Precise positioning method and system for vehicles in coal mines based on UWB technology

Abstract

The present application relates to the field of target positioning technology, specifically to a method and system for accurately positioning vehicles in coal mines based on UWB technology. The method comprises: deploying multiple UWB base stations within a preset area in the coal mine; installing a UWB signal transmitter on a vehicle in the coal mine, transmitting a signal through the vehicle and recording the signal transmission time, receiving the vehicle-transmitted signal through multiple base stations and recording the signal arrival time; calculating TOA data and TDOA data for the multiple base stations based on the vehicle's signal transmission time and the signal arrival time recorded by the multiple base stations; establishing multiple hyperbolas, each reflecting the estimated position of the vehicle; calculating the mean and standard deviation of the TOA data of the multiple base stations, the intersection and center points of the hyperbolas, the coverage area and overlap area of ​​the hyperbolas, and the relative positions of the hyperbolas, and using these as input features; inputting these features into a trained neural network to output the vehicle's position. The present invention is advantageous in improving the speed and accuracy of vehicle positioning in coal mines.

Description

Technical Field

[0001] The present invention relates to the field of target positioning technology, and more specifically, to a method and system for accurately positioning vehicles in coal mines based on UWB technology. Background Art

[0002] With the continuous development of the mining industry, increasing automation and intelligence in underground coal mine operations has become a key approach to improving production efficiency and safety. Precise vehicle positioning systems play a central role in this process, particularly in the complex, cramped, and dimly lit underground environments where accurate tracking and real-time vehicle location is crucial. Ultra-wideband (UWB) technology, with its high resolution, strong penetration, and robustness to multipath effects, is an ideal choice for vehicle positioning in underground coal mines.

[0003] However, existing UWB positioning systems face several challenges in underground coal mine applications. The most widely used solution currently is Time Difference of Arrival (TDOA), which uses the time difference between signals reaching a base station for positioning. However, in the complex environments of underground coal mines, this TDOA-based vehicle positioning method lacks accuracy. Therefore, an innovative technical solution is urgently needed to provide more efficient, accurate, and reliable positioning services for vehicles in underground coal mines, thereby promoting the intelligentization of underground coal mine operations. Summary of the Invention

[0004] In order to solve the above technical problems, the present application is proposed to provide a method and system for precise positioning of vehicles in coal mines based on UWB technology, which can provide more efficient, accurate and reliable positioning services for vehicles in coal mines.

[0005] In a first aspect, the present invention provides a method for precise positioning of vehicles in coal mines based on UWB technology, comprising: deploying multiple UWB base stations in a preset area in the coal mine; installing a UWB signal transmitter on the vehicle in the coal mine, transmitting a signal through the vehicle and recording the signal transmission time, receiving the signal transmitted by the vehicle through the multiple base stations and recording the signal arrival time; calculating the TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by the multiple base stations; establishing multiple hyperbolas based on the TDOA data of the multiple base stations, wherein each hyperbola reflects the estimated position of the vehicle; calculating the mean and standard deviation of the TOA data of the multiple base stations, the intersection point and center point of the multiple hyperbolas, the coverage area and overlapping area of ​​the multiple hyperbolas, and the relative positions of the multiple hyperbolas, and using them as input features; inputting the input features into a trained neural network, and obtaining the position of the vehicle output by the neural network.

[0006] Optionally, the aforementioned method for precise positioning of vehicles in coal mines based on UWB technology, wherein the signal transmitted by the vehicle is received through the multiple base stations and the signal arrival time is recorded, further comprising: taking any one of the multiple base stations as a target base station, obtaining a historical signal b1 received by the target base station at a historical time, a signal b2 obtained by processing the historical signal b1 through a filter at the historical time, a coefficient vector w1 of the filter at the historical time, and an original transmitted signal a corresponding to the historical signal b1; detecting the power spectral density p of the signal received by the target base station at the current time; setting the coefficient vector of the filter at the current time Wherein μ is a preset adjustment coefficient; the filter is used to process the signal received by the target base station at the current time.

