A method and system for statistically calculating the loading efficiency of a mine muck pile based on multi-dimensional data

Abstract

The present invention relates to the field of analysis of the working efficiency of mine exploitation, and in particular to a method and system for statistically calculating the shoveling efficiency of a mine muck pile based on multi-dimensional data. The method comprises the following steps: acquiring multi-dimensional real-time operation data of a scraper during the shoveling of a mine muck pile; obtaining multi-modal fusion feature information data of the scraper based on the multi-dimensional real-time operation data; obtaining operation cycle information data of the scraper according to the multi-modal fusion feature information data; constructing a statistical optimization model for the shoveling efficiency of the scraper in combination with the operation cycle information data; and obtaining a statistical result of the shoveling efficiency of the scraper according to the statistical optimization model for the shoveling efficiency, thereby completing the statistics of the shoveling efficiency of the mine muck pile. The present invention obtains multi-modal feature information based on the multi-dimensional operation data of the scraper, which helps to analyze the working state of the scraper to obtain the operation cycle, and further constructs a statistical optimization model for the shoveling efficiency, thus improving the accuracy of the statistics of the shoveling efficiency.

Description

Technical Field

[0001] The invention relates to the field of mining efficiency analysis, and in particular to a method and system for statistically analyzing mining blast pile shoveling efficiency based on multi-dimensional data. Background Art

[0002] At present, in the ore mining and transportation process of underground mines, loaders are the main mechanical equipment. With their excellent loading capacity and highly flexible maneuverability, loaders can efficiently dig ore from the blast pile and transport it to the designated location, which greatly promotes the improvement of the overall efficiency of mining. However, it is difficult to accurately calculate the loading efficiency of loaders during the blast pile loading operation in mines.

[0003] The traditional method of shoveling efficiency statistics mainly relies on manual calibration, which not only consumes a lot of human resources and increases unnecessary workload, but also due to the interference of human factors, the accuracy and reliability of the statistical results are often difficult to guarantee. The manual calibration process is cumbersome and time-consuming, and the statistical efficiency is low, making it difficult to provide accurate and effective data support for mine management decisions in a timely manner.

[0004] In view of this, improving the statistical method of shoveling efficiency of shovel loaders and realizing efficient and accurate automated statistics have become technical problems that need to be solved urgently in the field of mining. The present invention proposes a statistical method and system for mining blast pile loading efficiency based on multidimensional data; making full use of the precise measurement capability of sensors, it can monitor the various operating parameters of shovel loaders in real time and accurately during the loading process, thereby realizing high-precision statistics of loading efficiency; avoiding the tediousness of traditional manual calibration methods, and showing the ability of efficient real-time monitoring and optimization of operating processes in complex and changeable mining environments. Engineering personnel can more accurately grasp the working status of shovel loaders, and promptly discover and solve potential problems, thereby further improving the overall efficiency and safety of mining. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and system for calculating the efficiency of mine blasting pile shoveling based on multi-dimensional data.

[0006] To achieve the above object, in a first aspect, the present invention provides a method for statistically analyzing the loading efficiency of a mine muck pile based on multi-dimensional data. The method includes the following steps: obtaining multi-dimensional real-time operation data of a scraper during the loading of a mine muck pile; obtaining multi-modal fusion feature information data of the scraper based on the multi-dimensional real-time operation data; obtaining operation cycle information data of the scraper according to the multi-modal fusion feature information data; constructing a statistical optimization model for the loading efficiency of the scraper in combination with the operation cycle information data; and obtaining a statistical result of the loading efficiency of the scraper based on the statistical optimization model for the loading efficiency, thereby completing the statistical analysis of the loading efficiency of the mine muck pile. The present invention comprehensively and real-time captures multi-dimensional operation data of the scraper during the loading of the mine muck pile, and then obtains multi-modal feature information through data fusion, providing a data basis for accurately analyzing the working state of the scraper; obtaining the operation cycle of the scraper using the multi-modal feature information helps to deeply understand its operation rhythm and efficiency bottleneck; the statistical optimization model for the loading efficiency constructed in combination with the operation cycle information improves the accuracy of the loading efficiency evaluation and provides a scientific basis for optimizing the operation efficiency of the scraper; effectively promotes the intelligent management of the mine muck pile loading operation.

[0007] Optionally, the step of obtaining multi-dimensional real-time operation data of the scraper during the loading of the mine muck pile includes: configuring and installing a three-dimensional sensor on the scraper and setting the data sampling frequency of the three-dimensional sensor; based on the data sampling frequency, using the three-dimensional sensor to collect multi-dimensional real-time operation data of the scraper during the loading of the mine muck pile, where the multi-dimensional real-time operation data includes angles, angular velocities, and accelerations. The present invention accurately captures the dynamic changes of the scraper during the loading of the mine muck pile by configuring a three-dimensional sensor and reasonably setting the data sampling frequency; uses a high-precision three-dimensional sensor to collect multi-dimensional operation data of the scraper in real time, including angles, angular velocities, and accelerations, providing a rich and accurate data basis for subsequent data analysis and efficiency evaluation; ensures the real-time and comprehensiveness of the data, improves the fineness and accuracy of the monitoring of the loading operation process; better grasps the working state of the scraper through real-time data, discovers potential problems in a timely manner, and lays a solid foundation for statistically analyzing the loading efficiency, improving the operation safety, and the overall operation efficiency.

