the monitoring area. The system supports the increase or decrease of terminal nodes, can adapt to different monitoring needs and environmental conditions, and is particularly suitable for large or decentralized monitoring scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is an architecture diagram of a dangerous rock mass crack monitoring system based on Zigbee technology according to an embodiment of the present invention;

[0035] Figure 2 is a coordinator workflow diagram of an embodiment of the present invention;

[0036] Figure 3 1 is a Raspberry Pi workflow diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] Example 1

[0039] The existing crack monitoring systems for dangerous rock masses have the following technical problems: (1) High power consumption: Traditional crack monitoring systems consume high power in wireless data transmission and sensor power supply, especially in remote areas or environments with scarce electricity resources, and it is difficult to achieve long-term and stable operation. (2) Limited communication distance: Existing wireless sensor networks (such as Wi-Fi, cellular networks, etc.) are limited by communication distance and signal coverage, and it is difficult to meet the monitoring needs of large areas or complex terrain areas. (3) Insufficient real-time data processing: Many crack monitoring systems rely on uploading data to a remote server for processing. The delay in the data transmission process causes the system to be unable to respond to crack changes in a timely manner and cannot effectively achieve real-time warnings. (4) Lack of adaptive adjustment capabilities: Existing systems are usually fixed in terms of monitoring frequency and parameter settings, and cannot be adaptively adjusted according to the actual situation of the environment and crack changes, which can easily cause unnecessary power consumption or omission of key data.

[0040] The present invention is a dangerous rock mass crack monitoring system based on Zigbee technology, the system block diagram is as follows Figure 1 As shown, it includes a remote monitoring center, at least one coordinator node and an edge computing device, and multiple terminal nodes.

[0041] Multiple terminal nodes are respectively arranged at multiple monitoring points in the dangerous rock mass monitoring area. The terminal nodes include a crack data acquisition module, a Zigbee wireless communication module, an adaptive control module and a power management unit. The crack data acquisition module acquires crack data of crack width, depth and change rate at multiple monitoring points of the dangerous rock mass in real time. The crack data acquisition module includes a sensor and a microprocessor.

[0042] The sensor is a crack monitoring sensor based on the principle of resistance change, which obtains crack data of crack width, depth and change rate at multiple monitoring points with an accuracy of 0.1 mm. The sensor is electrically connected to the analog input terminal of the microprocessor, which digitizes the signal and sends it to the Zigbee wireless communication module through the serial interface.

[0043] The Zigbee wireless communication module wirelessly transmits crack data from multiple monitoring points. Zigbee technology has low power consumption, long-distance transmission, and network self-organizing functions, which is suitable for stable data transmission in complex terrain and large areas. The Zigbee wireless communication module is also used to automatically adjust the transmission power according to geographical conditions or signal strength to ensure the stability of data transmission.

[0044] The adaptive control module adjusts the data acquisition frequency of the crack monitoring sensor and the transmission interval of the Zigbee wireless communication module according to the crack change rate of the monitoring point, thereby optimizing energy consumption and response speed.

[0045] The power management unit includes a charging circuit that supports solar charging and battery management to ensure that the node can work stably for a long time in an unattended environment. The power management unit includes an electrically connected solar charging circuit and a solar charging battery.

[0046] In addition, the terminal node also includes multiple types of environmental parameter sensors; the multiple types of environmental parameter sensors are used to monitor external environmental data including temperature, humidity and pressure, and transmit the external environmental data and crack monitoring data to the edge computing device through the Zigbee wireless communication module.

[0047] The coordinator node is deployed in the center of the monitoring area or in a location with good signal. It is used to receive data from multiple terminal nodes and aggregate and preliminarily process the data. The coordinator node transmits the data to the edge computing device via wired or wireless means. The coordinator node also has a signal enhancement function to ensure stable data transmission over long distances and in complex terrain conditions. Figure 2 As shown, Figure 2 The workflow of the coordinator node starts with the power initialization and self-test of the device, and then enters the Zigbee network networking stage to automatically detect and register the surrounding terminal nodes. After the network is established, the coordinator node regularly receives data from each terminal node, performs preliminary time synchronization and data verification, and then optimizes the data transmission path according to the predetermined rules, and sends the data to the edge computing device through a wired or wireless network.

[0048] Edge computing devices are installed at the monitoring site or in the adjacent area and are responsible for localizing the received crack data. Through built-in machine learning algorithms (such as random forests, convolutional neural networks, etc.), edge computing devices can analyze crack data, identify danger signals, and generate real-time warnings. Edge computing devices also have historical data storage capabilities, which can store long-term crack monitoring data locally for subsequent analysis and dynamic adjustment of warning models. Based on real-time data and historical trends, edge computing devices can automatically adjust warning thresholds to improve the accuracy of warnings.

[0049] In this embodiment, the edge computing device is a Raspberry Pi. Figure 3 As shown, Figure 3The Raspberry Pi plays the role of an edge computing device in the system, responsible for processing data from the coordinator node. The received data first goes through a series of preprocessing steps, including data cleaning, normalization, and feature extraction. After the data is processed, the Raspberry Pi uses a pre-trained machine learning model to analyze the data and identify potential risk patterns. Once an abnormal pattern is found, an early warning signal is immediately generated and transmitted to the remote monitoring center through a secure network connection. At the same time, all monitoring data and analysis results are stored in a local high-speed storage device for subsequent trend analysis and historical data backtracking.

