Dynamic navigation positioning method and system for intelligent fully-mechanized coal mining of coal mine

Abstract

The invention provides a dynamic navigation and positioning method and system for intelligent fully-mechanized coal mining of a coal mine, and relates to the technical field of coal mining machine navigation and positioning. The method comprises the following steps: calculating a root mean square value of a three-axis vibration acceleration signal of a target coal mining machine; when the root-mean-square value is greater than or equal to a preset threshold value, the modulation frequency of the rotary modulation platform is improved, and meanwhile, the modulation angle range is reduced to a preset angle range for reciprocating motion; otherwise, the modulation frequency of the rotary modulation platform is reduced, the modulation angle range is recovered to 360 degrees, and periodic rotary motion is performed; correcting and compensating the output data of the gyroscope to obtain attitude data; and carrying out weighted fusion on the attitude data and the odometer data to obtain a navigation positioning result. By implementing the method, the motion parameters of the rotary modulation platform can be dynamically adjusted, the modulation frequency can be improved and the angle range can be narrowed during strong vibration, the frequency can be reduced for full-angle compensation during weak vibration, and the problem of poor compensation real-time performance of traditional fixed-frequency full-angle modulation under the working condition of strong vibration can be effectively solved.

Description

Technical Field

[0001] This application relates to the technical field of shearer navigation and positioning, and particularly to a dynamic navigation and positioning method and system for intelligent fully-mechanized coal mining in coal mines. Background Art

[0002] With the rapid development of intelligent coal mining technology, the automation and intelligence levels of coal mining faces are continuously improving. In the process of fully-mechanized coal mining, the accurate navigation and positioning of shearers is one of the key technologies for realizing intelligent mining. Especially in the mining of thin coal seams, higher requirements are placed on the navigation and positioning accuracy of shearers, which is directly related to coal mining efficiency and resource recovery rate. To meet the needs of intelligent mining, the shearer navigation and positioning system needs to provide continuous and reliable position and attitude information in a complex underground environment.

[0003] In related technologies, shearer navigation and positioning mainly adopts a combined navigation scheme based on an inertial navigation system with a gyroscope combined with an odometer. To improve the measurement accuracy of the gyroscope, a common practice is to set a rotation modulation platform on the gyroscope installation base, and compensate for the drift error of the gyroscope through a 360-degree periodic rotation at a fixed frequency. When this scheme is working, the rotation modulation platform rotates continuously at a preset fixed frequency, and the system calculates the error compensation value by collecting the output data of the gyroscope within a complete cycle, so as to obtain the corrected attitude data.

[0004] However, strong vibrations will be generated during the cutting process of the shearer, and the vibration intensity will change significantly with the change of the working state. Under strong vibration conditions, there is a problem of too long compensation period in the 360-degree periodic rotation modulation method at a fixed frequency. Since vibration will cause the error characteristics of the gyroscope to change rapidly, and it takes a long time to complete a 360-degree rotation, the error compensation value calculated based on the complete cycle data is difficult to reflect the current error state in a timely manner, reducing the compensation effect. Summary of the Invention

[0005] This application provides a dynamic navigation and positioning method and system for intelligent fully-mechanized coal mining in coal mines, which is used to solve the problem of how to improve the real-time performance of gyroscope error compensation under the condition that the vibration intensity of the shearer changes dynamically.

[0006] In the first aspect, this application provides a dynamic navigation and positioning method for intelligent fully-mechanized coal mining in coal mines, which is applied to a navigation and positioning system. The method includes: Real-time collect the three-axis vibration acceleration signals of the target shearer, and calculate the root mean square value of the three-axis acceleration; When the root mean square value is greater than or equal to a preset threshold, increase the modulation frequency of the rotation modulation platform according to a preset frequency mapping relationship, and at the same time reduce the modulation angle range to a preset angle range to make a reciprocating motion; When the root mean square value is less than the preset threshold, reduce the modulation frequency of the rotary modulation platform according to the preset frequency mapping relationship and restore the modulation angle range to 360° to perform periodic rotational motion; During the process of the rotary modulation platform moving at the modulation frequency, collect the output data of the gyroscope at different modulation angles; Adopt a sliding window algorithm to perform real-time processing on the output data, and calculate correction parameters according to the preset dynamic error compensation model to obtain the corrected attitude data of the target shearer; Substitute the variance eigenvalues of the attitude data and the odometer data into the preset weight calculation formula respectively to obtain the weight coefficients corresponding to the attitude data and the odometer data respectively; Perform weighted fusion on the attitude data and the odometer data according to the weight coefficients to obtain the navigation and positioning result of the target shearer.

[0007] Through the above embodiments, the navigation and positioning system dynamically adjusts the motion parameters of the rotary modulation platform by real-time monitoring the vibration state of the shearer, increases the modulation frequency and reduces the angle range during strong vibration, and reduces the frequency for full-angle compensation during weak vibration. This adaptive modulation strategy can maintain a good error compensation effect under different vibration conditions. At the same time, the sliding window algorithm is used to process data in real time, combined with the dynamic error compensation model, which can track the error change in a timely manner. By adaptively fusing the attitude and odometer data with weights, the reliability and accuracy of navigation and positioning are improved, thus effectively addressing the problem of poor real-time compensation of traditional fixed-frequency full-angle modulation under strong vibration conditions.