[0008] Optionally, obtaining the multi-modal fusion feature information data of the scraper based on the multi-dimensional real-time operation data includes: preprocessing the multi-dimensional real-time operation data to obtain the multi-dimensional real-time operation feature data of the scraper; performing data fusion on the multi-dimensional real-time operation feature data to obtain the multi-modal fusion feature information data of the scraper. By preprocessing the multi-dimensional real-time operation data of the scraper, the present invention effectively removes noise and outliers, and obtains the multi-dimensional real-time operation feature data reflecting the true working state of the scraper; and then completes data fusion to generate the multi-modal fusion feature information data, enhancing the representativeness and usability of the data, and providing comprehensive and accurate data support for subsequent analysis and modeling. The multi-modal fusion feature information data helps to more accurately understand the operation characteristics of the scraper, provides a scientific basis for the statistics of the loading efficiency, and provides strong support for the intelligent management decision-making of the mine loading operation.

[0009] Optionally, performing data fusion on the multi-dimensional real-time operation feature data to obtain the multi-modal fusion feature information data of the scraper includes:

[0010]

[0011] Wherein, is the comprehensive feature of multi-modal fusion, is the traversal count flag, is the dynamic weighting coefficient of the multi-dimensional real-time operation feature data, is the multi-dimensional real-time operation feature data. The present invention realizes the comprehensive processing of the multi-dimensional real-time operation feature data of the scraper to obtain the multi-modal fusion feature information data; introduces a dynamic weighting coefficient, which is flexibly adjusted according to the importance and real-time nature of different features, ensuring the accuracy and reliability of the fusion result; improves the efficiency and accuracy of data fusion, provides accurate data support for the optimization of the loading efficiency of the scraper; the multi-modal fusion feature information data helps to deeply explore the potential laws in the operation process of the scraper, and provides a scientific basis for the statistics of the loading efficiency of the mine operation.

[0012] Optionally, obtaining the operation cycle information data of the scraper based on the multi-modal fusion feature information data includes: obtaining a comprehensive feature vector based on the multi-modal fusion feature information data to identify the complete action cycle of the scraper; performing anomaly detection on the complete action cycle to obtain the operation cycle information data of the scraper. The present invention uses multi-modal fusion feature information data to obtain a comprehensive feature vector, accurately identifies the complete action cycle of the scraper, and provides support for in-depth analysis of the working state of the scraper; performs anomaly detection on the complete action cycle to timely discover possible faults or anomalies during the operation of the scraper, thereby obtaining operation cycle information data; enhances the controllability and safety of the scraper operation process, and provides a basis for subsequent maintenance management and efficiency statistics.

[0013] Optionally, obtaining a comprehensive feature vector based on the multi-modal fusion feature information data to identify the complete action cycle of the scraper includes:

[0014]

[0015] wherein, is the comprehensive feature vector, represents the amplitude of angle change, represents the angular velocity of angle change, is the mean value of angular velocity, is the standard deviation of angular velocity, is the mean value of acceleration, is the peak value of acceleration. The present invention uses multi-modal fusion feature information data to obtain a comprehensive feature vector, and uses the amplitude of angle change, the angular velocity of angle change, the mean value and standard deviation of angular velocity, and the mean value and peak value of acceleration to jointly reflect the dynamic characteristics of the scraper during the operation process; provides strong data support for accurately identifying the complete action cycle of the scraper; not only improves the accuracy and reliability of action cycle identification, but also provides an important basis for in-depth analysis of the working efficiency of the scraper; more precisely grasps the operating state of the scraper and provides data support for subsequent statistics of loading efficiency.

[0016] Optionally, constructing the statistical optimization model for the loading efficiency of the scraper based on the operation cycle information data includes: statistically analyzing the operation cycle information data to obtain the loading times and operation efficiency of the scraper, where the loading times and the operation efficiency are used as output targets; using the comprehensive feature vector as an input feature and constructing a mapping function between the input feature and the output target as the statistical model for the loading efficiency of the scraper; training and optimizing the statistical model for the loading efficiency to obtain the statistical optimization model for the loading efficiency of the scraper. The present invention constructs a statistical optimization model for the loading efficiency in combination with the operation cycle information data of the scraper; accurately calculates the loading times and operation efficiency of the scraper through statistical analysis of the operation cycle information and uses them as the output targets of the model; uses the comprehensive feature vector as an input feature to establish a mapping function between the input and the output as the statistical model for the loading efficiency; obtains the statistical optimization model for the loading efficiency through training and optimization; improves the evaluation accuracy of the loading efficiency of the scraper and provides a scientific basis for the operation optimization and efficiency improvement of the scraper.

[0017] Optionally, using the comprehensive feature vector as an input feature and constructing a mapping function between the input feature and the output target as the statistical model for the loading efficiency of the scraper includes:

[0018]

[0019] where, is the model output, represents the mapping function, is the comprehensive feature vector, are the model parameters. The present invention uses the comprehensive feature vector as an input feature to construct a statistical model for the loading efficiency of the scraper, accurately maps the relationship between the input feature and the loading efficiency, realizes the accurate statistics and evaluation of the loading efficiency of the scraper, improves the scientificity and accuracy of the loading efficiency statistics, and provides strong data support and theoretical basis for the optimization of the operation efficiency of the scraper.

