Mining personnel wireless positioning system based on Internet of Things

Abstract

The invention discloses a mining personnel wireless positioning system based on the Internet of Things, which comprises a positioning label, a positioning base station, a ground upper computer and a user terminal, and is characterized in that the positioning label comprises a sensor module and a wireless communication module, and the movement and position information of miners is monitored in real time by using an accelerometer, a gyroscope, a magnetometer and other sensors; signal intensity and environment data collected by the RSSI sensor and the environment monitoring sensor are combined and sent to the positioning base station through the wireless communication module, and the positioning base station receives data from the positioning label and remotely transmits the data to the ground upper computer; the ground upper computer carries out a series of operations such as preprocessing, fusion, feature extraction, initial position estimation, accurate position calculation, real-time calibration and smooth processing on the collected data, and the positioning precision and the robustness of the system are improved by utilizing technologies such as a machine learning algorithm and a weighted centroid algorithm.

Description

Technical Field

[0001] The present invention relates to the field of wireless positioning technology, and in particular to a wireless positioning system for mining personnel based on the Internet of Things. Background Art

[0002] The mining environment is complex and changeable, with rugged terrain, and is often accompanied by problems such as narrow underground space, insufficient light, and high dust concentration. These environmental factors not only increase the difficulty of operation, but also pose severe challenges to personnel safety management.

[0003] With the rapid development of Internet of Things technology, wireless positioning technology has gradually become a research hotspot in the field of mine safety management. Wireless positioning technology achieves real-time positioning of target objects through wireless signal transmission and reception. However, existing wireless positioning technology still faces many challenges in the mining environment.

[0004] First, the propagation characteristics of electromagnetic waves in the mining environment are complex, and there are problems such as multipath effect, attenuation, and reflection. These factors will affect the transmission quality of wireless signals and thus affect the positioning accuracy. Secondly, the internal spatial structure of the mine is complex, and the deployment of positioning base stations and tags is difficult, and it is necessary to comprehensively consider factors such as cost, coverage, and positioning accuracy. In addition, the mobility of mining workers is relatively high, and how to achieve dynamic and real-time positioning of personnel is also a major problem.

[0005] In view of the above situation, the present invention aims to provide a new solution to solve this problem. Summary of the invention

[0006] In view of the above situation, in order to overcome the defects of the prior art, the purpose of the present invention is to provide a wireless positioning system for mining personnel based on the Internet of Things.

[0007] The technical solution is: a wireless positioning system for mining personnel based on the Internet of Things, including a positioning tag, a positioning base station, a ground host computer and a user terminal. The positioning tag includes:

[0008] The sensor module uses multiple sensors to sense and collect the miners’ location information and environmental data in real time; and

[0009] A wireless communication module, used to send the data collected by the sensor module to the positioning base station;

[0010] The positioning base station receives the data from the positioning tag and remotely transmits it to the ground host computer;

[0011] The ground host computer performs the following operations on the received data:

[0012] S1, preprocessing the received data;

[0013] S2, fuse the preprocessed data and extract key features using machine learning algorithms;

[0014] S3. Calculate the distance of the positioning tag according to the RSSI value and the shadowing model, and perform an initial position estimation;

[0015] S4, using a weighted centroid algorithm to calculate the precise location of the mining personnel;

[0016] S5. Using a machine learning model to calibrate the position and distance information of the positioning tag in real time, and updating the model parameters according to the calibration results;

[0017] S6. Smooth the positioning result and output the positioning result.

[0018] Preferably, the sensor module includes an accelerometer, a gyroscope, a magnetometer, an RSSI sensor and an environmental monitoring sensor.

[0019] Preferably, the preprocessing operation in step S1 includes cleaning and normalization processing, and the formula for the normalization processing is:

[0020]

[0021] Among them, x′ is the normalized value, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

[0022] Preferably, the specific operation steps of step S2 are as follows:

[0023] Fusing the data of the accelerometer, gyroscope, and magnetometer to form a motion state vector;

[0024] The signal strength measured by the RSSI sensor is fused with the data of the environmental monitoring sensor to form an environmental state vector;

[0025] The PCA algorithm is used to extract key features from the fused data.

[0026] Preferably, the specific operation steps of step S3 are as follows:

[0027] The RSSI sensor is used to measure the signal strength between the positioning tag and the three nearest positioning base stations, and the shadowing model is used to convert the RSSI value into distance information;

[0028] An initial position estimation is performed using trilateration based on the distance information.