[0008] In some embodiments, before the step of collecting the three-axis vibration acceleration signals of the target shearer in real time and calculating the root mean square value of the three-axis acceleration, it further includes: Collect the cutting motor current, traction speed and coal seam hardness data of the target shearer, and establish a working condition feature vector; Train a vibration prediction model based on a deep learning algorithm, and input the working condition feature vector into the vibration prediction model to obtain the predicted values of the three-axis vibration acceleration signals within a future time window; Determine the pre-adjusted frequency and pre-adjusted angle according to the comparison result between the predicted value and the preset threshold; Send the pre-adjusted frequency and the pre-adjusted angle to the drive controller of the rotary modulation platform in advance for caching, and adjust the motor drive parameters at the corresponding time points within the future time window.

[0009] Through the above embodiments, the navigation and positioning system collects the working condition data of the shearer and establishes a feature vector, and uses a deep learning algorithm to predict the vibration condition within a future time window, realizing the advance presetting and caching of modulation parameters. This avoids the compensation lag caused by sudden vibration changes in the traditional scheme, enabling the system to adjust the operating parameters in advance to cope with the upcoming working condition changes. At the same time, the pre-cached modulation parameters also provide a more sufficient response time for the motor drive control, improving the dynamic adaptability of the system.

[0010] In some embodiments, after the step of collecting the three-axis vibration acceleration signals of the target shearer in real time and calculating the root mean square value of the three-axis accelerations, the method further includes: Determining whether the difference between the current three-axis vibration acceleration signal and the corresponding predicted value is less than a preset amplitude threshold; If so, continuing to adjust the motor drive parameters according to the pre-adjusted frequency and pre-adjusted angle; If not, determining the modulation frequency and modulation angle according to the comparison result between the root mean square value and the preset amplitude threshold.

[0011] Through the above embodiments, the navigation and positioning system establishes a prediction correction mechanism by comparing the difference between the actual vibration and the predicted vibration. When the prediction is accurate, the modulation parameters calculated in real time are adopted, and when the prediction deviation is large, the preset parameters are continued to be used. This dual-mode switching strategy not only ensures the system's fast response ability to working condition changes but also avoids frequent parameter fluctuations caused by prediction deviations. This solution improves the stability and reliability of modulation control.

[0012] In some embodiments, the step of increasing the modulation frequency of the rotary modulation platform according to a preset frequency mapping relationship specifically includes: Performing a fast Fourier transform on the vibration acceleration signal to obtain the main frequency value with the largest energy proportion and the corresponding amplitude coefficient in the vibration spectrum; Establishing a modulation frequency gradual change interval according to the main frequency value and the corresponding amplitude coefficient; Adjusting the operating frequency of the rotary modulation platform within the modulation frequency gradual change interval according to a preset step size.

[0013] Through the above embodiments, the navigation and positioning system analyzes the frequency domain characteristics of the vibration signal by using a fast Fourier transform, dynamically establishes a gradual change interval of the modulation frequency according to the main frequency component, and gradually adjusts the operating frequency according to a preset step size. This progressive frequency modulation scheme based on the vibration spectrum characteristics avoids sudden changes in the modulation frequency, making the gyroscope measurement process more stable. At the same time, associating the modulation frequency with the main vibration frequency improves the pertinence and effectiveness of error compensation.

[0014] In some embodiments, the step of reducing the modulation angle range to a preset angle range and making reciprocating motion specifically includes: Obtain the gyroscope output data and corresponding correction parameters at different modulation angles within a preset number of past sampling periods; According to the gyroscope output data and corresponding correction parameters, calculate the correction contribution degree of each modulation angle within 360° to the navigation error, and determine the preset angle range with the best navigation error correction effect; Control the rotation modulation platform to make reciprocating motion within the preset angle range.

[0015] Through the above embodiments, the navigation and positioning system dynamically selects the optimal angle range for reciprocating motion by analyzing the correction effects of different modulation angles on the navigation error in historical data. This adaptive angle selection strategy avoids wasting time in the angle range with poor effects and improves the compensation efficiency. At the same time, the reciprocating motion mode has a faster response speed compared to the traditional 360-degree rotation and can track error changes more timely.

[0016] In some embodiments, the step of respectively substituting the variance eigenvalues of the attitude data and the odometer data into a preset weight calculation formula to obtain the weight coefficients corresponding to the attitude data and the odometer data specifically includes: Calculate the jitter coefficient of the gyroscope output data based on the root mean square value, and determine the continuity score of the attitude data according to the jitter coefficient; Calculate the speed difference between adjacent sampling points of the odometer data, and determine the smoothness score according to the speed difference; Input the continuity score and the smoothness score into a preset fuzzy inference engine to calculate the weight coefficients corresponding to the attitude data and the odometer data respectively.

[0017] Through the above embodiments, the navigation and positioning system establishes a gyroscope data quality evaluation mechanism based on vibration intensity, combines the smoothness score of the odometer data, and determines the weight coefficients of different data sources through fuzzy inference. This multi-dimensional data quality evaluation method enables the system to adaptively adjust the credibility of each sensor data under different working conditions and improves the accuracy and reliability of the integrated navigation solution results.

[0018] In some embodiments, after the step of performing weighted fusion on the attitude data and the odometer data according to the weight coefficients to obtain the navigation and positioning result of the target shearer, it further includes: Obtain the current characteristic parameters, where the characteristic parameters include the root mean square value, modulation frequency, and modulation angle; Calculate the trajectory curvature value and the speed change rate based on the navigation and positioning result, and generate the trajectory abnormality degree; When the trajectory abnormality degree exceeds the preset abnormality threshold, store the mapping relationship between the characteristic parameters and the current weight coefficient into the optimization sample set for updating the fuzzy inference engine.