[0020] Optionally, obtaining the statistical result of the loading efficiency of the scraper based on the statistical optimization model for the loading efficiency and completing the statistics of the loading efficiency of the mine blast muck includes: performing fitting analysis on the process of loading the mine blast muck of the scraper based on the statistical optimization model for the loading efficiency to obtain the statistical result of the loading efficiency. The present invention uses the comprehensive feature vector as an input and the output of the statistical model for the loading efficiency to construct a mapping function; through the adjustment and optimization of the model parameters, it can accurately reflect the relationship between the dynamic characteristics in the operation process of the scraper and the loading efficiency; realizes the accurate mapping from the operation data of the scraper to the loading efficiency, more accurately evaluates the operation efficiency of the scraper, provides strong support for subsequent optimization control and operation management, and helps to improve the intelligent level and overall operation efficiency of the mine operation.

[0021] In a second aspect, the present invention provides a statistical system for the loading efficiency of mine blast heaps based on multi-dimensional data. The system executes the statistical method for the loading efficiency of mine blast heaps based on multi-dimensional data provided by the present invention. The system includes an input device, an output device, a processor, and a memory. Its advantage lies in that: the hardware facilities integrated in the present invention have excellent performance. The input device, output device, processor, and memory are interconnected with each other, and the information transmission between each component is smooth. Through the interaction of multiple hardware facilities, an efficient information processing system is constructed. The present invention constructs an efficient information processing platform by integrating high-performance hardware facilities, ensuring that the system can quickly process a large amount of multi-dimensional data. Through the collaborative work of multiple hardware facilities, the system can accurately and quickly count and analyze the loading efficiency of mine blast heaps. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of a statistical method for the loading efficiency of mine blast heaps based on multi-dimensional data according to an embodiment of the present invention;

[0023] Figure 2 It is a schematic structural diagram of a three-dimensional sensor according to an embodiment of the present invention;

[0024] Figure 3 It is a schematic diagram of the installation position of a three-dimensional sensor according to an embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of the lifting stage of a scraper according to an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the return stage of a scraper according to an embodiment of the present invention;

[0027] Figure 6 It is a histogram of the loading times of a scraper according to an embodiment of the present invention;

[0028] Figure 7 It is a distribution curve graph of the operation efficiency of a scraper according to an embodiment of the present invention;

[0029] Figure 8 It is a stacked bar chart of the action stage time of a scraper according to an embodiment of the present invention;

[0030] Figure 9 It is a pie chart of the proportion of the action stage time of a scraper according to an embodiment of the present invention;

[0031] Figure 10 It is a time series graph of a scraper according to an embodiment of the present invention;

[0032] Figure 11 It is a heat map of the feature correlation of a scraper according to an embodiment of the present invention;

[0033] Figure 12 Scatter plot matrix diagram of the scraper in the embodiment of the present invention;

[0034] Figure 13 Characteristic importance ranking diagram of the scraper in the embodiment of the present invention;

[0035] Figure 14 System framework diagram of a mine blast muck loading efficiency statistics based on multi-dimensional data in the embodiment of the present invention. Detailed implementation manners

[0036] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the present invention.

[0037] Throughout the specification, the reference to "an embodiment", "embodiment", "an example", or "example" means that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the present invention. Thus, the phrases "in an embodiment", "in embodiments", "an example", or "example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0038] Please refer to Figure 1 , an embodiment of the present invention provides a method for statistically analyzing the loading efficiency of a mine blast muck based on multi-dimensional data, and the method includes the following steps:

[0039] S1. Obtain multi-dimensional real-time operation data of the scraper during the process of loading the mine blast muck.

[0040] Wherein, S1 specifically includes the following steps:

[0041] S11. Configure and install a three-dimensional sensor on the scraper, and set the data sampling frequency of the three-dimensional sensor.

[0042] Please refer to Figure 2 , which shows a schematic diagram of the three-dimensional sensor structure. In the diagram, the three-dimensional sensor is marked with three directions of X, Y, and Z. The three-dimensional sensor can collect the angular, angular velocity, and acceleration change data in the X, Y, and Z directions, providing solid data support.

[0043] Please refer to Figure 3 , which is a schematic diagram of the installation position of the 3D sensor. First, fully charge the 3D sensor to ensure normal operation, and then install the 3D sensor at the middle and rear of the boom of the scraper. During the installation of the 3D sensor, the X direction needs to point to the front of the scraper.

[0044] Specifically, the data sampling frequency of the 3D sensor satisfies the following relationship:

[0045]

[0046] Wherein, is the th sampling time point, is the sampling time interval, is the sampling frequency.

[0047] S12. Based on the data sampling frequency, use the 3D sensor to collect the multi-dimensional real-time operation data of the scraper during the mining bench loading process, and the multi-dimensional real-time operation data includes angle, angular velocity, and acceleration.

[0048] In this embodiment, the 3D sensor with the set data sampling frequency is used to collect the angle, angular velocity, and acceleration of the boom of the scraper during the loading process, and form the multi-dimensional real-time operation data of the scraper, providing a data basis for subsequent analysis.

