Picks type pick tooth rock breaking load space-time evolution analysis method and system

Abstract

The application relates to the technical field of intelligent control of mining equipment, and in particular to a pick-type pick tooth rock breaking load space-time evolution analysis method and system. The method comprises the following steps: collecting multi-dimensional load signals in a rock breaking process through a sensor array; establishing a digital representation surface based on pick tooth geometric morphology and sensor coordinates; generating a load estimation value of any point on the surface by using a spatial interpolation algorithm; mapping to the surface to form a continuous space-time load distribution field; extracting rock breaking efficiency and pick tooth load state characteristic parameters; and generating equipment parameter optimization guidance information through a fuzzy inference rule base. The application solves the problem that traditional methods cannot represent the continuous space-time evolution of the load, realizes visual analysis of the load distribution in the rock breaking process and self-adaptive regulation and control of the equipment parameters, and significantly improves the rock breaking efficiency and the service life of the pick tooth.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology for mining equipment, and in particular to a method and system for spatiotemporal evolution analysis of rock-breaking load on pick-type cutting teeth. Background Technology

[0002] As the core rock-breaking component of mining cutting equipment, the load distribution characteristics of pick-type cutting teeth directly affect rock-breaking efficiency and equipment lifespan. Traditional analysis methods mainly rely on discrete sensors to measure resultant force or point load signals, failing to establish a continuous load field associated with the geometry of the cutting teeth. This results in the inability to accurately characterize the spatiotemporal evolution of loads during rock-breaking.

[0003] Existing technologies have three limitations: First, sensor signals are mostly single-dimensional mechanical data, lacking the fusion of multi-dimensional signals such as vibration, making it difficult to comprehensively reflect the rock-breaking state; second, the data processing process is not linked to the physical space of the cutting teeth, only obtaining abstract numerical values ​​and failing to reconstruct the continuous load distribution; third, equipment parameter adjustments rely on empirical rules, lacking quantitative guidance based on the spatiotemporal characteristics of the load. Furthermore, in hard rock strata, the cutting teeth are subjected to concentrated and drastically fluctuating loads, making it difficult for traditional methods to adapt to changes in the rock strata in real time, leading to increased abnormal wear of the cutting teeth and higher rock-breaking energy consumption. Therefore, there is an urgent need for a solution that can fuse multi-dimensional signals, combine the geometric characteristics of the cutting teeth, achieve continuous spatiotemporal analysis of the load, and guide the adaptive control of the equipment. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of this application provide a spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, this application provides a method for spatiotemporal evolution analysis of rock-breaking loads using pick-type cutting teeth, comprising:

[0006] A sensor array arranged on the pick-shaped cutting teeth is used to collect multi-dimensional load signals of the pick-shaped cutting teeth as they change over time during the rock breaking process.

[0007] Based on the geometry of the pick-shaped cutting tooth and the spatial coordinates of the sensor array, a digital characterization surface of the interface between the pick-shaped cutting tooth and the rock is established.

[0008] Based on the digital characterization surface, the multi-dimensional load signal is processed to generate the load estimate value of any point on the surface of the pick-shaped cutting tooth at any time.

[0009] The estimated load values ​​are mapped onto the digital representation surface to form a continuous spatiotemporal load distribution field.

[0010] From the continuous spatiotemporal load distribution field, characteristic parameters representing rock breaking efficiency and the loading state of the cutting teeth are extracted;

[0011] The feature parameters are associated and mapped with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters.

[0012] To address the aforementioned problems, this application also provides a spatiotemporal evolution analysis system for rock-breaking loads of pick-type cutting teeth, the system comprising:

[0013] The signal acquisition module is used to acquire the multi-dimensional load signal of the pick-shaped cutting tooth as it changes over time during the rock breaking process by using a sensor array arranged on the pick-shaped cutting tooth.

[0014] The surface modeling module is used to establish a digital characterization surface of the interaction interface between the pick-shaped cutting tooth and the rock based on the geometric shape of the pick-shaped cutting tooth and the spatial coordinates of the sensor array.

[0015] The load calculation module is used to process the multi-dimensional load signal based on the digital characterization surface to generate a load estimate of any point on the surface of the pick-shaped cutting tooth at any time.

[0016] The field construction module is used to map the load estimate to the digital representation surface to form a continuous spatiotemporal load distribution field;

[0017] The feature extraction module is used to extract feature parameters characterizing rock breaking efficiency and the loading state of the cutting teeth from the continuous spatiotemporal load distribution field.

[0018] The parameter optimization module is used to associate and map the feature parameters with the equipment parameters of the mining cutting equipment, and generate guidance information for optimizing the equipment parameters.

[0019] This application achieves continuous spatiotemporal evolution analysis of rock-breaking loads on pick-type cutting teeth through multi-dimensional signal acquisition and digital surface modeling, significantly improving the accuracy of rock-breaking efficiency analysis and equipment parameter optimization. Firstly, by fusing multiple signals from stress and vibration sensors and processing unified timestamps, the limitations of single-sensor dimensions and signal asynchrony are resolved, providing a comprehensive and synchronous data foundation for load analysis. Secondly, by combining 3D laser scanning and surface reconstruction to establish a digital representation surface, abstract data is precisely correlated with the physical space of the cutting teeth, overcoming the limitations of traditional point load analysis.

[0020] Next, based on the spatial interpolation algorithm of geodesic distance and dynamic correction of geological influence factors, the accurate estimation of load at any point on the surface was realized, overcoming the computational challenge of large load distribution fluctuations under hard rock conditions; by mapping the load value to the color depth of the surface, a visualized continuous spatiotemporal load distribution field was generated, and for the first time, an intuitive representation of the spatiotemporal evolution law of load during rock breaking was realized.

[0021] Finally, the characteristic parameters of the high load area change rate per unit time and the maximum load trajectory extracted from the load field were used to achieve a quantitative evaluation of rock breaking efficiency and cutter wear status. By associating the characteristic parameters with equipment parameters through a fuzzy inference rule base, specific adjustment amounts for cutting speed and installation angle were generated, which promoted the transformation of equipment control from experience-driven to data-driven, and ultimately achieved the dual optimization of improved rock breaking efficiency and extended cutter life. Attached Figure Description

[0022] Figure 1 This is a schematic flowchart illustrating the spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth provided in an embodiment of this application.

[0023] Figure 2 This is a functional block diagram of a rock-breaking load spatiotemporal evolution analysis system for pick-type cutting teeth provided in an embodiment of this application;

[0024] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0025] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0026] This application provides a method for spatiotemporal evolution analysis of rock-breaking loads from pick-shaped cutting edges. The execution subject of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms.

[0027] Reference Figure 1 The diagram shown is a schematic flowchart of a method for analyzing the spatiotemporal evolution of rock-breaking loads using pick-type cutting teeth, according to an embodiment of this application. In this embodiment, the method includes:

[0028] S1. A sensor array arranged on the pick-shaped cutting teeth is used to collect multi-dimensional load signals of the pick-shaped cutting teeth as they change over time during the rock breaking process.

[0029] In this embodiment, the sensor array refers to a collection of various types of sensors fixedly installed on the surface and at specific locations inside the pick-shaped cutting tooth. This collection includes stress sensors and vibration sensors, which are used to synchronously collect mechanical and vibration-related signals during the rock-breaking process of the pick-shaped cutting tooth. The multi-dimensional load signal refers to a combination signal containing a three-dimensional cutting force signal and a high-frequency vibration signal with a unified timestamp after time-domain synchronization processing. It can reflect the stress and vibration state of the pick-shaped cutting tooth during the rock-breaking process from different dimensions.

[0030] In some embodiments, the acquisition of multi-dimensional load signals of the pick-shaped cutting teeth over time during rock breaking via a sensor array arranged on the pick-shaped cutting teeth includes:

[0031] The sensor array includes a stress sensor and a vibration sensor, wherein the stress sensor detects the triaxial cutting force signal generated during the rock breaking process in real time, and the vibration sensor collects the high-frequency vibration signal caused by the rock breaking impact;

[0032] The triaxial cutting force signal and the high-frequency vibration signal are time-domain synchronized to form a multi-dimensional load signal with a unified timestamp.