[0007] Optionally, the aforementioned method for precise positioning of vehicles in coal mines based on UWB technology, wherein the signals transmitted by the vehicle are received by the multiple base stations and the arrival time of the signals is recorded, further comprising: setting the signal propagation dielectric coefficient ∈ in the coal mine according to the geological structure of the coal mine; obtaining the historical position s1 of the vehicle at the historical time; and calculating the path loss of the signal received by the target base station at the current time. Wherein f is the frequency of the signal received by the target base station at the current time, c is the speed of light, γ is the wavelength of the signal received by the target base station at the current time, s2 is the position of the target base station, k is the preset weight coefficient, and n is the preset path loss index; based on the path loss L of the signal received by the target base station at the current time, the signal received by the target base station at the current time is corrected.

[0008] Optionally, the aforementioned method for precise positioning of vehicles in coal mines based on UWB technology, before calculating the TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by the multiple base stations, also includes: calculating the maximum difference between the multiple signal arrival times recorded by the multiple base stations; when the maximum difference between the multiple signal arrival times is lower than a preset threshold, executing the calculation of the TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by the multiple base stations; when the maximum difference between the multiple signal arrival times exceeds the preset threshold, re-executing the step of receiving the signal transmitted by the vehicle through the multiple base stations and recording the signal arrival time.

[0009] Optionally, the aforementioned method for precise positioning of vehicles underground in coal mines based on UWB technology, before inputting the input features into the trained neural network, further includes: setting the calculation time limit of the neural network according to the time limit for positioning the vehicle; setting the maximum number of neurons in the neural network according to the calculation time limit of the neural network; and each time the neural network is iteratively trained, counting the weight value of each neuron in the neural network after training, and extracting a group of neurons with the lowest weight values ​​from the neural network, until the number of neurons in the neural network does not exceed the maximum number.

[0010] Optionally, the aforementioned method for precise positioning of vehicles in coal mines based on UWB technology, before inputting the input features into the trained neural network, further comprises: after each iterative training of the neural network, calculating the safety constraint loss loss1=max(0, D-dist(s, s s )), where D is the preset safety constraint distance, s is the position of the vehicle predicted during the neural network training, and s s The point closest to s on the boundary of the preset safe working area in the coal mine is used to calculate the distance between the two positions. The loss function of the neural network is calculated as loss = αMSE(s, s0) + (1-α)loss1, where α is a preset weight coefficient and s0 is the actual position of the vehicle during the training of the neural network. The MSE function is used to calculate the mean square error between the two positions. The weight values ​​of one or more neurons in the neural network are adjusted according to the loss function of the neural network.

[0011] Optionally, the aforementioned method for precise positioning of vehicles in coal mines based on UWB technology, wherein the input feature is input into a trained neural network and the position of the vehicle output by the neural network is obtained, further comprising: calculating the sum of errors T1 when positioning in the coal mine using the neural network; calculating the sum of errors T2 when positioning in the coal mine using a preset method other than the neural network; and calculating the position s of the vehicle at the current time by the preset method. a ; Correct the position of the vehicle output by the neural network, and the position of the vehicle after correction Wherein m1 is the number of times the neural network is used for positioning, and m2 is the number of times the preset method is used for positioning.

[0012] In the first aspect, the present invention provides a precise positioning system for vehicles in coal mines based on UWB technology, comprising: multiple UWB base stations deployed in a preset area in the coal mine; a UWB signal transmitter installed on the vehicle in the coal mine, transmitting signals through the vehicle and recording the signal transmission time, receiving the signals transmitted by the vehicle through the multiple base stations and recording the signal arrival time; a data calculation module, calculating the TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by the multiple base stations; a curve establishment module, establishing multiple hyperbolas based on the TDOA data of the multiple base stations, wherein each hyperbola reflects the estimated position of the vehicle; a feature calculation module, calculating the mean and standard deviation of the TOA data of the multiple base stations, the intersection points and center points of the multiple hyperbolas, the coverage areas and overlapping areas of the multiple hyperbolas, and the relative positions of the multiple hyperbolas, and using them as input features; a position calculation module, inputting the input features into a trained neural network, and obtaining the position of the vehicle output by the neural network.