[0049] Specifically, the time series of the angle output by the 3D sensor satisfies the following relationship:

[0050]

[0051] Wherein, is the angle of the boom, is the angle of the boom in the X direction, is the angle of the boom in the Y direction, is the angle of the boom in the Z direction.

[0052] Furthermore, the angular velocity represents the speed of change of the angle of the boom per unit time, reflecting the dynamic characteristics of the scraper during the loading process. The time series of the angular velocity satisfies the following relationship:

[0053]

[0054] Wherein, is the angular velocity of the boom, is the angular velocity of the boom in the X direction, is the angular velocity of the boom in the Y direction, is the angular velocity of the boom in the Z direction.

[0055] More specifically, the acceleration represents the acceleration of the boom of the scraper during operation, which is used to describe the start, stop, and vibration characteristics of the scraping action of the scraper. The time series of the acceleration satisfies the following relationship:

[0056]

[0057] Wherein, is the acceleration of the boom, is the acceleration of the boom in the X direction, is the acceleration of the boom in the Y direction, is the acceleration of the boom in the Z direction.

[0058] S2. Obtain the multi-modal fusion feature information data of the scraper based on the multi-dimensional real-time operation data.

[0059] Wherein, S2 specifically includes the following steps:

[0060] S21. Preprocess the multi-dimensional real-time operation data to obtain the multi-dimensional real-time operation feature data of the scraper.

[0061] Wherein, S21 specifically includes the following steps:

[0062] S211. Data preprocessing.

[0063] Specifically, the state variables satisfy the following relationship:

[0064]

[0065] Wherein, is the state vector, is the angle, is the angular velocity, is the acceleration, represents the transpose.

[0066] Furthermore, the prediction of the state vector satisfies the following relationship:

[0067]

[0068] Wherein, is the current state vector, is the state transition matrix, is the previous state vector, is the control input matrix, is the control input, is the process noise.

[0069] Even further, the observation correction of the state vector satisfies the following relationship:

[0070]

[0071] Among them, is the corrected state vector, is the predicted estimated value at time for time and is the Kalman gain, is the current observed value, is the observation matrix.

[0072] S212. Normalization processing.

[0073] In this embodiment, the data is normalized to satisfy the following relationship:

[0074]

[0075] Among them, is the normalized data, is the original data, is the minimum value of the original data, is the maximum value of the original data.

[0076] S213. Time alignment.

[0077] Specifically, in this embodiment, the multi-dimensional real-time operation data of the scraper is time-aligned by linear interpolation to satisfy the following relationship:

[0078]

[0079] Among them, is the data value aligned at time , is the original data value at time point , is the current time point, is the time point of the known data, is the next known time point immediately following , is the original data value at time point .

[0080] S214. Feature extraction.

[0081] In this embodiment, angle features, angular velocity features, and acceleration features are extracted from the processed multi-dimensional real-time operation data; the angle features include angle difference and angle change rate, the angular velocity features include average value and standard deviation, and the acceleration features include peak value.

[0082] Specifically, the angular difference satisfies the following relationship:

[0083]

[0084] The angular change rate satisfies the following relationship:

[0085]

[0086] Wherein, is the angular difference, is the maximum angle in the original angular data, is the minimum angle in the original angular data, is the angular change rate, is the angular change amplitude, is the sampling time interval.

[0087] Further, the average value satisfies the following relationship:

[0088]

[0089] The standard deviation satisfies the following relationship:

[0090]

[0091] Wherein, is the average angular velocity, is the total amount of angular velocity acquisition data, is the traversal count flag, is the original angular velocity data value, is the standard deviation of the angular velocity.

[0092] Furthermore, the peak value satisfies the following relationship:

[0093]

[0094] Wherein, is the peak value of the acceleration, represents taking the maximum value, is the original acceleration data value.

[0095] S22. Perform data fusion on the multi-dimensional real-time operation feature data to obtain the multi-modal fusion feature information data of the scraper.

[0096] In this embodiment, a dynamic Kalman filter fusion algorithm is used to perform data fusion on the multi-dimensional real-time operation feature data, satisfying the following relationship:

[0097]

[0098] Wherein, is the comprehensive feature of multimodal fusion, is the traversal count flag, is the dynamic weighting coefficient of the multi-dimensional real-time operation feature data, is the multi-dimensional real-time operation feature data.

[0099] Specifically, the dynamic weighting coefficient satisfies the following relationship:

[0100]

[0101]

[0102] where, is the dynamic weighting coefficient, is the natural exponential function, is the error value between the observed value and the predicted value, is the traversal count flag, is the error value of the overall sample, is the observed value, is the predicted value.

[0103] S3. Obtain the operation cycle information data of the scraper according to the multimodal fusion feature information data.

[0104] Among them, S3 specifically includes the following steps:

[0105] S31. Obtain a comprehensive feature vector based on the multimodal fusion feature information data, so as to identify the complete action cycle of the scraper.

[0106] In this embodiment, an action cycle recognition module is constructed. The action cycle recognition module combines signal decomposition, dynamic time warping and state transition model to cope with the irregular cycle characteristics under complex working conditions; the action cycle recognition module is used to accurately identify the complete action cycle of the scraper loading based on the comprehensive feature vector.