[0050] The remote monitoring center is located in a remote location where the monitoring manager or operator is located, and has the functions of real-time data reception, display and storage. The remote monitoring center is connected to the edge computing device through the Internet to obtain analysis results and warning information in real time. Managers can access their data through mobile devices or computers and adjust monitoring parameters, including sampling frequency, sensor sensitivity and data transmission interval. The monitoring center also has historical data storage and long-term trend analysis functions to help managers perform subsequent data backtracking and warning optimization.

[0051] The system proposed in the present invention utilizes Zigbee wireless communication technology to adjust the data acquisition frequency of the crack monitoring sensor and the transmission interval of the Zigbee wireless communication module according to the crack change rate of the monitoring point, thereby achieving low power consumption and long-distance crack data transmission, which is particularly suitable for long-term monitoring in remote areas and complex terrains.

[0052] The system proposed in the present invention automatically adjusts the collection frequency and transmission interval to minimize power consumption and extend the battery life of the equipment while ensuring monitoring accuracy. It is suitable for long-term unattended monitoring scenarios.

[0053] The system proposed in this invention applies machine learning algorithms to real-time analysis of crack monitoring data through edge computing devices, which can quickly respond to data changes, identify potential dangerous situations and generate warnings, avoiding the delay problem caused by traditional monitoring systems relying on remote server processing. In addition, edge computing devices can dynamically adjust warning thresholds based on real-time data and historical data, further improving the accuracy of warnings.

[0054] The system proposed in this invention adopts a modular design, and the terminal nodes, coordinator nodes and edge computing devices can be flexibly configured according to the scale and complexity of the monitoring area. The system supports the increase or decrease of terminal nodes, can adapt to different monitoring needs and environmental conditions, and is particularly suitable for large or decentralized monitoring scenarios.

[0055] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dangerous rock mass crack monitoring system based on Zigbee technology, characterized in that: include: Multiple terminal nodes are respectively arranged at multiple monitoring points in the dangerous rock mass monitoring area; The terminal node includes a crack data acquisition module, a Zigbee wireless communication module and an adaptive control module; the crack data acquisition module acquires crack data of crack width, depth and change rate of multiple monitoring points of the dangerous rock mass in real time; the Zigbee wireless communication module wirelessly transmits the crack data of multiple monitoring points; the adaptive control module adjusts the data acquisition frequency of the crack monitoring sensor and the transmission interval of the Zigbee wireless communication module according to the crack change rate of the monitoring point; at least one coordinator node, connected in communication with the plurality of terminal nodes, for receiving crack data of a plurality of monitoring points; At least one edge computing device, in communication with the coordinator node, configured to analyze dangerous signals in the crack data using a trained machine learning model and generate a real-time warning signal; A remote monitoring center is connected to the edge computing device for receiving, displaying and storing analysis results and warning signals.

2. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 1 is characterized in that: The crack data acquisition module includes a sensor and a microprocessor; The sensor is a crack monitoring sensor based on the principle of resistance change, which obtains crack data of crack width, depth and change rate at multiple monitoring points; the sensor is electrically connected to the analog input terminal of the microprocessor, and the microprocessor digitizes the signal and sends it to the Zigbee wireless communication module through the serial interface.

3. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 1 is characterized in that: The Zigbee wireless communication module is also used to automatically adjust the transmission power according to geographical conditions or signal strength.

4. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 1 is characterized in that: The terminal node also includes multiple types of environmental parameter sensors; the multiple types of environmental parameter sensors are used to monitor external environmental data including temperature, humidity and pressure, and transmit the external environmental data and crack monitoring data to the edge computing device through the Zigbee wireless communication module.

5. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 4 is characterized in that: The edge computing device is used to pre-process the received external environment data and crack monitoring data; the pre-processing includes data cleaning, normalization and feature extraction; The edge computing device is also used to predict the pre-processed crack monitoring data through a pre-trained machine learning recognition model to obtain crack development trend analysis results; The edge computing device is used to automatically adjust the warning threshold according to the crack monitoring data and the external environment data through a pre-trained machine learning threshold adjustment model. When the prediction result exceeds the warning threshold, a warning signal is generated and transmitted to the remote monitoring center.

6. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 5 is characterized in that: The edge computing device is a Raspberry Pi.

7. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 1 is characterized in that: The terminal node also includes a power management unit; the power management unit includes an electrically connected solar charging circuit and a solar charging battery.

8. The Zigbee-based dangerous rock mass crack monitoring system according to claim 1 is characterized in that: It also includes a high-speed storage device; the high-speed storage device is electrically connected to the remote monitoring system, and the high-speed storage device is used to store all external environment data and crack monitoring data, as well as crack development trend analysis results; The edge computing device also includes a local storage module; the local storage module is used to store historical crack monitoring data and upload the historical crack monitoring data to the remote monitoring center when necessary.

9. The dangerous rock mass crack monitoring system based on Zigbee technology according to claim 1 is characterized in that: The remote monitoring system is also used to access its data through a mobile device or computer and adjust monitoring parameters, including sampling frequency, sensor sensitivity and data transmission interval.

10. A method for monitoring cracks in dangerous rock mass based on Zigbee technology, characterized in that: The following steps are involved: Collect crack data of crack width, depth and change rate at multiple monitoring points in dangerous rock mass in real time; The crack data of multiple monitoring points are wirelessly transmitted through Zigbee wireless communication; wherein the collection frequency of the crack data and the transmission interval of the Zigbee wireless communication are adjusted according to the crack change rate of the monitoring point; The trained machine learning model is used to analyze the dangerous signals in the crack data and generate real-time warning signals. The analysis results and warning signals are then displayed and stored.

Images