[0013] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0014] The technical solution of the present invention innovates the existing UWB technology, calculates the statistical characteristics of TOA data and the intersection and center point of the hyperbola corresponding to the TODA data as input features, and introduces a neural network to analyze and process the input features, thereby realizing intelligent vehicle position judgment, improving the speed and accuracy of positioning, significantly reducing the errors caused by multipath effects and environmental interference, and ensuring the precise positioning of vehicles in complex underground environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 Flowchart of a method for precise positioning of vehicles in coal mines based on UWB technology according to an embodiment of the present application;

[0017] Figure 2 This is a partial flow chart of a method for precise positioning of vehicles in coal mines based on UWB technology according to an embodiment of the present application;

[0018] Figure 3This is another partial flow chart of the method for precise positioning of vehicles in coal mines based on UWB technology according to an embodiment of the present application;

[0019] Figure 4 This is another partial flow chart of a method for precise positioning of vehicles in coal mines based on UWB technology according to an embodiment of the present application;

[0020] Figure 5 This is another partial flow chart of the method for precise positioning of vehicles in coal mines based on UWB technology according to an embodiment of the present application;

[0021] Figure 6 This is a block diagram of a precise positioning system for underground vehicles in coal mines based on UWB technology according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Some embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] like Figure 1 As shown, the present invention provides a method for accurately positioning vehicles in coal mines based on UWB technology, comprising:

[0024] Step S110: deploy multiple UWB base stations in a preset area underground in a coal mine.

[0025] Step S120: Install a UWB signal transmitter on a vehicle in the coal mine, transmit a signal through the vehicle and record the signal transmission time, receive the signal transmitted by the vehicle through multiple base stations and record the signal arrival time.

[0026] Step S130 , calculating TOA data and TDOA data of multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by multiple base stations.

[0027] In this embodiment, TOA (Time of Arrival) means “time of arrival” and TDOA (Time Difference of Arrival) means “time difference of arrival”.

[0028] Step S140: establishing multiple hyperbolas based on the TDOA data of multiple base stations, wherein each hyperbola reflects the estimated position of the vehicle.

[0029] In this embodiment, by constructing a hyperbola based on TDOA data, multi-dimensional estimation of the vehicle position can be achieved, which is conducive to reducing errors caused by multipath effects and environmental interference, and ensuring the precise positioning of the vehicle in a complex underground environment in subsequent steps.

[0030] Step S150 , calculating the mean and standard deviation of TOA data of multiple base stations, the intersection points and center points of multiple hyperbolas, the coverage areas and overlapping areas of multiple hyperbolas, and the relative positions of multiple hyperbolas, and using them as input features.

[0031] In this embodiment, the intersection and center points of the statistical features of the TOA data and the hyperbola are calculated as input features. The input features can reflect the propagation of the signal in the complex environment of the coal mine, which is conducive to achieving accurate positioning of the vehicle.

[0032] Step S160: Input the input features into the trained neural network, and obtain the position of the vehicle output by the neural network.

[0033] In this embodiment, a neural network is used to perform a comprehensive analysis of the above-mentioned multiple features to achieve intelligent vehicle position judgment, which not only improves the positioning speed, but also can better adapt to complex environments and make fast and accurate positioning decisions in coal mine scenarios.

[0034] According to the technical solution of this embodiment, innovation is made based on the existing UWB technology, and the intersection and center point of the statistical characteristics of the TOA data and the hyperbola corresponding to the TODA data are calculated as input features. At the same time, a neural network is introduced to analyze and process the input features, thereby realizing intelligent vehicle position judgment, improving the speed and accuracy of positioning, significantly reducing the errors caused by multipath effects and environmental interference, and ensuring the accurate positioning of the vehicle in complex underground environments.

[0035] like Figure 2 As shown, the present invention provides a method for accurately positioning vehicles in coal mines based on UWB technology. Compared with the previous embodiment, the method for accurately positioning vehicles in coal mines based on UWB technology in this embodiment further includes:

[0036] In step S210, any base station among the multiple base stations is used as the target base station, and the historical signal b1 received by the target base station at the historical time is obtained, the signal b2 obtained after the historical signal b1 is processed by the filter at the historical time, the coefficient vector w1 of the filter at the historical time, and the original transmitted signal a corresponding to the historical signal b1.