[0019] Through the above embodiments, the navigation and positioning system monitors the abnormality degree of the navigation trajectory and establishes an online optimization mechanism for the weight allocation strategy. When a trajectory abnormality occurs, store the current mapping relationship between the characteristic parameters and the weights into the sample set for updating the fuzzy inference engine, realizing the self-learning evolution of the system. This closed-loop optimization design improves the long-term reliability of the navigation system, enabling it to continuously adapt to and optimize the processing strategies for different working conditions.

[0020] In a second aspect, the present application provides a navigation and positioning system, which includes: one or more processors and a memory; The memory is coupled to the one or more processors. The memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions so that the navigation and positioning system can implement a dynamic navigation and positioning method for intelligent fully-mechanized coal mining provided in the above embodiments, which will not be elaborated here.

[0021] In a third aspect, the present application provides a computer-readable storage medium, including instructions. When the instructions run on the navigation and positioning system, the navigation and positioning system can implement a dynamic navigation and positioning method for intelligent fully-mechanized coal mining provided in the above embodiments, which will not be elaborated here.

[0022] In a fourth aspect, the present application provides a computer program product. When the computer program product runs on the navigation and positioning system, the navigation and positioning system can implement a dynamic navigation and positioning method for intelligent fully-mechanized coal mining provided in the above embodiments, which will not be elaborated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By real-time monitoring the vibration state of the shearer, increase the modulation frequency and reduce the angle range to make reciprocating movements under strong vibration, and reduce the frequency for full-angle compensation under weak vibration. At the same time, combined with the deep learning prediction model, realize the early prediction and parameter pre-adjustment of the vibration working conditions, and establish a dynamic mapping mechanism among the vibration intensity, modulation frequency, and angle range. This adaptive modulation scheme well solves the problem of poor real-time compensation of traditional fixed-frequency full-angle modulation under strong vibration working conditions.

[0024] 2. Combine the smoothness score of the odometer data and dynamically determine the weight coefficients of different data sources through fuzzy inference. The system also establishes a weight optimization mechanism based on trajectory anomaly detection, realizes the self-learning evolution of the fuzzy inference engine through the dynamic update of the sample set, and forms a closed-loop data quality evaluation and optimization system.

[0025] 3. The system uses the fast Fourier transform to analyze the frequency domain characteristics of the vibration signal, establishes a modulation frequency gradient interval according to the main frequency component, and realizes precise frequency modulation based on vibration characteristics. At the same time, by analyzing the correction contribution degree of different modulation angles to the navigation error in historical data, dynamically select the optimal angle range for reciprocating motion, improving the compensation efficiency. This parameter optimization scheme based on data analysis significantly improves the dynamic response ability and compensation accuracy of the system. Description of the Drawings

[0026] Figure 1 is a schematic flow chart of a dynamic navigation and positioning method for intelligent fully mechanized coal mining in an embodiment of the present application; Figure 2 is another schematic flow chart of a dynamic navigation and positioning method for intelligent fully mechanized coal mining in an embodiment of the present application; Figure 3 is a schematic structural diagram of an entity device of the navigation and positioning system in an embodiment of the present application. Detailed Embodiments

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0029] It is understandable that inertial navigation is one of the core systems for realizing the navigation and positioning of shearers. It mainly relies on inertial sensors such as gyroscopes and accelerometers to determine the attitude and position information of shearers. The gyroscope is responsible for measuring the angular rate of the shearer in the inertial navigation system, and then calculating the attitude change of the shearer. However, the gyroscope has drift errors. Even when the shearer is stationary, its output will change over time. This error will accumulate continuously, seriously affecting the accuracy of the inertial navigation system in measuring the attitude of the shearer, and then reducing the accuracy of navigation and positioning.

[0030] To improve the measurement accuracy of the gyroscope and reduce the influence of drift errors on the inertial navigation system, a rotation modulation platform is introduced in this application. Among them, the rotation modulation platform is the base device for installing the gyroscope. It changes the sensitive axis direction of the gyroscope by rotating at a certain frequency and angle. During the rotation, the gyroscope collects data at different modulation angles. Since the influence of drift errors in different directions is different, by comprehensively processing the measurement data at multiple angles, the influence of drift errors on the measurement results can be effectively reduced. For example, the system will adjust the modulation frequency and angle range of the rotation modulation platform according to the vibration state of the shearer. When the vibration is strong, the modulation frequency is increased and the angle range is reduced for reciprocating motion. When the vibration is weak, the frequency is reduced and the 360° periodic rotation motion is restored to adapt to different working conditions and more accurately compensate for the gyroscope drift error.

[0031] For the convenience of understanding, the method provided in this embodiment is described in the following process. Please refer to Figure 1 , which is a schematic flow diagram of a dynamic navigation and positioning method for intelligent fully-mechanized coal mining in this application embodiment.

[0032] S101. Real-time collect the three-axis vibration acceleration signals of the target shearer and calculate the root mean square value of the three-axis acceleration.

[0033] Among them, the target shearer refers to the mechanical equipment that performs coal mining tasks during coal mining. The three-axis vibration acceleration signal represents the signal generated by the vibration acceleration of the target shearer in three mutually perpendicular directions (generally the x-axis, y-axis, and z-axis).

[0034] Specifically, the navigation and positioning system installs acceleration sensors on the target shearer to obtain the vibration acceleration signals of the shearer in the x-axis, y-axis, and z-axis directions in real time. These sensors convert the physical quantities generated by the shearer vibration into electrical signals and other processable forms and transmit them to the navigation and positioning system. After receiving the signals, the system calculates the three-axis vibration acceleration signals according to the calculation formula of the root mean square value to obtain a root mean square value that can comprehensively reflect the vibration intensity of the shearer.