[0033] In this embodiment, the stress sensor is a sensor capable of detecting in real time the magnitude of the cutting force along the X-axis, Y-axis, and Z-axis of the pick-shaped cutting tooth during rock breaking, and outputting the detection result in the form of a three-dimensional cutting force signal. The three-dimensional cutting force signal is detected by the stress sensor and can respectively reflect the magnitude of the cutting force along the cutting direction (X-axis), feed direction (Y-axis), and vertical direction (Z-axis) of the pick-shaped cutting tooth during rock breaking. The vibration sensor is a sensor capable of collecting the high-frequency vibration of the pick-shaped cutting tooth caused by rock impact during rock breaking, and outputting the collection result in the form of a high-frequency vibration signal.

[0034] In this embodiment, the high-frequency vibration signal is acquired by a vibration sensor and reflects the intensity of high-frequency vibration generated by the pick-shaped cutting tooth during rock breaking due to mutual impact with the rock. The frequency range of this signal is mainly concentrated in 1-10kHz, which can effectively reflect the characteristic impact situation when the rock is broken. The time-domain synchronization processing refers to the problem that the timestamps of the three-dimensional cutting force signal output by the stress sensor and the high-frequency vibration signal output by the vibration sensor may be inconsistent due to the difference in their sampling frequencies. A specific algorithm is used to adjust the timestamps of the two types of signals to a uniform precision to ensure that the signals at the same time can correspond to the processing of the same rock breaking state of the cutting tooth.

[0035] In this embodiment, a unified timestamp refers to a time marker with consistent time precision that is shared by the three-dimensional cutting force signal and the high-frequency vibration signal after time-domain synchronization processing. In this embodiment, the precision of the unified timestamp is set to 1ms to ensure the matching of the two types of signals in the time dimension.

[0036] In this embodiment, the sensor array is first arranged by selecting stress and vibration sensors suitable for the working environment and detection requirements of the pick-shaped cutting tooth. The stress sensor is model HBMC16, and the vibration sensor is model PCB356A16. Based on the geometry of the pick-shaped cutting tooth and the main stress areas during rock breaking, holes are drilled at key locations on the tooth surface. The holes have a diameter of 5mm and a depth of 3mm. Eight stress sensors are embedded in and fixed in these holes. Simultaneously, two vibration sensors are fixed at locations on the cutting tooth where vibration is transmitted directly but not primarily due to stress, ensuring that the sensor array can comprehensively collect relevant signals during the rock breaking process.

[0037] In this embodiment, after the sensor array is arranged, the sensors are activated to acquire signals. During the rock-breaking process of the pick-shaped cutting tooth, the stress sensor detects the cutting force in real time along the X, Y, and Z axes, converting the detected mechanical signals into voltage signals for output. For example, when the cutting tooth is subjected to a cutting force of 125kN along the X-axis, the stress sensor outputs a 2.5V voltage signal; when it is subjected to a cutting force of 75kN along the Y-axis, it outputs a 1.5V voltage signal; and when it is subjected to a cutting force of 50kN along the Z-axis, it outputs a 1.0V voltage signal. The vibration sensor synchronously acquires the high-frequency vibration signal generated by the impact of the cutting tooth with the rock, also converting it into a voltage signal for output. For example, when the cutting tooth is subjected to a vibration acceleration of 5g, the vibration sensor outputs a 500mV voltage signal.

[0038] In this embodiment, since the sampling frequency of the stress sensor is 1kHz and that of the vibration sensor is 10kHz, the timestamps of the output signals from the two types of sensors differ and cannot directly correspond to the same rock-breaking moment. Therefore, it is necessary to perform time-domain synchronization processing on the acquired triaxial cutting force signal and high-frequency vibration signal. This embodiment uses a cross-correlation algorithm to achieve time-domain synchronization, taking the timestamp of the stress sensor output signal as the reference. The interval of this timestamp is 1ms, i.e., the time points are 0ms, 1ms, 2ms, etc. For the high-frequency vibration signal output by the vibration sensor with a timestamp interval of 0.1ms (time points are 0ms, 0.1ms, 0.2ms, etc.), it is resampled to the same 1ms time interval as the stress sensor signal through linear interpolation, so that each 1ms time point simultaneously has the corresponding triaxial cutting force signal and high-frequency vibration signal, forming a multi-dimensional load signal with a unified timestamp.

[0039] For example, at the time point 1ms, there are simultaneously three-dimensional cutting force signals output by the stress sensor: 125kN (2.5V) on the X-axis, 75kN (1.5V) on the Y-axis, and 50kN (1.0V) on the Z-axis, as well as a high-frequency vibration signal of 5g (500mV) output by the vibration sensor. Together, they constitute the multi-dimensional load signal at that moment.

[0040] In this embodiment, multi-dimensional load signals are acquired by a sensor array and synchronized in the time domain. This solves the problems of insufficient signal dimensions from a single sensor and the inability to accurately correspond to the same rock-breaking state due to time asynchrony between signals from different types of sensors. Multi-dimensional load signals can comprehensively reflect the force and vibration conditions during the rock-breaking process of the pick cutter from both mechanical and vibrational perspectives. This avoids distortion of subsequent analysis results due to missing data dimensions or time asynchrony, thus laying a reliable data foundation for accurately reconstructing the continuous load distribution field at the interface between the pick cutter and the rock.

[0041] S2. Based on the geometry of the pick-shaped cutting tooth and the spatial coordinates of the sensor array, establish a digital characterization surface of the interface between the pick-shaped cutting tooth and the rock.

[0042] In this embodiment, the geometric morphology of the pick-shaped cutting tooth refers to its three-dimensional structural features, including the tooth tip curvature, tooth surface inclination angle, tooth root shape, and overall dimensional parameters. These features directly determine the contact interface morphology between the cutting tooth and the rock. The spatial coordinates of the sensor array refer to the specific position coordinates of each sensor in the three-dimensional space. These coordinates are based on a specific spatial coordinate system and can accurately reflect the installation position of the sensor on the pick-shaped cutting tooth. The interface between the pick-shaped cutting tooth and the rock refers to the area where the surface of the pick-shaped cutting tooth directly contacts the rock and where force transmission and energy exchange occur during rock breaking. The load distribution in this area is key to analyzing rock breaking efficiency and the loading state of the cutting tooth. The digital characterization surface refers to the transformation of the geometric morphology of the interface between the pick-shaped cutting tooth and the rock into a digital three-dimensional surface model through specific technical means. This model can accurately reproduce the actual geometric features of the interface and provide a spatial reference for subsequent load signal processing and load distribution field construction.

[0043] In some embodiments, establishing a digital characterization surface of the interaction interface between the pick-shaped cutting tooth and the rock based on the geometry of the pick-shaped cutting tooth and the spatial coordinates of the sensor array includes:

[0044] Geometric topography point cloud data of the pick-shaped cutting tooth surface was obtained by three-dimensional laser scanning;

[0045] Based on the actual installation location of each sensor in the sensor array, determine the precise spatial coordinates of the sensor in the geometric topography point cloud data;

[0046] The geometric point cloud data containing sensor coordinates is reconstructed into a surface to generate a digital characterization surface that matches the surface of the cutting tooth.

[0047] In this embodiment of the application, three-dimensional laser scanning refers to the technical means of using a three-dimensional laser scanner to emit a laser beam to scan the surface of the pick-shaped cutting tooth in all directions, and obtaining the three-dimensional coordinate information of each point on the cutting tooth surface by receiving the reflected laser beam, thereby obtaining geometric shape point cloud data; geometric shape point cloud data refers to a large number of discrete datasets obtained by three-dimensional laser scanning, which contain the three-dimensional coordinates (X-axis, Y-axis, Z-axis coordinates) of each point on the surface of the pick-shaped cutting tooth, and these data can comprehensively reflect the geometric morphological details of the cutting tooth surface.