[0037] Step S220: Detect the power spectrum density p of the signal received by the target base station at the current time.

[0038] Step S230, set the coefficient vector of the filter at the current time Where μ is the preset adjustment coefficient.

[0039] In this embodiment, by introducing the power spectral density comparison of the signal and dynamically adjusting the filter coefficients, the filter can be adaptively optimized for the specific noise type and intensity in the current environment, effectively suppressing environmental noise and multipath interference, especially the common equipment and geological echo interference in mines, and improving the purity of the signal.

[0040] Step S240: Use a filter to process the signal received by the target base station at the current time.

[0041] According to the technical solution of this embodiment, the filter coefficients are monitored and adjusted in real time, and environmental changes are responded to in real time according to the current signal conditions to ensure the best match between the filtering effect and the current transmission conditions. There is no need to preset fixed parameters, which enhances the environmental adaptability of the system and the real-time positioning.

[0042] like Figure 3 As shown, the present invention provides a method for accurately positioning vehicles in coal mines based on UWB technology. Compared with the previous embodiment, the method for accurately positioning vehicles in coal mines based on UWB technology in this embodiment further includes:

[0043] Step S310: setting the signal propagation dielectric coefficient ε in the coal mine according to the geological structure of the coal mine.

[0044] In this embodiment, by setting the dielectric constant according to the geological structure underground in the coal mine, the specific influence of the geological medium on signal propagation is taken into account, so that the technical solution of this embodiment can better adapt to the signal attenuation under different geological conditions, such as hard rock, soft soil layer, aquifer, etc., thereby improving the environmental adaptability and robustness of positioning.

[0045] Step S320: Obtain the historical position s1 of the vehicle at the historical time.

[0046] Step S330: Calculate the path loss of the signal received by the target base station at the current time. Where f is the frequency of the signal received by the target base station at the current time, c is the speed of light, γ is the wavelength of the signal received by the target base station at the current time, s2 is the location of the target base station, k is the preset weight coefficient, and n is the preset path loss index.

[0047] In this embodiment, parameters such as signal frequency, speed of light, wavelength, target base station location, historical vehicle location and dielectric constant are comprehensively considered to accurately calculate the path loss, reflecting the propagation characteristics of the signal in the complex environment of coal mines, providing an accurate basis for signal correction, and significantly improving the accuracy of signal processing and positioning accuracy.

[0048] Step S340: Based on the path loss L of the signal received by the target base station at the current time, the signal received by the target base station at the current time is corrected.

[0049] According to the technical solution of this embodiment, by integrating geological environment characteristics, historical location information and signal propagation models, accurate correction of the target base station receiving signal is achieved, effectively addressing the impact of the complex geological environment underground in coal mines on UWB signal propagation, and significantly improving the positioning accuracy, stability and environmental adaptability of the positioning system, providing a better solution for the precise positioning of vehicles underground in coal mines.

[0050] The present invention provides a method for accurately positioning a vehicle in a coal mine based on UWB technology. Compared with the previous embodiment, the method for accurately positioning a vehicle in a coal mine based on UWB technology in this embodiment further includes, before step S130:

[0051] (1) Calculate the maximum difference in the arrival times of multiple signals recorded by multiple base stations.

[0052] (2) When the maximum difference between the arrival times of the multiple signals is lower than a preset threshold, the TOA data and TDOA data of the multiple base stations are calculated based on the signal transmission time of the vehicle and the signal arrival times recorded by the multiple base stations.

[0053] In this embodiment, TOA and TDOA data calculations are performed when signal arrival time differences are small and data quality is high. This ensures that the positioning algorithm is based on high-quality input data, thereby improving positioning accuracy. This conditional processing logic avoids the negative impact of inaccurate data on the positioning algorithm and improves overall positioning performance.

[0054] (3) When the maximum difference between the arrival times of the multiple signals exceeds a preset threshold, the process of receiving the signals transmitted by the vehicle through the multiple base stations is repeated and the arrival times of the signals are recorded.