[0035] S102. Whether the root mean square value is greater than or equal to the preset threshold.

[0036] Specifically, the navigation and positioning system compares the root mean square value calculated in step S101 with a preset threshold. If the root mean square value is greater than or equal to the preset threshold, it is determined that the shearer is in a strong vibration state; if the root mean square value is less than the preset threshold, it is determined that the vibration of the shearer is relatively weak. This comparison result will determine the subsequent adjustment strategy of the system for the motion parameters of the rotary modulation platform.

[0037] It should be noted that the preset threshold is a numerical standard preset in the navigation and positioning system. It is used to divide the vibration intensity of the shearer into different levels and serve as the basis for judging whether it is necessary to adjust the motion parameters of the rotary modulation platform.

[0038] S103. Increase the modulation frequency of the rotary modulation platform according to the preset frequency mapping relationship, and at the same time reduce the modulation angle range to the preset angle range for reciprocating motion.

[0039] Among them, the rotary modulation platform is the base device for installing the gyroscope, which compensates for the drift error of the gyroscope through rotational motion; the modulation frequency represents the rotational frequency of the rotary modulation platform; the modulation angle range refers to the angular interval of the rotary modulation platform's rotation.

[0040] When it is determined in step S102 that the root mean square value is greater than or equal to the preset threshold, that is, when the shearer is in a strong vibration state, this step is executed to optimize the gyroscope error compensation and adapt to the strong vibration working condition.

[0041] Specifically, the navigation and positioning system determines the modulation frequency that the rotary modulation platform should increase to in the current strong vibration state according to the preset frequency mapping relationship. This frequency mapping relationship can be a functional relationship obtained by fitting experimental data or a look-up table set based on experience. At the same time, the system reduces the modulation angle range of the rotary modulation platform to the preset angle range and controls the platform to perform reciprocating motion within this range. For example, the preset angle range may be ±30°, and the platform rotates back and forth between -30° and 30°, which can more quickly track the change of the gyroscope error and improve the real-time performance of error compensation.

[0042] Optionally, a preset frequency mapping relationship look-up table is stored in the processor of the navigation and positioning system. When it is determined that the modulation frequency needs to be increased, the processor finds the corresponding modulation frequency value in the look-up table according to the root mean square value. Then, by controlling the motor driver, the pulse frequency of the motor driving the rotary modulation platform is adjusted, thereby changing the modulation frequency. For the control of the modulation angle range, the processor sends specific control instructions to the motor driver to make the motor perform reciprocating motion according to the preset angle range, such as sending a control pulse sequence to limit the rotation angle range of the motor, which is not limited here.

[0043] S104. Reduce the modulation frequency of the rotary modulation platform according to the preset frequency mapping relationship and restore the modulation angle range to 360° to perform periodic rotational motion.

[0044] When it is determined in step S102 that the root mean square value is less than the preset threshold, that is, when the shearer is in a weak vibration state, this step is executed to restore to the conventional gyroscope error compensation method.

[0045] Specifically, the navigation and positioning system determines the modulation frequency to which the rotary modulation platform should be reduced in the current weak vibration state according to the preset frequency mapping relationship. Then, through corresponding control means, the parameters of the drive motor of the rotary modulation platform are adjusted to reduce the modulation frequency. At the same time, the modulation angle range of the rotary modulation platform is restored to 360°, and the platform is controlled to perform periodic 360° rotational motion. In this way, under weak vibration conditions, the drift error of the gyroscope can be compensated more comprehensively through full-angle rotation.

[0046] S105. During the process of the rotary modulation platform moving at the modulation frequency, collect the output data of the gyroscope at different modulation angles.

[0047] After the rotary modulation platform starts to move at the modulation frequency determined in step S103 or S104, the navigation and positioning system needs to obtain the measurement data of the gyroscope at different angles for subsequent error compensation and attitude calculation.

[0048] Specifically, the navigation and positioning system synchronously starts the acquisition work of the gyroscope data during the continuous rotation of the rotary modulation platform at the set modulation frequency. As the rotary modulation platform rotates, it will pass through different modulation angles. At each specific modulation angle position, the navigation and positioning system records the measurement data output by the gyroscope at this time. These data contain the measurement information of the gyroscope on the current attitude change of the shearer and are an important basis for subsequent error compensation and attitude solution.

[0049] S106. Use the sliding window algorithm to process the output data in real time, calculate the correction parameters according to the preset dynamic error compensation model, and obtain the corrected attitude data of the target shearer.

[0050] Specifically, the navigation and positioning system first processes the output data of the gyroscope collected by using the sliding window algorithm. A sliding window of a suitable size is set on the data sequence. As new data is continuously collected, the window slides step by step on the data sequence. Each time the window slides, statistical analysis is performed on the data within the window, such as calculating eigenvalue features such as the mean and variance. Then, the processed data is input into a preset dynamic error compensation model. Based on the input data, combined with the preset parameters and algorithms, the model calculates the correction parameters for the current gyroscope measurement data. Finally, the original measurement data of the gyroscope is corrected using these correction parameters, so as to obtain the corrected attitude data that can more accurately reflect the actual attitude of the target shearer.

[0051] Optionally, code for the sliding window algorithm is written using a programming language (such as C, C++). Define an array as the sliding window, and sequentially store the collected gyroscope data into the array according to the set window size and sliding step. After each window slide, calculate the relevant statistical eigenvalue features by looping through the array. Take these eigenvalue features as inputs and call a pre-written dynamic error compensation model function. This function calculates the correction parameters according to the model algorithm, and then corrects the original data using the correction parameters.