[0107] Among them, S31 specifically includes the following steps:

[0108] S311. Obtain the comprehensive feature vector.

[0109] Specifically, obtain a comprehensive feature vector based on the multimodal fusion feature information data. The comprehensive feature vector satisfies the following relationship:

[0110]

[0111] where, is the comprehensive feature vector, represents the amplitude of angle change, represents the angle change speed, is the average angular velocity, is the standard deviation of angular velocity, is the average acceleration, is the peak acceleration.

[0112] S312. Define the motion characteristics for different stages in the complete motion cycle.

[0113] In this embodiment, the complete motion cycle includes five stages: loading, transportation, lifting, unloading, and returning.

[0114] Specifically, the motion characteristics of the loading stage: During the loading stage, when the bucket enters the ore, the boom maintains a low angle, and the linear acceleration increases. At this time, the change amplitude of the boom angle is relatively small, while the acceleration gradually increases, indicating that the bucket contacts the ore and starts to scoop. And set thresholds to determine whether it is in the loading stage, satisfying the following relationship:

[0115]

[0116] Wherein, is the change amplitude of the boom angle, is the acceleration of the boom along the X direction, is the lower amplitude threshold of the boom angle, is the threshold of the boom acceleration.

[0117] Specifically, the motion characteristics of the transportation stage: The boom gradually rises, maintains a stable angle, the angular velocity is close to zero, and the acceleration decreases. At this time, the boom is in a stable position, mainly driven by the movement of the vehicle, and the changes in angular velocity and acceleration are small, satisfying the following relationship:

[0118]

[0119] Wherein, is the change amplitude of the boom angle, is the lower amplitude threshold of the boom angle, is the upper amplitude threshold of the boom angle, is the angular velocity of the boom along the X direction.

[0120] Specifically, the motion characteristics of the lifting stage: The boom quickly rises to the highest point, and the angular velocity increases. This stage is the process of the boom quickly rising during the loading operation, with a large angle change, and the angular velocity and acceleration increase sharply, satisfying the following relationship:

[0121]

[0122] Wherein, is the change amplitude of the boom angle, is the upper amplitude threshold of the boom angle, is the angular velocity of the boom along the X direction, is the lower threshold value of the angular velocity.

[0123] Further, please refer to Figure 4 , which is a schematic diagram of the lifting stage of the scraper, showing the state where the boom of the scraper is lifted to the highest position.

[0124] Specifically, the action characteristics of the unloading stage: the bucket unloads the ore, the boom remains at a high position and gradually descends. At this time, the change range of the boom angle tends to be stable, and the acceleration gradually decreases, satisfying the following relationship:

[0125]

[0126] where is the change range of the boom angle, is the acceleration of the boom in the X direction, is the threshold value of the acceleration during unloading.

[0127] Specifically, the action characteristics of the return stage: the boom returns to the initial position, the angle returns to the lowest point, the angular velocity and acceleration are close to zero. At this time, the movement of the boom tends to be stable, and the dynamic changes during the return process are small, satisfying the following relationship:

[0128]

[0129] where is the change range of the boom angle, is the lower limit amplitude threshold of the boom angle, is the angular velocity of the boom in the X direction, is the acceleration of the boom in the X direction.

[0130] Further, please refer to Figure 5 , which is a schematic diagram of the return stage, showing the state of the return stage of the scraper.

[0131] S313, Identification and statistics of the action cycle.

[0132] In this embodiment, the action cycle identification module combines signal decomposition, dynamic time warping and state transition model, and combines the comprehensive feature vector and the action feature definition to perform stage identification on the loading process of the scraper.

[0133] Specifically, the state transition model is based on the hidden Markov model, and defines the state transition probability, satisfying the following relationship:

[0134]

[0135] where represents that the prerequisite is the current action stage when the next action stage is The probability, is the number of stage transitions, is the action stage at the next moment, is the action stage at the current moment, is the number of occurrences of the current stage.

[0136] Furthermore, according to the action characteristics of different stages, a complete action cycle is defined. The complete action cycle includes five state sequences: loading, transportation, lifting, unloading, and returning, satisfying the following relationship:

[0137]

[0138] Among them, represents a complete state sequence. If a complete state sequence is detected, the cycle counting function Otherwise .

[0139] Furthermore, the number of complete cycles during the loading process of the scraper satisfies the following relationship:

[0140]

[0141] Among them, is the number of complete cycles, is the total number of time steps, represents a complete state sequence.

[0142] S32. Perform anomaly detection on the complete action cycle to obtain the operation cycle information data of the scraper.

[0143] In this embodiment, the operation cycle information data of the scraper is obtained by excluding abnormal cycle information through anomaly detection.

[0144] Among them, S32 specifically includes the following steps:

[0145] S321. Exclude abnormal cycles.

[0146] An abnormal cycle is defined as an incomplete action cycle, lacking some action stages, such as not entering the unloading stage or the returning stage; the abnormal cycle detection condition is that the complete state sequence is not satisfied.

[0147] In this embodiment, statistical features are used to perform anomaly detection on the action cycle, calculate the feature mean and standard deviation, and exclude abnormal values outside the range.