[0048] In this embodiment, the actual embedding position of the sensor refers to the physical position of the sensor center within the physical structure of the pick-shaped cutting tooth when the sensor is installed by drilling a hole in the cutting tooth. This position is the basis for determining the spatial coordinates of the sensor in the geometric topography point cloud data. The precise spatial coordinates refer to the three-dimensional coordinate values ​​that can accurately represent the actual embedding position of the sensor in the spatial coordinate system corresponding to the geometric topography point cloud data. The accuracy of these coordinate values ​​directly affects the accuracy of subsequent load mapping and analysis.

[0049] In this embodiment of the application, surface reconstruction refers to the process of using specific mathematical algorithms to fit, smooth, and stitch together discrete point cloud data containing precise spatial coordinates of sensors, ultimately generating a continuous, smooth digital surface that highly matches the actual geometric shape of the pick-shaped cutting tooth surface.

[0050] In this embodiment, the operation of acquiring point cloud data of the geometric topography of the pick-shaped cutting tooth surface through three-dimensional laser scanning is first performed. A FaroFocus S70 three-dimensional laser scanner is selected, and the pick-shaped cutting tooth is fixed on a dedicated tooling positioning fixture. The positioning error of the fixture is controlled within ±0.05mm to ensure that the cutting tooth is stable in position and does not shift during the scanning process. The three-dimensional laser scanner is started, and the surface of the cutting tooth is scanned in all directions according to the preset scanning path. The scanning range covers the entire interface area where the pick-shaped cutting tooth interacts with the rock, including key parts such as the tooth tip, tooth surface, and tooth root. After the scanning is completed, the device automatically generates geometric topography point cloud data containing the three-dimensional coordinates of each point on the cutting tooth surface. For example, the coordinates of a tooth tip point are (15mm, 8mm, 5mm), and the coordinates of a tooth surface point are (20mm, 12mm, 3mm). These discrete coordinate points together constitute a point cloud dataset reflecting the geometric morphology of the cutting tooth.

[0051] In this embodiment, after acquiring the geometric topography point cloud data, the next step is to determine the precise spatial coordinates of the sensor within the geometric topography point cloud data. First, the actual embedding of the sensor array in step S1 is recorded, including the drilling position of each sensor on the pick-shaped cutting tooth (e.g., drilling 10mm from the tooth tip and 20mm from the tooth root), the diameter (5mm) and depth (3mm) of the drilling, and the relative distance between the center position of the embedded sensor and the surface of the cutting tooth (e.g., the sensor center is located 2mm below the cutting tooth surface). The scanned geometric topography point cloud data is imported into CloudCompare software, which has point cloud data processing and coordinate matching functions. In the software, the area corresponding to the actual embedding position is first found based on the overall geometric characteristics of the cutting tooth (e.g., the sharp shape of the tooth tip and the tilt angle of the tooth surface). Then, combined with the parameters of the drilling size and the relative position of the sensor center, the point cloud data of this area is analyzed and calculated using the software's coordinate calibration tool.

[0052] For example, for a certain stress sensor, its actual installation location is in an area with a tooth surface inclination angle of 15°, and the distance from the center of the drill hole to the tooth tip is 12mm. Based on the coordinate distribution of this area in the point cloud data, the precise spatial coordinates of the sensor in the point cloud data are calculated to be (18mm, 10mm, 4mm). Following the same method, the precise spatial coordinates of all 8 stress sensors and 2 vibration sensors in the sensor array are determined in sequence and marked in the point cloud data.

[0053] In this embodiment, after determining the precise spatial coordinates of the sensor, a surface reconstruction operation is performed on the geometric point cloud data containing the sensor coordinates. The geometric point cloud data marked with the precise spatial coordinates of the sensor is imported into Geomagic DesignX software, which supports the reconstruction of complex surfaces. First, the point cloud data is preprocessed, including removing noise points (such as invalid coordinate points caused by dust interference) and redundant points (such as identical coordinate points generated by repeated scanning) generated during the scanning process to ensure the purity of the point cloud data. Then, the B-spline surface fitting algorithm is selected as the core algorithm for surface reconstruction. This algorithm has good smoothness and fitting accuracy, and can accurately reproduce the complex geometric shape of the cutting tooth surface. The accuracy parameters of the surface fitting are set in the software, and the fitting error is controlled within the range of ≤0.02mm to ensure that the reconstructed surface highly matches the actual surface of the cutting tooth. After starting the surface reconstruction program, the software will automatically analyze the preprocessed point cloud data, generate an initial surface model based on the distribution pattern and geometric features of the point cloud, and then continuously iterate and optimize to adjust the curvature and smoothness of the surface, while ensuring that the precise spatial coordinates of the sensor can accurately fall on the reconstructed surface.

[0054] For example, for a sensor marked with coordinates (18mm, 10mm, 4mm), the reconstruction of the surface ensures that the coordinate point becomes a component of the surface, preventing the sensor coordinates from deviating from the surface. The final result is a digitally represented surface that perfectly matches the pick-shaped cutting surface and contains all the precise spatial coordinates of the sensors. This surface serves as the spatial reference for subsequent load signal processing and the construction of the spatiotemporal load distribution field.

[0055] In this embodiment, by establishing a digital characterization surface of the interface between the pick-shaped cutting tooth and the rock, the problem of not being able to correlate discrete sensor signals with the actual physical space of the cutting tooth due to the lack of a digital definition of the complex geometry of the cutting tooth is solved. The digital characterization surface can accurately reproduce the geometry of the interface between the cutting tooth and the rock, providing a reliable spatial carrier for subsequently converting multi-dimensional load signals into a continuous load distribution on the cutting tooth surface. This avoids the situation where load analysis is disconnected from the actual cutting tooth structure due to the lack of a spatial reference, thus laying a key geometric foundation for accurately reconstructing the continuous load distribution field and quantifying the rock-breaking efficiency.

[0056] S3. Based on the digital representation surface, process the multi-dimensional load signal to generate a load estimate at any point on the surface of the pick-shaped cutting tooth at any time.

[0057] In some embodiments, processing the multi-dimensional load signal based on the digitally represented surface to generate a load estimate at any point on the surface of the pick-shaped cutting tooth at any time includes:

[0058] A spatial interpolation weighting function is established based on the geometric characteristics of the digitally represented surface, wherein the spatial interpolation weighting function considers the geodesic distance between any point on the surface and each sensor.

[0059] Based on the spatial distribution characteristics of each sensor signal in the multi-dimensional load signal, the parameter configuration of the spatial interpolation weighting function is dynamically optimized;

[0060] The sensor signal is spatially interpolated using an optimized spatial interpolation weight function to obtain the load estimate at any point on the digital representation surface. The spatial interpolation is calculated using the following formula:

[0061] ;

[0062] In the formula, Representing coordinates on the surface At any moment The estimated load value, The summation symbol is used to represent the summation symbol. It depends on geodetic distance The The weighting function for each sensor, It is the first Each sensor at time The measured value.

[0063] In this embodiment, the spatial interpolation weighting function is a mathematical function constructed based on the geometric characteristics of the digitally represented surface. Its function is to determine the contribution of each sensor to the load estimate at any point on the digitally represented surface. The value of this function changes with the geodesic distance between any point on the surface and each sensor. The geodesic distance refers to the shortest path length along the surface between any two points on the digitally represented surface, not the straight-line distance between the two points. This distance can truly reflect the spatial positional relationship between points on the surface.

[0064] In the embodiments of this application, the spatial distribution characteristics of the sensing signal refer to the distribution patterns of signal intensity, change trends, etc., of the signals output by different sensors in the multi-dimensional load signal at the corresponding spatial positions on the digital characterization surface. These characteristics can reflect the initial distribution of the load on the cutting tooth surface.

[0065] In this embodiment, parameter configuration dynamic optimization refers to the process of adjusting and optimizing the parameters in the spatial interpolation weighting function in real time based on the spatial distribution characteristics of the sensing signal. The purpose is to make the weighting function more consistent with the actual load distribution and improve the accuracy of the load estimate. Spatial interpolation is a method of calculating and extrapolating the sensing signals collected by discrete sensors using the optimized spatial interpolation weighting function to obtain the load value at any location on the surface where no sensor is placed.