[0052] Among them, the dynamic error compensation model is a mathematical model preset by the navigation and positioning system. It takes into account the error factors that the gyroscope may generate under different working conditions of the shearer, and calculates the correction parameters for the gyroscope measurement data by inputting relevant data.

[0053] S107: Substitute the variance eigenvalue features of the attitude data and the odometer data into the preset weight calculation formula respectively to obtain the weight coefficients corresponding to the attitude data and the odometer data.

[0054] Among them, the odometer data is the data measured by the odometer installed on the shearer, and is usually used to represent the moving distance and speed information of the shearer.

[0055] Specifically, the navigation and positioning system first calculates the variance eigenvalue features of the attitude data and the odometer data. For the attitude data, calculate the average value of the squared deviations of each data point from the mean value within a period of time to obtain the variance eigenvalue feature of the attitude data; similarly, perform the same operation on the odometer data to obtain its variance eigenvalue feature. Then, substitute these two variance eigenvalue features into the preset weight calculation formula to calculate the weight coefficients corresponding to the attitude data and the odometer data respectively.

[0056] The weight calculation formula is: ; ; where represents the weight coefficient corresponding to the attitude data, Represents the weight coefficient corresponding to the odometer data, Represents the variance eigenvalue of the attitude data, Represents the variance eigenvalue of the odometer data.

[0057] Optionally, the navigation and positioning system can also calculate the jitter coefficient of the gyroscope output data based on the root mean square value, and determine the continuity score of the attitude data according to the jitter coefficient; at the same time, calculate the speed difference between adjacent sampling points of the odometer data, and determine the smoothness score according to the speed difference; then input the continuity score and the smoothness score into a preset fuzzy inference engine to calculate the weight coefficients corresponding to the attitude data and the odometer data respectively. Among them, the fuzzy inference engine operates based on fuzzy logic rules, and these rules are preset according to a large amount of experimental data and actual coal mining working conditions experience. The fuzzy inference engine, based on the input scores, through a series of processing processes such as fuzzification, fuzzy inference, and defuzzification, finally calculates the weight coefficients corresponding to the attitude data and the odometer data respectively. For example, when the continuity score of the attitude data is high and the smoothness score of the odometer data is also high, the fuzzy inference engine may assign relatively close weight coefficients to both; if the continuity score of the attitude data is high but the smoothness score of the odometer data is low, the fuzzy inference engine will appropriately increase the weight coefficient of the attitude data and decrease the weight coefficient of the odometer data.

[0058] It can be understood that a smaller jitter coefficient indicates that the gyroscope output data is less affected by vibration, the continuity of the attitude data is good, and the corresponding continuity score is high; conversely, a larger jitter coefficient results in a lower continuity score.

[0059] In addition, a smaller speed difference between adjacent sampling points indicates that the running speed of the shearer changes smoothly, and the smoothness of the odometer data is high; conversely, a larger speed difference results in a lower smoothness. The system can convert the speed difference into a smoothness score according to the preset scoring criteria. For example, it is set that a speed difference within a certain range corresponds to a higher smoothness score, and the score decreases when it exceeds the range.

[0060] S108. Weightedly fuse the attitude data and the odometer data according to the weight coefficients to obtain the navigation and positioning result of the target shearer.

[0061] Specifically, the navigation and positioning system performs weighted calculation on these two sets of data according to the weight coefficients corresponding to the attitude data and the odometer data obtained in step S107. Assuming the attitude data is A and the odometer data is B, the calculation method of weighted fusion is: Navigation and positioning result = A + B.

[0062] Further, after the navigation and positioning system completes the weighted fusion of the attitude data and the odometer data to obtain the navigation and positioning result of the target shearer, the system immediately acquires the relevant characteristic parameters of the current shearer, including the root mean square value of the three-axis vibration acceleration signal, the modulation frequency, and the modulation angle of the rotation modulation platform.

[0063] The system then calculates the curvature value and the rate of change of speed of the shearer's running trajectory based on a series of navigation and positioning results obtained within a preset time period. The system comprehensively processes the trajectory curvature value and the rate of change of speed through a specific algorithm to generate an index that can measure the degree of trajectory abnormality, namely the trajectory abnormality degree. For example, a reasonable range of the trajectory curvature value and the rate of change of speed during normal operation is set, and when the actual calculated value exceeds this range, the trajectory abnormality degree will increase accordingly.

[0064] Finally, the system compares the calculated trajectory abnormality degree with a preset abnormality threshold. If the trajectory abnormality degree exceeds the preset threshold, it indicates that the running trajectory of the shearer is abnormal. At this time, the navigation and positioning system records the mapping relationship between the currently acquired characteristic parameters (root mean square value, modulation frequency, modulation angle) and the weight coefficients used when calculating the navigation and positioning results, and stores them in the optimization sample set. As time goes by and the shearer operation data accumulates, a large amount of such mapping relationship data will be stored in the optimization sample set. The system can use these data to regularly update the fuzzy inference engine, and by adjusting the rules and parameters inside the fuzzy inference engine, it can better adapt to different coal mining working conditions, thereby improving the accuracy and reliability of the navigation and positioning results.

[0065] In the above embodiment, the navigation and positioning system dynamically adjusts the motion parameters of the rotation modulation platform by real-time monitoring the vibration state of the shearer, increasing the modulation frequency and narrowing the angle range during strong vibration, and reducing the frequency for full-angle compensation during weak vibration. This adaptive modulation strategy can maintain a good error compensation effect under different vibration working conditions. At the same time, the sliding window algorithm is used to process data in real time, cooperating with the dynamic error compensation model, which can timely track the error change. By adaptively fusing the attitude and odometer data with weights, the reliability and accuracy of the navigation and positioning are improved, thus effectively addressing the problem of poor real-time compensation of traditional fixed-frequency full-angle modulation under strong vibration working conditions.