[0029] Preferably, the weighted centroid algorithm is:

[0030]

[0031] Among them, (x i ,y i , z i ) is the coordinate of anchor node i, ω i is the weight of anchor node i, and n is the number of anchor nodes.

[0032] Preferably, in step S5, a pre-trained SVM model is used to perform real-time calibration and prediction on the new positioning data.

[0033] Preferably, the step S6 uses a Kalman filter to smooth the positioning result to reduce noise and fluctuation.

[0034] Preferably, the wireless communication module uses a W5110 NB-IoT module.

[0035] Through the above technical scheme, the beneficial effects of the present invention are as follows: the wireless positioning system for mining personnel based on the Internet of Things in this application uses sensors such as accelerometers, gyroscopes, and magnetometers to monitor the movement and position information of miners in real time, and combines the signal strength and environmental data collected by RSSI sensors and environmental monitoring sensors, and sends them to the positioning base station through the wireless communication module, thereby realizing the real-time dynamic positioning of miners. The ground host computer performs a series of operations such as preprocessing, fusion, feature extraction, initial position estimation, precise position calculation, real-time calibration and smoothing on the collected data, and uses machine learning algorithms and weighted centroid algorithms and other technologies to improve the positioning accuracy and system robustness. In particular, by applying the SVM model and Kalman filter, the system can dynamically adjust the positioning parameters, adapt to changes in the mine environment, reduce positioning errors, and ensure long-term stable operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a structural block diagram of a wireless positioning system for mining personnel based on the Internet of Things provided by one embodiment of the present invention.

[0037] Figure 2 A schematic diagram of the operation flow of a ground host computer provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0038] The above and other technical contents, features and effects of the present invention are described in detail below with reference to the attached Figure 1 To Attachment Figure 2 The detailed description of the embodiments will clearly show that the structural contents mentioned in the following embodiments are all based on the drawings in the specification.

[0039] Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings.

[0040] like Figure 1As shown, the wireless positioning system for mining personnel based on the Internet of Things includes a positioning tag 10, a positioning base station 20, a ground host computer 30 and a user terminal 40. Among them, the positioning tag 10 includes:

[0041] The sensor module uses multiple sensors to sense and collect the miners’ location information and environmental data in real time; and

[0042] The wireless communication module is used to send the data collected by the sensor module to the positioning base station.

[0043] In a specific embodiment, the sensor module includes an accelerometer, a gyroscope, a magnetometer, an RSSI sensor, and an environmental monitoring sensor. First, the accelerometer, gyroscope, magnetometer and other sensors in the sensor module monitor and collect the movement and position information of the miners in real time, while the RSSI sensor and the environmental monitoring sensor collect signal strength and environmental data. These raw data are sent to the positioning base station through the wireless communication module. In this process, the positioning tag is equivalent to a data collection and transmission node, which continuously transmits the real-time data collected by the sensor to the positioning base station wirelessly for subsequent position calculation and data analysis.

[0044] The wireless communication module uses the W5110 NB-IoT module because it has low-power wide area network (LPWAN) technology and is suitable for long-distance communication in complex environments such as mines. The module supports multiple network protocols and can ensure the stability and reliability of data transmission. In addition, the W5110 module also has good anti-interference performance and can adapt to possible electromagnetic interference in mines to ensure the normal operation of the positioning system.

[0045] When the positioning tag sends a signal containing the miner's location information and environmental data through the wireless communication module, the positioning base station, as the receiving end, captures these signals and converts them into digital data. The base station performs preliminary processing on these data, such as demodulation, decoding and possible signal enhancement, to ensure the integrity and accuracy of the data. Subsequently, the base station transmits the processed data to the ground host computer through a remote communication link.

[0046] After receiving the data, the ground host computer will conduct further analysis and processing, such as Figure 2 As shown, the specific operations include the following:

[0047] S1, preprocessing the received data;

[0048] S2, fuse the preprocessed data and extract key features using machine learning algorithms;

[0049] S3, calculate the distance of the positioning tag according to the RSSI value and the shadowing model, and perform initial position estimation;

[0050] S4, using a weighted centroid algorithm to calculate the precise location of the mining personnel;

[0051] S5. Use the machine learning model to calibrate the position and distance information of the positioning tag in real time, and update the model parameters according to the calibration results;

[0052] S6. Smooth the positioning result and output the positioning result.