[0148] Specifically, the feature mean and the standard deviation respectively satisfy the following relationships:

[0149]

[0150]

[0151] Among them, is the feature mean value, is the total number of action cycles, is the th eigenvalue of the cycle, is the standard deviation.

[0152] Furthermore, an abnormal rejection rule is established based on the feature mean value and the standard deviation, and the abnormal rejection rule satisfies the following relationship:

[0153]

[0154] Among them, is the th eigenvalue of the cycle, is the feature mean value, is the standard deviation.

[0155] In an alternative embodiment, machine learning is used, and a supervised learning model (such as a random forest) is used to classify the cycles, satisfying the following relationship:

[0156]

[0157] Among them, represents the probability of an abnormal cycle occurring under the condition of , is the current cycle feature vector, represents finding the that maximizes the probability , represents the probability that the category is under the condition , is the normal category or the abnormal category.

[0158] Furthermore, the number of effective cycles after removing the abnormal cycles satisfies the following relationship:

[0159]

[0160] Among them, is the number of effective cycles, is the total number of cycles, is the number of abnormal cycles.

[0161] In this embodiment, by combining feature threshold detection, hidden Markov model and statistical analysis, the complete cycles of the scraper are accurately identified and abnormal cycles are removed, significantly improving the reliability of cycle statistics and providing an accurate data basis for subsequent efficiency analysis; it should be noted that the features can be automatically identified or set manually.

[0162] Adopt data-driven automatic threshold recognition. This method has strong adaptability. It automatically recognizes the threshold through machine learning and data analysis, can adapt to different working environments and working conditions changes. The threshold can be dynamically adjusted according to the patterns in the data. At the same time, the automatic recognition of the threshold reduces the need for manual intervention, can be adjusted according to real-time data, and provides higher accuracy.

[0163] S322. Recognition of non-working time period.

[0164] Specifically, when the boom of the scraper loader remains stationary or swings at a non-working position, the equipment runs without load. The characteristic performance satisfies the following relationship:

[0165]

[0166] Among them, is the change amplitude of the boom angle, is the minimum threshold of the boom angle change, is the angular velocity of the boom along the X direction, is the acceleration of the boom along the X direction.

[0167] Furthermore, data noise or mutation is manifested as abnormal peaks or mutations in the three-dimensional sensor data. The characteristic performance satisfies the following relationship:

[0168]

[0169] Among them, is the acceleration of the boom along the X direction, is the maximum threshold of the acceleration noise, is the angular velocity of the boom along the X direction, is the maximum threshold of the angular velocity noise.

[0170] Through the above feature definition and threshold setting, five key stages in the loading operation process of the scraper loader can be accurately recognized: loading, transportation, lifting, unloading, and returning. In the cycle recognition module, by combining multi-modal data (such as the angle, angular velocity, and acceleration of the boom) and dynamic time warping and state transition models, it can handle irregular cycle changes in complex environments; in addition, using anomaly detection algorithms to further eliminate incomplete cycles, non-working times, and noise data to ensure the accuracy and reliability of cycle statistics; this method can provide high-precision cycle recognition and operation efficiency analysis, providing strong data support for the optimization of mine operations.

[0171] S4. Construct the statistical optimization model of the loading efficiency of the scraper loader by combining the operation cycle information data.

[0172] Among them, S4 specifically includes the following steps:

[0173] S41. Statistically analyze the operation cycle information data to obtain the loading times and operation efficiency of the scraper, and use the loading times and the operation efficiency as output targets.

[0174] Specifically, the loading times are the statistical results of valid cycles after excluding abnormal action cycles; the operation efficiency is the unit-time loading efficiency within the valid working time, and the operation efficiency satisfies the following relationship:

[0175]

[0176] where, is the operation efficiency, is the number of valid cycles, is the valid working time.

[0177] S42. Use the comprehensive feature vector as the input feature, and construct a mapping function between the input feature and the output target as the loading efficiency statistical model of the scraper.

[0178] In this embodiment, the mapping function serves as the loading efficiency statistical model and satisfies the following relationship;

[0179]

[0180] where, is the model output, represents the mapping function, is the comprehensive feature vector, is the model parameter.

[0181] In an alternative embodiment, a regression model is constructed for comparative analysis with the loading efficiency statistical model; the regression model includes a linear regression model, a random forest regression model, and a gradient boosting regression tree model.

[0182] Specifically, the linear regression model is used to evaluate the linear relationship between the input feature and the output target and satisfies the following relationship:

[0183]

[0184] where, is the model output, is the intercept, is the regression coefficient, is the input feature.

[0185] Specifically, the random forest regression model is used to capture the non-linear relationship between features and is robust to high-dimensional features and noisy data, and satisfies the following relationship:

[0186]

[0187] Among them, is the model output, is the total number of decision trees, is the output of the

[0188] Specifically, the gradient boosting regression tree model has excellent performance in small sample data, and optimizes the model accuracy through weighted iteration, satisfying the following relationship:

[0189]

[0190] Among them, represents the predicted value of the model for the input after rounds of iteration, represents the predicted value of the model for the input after rounds of iteration, is the learning rate, is the residual predicted by the

[0191] S43. Train and optimize the loading efficiency statistical model to obtain the optimized loading efficiency statistical model of the scraper.