[0055] In this embodiment, when the difference in signal arrival times exceeds a preset threshold, indicating a significant inconsistency, the system automatically triggers re-reception and recording of signal arrival times. This dynamic adjustment mechanism enables immediate response to complex environmental changes, reduces positioning errors caused by multipath interference or uneven signal propagation, and enhances system robustness.

[0056] like Figure 4 As shown, the present invention provides a method for accurately positioning a vehicle in a coal mine based on UWB technology. Compared with the previous embodiment, the method for accurately positioning a vehicle in a coal mine based on UWB technology in this embodiment further includes, before step S160:

[0057] Step S410: Setting the calculation time limit of the neural network according to the time limit for positioning the vehicle.

[0058] Step S420: setting the maximum number of neurons in the neural network according to the calculation time limit of the neural network.

[0059] In this embodiment, the maximum number of neurons is set according to the calculation time limit of the neural network, and the network scale is dynamically adjusted, so that the network design is more in line with actual application needs, avoiding the overfitting problem caused by an overly large network, while also reducing the computational burden and improving the efficiency of training and prediction.

[0060] Step S430, each time the neural network is iteratively trained, the weight value of each neuron in the trained neural network is counted, and a group of neurons with the lowest weight value is extracted from the neural network until the number of neurons in the neural network does not exceed the maximum number.

[0061] According to the technical solution of this embodiment, at each iteration, neurons with the lowest weights are counted and removed until the network size reaches a preset upper limit. This mechanism effectively removes neurons with less contribution to the model, optimizes the network structure, and improves the model's simplicity and interpretability. This process also indirectly promotes the model's generalization ability by removing redundant parameters that may lead to overfitting, thereby enhancing the prediction accuracy of unseen data.

[0062] The present invention provides a method for accurately positioning a vehicle in a coal mine based on UWB technology. Compared with the previous embodiment, the method for accurately positioning a vehicle in a coal mine based on UWB technology in this embodiment further includes, before step S160:

[0063] (1) After each iterative training of the neural network, the safety constraint loss loss1 = max(0, D-dist(s, s s ), where D is the preset safety constraint distance, s is the vehicle position predicted during neural network training, and s s is the point closest to s on the boundary of the preset safe working area in the coal mine. The dist function is used to calculate the distance between two locations.

[0064] In this embodiment, by introducing safety constraint loss, safety specifications are directly integrated into the neural network training process, fully considering the impact of the predicted vehicle position being far away from the preset safe operating area boundary, and strengthening the neural network's prediction of potential dangers.

[0065] (2) Calculate the loss function of the neural network: loss = αMSE(s, s0) + (1-α)loss1, where α is the preset weight coefficient, s0 is the actual position of the vehicle during neural network training, and the MSE function is used to calculate the mean square error between two positions.

[0066] (3) Adjusting the weight values ​​of one or more neurons in the neural network according to the loss function of the neural network.

[0067] The technical solution of this embodiment combines positioning accuracy loss (mean square error) with safety constraint loss, achieving a balance between positioning accuracy and safety through flexible adjustment of weight parameters. This ensures high-precision positioning while also meeting the stringent safety requirements of underground coal mine operations, improving the practicality of the overall system.

[0068] like Figure 5 As shown, the present invention provides a method for accurately positioning a vehicle in a coal mine based on UWB technology. Compared with the previous embodiment, the method for accurately positioning a vehicle in a coal mine based on UWB technology in this embodiment further includes, in step S160:

[0069] Step S510, calculating the sum T1 of the errors of positioning using the neural network in the coal mine.

[0070] Step S520 , calculating the sum T2 of positioning errors in the coal mine using a preset method other than the neural network.

[0071] Step S530, calculate the vehicle's current position s by a preset method a .

[0072] Step S540: Correct the position of the vehicle output by the neural network. The corrected position of the vehicle Where m1 is the number of times the neural network is used for positioning, and m2 is the number of times the preset method is used for positioning.

[0073] The technical solution of this embodiment achieves the fusion of positioning results generated by the two methods. This formula dynamically adjusts the weights of the two positioning results based on their errors and usage counts, achieving a complementary advantage. This leverages the intelligent learning capabilities of the neural network while maintaining the reliability of the pre-set method. Specifically, when neural network positioning is unstable or exhibits significant errors, this method automatically increases the weight of the pre-set method, improving overall positioning stability. Conversely, when the pre-set method is inaccurate, the neural network positioning takes the lead, ensuring positioning reliability.