[0066] The following further describes the more specific process of the method provided in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of a dynamic navigation and positioning method for intelligent fully mechanized coal mining in this application embodiment.

[0067] S201. Collect the cutting motor current, traction speed, and coal seam hardness data of the target shearer, and establish a working condition feature vector.

[0068] Before the start of coal mining operations or during continuous mining, the navigation and positioning system needs to know the working conditions of the shearer in real time, so as to predict the vibration situation in advance and prepare for adjusting the parameters of the rotary modulation platform. Therefore, this step will be executed.

[0069] Specifically, the navigation and positioning system collects the cutting motor current data by installing a current sensor in the cutting motor circuit of the target shearer. The current sensor converts the current signal into an electrical signal suitable for system processing and transmits it to the navigation and positioning system. For the acquisition of the traction speed, a speed sensor, such as an encoder, can be installed on the traveling mechanism of the shearer. It generates pulse signals according to the rotation of the shearer's traveling wheels. The navigation and positioning system calculates the traction speed by counting the pulse signals and measuring the time. The coal seam hardness data can be obtained through pre - geological exploration or by using some special sensors during coal mining, such as a coal seam hardness detection sensor based on the principle of acoustic wave reflection. After obtaining these three data, the navigation and positioning system combines them into a vector in a specific format, that is, the working condition feature vector.

[0070] S202. Train a vibration prediction model based on a deep - learning algorithm, and input the working condition feature vector into the vibration prediction model to obtain the predicted values of the three - axis vibration acceleration signals within a future time window.

[0071] Specifically, the navigation and positioning system first prepares a large amount of historical data, including the working condition feature vectors of the shearer in different working states and the corresponding three - axis vibration acceleration signals. Use this historical data to train the deep - learning algorithm and construct a vibration prediction model. During the training process, the deep - learning algorithm continuously adjusts the parameters of the model to minimize the error between the predicted value and the actual value. After training is completed, the currently collected working condition feature vector is input into the trained vibration prediction model. The model analyzes and processes the input working condition feature vector according to the learned rules and finally outputs the predicted values of the three - axis vibration acceleration signals within a future time window.

[0072] Optionally, an open - source deep - learning framework (such as TensorFlow) can be used for model training, or a dedicated deep - learning hardware acceleration device (such as an NVIDIA GPU) can be used in combination with a deep - learning platform for training and prediction. There is no limitation here.

[0073] S203. Determine the pre - adjustment frequency and pre - adjustment angle according to the comparison result between the predicted value and the preset threshold.

[0074] Specifically, the navigation and positioning system compares the predicted value of the three-axis vibration acceleration signal obtained in step S202 with a preset threshold. If the predicted value is greater than or equal to the preset threshold, it is determined that the shearer may be in a strong vibration state in the future. The navigation and positioning system determines to increase the pre-adjustment frequency of the rotation modulation platform and narrow the modulation angle range according to the pre-set rules to obtain the pre-adjustment angle. For example, if the preset threshold is a specific root mean square value of vibration acceleration, when the predicted value exceeds the threshold, a higher pre-adjustment frequency is determined according to the pre-set frequency mapping relationship (such as an empirical formula or a look-up table), and at the same time, the modulation angle range is narrowed to a smaller interval as the pre-adjustment angle, such as ±20°. Conversely, if the predicted value is less than the preset threshold, it indicates that the predicted vibration of the shearer in the future is weak, and the system reduces the pre-adjustment frequency according to the rules and restores the modulation angle range to the full angle (such as 360°) as the pre-adjustment angle.

[0075] S204. Whether the difference between the three-axis vibration acceleration signal and the corresponding predicted value is less than the preset amplitude threshold.

[0076] After the three-axis vibration acceleration signal of the target shearer is collected in real time and the predicted value has been obtained through the vibration prediction model, the navigation and positioning system needs to judge the accuracy of the prediction to determine which modulation parameters to use subsequently. This step is executed at this time.

[0077] Specifically, the navigation and positioning system calculates the difference between the three-axis vibration acceleration signal of the target shearer collected in real time and the corresponding predicted value obtained through the vibration prediction model before. The differences between the actual values and the predicted values of the vibration acceleration signals in the x-axis, y-axis, and z-axis directions are calculated respectively. Then, the differences in these three directions are compared with the preset amplitude threshold. If the differences in all three directions are less than the preset amplitude threshold, it indicates that the prediction of the vibration prediction model is relatively accurate; if there is at least one direction in which the difference is greater than or equal to the preset amplitude threshold, it indicates that there is a deviation in the prediction. This judgment result will directly affect the determination method of the modulation frequency and modulation angle of the subsequent rotation modulation platform.

[0078] S205. Send the pre-adjustment frequency and pre-adjustment angle to the drive controller of the rotation modulation platform in advance for caching, and adjust the motor drive parameters at the corresponding time points in the future time window.

[0079] Specifically, the navigation and positioning system sends the pre-adjusted frequency and pre-adjusted angle determined in step S203 to the drive controller of the rotation modulation platform. After receiving these parameters, the drive controller stores them in the internal cache area. At the same time, the navigation and positioning system records the start time and duration of the future time window. When the corresponding time point of the future time window arrives, the navigation and positioning system sends a trigger signal to the drive controller, and the drive controller adjusts the motor drive parameters according to the cached pre-adjusted frequency and pre-adjusted angle. For example, if the pre-adjusted frequency is high, the drive controller increases the pulse frequency of the motor; if the range of the pre-adjusted angle is reduced, the drive controller adjusts the control signal of the motor to make the rotation modulation platform move within the set angle range.