[0192] In this embodiment, the original data set is divided into a training set, a validation set, and a test set. The training set is used for model training, the validation set is used for model hyperparameter optimization, and the test set is used for model performance evaluation. The training set, validation set, and test set satisfy the following relationship:

[0193]

[0194] Among them, is the original data set, is the training set, is the validation set, is the test set.

[0195] Among them, S43 specifically includes the following steps:

[0196] S431. Model training and optimization.

[0197] In this embodiment, a loss function is constructed using a random forest, and the model is recursively optimized based on the training set combined with the residual. By calculating the splitting contributions of different features, the feature weights are dynamically adjusted. The recursive optimization satisfies the following relationship:

[0198]

[0199] Among them, is the The residual at the i-th iteration, is the true value of the n-th sample, and is the predicted value of the previous

[0200] S432. Model hyperparameter optimization.

[0201] In this embodiment, grid search and Bayesian optimization are used to adjust the model hyperparameters. The model hyperparameters include random forest parameters (such as the number of trees and the maximum depth) and GBDT parameters (learning rate and the number of sub-models). The model hyperparameter optimization satisfies the following relationship:

[0202]

[0203] where, is the set of optimal hyperparameters, represents finding the set of hyperparameters that minimizes the loss function, are the model parameters, is the loss function value on the validation set.

[0204] S433. Model performance evaluation.

[0205] In this embodiment, the performance of the model is evaluated using the test set, including cross-validation, mean squared error, mean absolute error, and coefficient of determination.

[0206] Specifically, the cross-validation uses k-fold cross-validation to evaluate the model performance, satisfying the following relationship:

[0207]

[0208] where, is the evaluation metric, is the number of folds, is the loss function value of the i-th fold.

[0209] Specifically, the mean squared error satisfies the following relationship:

[0210]

[0211] where, is the mean squared error, is the total number of samples, is the true value of the i-th sample; is the predicted value of the i-th sample.

[0212] Specifically, the mean absolute error satisfies the following relationship:

[0213]

[0214] where is the mean squared error, is the total number of samples, is the th true value of the sample; is the th predicted value of the sample.

[0215] Specifically, the coefficient of determination satisfies the following relationship:

[0216]

[0217] where is the coefficient of determination, is the th true value of the sample, is the th predicted value of the sample, is the mean of the true values of the samples.

[0218] S5. Obtain the statistical result of the loading efficiency of the scraper based on the optimized statistical model of the loading efficiency, and complete the statistics of the loading efficiency of the mine blast muck.

[0219] Specifically, perform a fitting analysis on the loading process of the mine blast muck of the scraper based on the optimized statistical model of the loading efficiency to obtain the statistical result of the loading efficiency.

[0220] In this embodiment, the statistical result of the loading efficiency is obtained by deeply analyzing the action cycle and operation efficiency of the scraper, and the statistical result of the loading efficiency is visualized; the statistical result of the loading efficiency includes a histogram of the number of loading times, a distribution curve of the operation efficiency, a stacked bar chart of the action stage time, a pie chart of the proportion of the action stage time, a time series chart, a heat map of feature correlation, a pairwise scatter matrix chart, and a feature importance ranking chart.

[0221] S51. Histogram of the number of loading times.

[0222] Please refer to Figure 6 , which shows the histogram of the number of loading times of the scraper; to count the distribution of the number of loading times per hour and intuitively understand the operation frequency of the scraper, the data of the number of loading times is divided into several intervals, and the distribution of the number of loading times is plotted. The figure shows the number of loading times per hour within 12 hours, and the horizontal axis time can be adjusted according to specific needs.

[0223] Specifically, the distribution of the number of loading times satisfies the following relationship:

[0224]

[0225] Among them, is the number of loading operations, is the total number of operations, is the number of intervals.

[0226] S52. Distribution curve graph of operation efficiency.

[0227] Please refer to Figure 7 , which shows the distribution curve graph of the operation efficiency of the scraper; to plot the distribution trend of the operation efficiency, display the proportion of high-efficiency and low-efficiency working conditions, based on the operation efficiency expression calculated from the effective working time, use kernel density estimation to generate a probability density curve as the distribution curve graph of the operation efficiency.

[0228] Specifically, the kernel density estimation satisfies the following relationship:

[0229]

[0230] Among them, represents the estimated value of the probability density function at the data point , is the number of samples, is the bandwidth, is the kernel function, represents the data point, represents the sample data point, represents that each sample data point is scaled by the bandwidth and standardized with respect to the data point .

[0231] S53. Stacked bar chart of action phase time.

[0232] Please refer to Figure 8 , which shows the stacked bar chart of the action phase time of the scraper; to analyze the distribution of each action phase (loading, transportation, lifting, unloading, returning) of the scraper in the total cycle time. The cumulative time of each action phase is statistically calculated and satisfies the following relationship:

[0233]

[0234] Among them, is the total time of the th phase, is the number of effective cycles, is the nd cycle, and is the time of the

[0235] S54. Pie chart of the proportion of action phase time.

[0236] Please refer to Figure 9 , which shows a pie chart of the time proportion of the operation stages of the scraper; the time proportion of each operation stage is calculated by the cumulative time and the total time of each operation stage; the time proportion satisfies the following relationship:

[0237]

[0238] Wherein, is the time proportion of the stage, is the total time of the stage, is the total time of the complete operation cycle.