[0066] In some embodiments, the spatial interpolation weighting function, which considers the geodesic distance between any point on the surface and each sensor, further includes:

[0067] Based on the changes in rock mechanical properties during rock breaking, the geological influence factor in the spatial interpolation weight function is updated in real time. The spatial interpolation weight function is expressed by the following formula:

[0068] ;

[0069] In the formula, It depends on geodetic distance The The weighting function for each sensor, The interpolation smoothing coefficient is... For relevant distance parameters, For geological influence factor functions, This indicates the current rock mechanical properties parameters.

[0070] In this embodiment, the geological influence factor is a correction parameter in the spatial interpolation weighting function. The value of this parameter is updated in real time according to the changes in rock mechanical properties during the rock breaking process, and is used to compensate for the influence of different rock properties on the load distribution. The rock mechanical property parameter is an indicator describing the physical and mechanical properties of rock. In this embodiment, the rock compressive strength is mainly used as this parameter. Its value is obtained by inversion of high-frequency vibration signals collected by vibration sensors, which can reflect the rock hardness of the current rock breaking object.

[0071] In this embodiment, the interpolation smoothing coefficient is a fixed parameter in the spatial interpolation weighting function, used to control the smoothness of the spatial interpolation result, avoid drastic changes in the load estimate due to fluctuations in discrete sensing signals, and ensure the continuity of the load distribution.

[0072] In this embodiment, the relevant distance parameter is a parameter in the spatial interpolation weighting function, and its value is equal to the average spacing between the sensors in the sensor array. It is used to define the range of influence of the sensor on the load estimation values ​​of different locations on the curved surface.

[0073] In this embodiment, the operation of establishing a spatial interpolation weighting function based on the geometric properties of the digitally represented surface is performed:

[0074] First, the geometric characteristics of the digitally represented surface are analyzed, including the curvature variation and the smoothness of different regions, to clarify the method for calculating the geodesic distance between any point on the surface and each sensor. In this embodiment, Dijkstra's algorithm is used to calculate the geodesic distance, which can efficiently solve for the shortest path between two points on the surface.

[0075] Next, the basic form of the spatial interpolation weighting function was determined, with the Gaussian function chosen as the core framework. An initial spatial interpolation weighting function was constructed by combining it with geodesic distance. Simultaneously, initial values ​​for the interpolation smoothing coefficient and relevant distance parameters were set, with the interpolation smoothing coefficient set to 0.9. This value was determined based on the point cloud density of the digitally represented surface (…). The determination of the sensor arrangement density can ensure interpolation accuracy while avoiding excessive smoothing; the relevant distance parameter is set to 5mm, which is equal to the average spacing of the sensor array in step S1 (the actual physical spacing between the sensors is 5mm), and is used to reasonably define the influence range of the sensors.

[0076] For example, for any point with coordinates (17mm, 6mm, 3mm) on the digital representation surface, the geodesic distance between the point and the eight stress sensors is calculated using the Dijkstra algorithm. The geodesic distance between the point and the sixth sensor (coordinates 17.5mm, 8mm, 3mm) is 2.1mm, and the geodesic distance between the point and the second sensor (coordinates 15mm, 5mm, 3mm) is 2.8mm. These geodesic distances will serve as key inputs to the spatial interpolation weighting function.

[0077] In this embodiment of the application, after the initial establishment of the spatial interpolation weight function is completed, the step of dynamically optimizing the parameter configuration based on the spatial distribution characteristics of each sensor signal in the multi-dimensional load signal is entered.

[0078] First, extract the sensing signal values ​​of each sensor at the same time from the multi-dimensional load signal collected in step S1. For example, at time t=100ms, the measured values ​​of the 8 stress sensors are 90kN, 100kN, 85kN, 80kN, 95kN, 105kN, 88kN, and 78kN, respectively.

[0079] Next, the spatial distribution characteristics of these sensor signals are analyzed, and the variance of each sensor signal is calculated. The variance of the first sensor signal is 100 kN², and the variance of the second sensor signal is 50 kN². The larger the variance, the more severe the load fluctuation at the sensor's location. The interpolation smoothing coefficient is dynamically optimized based on the signal fluctuation. For sensors with large signal variance, their corresponding interpolation smoothing coefficient is increased by 10% (e.g., the interpolation smoothing coefficient for the first sensor is adjusted from 0.9 to 0.99), reducing the influence weight of the sensor signal on the load estimate of surrounding points and avoiding distortion of the estimate due to fluctuating signals. For sensors with small signal variance, the interpolation smoothing coefficient is kept unchanged to ensure that their signal can stably contribute to the load estimate.

[0080] Meanwhile, the relevant distance parameters are adjusted according to the overall uniformity of the sensor signal distribution. If the signal distribution is relatively concentrated, the relevant distance parameters are reduced by 5% (e.g., from 5mm to 4.75mm) to reduce the sensor's influence range and improve the accuracy of local load estimation. If the signal distribution is uniform, the relevant distance parameters are kept unchanged.

[0081] In this embodiment of the application, after the parameter configuration optimization is completed, the geological influence factor in the spatial interpolation weight function also needs to be updated in real time according to the changes in rock mechanical properties during the rock breaking process.

[0082] First, the rock mechanical property parameters (rock compressive strength) are inverted using the high-frequency vibration signal collected by the vibration sensor in step S1. The inversion relationship is that the rock compressive strength is equal to 5 times the dominant vibration frequency. For example, when the dominant frequency of the high-frequency vibration signal collected by the vibration sensor is 16kHz, the rock compressive strength is calculated to be 80MPa.

[0083] Next, a geological influence factor function is constructed. This function is expressed as 1 minus 0.01 multiplied by the rock compressive strength. Substituting the rock compressive strength of 80 MPa into the function yields a geological influence factor of 0.2. The geological influence factor is then substituted into the spatial interpolation weighting function formula to modify the weighting function. The modified weighting function can compensate for the influence of hard rock (high compressive strength) or soft rock (low compressive strength) on load distribution. For example, in hard rock conditions, the geological influence factor is smaller, which reduces the absolute value of each sensor weight, making the load estimate more closely reflect the actual situation of concentrated but fluctuating loads in hard rock.

[0084] In this embodiment of the application, after optimizing and correcting the spatial interpolation weighting function, the function is used to perform spatial interpolation on the sensing signal to obtain the load estimate.

[0085] First, determine the target point where the load estimate needs to be calculated, which is any point on the digital representation surface, such as the point with coordinates (17mm, 6mm, 3mm) and the corresponding time t=100ms.

[0086] Then, based on the optimized and corrected spatial interpolation weight function, the weight values ​​between the target point and each sensor are calculated. For example, the weight of the point with the 6th sensor is 0.55, the weight with the 2nd sensor is 0.25, and the weights with other sensors are 0.02, 0.03, 0.01, 0.08, 0.04, and 0.02, respectively. The sum of all weight values ​​is 1, which meets the requirement of reasonable weight allocation.

[0087] Finally, the measured values ​​of each sensor at time t=100ms are multiplied by their corresponding weight values, and then all products are summed. Substituting these products into the spatial interpolation formula (the estimated load at a point on the surface at a certain time is equal to the sum of the products of the weight functions of all sensors and the corresponding sensor's measured values ​​at that time), the estimated load at that point at t=100ms is calculated. This enables the generation of load estimates for any point on a digitally represented surface at any time.

[0088] In this embodiment, load estimates are generated by processing multi-dimensional load signals based on a digitally characterized surface. This solves the problems of abstract data processing, lack of correlation with the precise physical geometry of the cutting tooth, and the inability to obtain only point signals or resultant force signals, thus failing to achieve continuous load distribution analysis on the cutting tooth surface. The load estimates generated in this step can cover any position on the cutting tooth surface and are dynamically adjusted in conjunction with rock mechanical properties, making the load analysis results more consistent with actual rock breaking conditions.