[0074] like Figure 6 As shown, in one embodiment of the present invention, a precise positioning system for underground vehicles in a coal mine based on UWB technology is provided, comprising:

[0075] Multiple UWB base stations 610 are deployed in a preset area underground in the coal mine.

[0076] The UWB signal transmitter 620 is installed on a vehicle in a coal mine. The vehicle transmits a signal and records the signal transmission time. The vehicle transmits a signal through multiple base stations and records the signal arrival time.

[0077] The data calculation module 630 calculates TOA data and TDOA data of multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by multiple base stations.

[0078] The curve establishment module 640 establishes multiple hyperbolas based on the TDOA data of multiple base stations, wherein each hyperbola reflects the estimated position of the vehicle.

[0079] In this embodiment, by constructing a hyperbola based on TDOA data, multi-dimensional estimation of the vehicle position can be achieved, which is conducive to reducing errors caused by multipath effects and environmental interference, and ensuring the precise positioning of the vehicle in a complex underground environment in subsequent steps.

[0080] The feature calculation module 650 calculates the mean and standard deviation of TOA data of multiple base stations, the intersection points and center points of multiple hyperbolas, the coverage areas and overlapping areas of multiple hyperbolas, and the relative positions of multiple hyperbolas, and uses them as input features.

[0081] In this embodiment, the intersection and center points of the statistical features of the TOA data and the hyperbola are calculated as input features. The input features can reflect the propagation of the signal in the complex environment of the coal mine, which is conducive to achieving accurate positioning of the vehicle.

[0082] The position calculation module 660 inputs the input features into the trained neural network and obtains the vehicle position output by the neural network.

[0083] In this embodiment, a neural network is used to perform a comprehensive analysis of the above-mentioned multiple features to achieve intelligent vehicle position judgment, which not only improves the positioning speed, but also can better adapt to complex environments and make fast and accurate positioning decisions in coal mine scenarios.

[0084] According to the technical solution of this embodiment, innovation is made based on the existing UWB technology, and the intersection and center point of the statistical characteristics of the TOA data and the hyperbola corresponding to the TODA data are calculated as input features. At the same time, a neural network is introduced to analyze and process the input features, thereby realizing intelligent vehicle position judgment, improving the speed and accuracy of positioning, significantly reducing the errors caused by multipath effects and environmental interference, and ensuring the accurate positioning of the vehicle in complex underground environments.

[0085] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0086] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0087] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0088] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0089] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for precise positioning of vehicles in coal mines based on UWB technology, characterized in that: include: Deploy multiple UWB base stations in a pre-set area underground in the coal mine; Installing a UWB signal transmitter on a vehicle in the coal mine, transmitting a signal through the vehicle and recording a signal transmission time, receiving the signal transmitted by the vehicle through the multiple base stations and recording a signal arrival time; Calculating TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival times recorded by the multiple base stations; establishing a plurality of hyperbolas based on TDOA data from a plurality of base stations, wherein each hyperbola reflects an estimated position of the vehicle; Calculating the mean and standard deviation of the TOA data of the multiple base stations, the intersection point and center point of the multiple hyperbolas, the coverage areas and overlapping areas of the multiple hyperbolas, and the relative positions of the multiple hyperbolas as input features; Inputting the input features into a trained neural network, and obtaining the position of the vehicle output by the neural network; The step of receiving the signals transmitted by the vehicle through the plurality of base stations and recording the arrival times of the signals includes: Take any base station among the multiple base stations as the target base station, and obtain the historical signal received by the target base station at the historical time. , the historical signal is filtered at the historical time The processed signal , the coefficient vector of the filter at the historical time , and the historical signal The corresponding original transmission signal ; Detect the power spectrum density of the signal received by the target base station at the current time ; Set the coefficient vector of the filter at the current time ,in, is the preset adjustment coefficient; The filter is used to process a signal received by the target base station at the current time.