[0053] In a specific embodiment, the preprocessing operation in step S1 includes cleaning and normalization processing. Data cleaning is to remove noise, outliers and duplicates in the data to ensure the accuracy and reliability of subsequent analysis. Normalization processing is to scale the data according to certain rules so that data of different dimensions can be compared and calculated on the same scale, thereby improving the efficiency and accuracy of the algorithm. Among them, the formula for normalization processing is:

[0054]

[0055] Among them, x′ is the normalized value, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

[0056] In combination with the above embodiment, the specific operation steps of step S2 are as follows:

[0057] The data from the accelerometer, gyroscope, and magnetometer are integrated to form a motion state vector, which can more accurately describe the miner's motion state, including speed, acceleration, and direction;

[0058] The signal strength measured by the RSSI sensor is fused with the data from the environmental monitoring sensor to form an environmental state vector, which provides detailed information about the internal environment of the mine.

[0059] After completing the construction of these two vectors, the ground host computer uses the principal component analysis (PCA) algorithm to extract features from the fused data. The PCA algorithm is a commonly used data dimensionality reduction technology that projects high-dimensional data into a low-dimensional space by calculating the principal components of the data while retaining as much important information as possible in the original data. In this step, the PCA algorithm is used to extract key features that have an important impact on the positioning results from the fused motion state vector and environment state vector, providing key feature input for subsequent position estimation and machine learning models.

[0060] In combination with the above embodiment, the specific operation steps of step S3 are as follows:

[0061] The RSSI sensor measures the signal strength between the positioning tag and the three nearest positioning base stations around it. The RSSI value reflects the attenuation of the signal during propagation. The ground host computer converts these RSSI values ​​into distance information by applying the shadowing model, which takes into account the attenuation of the signal due to multipath effects and occlusion in the mine environment.

[0062] After obtaining the distance information, the ground host computer uses trilateration to estimate the initial position. Trilateration is a distance-based positioning technology that measures the distance from the positioning tag to three base stations and uses this distance information to estimate the initial position of the positioning tag. Specifically, let the coordinates of the three base stations be (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3), and the measured distances are d1, d2, and d3 respectively. Then the position of the mining personnel (x, y, z) satisfies the equation group:

[0063]

[0064] Solve this system of equations to get the initial position.

[0065] In step S4, the ground host computer uses a weighted centroid algorithm to calculate the precise location of the mining personnel. Specifically, the algorithm takes into account the distance information between the positioning tag and multiple positioning base stations (anchor nodes), whose coordinates are known. Each base station is assigned a weight based on its signal strength or other factors, which reflects the importance or reliability of each base station in the positioning process. The weighted centroid algorithm is:

[0066]

[0067] Among them, (x i ,y i , z i ) is the coordinate of anchor node i, ω i is the weight of anchor node i, and n is the number of anchor nodes.

[0068] Through the above processing, the weighted centroid algorithm outputs a coordinate point that integrates the information of all anchor nodes. This coordinate point represents the precise position of the positioning tag. This method can reduce the impact of single base station errors and improve the accuracy and robustness of positioning.

[0069] In step S5, the ground host computer uses a pre-trained support vector machine (SVM) model to calibrate and predict the new positioning data in real time, thereby optimizing the positioning accuracy. By learning historical positioning data, the SVM model can identify complex patterns and features in the mine environment and make accurate predictions for new data. In practical applications, the SVM model can dynamically adjust positioning parameters according to the movement speed and direction of miners and specific environmental factors in the mine to adapt to changing working conditions. In addition, the model can also correct positioning deviations caused by factors such as equipment aging and environmental changes through real-time calibration, ensuring the long-term stable operation of the positioning system.

[0070] Step S6 uses a Kalman filter to smooth the positioning results to reduce noise and fluctuations. The Kalman filter is an effective recursive filter that estimates the state of a dynamic system through two steps: prediction and update. In the mine personnel wireless positioning system, the Kalman filter first predicts the next state of the positioning tag based on the dynamic model of the system, and then uses the new measurement data to update this prediction. This process is continuously iterated to provide smooth and accurate positioning results in the presence of noise. In this way, the Kalman filter can effectively reduce random errors and system noise, and improve the continuity and reliability of positioning data. Ultimately, the positioning data processed by the Kalman filter can provide more accurate and stable information for mine safety monitoring and personnel management.