[0089] S4. Map the estimated load values ​​to the digital representation surface to form a continuous spatiotemporal load distribution field.

[0090] In some embodiments, mapping the load estimate to the digital representation surface to form a continuous spatiotemporal load distribution field includes:

[0091] The load estimates calculated at different times are arranged in time series to form a time series set of load values;

[0092] Assign each load value in the time series set to the corresponding surface space coordinates;

[0093] The load values ​​are converted into color depth on the surface to generate a visualized continuous spatiotemporal load distribution field.

[0094] In this embodiment, the time series set of load values ​​is a dataset formed by organizing and arranging the estimated load values ​​of any point on the surface of the pick-shaped cutting tooth calculated at different times in chronological order. This set can reflect the law of change of the load estimate over time. The surface space coordinates refer to the specific coordinate values ​​of each point on the digitally represented surface in three-dimensional space. These coordinate values ​​are consistent with the geometric parameters of the digitally represented surface established in step S2 and are used to determine the specific position of the load value on the surface.

[0095] In this embodiment, color depth is a visual indicator used to intuitively reflect the magnitude of the load value. By corresponding different ranges of load values ​​with specific shades of color, the load distribution can be directly observed and distinguished visually. The visualized continuous spatiotemporal load distribution field is a visualization model that combines the time series set of load values ​​with the corresponding curved surface spatial coordinates and is formed by color depth conversion. It can dynamically display the continuous changes of the load on the cutting tooth surface in the spatial and temporal dimensions.

[0096] In this embodiment, the operation of arranging the load estimates calculated at different times into a time series set of load values ​​is performed. The time interval of the time series is determined to be consistent with the unified timestamp precision of the multi-dimensional load signals in step S1, which is 1ms, to ensure the continuity and consistency of the time dimension. From the load estimates generated in step S3, the load estimates of all target points (including sensor placement points and interpolation points without sensor placement, selecting a total of 1000 uniformly distributed target points to cover the entire interaction interface) on the digital representation surface at each time point are extracted. For example, at time t=100ms, the load estimate of the point with coordinates (17mm, 6mm, 3mm) is extracted as 101.27kN, and the load estimate of the point with coordinates (18mm, 6mm, 3mm) is extracted as 103.5kN, etc.; at time t=101ms, the load estimate of the corresponding coordinate point is extracted, such as the load estimate of the point with coordinates (17mm, 6mm, 3mm) as 102.1kN, etc. The load estimates of 1,000 target points at each time point are arranged sequentially according to the time order from 0ms to 1,000ms, forming a load value time series set containing 1,000 time points and 1,000 load values ​​at each time point. This set is stored in tabular form, with each row corresponding to a time point and each column corresponding to the coordinates of a target point and the load estimate of that coordinate point at that time point.

[0097] In this embodiment, after constructing the time series set of load values, the next step is to assign corresponding surface space coordinates to each load value in the time series set. First, the coordinate data of the digitally represented surface established in step S2 is retrieved. This data contains the three-dimensional coordinates (X-axis, Y-axis, Z-axis) of all points on the surface and is completely consistent with the coordinate system used in step S3 when calculating the load estimate. For each load value in the time series set, the surface space coordinates corresponding to the target point are found in the coordinate data of the digitally represented surface based on its corresponding target point identifier. For example, for the load estimate of 101.27 kN at t=100 ms in the time series set, the surface space coordinates of the corresponding target point are found to be (17 mm, 6 mm, 3 mm). The load value is then bound to these coordinates, forming a correspondence of "coordinates (17 mm, 6 mm, 3 mm) - time t=100 ms - load 101.27 kN". In the same way, each load value at all times in the time series set is bound to the corresponding surface space coordinates to ensure that each load value can find a unique corresponding spatial position on the digital representation surface, thus avoiding the situation where the load value and the spatial position are misaligned.

[0098] In this embodiment of the application, after binding the load value with the surface space coordinates, the operation of converting the load value magnitude into the color depth on the surface is performed to generate a visualized continuous spatiotemporal load distribution field.

[0099] First, the correspondence between load values ​​and color depths is determined. Based on the calculation range of the estimated load value (0-150kN) in step S3, the load values ​​are divided into four intervals: 0-50kN, 50-80kN, 80-100kN, and 100-150kN. A corresponding color and color depth are assigned to each interval. Specifically, 0-50kN corresponds to light blue (color depth value 0.2), 50-80kN corresponds to green (color depth value 0.4), 80-100kN corresponds to yellow (color depth value 0.6), and 100-150kN corresponds to red (color depth value 0.8-1.0, with higher load values ​​resulting in higher color depth). This correspondence rule is based on the sensitivity of human vision to changes in color depth, ensuring clear distinction between different load intervals.

[0100] Next, ParaView visualization software was used to import the time series set of load values ​​bound to the surface spatial coordinates. The digital representation surface model established in step S2 was then loaded into the software. Using the software's color mapping function, each load value was converted into a corresponding color depth according to a preset rule, and this color depth was assigned to the corresponding spatial coordinate point on the digital representation surface. For example, the load value of 101.27kN at coordinates (17mm, 6mm, 3mm) at t=100ms was converted to red with a color depth of 0.82, and the software displayed the corresponding red at that coordinate point; the load value of 45kN at coordinates (12mm, 5mm, 3mm) at t=100ms was converted to light blue with a color depth of 0.2, and the software displayed the corresponding light blue at that coordinate point.

[0101] Finally, through the software's animation generation function, the load color distribution at different times is played continuously in a time sequence to form a dynamic and visualized continuous spatiotemporal load distribution field. This distribution field can intuitively show the distribution of the load on the cutting tooth surface at different times and in different spatial locations. For example, the tooth tip area is always predominantly red (high load) during rock breaking, and the red area slowly moves towards the center of the tooth surface over time.

[0102] In this embodiment of the application, by mapping the load estimate to a digital characterization surface to form a continuous spatiotemporal load distribution field, the problem of not being able to intuitively and continuously display the load distribution on the cutting tooth surface and its evolution over time is solved.

[0103] S5. Extract characteristic parameters representing rock breaking efficiency and cutting tooth loading state from the continuous spatiotemporal load distribution field.

[0104] In this embodiment, the characteristic parameter characterizing rock-breaking efficiency is a parameter extracted from the continuous spatiotemporal load distribution field that can quantify the rock-breaking efficiency of the pick-type cutting tooth during the rock-breaking process. Specifically, in this embodiment, it is the area change rate of the high-load region per unit time. The characteristic parameter characterizing the loading state of the cutting tooth is a parameter extracted from the continuous spatiotemporal load distribution field that can reflect the load condition and its own state of the pick-type cutting tooth during the rock-breaking process. Specifically, in this embodiment, it is the spatial location of the maximum load value and the trajectory of the maximum load value.

[0105] In some embodiments, extracting characteristic parameters representing rock-breaking efficiency and the loading state of the cutting teeth from the continuous spatiotemporal load distribution field includes:

[0106] Extract the spatial location of the maximum load value and the movement trajectory of the maximum load value in the continuous spatiotemporal load distribution field as characteristic parameters of the cutter wear state;

[0107] The rate of change of the area of ​​the high-load region in the continuous spatiotemporal load distribution field per unit time is used as a characteristic parameter of rock breaking efficiency.

[0108] In this embodiment, the spatial location of the maximum load value refers to the three-dimensional spatial coordinates of the point on the digital representation surface where the load value on the surface of the pick-shaped cutting tooth is the largest at each moment in the continuous spatiotemporal load distribution field. This location can reflect the area where the load on the cutting tooth is most concentrated. The movement trajectory of the maximum load value refers to the path formed by connecting the spatial locations of the maximum load values ​​at different moments in the continuous spatiotemporal load distribution field in chronological order. This path can reflect the change of the area where the load on the cutting tooth is most concentrated over time. The wear state of the cutting tooth refers to the degree of wear on the tooth tip and tooth surface caused by friction and impact with the rock during long-term rock breaking. The movement trajectory of the maximum load value can indirectly reflect this state. If the trajectory deviates significantly, it indicates that the cutting tooth may have severe wear.