2. The method for precise positioning of vehicles in coal mines based on UWB technology according to claim 1, characterized in that: Before receiving the signals transmitted by the vehicle through the multiple base stations and recording the arrival time of the signals, the method further includes: According to the geological structure of the coal mine, the signal propagation dielectric coefficient of the coal mine is set. ; Get the historical position of the vehicle at the historical time ; Calculate the path loss of the signal received by the target base station at the current time ,in, is the frequency of the signal received by the target base station at the current time, is the speed of light, the wavelength of the signal received by the target base station at the current time, is the location of the target base station, is the preset weight coefficient, is the preset path loss index; Based on the path loss of the signal received by the target base station at the current time , correcting the signal received by the target base station at the current time.

3. The method for precise positioning of vehicles in coal mines based on UWB technology according to claim 1, characterized in that: Before inputting the input features into the trained neural network, the method for precise positioning of vehicles in coal mines based on UWB technology further includes: Setting a calculation time limit for the neural network according to a time limit for positioning the vehicle; Setting a maximum number of neurons in the neural network according to a computation time limit of the neural network; Each time the neural network is iteratively trained, the weight value of each neuron in the neural network after training is counted, and a group of neurons with the lowest weight values ​​are extracted from the neural network until the number of neurons in the neural network does not exceed the maximum number.

4. The method for precise positioning of vehicles in coal mines based on UWB technology according to claim 1, characterized in that: Before inputting the input features into the trained neural network, the method for precise positioning of vehicles in coal mines based on UWB technology further includes: After each iterative training of the neural network, the safety constraint loss of the training result is calculated. , where D is the preset safety constraint distance, is the position of the vehicle predicted during the training of the neural network, The boundary of the preset safe operation area of ​​the coal mine The nearest point, The function is used to calculate the distance between two locations; Calculate the loss function of the neural network ,in, is the preset weight coefficient, is the actual position of the vehicle during the training of the neural network, The function is used to calculate the mean square error between two positions; The weight values ​​of one or more neurons in the neural network are adjusted according to the loss function of the neural network.

5. The method for precise positioning of vehicles in underground coal mines based on UWB technology according to claim 4, characterized in that: Inputting the input features into a trained neural network and obtaining the position of the vehicle output by the neural network includes: Calculate the sum of the errors of positioning using the neural network in the coal mine ; Calculate the sum of the errors of positioning in the coal mine using a preset method other than the neural network ; Calculate the vehicle's current position using the preset method ; The position of the vehicle output by the neural network is corrected, and the position of the vehicle after correction is corrected. ,in, is the number of times the neural network is used for positioning, The number of times positioning is performed using the preset method.

6. A precise positioning system for underground vehicles in coal mines based on UWB technology, characterized in that: include: Multiple UWB base stations are deployed in a preset area underground in the coal mine; A UWB signal transmitter is installed on a vehicle in the coal mine, transmits a signal through the vehicle and records the signal transmission time, receives the signal transmitted by the vehicle through the multiple base stations and records the signal arrival time; a data calculation module, calculating TOA data and TDOA data of the multiple base stations based on the signal transmission time of the vehicle and the signal arrival time recorded by the multiple base stations; a curve establishing module, which establishes a plurality of hyperbolas based on the TDOA data of a plurality of base stations, wherein each hyperbola reflects the estimated position of the vehicle; a feature calculation module that calculates the mean and standard deviation of the TOA data of the multiple base stations, the intersection point and center point of the multiple hyperbolas, the coverage area and overlapping area of ​​the multiple hyperbolas, and the relative positions of the multiple hyperbolas, and uses them as input features; a position calculation module, inputting the input features into a trained neural network and obtaining the position of the vehicle output by the neural network; Receiving the signals transmitted by the vehicle through the multiple base stations and recording the arrival time of the signals includes: Take any base station among the multiple base stations as the target base station, and obtain the historical signal received by the target base station at the historical time. , the historical signal is filtered at the historical time The processed signal , the coefficient vector of the filter at the historical time , and the historical signal The corresponding original transmission signal ; Detect the power spectrum density of the signal received by the target base station at the current time ; Set the coefficient vector of the filter at the current time ,in, is the preset adjustment coefficient; The filter is used to process a signal received by the target base station at the current time.

Images