[0071] In summary, the wireless positioning system for mining personnel based on the Internet of Things provided by this application can effectively overcome the challenges of complex electromagnetic wave propagation characteristics, complex spatial structure, and high personnel mobility in the mining environment by integrating sensor modules and wireless communication technology. The system uses sensors such as accelerometers, gyroscopes, and magnetometers to monitor the movement and position information of miners in real time, and combines the signal strength and environmental data collected by RSSI sensors and environmental monitoring sensors, and sends them to the positioning base station through wireless communication modules, thereby realizing real-time dynamic positioning of miners.

[0072] The ground host computer performs a series of operations such as preprocessing, fusion, feature extraction, initial position estimation, precise position calculation, real-time calibration and smoothing on the collected data, and uses machine learning algorithms and weighted centroid algorithms to improve positioning accuracy and system robustness. In particular, by applying the SVM model and Kalman filter, the system can dynamically adjust positioning parameters, adapt to changes in the mine environment, reduce positioning errors, and ensure long-term stable operation.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0076] The above is a further detailed description of the present invention in combination with a specific implementation method, and it cannot be determined that the specific implementation of the present invention is limited to this; for technical personnel in the technical fields to which the present invention belongs and related technical fields, based on the technical solution of the present invention, the expansion and replacement of operating methods and data should all fall within the protection scope of the present invention.

Claims

1. A wireless positioning system for mining personnel based on the Internet of Things, including a positioning tag, a positioning base station, a ground host computer and a user terminal, characterized in that: The positioning tag includes: The sensor module uses multiple sensors to sense and collect the miners’ location information and environmental data in real time; and A wireless communication module, used to send the data collected by the sensor module to the positioning base station; The positioning base station receives the data from the positioning tag and remotely transmits it to the ground host computer; The ground host computer performs the following operations on the received data: S1, preprocessing the received data; S2, fuse the preprocessed data and extract key features using machine learning algorithms; S3. Calculate the distance of the positioning tag according to the RSSI value and the shadowing model, and perform an initial position estimation; S4, using a weighted centroid algorithm to calculate the precise location of the mining personnel; S5. Using a machine learning model to calibrate the position and distance information of the positioning tag in real time, and updating the model parameters according to the calibration results; S6. Smooth the positioning result and output the positioning result.

2. According to the wireless positioning system for mining personnel based on the Internet of Things according to claim 1, it is characterized in that: The sensor module includes an accelerometer, a gyroscope, a magnetometer, an RSSI sensor and an environmental monitoring sensor.

3. According to the wireless positioning system for mining personnel based on the Internet of Things as claimed in claim 2, it is characterized in that: The pre-processing operation in step S1 includes cleaning and normalization processing, and the formula for the normalization processing is: Among them, x′ is the normalized value, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

4. According to claim 3, the wireless positioning system for mining personnel based on the Internet of Things is characterized by: The specific operation steps of step S2 are as follows: Fusing the data of the accelerometer, gyroscope, and magnetometer to form a motion state vector; The signal strength measured by the RSSI sensor is fused with the data of the environmental monitoring sensor to form an environmental state vector; The PCA algorithm is used to extract key features from the fused data.

5. The wireless positioning system for mining personnel based on the Internet of Things according to claim 4 is characterized in that: The specific operation steps of step S3 are as follows: The RSSI sensor is used to measure the signal strength between the positioning tag and the three nearest positioning base stations, and the shadowing model is used to convert the RSSI value into distance information; An initial position estimation is performed using trilateration based on the distance information.

6. The wireless positioning system for mining personnel based on the Internet of Things according to claim 5 is characterized in that: The weighted centroid algorithm is: Among them, (x i ,y i , z i ) is the coordinate of anchor node i, ω i is the weight of anchor node i, and n is the number of anchor nodes.

7. The wireless positioning system for mining personnel based on the Internet of Things according to claim 6 is characterized in that: In step S5, the pre-trained SVM model is used to perform real-time calibration and prediction on the new positioning data.

8. The wireless positioning system for mining personnel based on the Internet of Things according to claim 7 is characterized in that: The step S6 uses a Kalman filter to smooth the positioning result to reduce noise and fluctuation.

9. The wireless positioning system for mining personnel based on the Internet of Things according to claim 1 is characterized in that: The wireless communication module uses the W5110 NB-IoT module.

Images