[0109] In this embodiment, the high-load region refers to the region in a continuous spatiotemporal load distribution field where the load value reaches or exceeds a preset threshold. In this embodiment, the preset threshold is set to 80kN. This threshold is determined based on the design bearing capacity of the pick-type cutting tooth and the effective rock-breaking load range under common rock-breaking conditions. The area change rate of the high-load region per unit time refers to the ratio of the area difference of the high-load region between two adjacent moments in a continuous spatiotemporal load distribution field to the time interval. This ratio can directly reflect the change in the effective rock-breaking area of ​​the cutting tooth per unit time, thereby reflecting the rock-breaking efficiency.

[0110] In this embodiment, the spatial location and trajectory of the maximum load value in the continuous spatiotemporal load distribution field are first extracted. The extraction time range is determined to be consistent with the time range of the continuous spatiotemporal load distribution field in step S4, i.e., from 0ms to 1000ms, to ensure data integrity. The continuous spatiotemporal load distribution field data generated in step S4 (containing the load values ​​and corresponding spatial coordinates of 1000 target points at each time step) is imported into MATLAB software. Using a pre-written extreme value extraction algorithm, the 1000 load values ​​at each time step are iterated and compared to find the maximum load value and its corresponding spatial coordinates at each time step. For example, at t=100ms, the load values ​​of all target points are iterated, and the maximum load value is determined to be 105kN, with corresponding spatial coordinates of (17.5mm, 8mm, 3mm); at t=200ms, the maximum load value is determined to be 108kN, with corresponding spatial coordinates of (18.5mm, 8mm, 3mm); at t=300ms, the maximum load value is determined to be 110kN, with corresponding spatial coordinates of (19.5mm, 8mm, 3mm). The spatial coordinates of the maximum load value at each moment are recorded sequentially according to time order, forming a coordinate sequence. Then, using MATLAB's plotting function, this coordinate sequence is connected on a 3D model of the digitally represented surface to generate the trajectory of the maximum load value. In this embodiment, the trajectory shows a slow offset trend along the horizontal direction of the tooth surface, with the offset direction consistent with the cutting direction of the cutting tooth.

[0111] In this embodiment, after extracting the relevant parameters of the maximum load value, the operation of statistically analyzing the area change rate of high-load regions in the continuous spatiotemporal load distribution field per unit time is performed. First, the criteria for determining high-load regions are clarified. Regions with load values ​​≥ 80 kN are defined as high-load regions. This standard is based on verification through numerous rock-breaking experiments. When the load value reaches 80 kN, the cutting teeth can effectively break rocks of common hardness (such as rocks with compressive strength of 50-100 MPa). Regions with values ​​below this are poorly broken and are not included in the statistics of effective broken regions. Using a region area calculation algorithm in MATLAB software, the area of ​​high-load regions at each time point is calculated. This algorithm identifies target points with load values ​​≥ 80 kN at each time point and calculates the area of ​​the regions they constitute based on the spatial coordinates of these target points on the digital representation surface.

[0112] For example, at t=100ms, 150 target points with load values ​​≥80kN were identified, and the area of ​​the high-load region was calculated based on the coordinates of these points. At t=200ms, 200 target points with load values ​​≥80kN were identified, and the area of ​​the high-load region was calculated. At t=300ms, 220 target points with load values ​​≥80kN were identified, and the area of ​​the high-load region was calculated. Determine the time interval Δt, which is consistent with the timestamp accuracy of the continuous spatiotemporal load distribution field, i.e., 100ms (0.1s). Calculate the area change of the high-load region at adjacent times, such as the area change from t=100ms to t=200ms. The change in area from t=200ms to t=300ms Then, based on the formula for calculating the rate of change of area (rate of change of area = change in area / time interval), the rate of change of area from t=100ms to t=200ms is calculated. Rate of change of area from t=200ms to t=300ms Finally, the area change rates over different time periods were compiled to form a set of characteristic parameters that reflect the changing trend of rock breaking efficiency. This set can be directly used for subsequent correlation analysis with equipment parameters.

[0113] In this embodiment, by extracting characteristic parameters from the continuous spatiotemporal load distribution field, the problem of being unable to directly quantify rock-breaking efficiency and the loading state of the cutting teeth, and having to rely on empirical judgment or indirect indicators for estimation, is solved. The area change rate, which characterizes rock-breaking efficiency, can directly reflect the change in the effective breaking area per unit time, avoiding the efficiency judgment bias caused by relying on indirect indicators such as cutting speed; the maximum load movement trajectory, which characterizes the loading state of the cutting teeth, can provide early warning of cutting tooth wear, avoiding damage to the cutting teeth or a sudden drop in rock-breaking efficiency due to undetected wear. These characteristic parameters provide accurate quantitative basis for subsequent equipment parameter optimization, promoting the transformation of rock-breaking equipment control from experience-driven to data-driven.

[0114] S6. Associate and map the feature parameters with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters.

[0115] In this embodiment, the equipment parameters of the mining cutting equipment refer to the key operating parameters that are adjustable during rock breaking operations and affect the rock breaking efficiency and the stress state of the cutting teeth. In this embodiment, these parameters specifically include the cutting speed and the cutting tooth installation angle. The correlation mapping refers to the process of establishing a correspondence between the characteristic parameters representing the rock breaking efficiency and the loading state of the cutting teeth and the equipment parameters of the mining cutting equipment. Through this process, the optimization direction and adjustment range of the equipment parameters can be determined based on the changes in the characteristic parameters. The guidance information refers to the specific instructions generated based on the correlation mapping results between the characteristic parameters and the equipment parameters, used to adjust the working parameters of the mining cutting equipment. In this embodiment, these instructions specifically include the cutting speed adjustment amount and the cutting tooth installation angle adjustment amount.

[0116] In some embodiments, the step of associating and mapping the feature parameters with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters includes:

[0117] Establish a first fuzzy inference rule base with characteristic parameters representing rock breaking efficiency as input and recommended cutting speed as output;

[0118] Establish a second fuzzy inference rule base with characteristic parameters representing the loading state of the cutting tooth as input and suggested cutting tooth installation angle as output;

[0119] Based on the output results of the first fuzzy inference rule base and the second fuzzy inference rule base, comprehensive guidance information including the cutting speed adjustment amount and the cutting tooth installation angle adjustment amount is generated.

[0120] In this embodiment, the first fuzzy inference rule base refers to a set of inference rules constructed through fuzzy logic, using the characteristic parameter (the rate of change of area of ​​the high-load region per unit time) representing rock-breaking efficiency as the input variable and the recommended cutting speed as the output variable. This set is used to determine the appropriate cutting speed based on the rock-breaking efficiency. The recommended cutting speed refers to the cutting speed value output by the first fuzzy inference rule base based on the input rock-breaking efficiency characteristic parameter, which enables the mining cutting equipment to maintain a relatively good rock-breaking efficiency under the current rock strata conditions.

[0121] In this embodiment, the second fuzzy inference rule base refers to a set of inference rules constructed through fuzzy logic, using the characteristic parameters (the movement trajectory of the maximum load value) representing the loading state of the cutting tooth as input variables and the suggested cutting tooth installation angle as output variables. This set of rules is used to determine the appropriate cutting tooth installation angle based on the loading state of the cutting tooth. The suggested cutting tooth installation angle refers to the installation angle value output by the second fuzzy inference rule base based on the input characteristic parameters of the cutting tooth loading state, which enables the pick-type cutting tooth to be subjected to more uniform force and reduce wear during rock breaking.

[0122] In this embodiment, the cutting speed adjustment amount refers to the difference between the recommended cutting speed and the current cutting speed of the mining cutting equipment. If the difference is positive, it means that the cutting speed needs to be increased; if the difference is negative, it means that the cutting speed needs to be decreased. The cutting tooth installation angle adjustment amount refers to the difference between the suggested cutting tooth installation angle and the current installation angle of the pick-type cutting tooth. If the difference is positive, it means that the installation angle needs to be increased; if the difference is negative, it means that the installation angle needs to be decreased.