[0080] S206. Determine the modulation frequency and modulation angle according to the comparison result between the root mean square value and the preset amplitude threshold.

[0081] Specifically, the navigation and positioning system compares the root mean square value calculated from the target shearer's three-axis vibration acceleration signals collected in real time with the preset amplitude threshold. If the root mean square value is greater than or equal to the preset amplitude threshold, it is determined that the shearer is currently in a strong vibration state, and the navigation and positioning system increases the modulation frequency of the rotation modulation platform according to the preset rules and simultaneously reduces the modulation angle range. For example, according to the preset frequency mapping relationship, a higher modulation frequency is selected from the frequency interval corresponding to the current root mean square value, and the modulation angle range is reduced to a smaller interval, such as ±30°. If the root mean square value is less than the preset amplitude threshold, it indicates that the shearer's vibration is relatively weak, and the navigation and positioning system reduces the modulation frequency according to the preset rules and restores the modulation angle range to 360° to perform full-angle gyroscope error compensation.

[0082] S207. When the root mean square value is greater than or equal to the preset threshold, perform a fast Fourier transform on the vibration acceleration signal to obtain the main frequency value with the largest energy proportion and the corresponding amplitude coefficient in the vibration spectrum.

[0083] When it is determined that the shearer is in a strong vibration state (i.e., the root mean square value is greater than or equal to the preset threshold), in order to more accurately adjust the modulation frequency of the rotation modulation platform to match the vibration characteristics of the shearer, the navigation and positioning system executes this step.

[0084] Specifically, when the navigation and positioning system determines that the root mean square value is greater than or equal to the preset threshold, a fast Fourier transform operation is performed on the collected vibration acceleration signal. The system digitizes the continuously collected vibration acceleration signals over a period of time and converts the time-domain signals into frequency-domain signals according to the process of the fast Fourier transform algorithm to obtain a vibration spectrum. Then, in the obtained vibration spectrum, the frequency component with the largest energy proportion is found through data analysis. This frequency is the main frequency value, and the corresponding amplitude coefficient is obtained at the same time. These main frequency values and amplitude coefficients will provide a key basis for establishing a modulation frequency gradient interval in the subsequent steps.

[0085] S208. Establish a modulation frequency gradient interval based on the main frequency value and the corresponding amplitude coefficient, and adjust the operating frequency of the rotary modulation platform within the modulation frequency gradient interval according to a preset step size.

[0086] Specifically, the navigation and positioning system determines the modulation frequency gradient interval based on the main frequency value and the amplitude coefficient obtained in step S207. For example, a frequency range can be determined with the main frequency value as the center according to the magnitude of the amplitude coefficient. For instance, a frequency interval with a certain proportion (such as 10%) of fluctuation above and below the main frequency value is used as the modulation frequency gradient interval. After determining the gradient interval, the operating frequency of the rotary modulation platform is gradually adjusted within this interval according to the preset step size. The system sends control commands to the drive controller of the rotary modulation platform, and the drive controller adjusts the drive parameters of the motor according to the commands, thereby changing the operating frequency of the rotary modulation platform. The adjustment amplitude for each time is the preset step size until the operating frequency is adjusted to an appropriate value.

[0087] S209. Obtain the gyroscope output data and the corresponding correction parameters at different modulation angles within the past preset number of sampling periods.

[0088] Specifically, the navigation and positioning system reads the gyroscope output data at different modulation angles within the past preset number of sampling periods from its data storage unit. These data are collected and stored in real time by the gyroscope during the operation of the rotary modulation platform. At the same time, the system obtains the correction parameters corresponding to these gyroscope output data, which are calculated and stored through a preset dynamic error compensation model before. After obtaining these data and parameters, it provides a data basis for analyzing the correction contribution degree of different modulation angles to the navigation error in the next step.

[0089] S210. Calculate the correction contribution degree of each modulation angle within 360° to the navigation error based on the gyroscope output data and the corresponding correction parameters, and determine the preset angle range with the best navigation error correction effect for reciprocating motion.

[0090] Specifically, the navigation and positioning system analyzes each modulation angle within the 360° range according to the obtained gyroscope output data and the corresponding correction parameters. For each modulation angle, the corresponding gyroscope output data is corrected using the correction parameters, and then the navigation error is calculated based on the corrected data. By comparing the corrected navigation error with the uncorrected navigation error at different modulation angles, the correction contribution degree of each modulation angle to the navigation error is calculated.

[0091] For example, the correction contribution degree can be quantified in ways such as the error reduction ratio. After calculating the correction contribution degrees of all modulation angles, these contribution degrees are sorted and analyzed to find the angle range with a higher correction contribution degree, which is determined as the preset angle range with the best navigation error correction effect. Finally, the navigation and positioning system controls the rotation modulation platform to reciprocate within this preset angle range to achieve more efficient gyroscope error compensation.

[0092] The navigation and positioning system of the embodiment of the present invention is applied to an electronic device. Figure 3 The schematic diagram of the architecture of the electronic device suitable for implementing the embodiment of the present invention is shown.

[0093] It should be noted that Figure 3 The shown electronic device is only an example and should not impose any limitation on the functions and usage scope of the embodiment of the present invention.

[0094] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or the relevant hardware can be controlled by instructions (computer programs). The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor. Among them, multiple instructions are stored in the storage medium, and these instructions can be loaded by the processor to execute any step of the method provided by the embodiment of the present invention.