[0123] In some embodiments, the guidance information is input to the control system of the mining cutting equipment, and the control system dynamically adjusts the working parameters of the cutting head in the current rock stratum according to the guidance information to achieve adaptive cutting.

[0124] In this embodiment, the control system of the mining cutting equipment refers to a system with a programmable logic controller (PLC) as its core, used to receive guidance information and control the mining cutting equipment to perform parameter adjustment operations, and has real-time data processing and equipment control capabilities; adaptive cutting refers to the control system of the mining cutting equipment dynamically adjusting the working parameters of the cutting head according to the guidance information, so that the equipment can automatically adapt to the optimal operating parameters of the rock breaking operation mode according to the current rock strata conditions and the state of the cutting teeth.

[0125] In this embodiment, the operation of establishing a first fuzzy inference rule base is performed. The input and output variables of the first fuzzy inference rule base are defined. The input variable is the "area change rate of the high-load region per unit time" (denoted as v) extracted in step S5, and the output variable is the "recommended truncation speed" (denoted as v). n Based on extensive rock-breaking experimental data, the fuzzy subset partitioning of input and output variables was determined: the area change rate v was divided into three fuzzy subsets: "low," "medium," and "high," with corresponding numerical ranges of [missing information]. (Low), (middle), (High); Recommended cutting speed Divided into three fuzzy subsets: "low," "medium," and "high," with corresponding numerical ranges of respectively. (Low), (middle), (High). Inference rules are constructed based on fuzzy subsets. Rule 1 states that "if the area change rate v is low, then the cutting speed is recommended." "Low"; Rule 2 is "If the area change rate v is medium, then the recommended cutting speed is..." "For medium"; Rule 3 is "If the area change rate v is high, then the cutting speed is recommended". "High". The triangular membership function is used to fuzzify the input and output variables, for example, for the rate of change of area. (Belonging to the "medium" fuzzy subset), its membership degree to the "medium" subset is calculated as 1 using the membership function, and its membership degree to the "low" and "high" subsets is 0; then, the rules are reasoned using a fuzzy inference algorithm (such as the Mamdani algorithm), and finally, the centroid method is used to defuzzify the data to obtain the specific recommended cut-off speed value. For example, when the area change rate calculated in step S5 is input... At that time, after fuzzy inference and defuzzification, the recommended truncation speed is output. .

[0126] In this embodiment, after establishing the first fuzzy inference rule base, the operation of establishing the second fuzzy inference rule base is performed. The input and output variables of the second fuzzy inference rule base are determined. The input variable is the "trajectory offset of the maximum load value" extracted in step S5 (denoted as Δs, i.e., the distance between the maximum load position and the initial position at different times), and the output variable is the "suggested cutting tooth installation angle" (denoted as θ). n Based on the cutter wear test data, the input and output variables were divided into fuzzy subsets: the trajectory offset Δs was divided into three fuzzy subsets: "small," "medium," and "large," with corresponding numerical ranges of Δs < 1 mm (small), 1 mm ≤ Δs ≤ 2 mm (medium), and Δs > 2 mm (large), respectively; the suggested cutter installation angle θ was also determined. n Divided into three fuzzy subsets: "small," "medium," and "large," with corresponding numerical ranges of respectively. (Small), (middle), (Large). Construct inference rules, rule 1 is "If the trajectory offset Δs is small, then it is recommended to install at a certain angle". "If the trajectory offset Δs is in the middle, then the installation angle is recommended." Rule 2 is "If the trajectory offset Δs is in the middle, then the installation angle is recommended." "For the middle"; Rule 3 is "If the trajectory offset Δs is large, then it is recommended to install at an angle". "For large". Similarly, the triangular membership function is used for fuzzification. For example, the trajectory offset Δs = 2mm calculated in step S5 (belonging to the "medium" fuzzy subset) has a membership degree of 1 to the "medium" subset. After inference using the Mamdani algorithm, the suggested cutting tooth installation angle is obtained by defuzzifying using the centroid method. For example, when Δs = 2mm, the suggested installation angle is output. .

[0127] In this embodiment, after establishing two fuzzy inference rule bases, the operation of generating comprehensive guidance information is performed. The current equipment parameters of the mining cutting equipment are obtained, assuming the current cutting speed... Current cutting tooth installation angle Calculate the slicing speed adjustment based on the recommended slicing speed output from the first fuzzy inference rule base. Adjustment amount This means that the cutting speed needs to be increased. Calculate the adjustment amount of the cutting tooth installation angle, based on the suggested installation angle output from the second fuzzy inference rule base. Adjustment amount This means that the installation angle of the cutting teeth needs to be increased. Adjust the cutting speed by (+0.5 m / min) and the cutting tooth installation angle by ( This information is integrated to form comprehensive guidance information containing specific adjustment values ​​and directions. The format of the guidance information is: "Cutting speed: currently 2.5m / min, recommended adjustment to 3.0m / min, adjustment amount +0.5m / min; Cutting tooth installation angle: currently..." It is recommended to adjust to Adjustment amount ".

[0128] In this embodiment, to achieve adaptive cutting, it is also necessary to input guidance information into the control system and adjust equipment parameters. A PLC is selected as the core of the control system for the mining cutting equipment. The generated comprehensive guidance information is transmitted to the PLC via an industrial Ethernet network. After receiving the guidance information, the PLC first parses the information, extracting the cutting speed adjustment and the cutting tooth installation angle adjustment. For the cutting speed adjustment, the PLC sends a control command to the frequency converter of the cutting motor (such as a Siemens G120) to adjust the output frequency of the frequency converter from the current 50Hz (corresponding to 2.5m / min) to 55Hz (corresponding to 3.0m / min), thereby controlling the cutting motor speed to increase and bring the cutting speed to the recommended value. For the cutting tooth installation angle adjustment, the PLC sends a control command to the hydraulic adjustment mechanism to control the hydraulic cylinder to extend and retract, pushing the cutting tooth support to rotate. The angle sensor provides real-time feedback on the cutting tooth installation angle. When the angle reaches the recommended value... At this point, the PLC sends a stop command to complete the angle adjustment. After the adjustment is completed, the control system collects the new signals from the sensor array in step S1 in real time, repeats steps S2-S6, forming a closed loop of "data acquisition-analysis-adjustment-reacquisition" to achieve adaptive cutting.

[0129] In this embodiment, by associating and mapping feature parameters with equipment parameters and generating guidance information, the problem of equipment parameter adjustment relying on human experience and being unable to be dynamically optimized based on real-time rock breaking conditions is solved. The establishment of the first and second fuzzy inference rule bases transforms the association between feature parameters and equipment parameters from "experience-based judgment" to "data-driven," avoiding the subjectivity and lag of manual adjustments. The comprehensive guidance information provides specific adjustment values, making equipment parameter optimization operable. If adaptive cutting is further implemented, the problems of slow response and inability to adapt to real-time changes in rock strata can be solved, ensuring that the cutting equipment is always in the optimal state of efficient rock breaking and low cutter wear, thereby improving the stability and economy of rock breaking operations.

[0130] like Figure 2 The diagram shown is a functional block diagram of a rock-breaking load spatiotemporal evolution analysis system for pick-type cutting teeth provided in an embodiment of this application.

[0131] The pick-type cutting tooth rock-breaking load spatiotemporal evolution analysis system 100 described in this application can be installed in an electronic device. Depending on the functions implemented, the pick-type cutting tooth rock-breaking load spatiotemporal evolution analysis system 100 may include a signal acquisition module 101, a surface modeling module 102, a load calculation module 103, a field construction module 104, a feature extraction module 105, and a parameter optimization module 106. The module described in this application can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0132] In this embodiment, the functions of each module / unit are as follows:

[0133] The signal acquisition module 101 is used to acquire the multi-dimensional load signal of the pick-shaped cutting tooth as it changes over time during the rock breaking process by means of a sensor array arranged on the pick-shaped cutting tooth.