[0095] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0096] Further, the software programs and modules in the above storage medium may further include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide a running environment for other software components. The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which can implement or execute the various methods, steps, and logic flow block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0097] Since the instructions stored in the storage medium can execute the steps in any of the methods provided in the embodiments of the present invention, the beneficial effects of any of the methods provided in the embodiments of the present invention can be achieved. For details, see the previous embodiments and will not be repeated here.

[0098] As described above, it is only the preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A dynamic navigation and positioning method for intelligent comprehensive mining in coal mines, applied to a navigation and positioning system, characterized in that: The method comprises: Collect the three-axis vibration acceleration signal of the target coal mining machine in real time and calculate the root mean square value of the three-axis acceleration; When the RMS value is greater than or equal to a preset threshold, the modulation frequency of the rotary modulation platform is increased according to a preset frequency mapping relationship, and the modulation angle range is reduced to a preset angle range for reciprocating motion; When the RMS value is less than a preset threshold, the modulation frequency of the rotary modulation platform is reduced according to a preset frequency mapping relationship and the modulation angle range is restored to 360° for periodic rotational motion; While the rotary modulation platform is moving at the modulation frequency, collecting output data of the gyroscope at different modulation angles; The output data is processed in real time using a sliding window algorithm, and correction parameters are calculated according to a preset dynamic error compensation model to obtain the corrected posture data of the target coal mining machine; Substituting the variance characteristic values ​​of the posture data and the odometer data into a preset weight calculation formula respectively to obtain weight coefficients corresponding to the posture data and the odometer data respectively; The posture data and the odometer data are weightedly fused according to the weight coefficient to obtain a navigation and positioning result of the target coal mining machine.

2. The method according to claim 1, characterized in that Before the step of collecting the three-axis vibration acceleration signal of the target coal mining machine in real time and calculating the root mean square value of the three-axis acceleration, the method further includes: Collect the cutting motor current, traction speed and coal seam hardness data of the target coal mining machine and establish the working condition characteristic vector; Training a vibration prediction model based on a deep learning algorithm, and inputting the operating condition feature vector into the vibration prediction model to obtain a predicted value of a triaxial vibration acceleration signal within a future time window; Determining a pre-adjustment frequency and a pre-adjustment angle according to a comparison result between the predicted value and the preset threshold value; The pre-adjusted frequency and the pre-adjusted angle are sent to the drive controller of the rotary modulation platform in advance for buffering, and the motor drive parameters are adjusted at the corresponding time point in the future time window.

3. The method according to claim 2, characterized in that After the step of collecting the three-axis vibration acceleration signal of the target coal mining machine in real time and calculating the root mean square value of the three-axis acceleration, the method further includes: Determine whether the difference between the current three-axis vibration acceleration signal and the corresponding predicted value is less than a preset amplitude threshold; If yes, determining the modulation frequency and the modulation angle according to the comparison result of the RMS value and the preset amplitude threshold; If not, continue to adjust the motor drive parameters according to the pre-adjusted frequency and pre-adjusted angle.

4. The method according to claim 1, characterized in that: The step of increasing the modulation frequency of the rotary modulation platform according to the preset frequency mapping relationship specifically includes: Performing a fast Fourier transform on the vibration acceleration signal to obtain a main frequency value with the largest energy proportion in the vibration spectrum and a corresponding amplitude coefficient; Establishing a modulation frequency gradient interval according to the main frequency value and the corresponding amplitude coefficient; The operating frequency of the rotary modulation platform is adjusted within the modulation frequency gradient interval according to a preset step length.

5. The method according to claim 1, characterized in that: The step of reducing the modulation angle range to a preset angle range for reciprocating motion specifically includes: Obtaining gyroscope output data and corresponding correction parameters at different modulation angles within a preset number of sampling periods in the past; According to the gyroscope output data and the corresponding correction parameters, the correction contribution of each modulation angle within the 360° range to the navigation error is calculated, and the preset angle range with the best navigation error correction effect is determined; The rotary modulation platform is controlled to perform reciprocating motion within the preset angle range.

6. The method according to claim 1, characterized in that The step of substituting the variance eigenvalues ​​of the posture data and the odometer data into a preset weight calculation formula to obtain the weight coefficients corresponding to the posture data and the odometer data, respectively, specifically includes: Calculating a jitter coefficient of the gyroscope output data based on the root mean square value, and determining a continuity score of the posture data according to the jitter coefficient; Calculating speed differences between adjacent sampling points of the odometer data, and determining a smoothness score based on the speed differences; The continuity score and the smoothness score are input into a preset fuzzy inference engine to calculate the weight coefficients corresponding to the posture data and the odometer data respectively.

7. The method according to claim 6, characterized in that After the step of weighted fusion of the posture data and the odometer data according to the weight coefficient to obtain the navigation positioning result of the target coal mining machine, the method further includes: Acquire current characteristic parameters, wherein the characteristic parameters include root mean square value, modulation frequency, and modulation angle; Calculate the trajectory curvature value and the speed change rate based on the navigation positioning result to generate a trajectory abnormality; When the trajectory abnormality exceeds a preset abnormality threshold, the mapping relationship between the characteristic parameter and the current weight coefficient is stored in an optimized sample set for updating the fuzzy inference device.

8. A navigation and positioning system, characterized in that: The navigation and positioning system includes: one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the navigation and positioning system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a navigation and positioning system, the navigation and positioning system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a navigation and positioning system, the navigation and positioning system is enabled to execute the method according to any one of claims 1 to 7.

Images