[0134] The surface modeling module 102 is used to establish a digital characterization surface of the interaction interface between the pick-shaped cutting tooth and the rock based on the geometric shape of the pick-shaped cutting tooth and the spatial coordinates of the sensor array.

[0135] The load calculation module 103 is used to process the multi-dimensional load signal based on the digital characterization surface to generate a load estimate of any point on the surface of the pick-shaped cutting tooth at any time.

[0136] The field construction module 104 is used to map the load estimate to the digital representation surface to form a continuous spatiotemporal load distribution field.

[0137] Feature extraction module 105 is used to extract feature parameters characterizing rock breaking efficiency and cutting tooth loading state from the continuous spatiotemporal load distribution field.

[0138] The parameter optimization module 106 is used to associate and map the feature parameters with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters.

[0139] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0140] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0142] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application.

[0143] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for analyzing the spatiotemporal evolution of rock-breaking load on pick-type cutting teeth, characterized in that, The method includes: A sensor array arranged on the pick-shaped cutting teeth is used to collect multi-dimensional load signals of the pick-shaped cutting teeth as they change over time during the rock breaking process. Based on the geometric shape of the pick-shaped cutting tooth and the spatial coordinates of the sensor array, a digital characterization surface for the interaction interface between the pick-shaped cutting tooth and the rock is established, including: acquiring geometric shape point cloud data of the pick-shaped cutting tooth surface through three-dimensional laser scanning; determining the precise spatial coordinates of the sensors in the geometric shape point cloud data according to the actual embedding positions of each sensor in the sensor array; and reconstructing the geometric shape point cloud data containing the sensor coordinates to generate a digital characterization surface that matches the cutting tooth surface. Based on the digitally represented surface, the multi-dimensional load signal is processed to generate an estimated load value at any point on the surface of the pick-shaped cutting tooth at any time, including: A spatial interpolation weighting function is established based on the geometric characteristics of the digitally represented surface, wherein the spatial interpolation weighting function considers the geodesic distance between any point on the surface and each sensor; based on the spatial distribution characteristics of each sensor signal in the multi-dimensional load signal, the parameter configuration of the spatial interpolation weighting function is dynamically optimized; the optimized spatial interpolation weighting function is used to perform spatial interpolation on the sensor signals to obtain the load estimate at any point on the digitally represented surface, wherein the spatial interpolation is calculated using the following formula: In the formula, F(u,v,t) represents the estimated load value of the coordinates (u,v) on the surface at time t, Σ|*| represents the summation sign, and w i (d i It depends on the geodetic distance d. i The weighting function for the i-th sensor, f i (t) is the measurement value of the i-th sensor at time t; The estimated load values ​​are mapped onto the digital representation surface to form a continuous spatiotemporal load distribution field. From the continuous spatiotemporal load distribution field, characteristic parameters representing rock breaking efficiency and the loading state of the cutting teeth are extracted; The feature parameters are associated and mapped with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters.

2. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The method involves acquiring multi-dimensional load signals of the pick-shaped cutting teeth over time through a sensor array arranged on the pick-shaped cutting teeth, including: The sensor array includes a stress sensor and a vibration sensor, wherein the stress sensor detects the triaxial cutting force signal generated during the rock breaking process in real time, and the vibration sensor collects the high-frequency vibration signal caused by the rock breaking impact; The triaxial cutting force signal and the high-frequency vibration signal are time-domain synchronized to form a multi-dimensional load signal with a unified timestamp.

3. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The spatial interpolation weighting function considers the geodesic distance between any point on the surface and each sensor, and also includes: Based on the changes in rock mechanical properties during rock breaking, the geological influence factor in the spatial interpolation weight function is updated in real time. The spatial interpolation weight function is expressed by the following formula: In the formula, w i (d i It depends on the geodetic distance d. i The weight function of the i-th sensor, α is the interpolation smoothing coefficient, δ is the correlation distance parameter, γ(G) is the geological influence factor function, and G represents the current rock mechanical property parameter.

4. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The step of mapping the load estimate to the digital representation surface to form a continuous spatiotemporal load distribution field includes: The load estimates calculated at different times are arranged in time series to form a time series set of load values; Assign each load value in the time series set to the corresponding surface space coordinates; The load values ​​are converted into color depth on the surface to generate a visualized continuous spatiotemporal load distribution field.

5. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The extraction of characteristic parameters representing rock-breaking efficiency and the loading state of the cutting teeth from the continuous spatiotemporal load distribution field includes: Extract the spatial location of the maximum load value and the movement trajectory of the maximum load value in the continuous spatiotemporal load distribution field as characteristic parameters of the cutter wear state; The rate of change of the area of ​​the high-load region in the continuous spatiotemporal load distribution field per unit time is used as a characteristic parameter of rock breaking efficiency.

6. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The step of associating and mapping the feature parameters with the equipment parameters of the mining cutting equipment to generate guidance information for optimizing the equipment parameters includes: Establish a first fuzzy inference rule base with characteristic parameters representing rock breaking efficiency as input and recommended cutting speed as output; Establish a second fuzzy inference rule base with characteristic parameters representing the loading state of the cutting tooth as input and suggested cutting tooth installation angle as output; Based on the output results of the first fuzzy inference rule base and the second fuzzy inference rule base, comprehensive guidance information including the cutting speed adjustment amount and the cutting tooth installation angle adjustment amount is generated.

7. The spatiotemporal evolution analysis method for rock-breaking load of pick-type cutting teeth as described in claim 1, characterized in that, The method further includes: The guidance information is input into the control system of the mining cutting equipment. The control system dynamically adjusts the working parameters of the cutting head in the current rock stratum according to the guidance information to achieve adaptive cutting.

8. A spatiotemporal evolution analysis system for rock-breaking load of a pick-type cutting tooth, characterized in that, The system includes: The signal acquisition module is used to acquire the multi-dimensional load signal of the pick-shaped cutting tooth as it changes over time during the rock breaking process by using a sensor array arranged on the pick-shaped cutting tooth. The surface modeling module is used to establish a digital characterization surface of the interaction interface between the pick-shaped cutting tooth and the rock based on the geometric shape of the pick-shaped cutting tooth and the spatial coordinates of the sensor array. This includes: acquiring geometric shape point cloud data of the pick-shaped cutting tooth surface through three-dimensional laser scanning; determining the precise spatial coordinates of the sensors in the geometric shape point cloud data based on the actual embedding positions of each sensor in the sensor array; and reconstructing the geometric shape point cloud data containing the sensor coordinates to generate a digital characterization surface that matches the cutting tooth surface. The load calculation module is used to process the multi-dimensional load signal based on the digitally represented surface to generate a load estimate of any point on the surface of the pick-shaped cutting tooth at any time, including: A spatial interpolation weighting function is established based on the geometric characteristics of the digitally represented surface, wherein the spatial interpolation weighting function considers the geodesic distance between any point on the surface and each sensor; based on the spatial distribution characteristics of each sensor signal in the multi-dimensional load signal, the parameter configuration of the spatial interpolation weighting function is dynamically optimized; the optimized spatial interpolation weighting function is used to perform spatial interpolation on the sensor signals to obtain the load estimate at any point on the digitally represented surface, wherein the spatial interpolation is calculated using the following formula: In the formula, F(u,v,t) represents the estimated load value of the coordinates (u,v) on the surface at time t, Σ|*| represents the summation sign, and w i (d i It depends on the geodetic distance d. i The weighting function for the i-th sensor, f i (t) is the measurement value of the i-th sensor at time t; The field construction module is used to map the load estimate to the digital representation surface to form a continuous spatiotemporal load distribution field; The feature extraction module is used to extract feature parameters characterizing rock breaking efficiency and the loading state of the cutting teeth from the continuous spatiotemporal load distribution field. The parameter optimization module is used to associate and map the feature parameters with the equipment parameters of the mining cutting equipment, and generate guidance information for optimizing the equipment parameters.

Images