[0239] S55. Time series diagram.

[0240] Please refer to Figure 10 , which shows the time series diagram of the scraper. The horizontal axis is time and the vertical axis is the operation efficiency, describing the change relationship of the operation efficiency with time and exploring the existence of trends or periodic changes; the operation efficiency time series satisfies the following relationship:

[0241]

[0242] Wherein, represents the operation efficiency within the time , represents the number of operation cycles within the time , is the total time period.

[0243] S56. Feature correlation heat map.

[0244] Please refer to Figure 11 , which shows the feature correlation heat map of the scraper. The correlation degree between features is represented by the depth of color, showing the correlation between loading, transportation, lifting, unloading, return, cycle time and operation efficiency.

[0245] Specifically, calculate the correlation between features, construct a correlation matrix as the feature correlation heat map, which satisfies the following relationship:

[0246]

[0247] Wherein, is the correlation coefficient between features and , is the covariance, and are the standard deviations.

[0248] S57. Pairwise scatter matrix diagram.

[0249] Please refer to Figure 12 , which is a paired scatter matrix diagram of a scraper, showing the relationship between the cycle time, characteristics, and operation efficiency of the scraper; showing the relationship between multiple characteristics and operation efficiency. Especially when there are many characteristics, a paired scatter matrix diagram is used to show the pairwise relationship of each characteristic and the correlation between the characteristics and efficiency.

[0250] S58. Feature importance ranking diagram.

[0251] Please refer to Figure 13 , which is a feature importance ranking diagram of a scraper, showing the importance of features for predicting operation efficiency, and is crucial for feature selection and model optimization. The features include loading, transportation, lifting, unloading, return, and cycle time.

[0252] Please refer to Figure 14 , in an optional embodiment, in order to efficiently execute the method for statistically analyzing the loading efficiency of a mine blast heap based on multi-dimensional data provided by the present invention, the present invention provides a system for statistically analyzing the loading efficiency of a mine blast heap based on multi-dimensional data. The system includes an input device, an output device, a processor, and a memory, and the hardware facilities are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the steps of the specific embodiments of the method of the present invention. The system for statistically analyzing the loading efficiency of a mine blast heap based on multi-dimensional data provided by the present invention has a complete structure, is objective and stable, and improves the overall applicability and practical application ability of the method of the present invention.

[0253] In summary, the method and system for statistically analyzing the loading efficiency of a mine blast heap based on multi-dimensional data provided by the method of the present invention collect multi-dimensional operation data of a scraper, fuse to obtain multi-modal feature information, analyze the operation cycle of the scraper, construct a loading efficiency optimization model, improve the accuracy of efficiency statistics, and provide a reference basis for optimizing operation efficiency, promoting the intelligent management of mine loading operations. The method of the present invention is easy to understand, simple to calculate, has a small workload, is convenient for engineering applications, and provides a theoretical basis and technical support for the further development of the field of work efficiency analysis in mine mining.

[0254] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. A statistical method for mining pile shoveling efficiency based on multidimensional data, characterized in that: The steps include: Obtain multi-dimensional real-time operation data of the loader during the mine blast pile loading process; Obtaining multimodal fusion feature information data of the scraper based on the multidimensional real-time operation data; Obtaining operation cycle information data of the scraper according to the multimodal fusion feature information data; Building a statistical optimization model of the shoveling efficiency of the scraper in combination with the operation cycle information data; Obtaining the shoveling efficiency statistical results of the scraper according to the shoveling efficiency statistical optimization model, and completing the statistics of the shoveling efficiency of the mine blast pile; The step of obtaining the operation cycle information data of the scraper according to the multimodal fusion feature information data includes: Obtaining a comprehensive feature vector based on the multimodal fusion feature information data, thereby identifying a complete action cycle of the scraper; Performing abnormality detection on the complete action cycle to obtain operation cycle information data of the scraper; The step of constructing a loading efficiency statistical optimization model of the scraper in combination with the operation cycle information data includes: Performing statistical analysis on the operation cycle information data to obtain the number of shoveling times and the operating efficiency of the scraper, and the number of shoveling times and the operating efficiency are used as output targets; Taking the comprehensive feature vector as an input feature, constructing a mapping function between the input feature and the output target as a loading efficiency statistical model of the scraper; Training and optimizing the shoveling efficiency statistical model to obtain the shoveling efficiency statistical optimization model of the scraper; The method of taking the comprehensive feature vector as an input feature and constructing a mapping function between the input feature and the output target as a statistical model of the loading efficiency of the scraper includes: ； in, is the model output, represents the mapping function, is the comprehensive feature vector, are model parameters; The method of obtaining the shoveling efficiency statistical result of the scraper according to the shoveling efficiency statistical optimization model and completing the statistics of the shoveling efficiency of the mine blast pile includes: The loading efficiency statistical optimization model is used to fit the mine blast pile loading process of the scraper to obtain the loading efficiency statistical results.

2. The method for calculating the efficiency of mine blasting pile shoveling based on multidimensional data according to claim 1 is characterized in that: The multi-dimensional real-time operation data of the scraper during the mine blast pile shoveling process is obtained, including: A three-dimensional sensor is installed on the scraper, and a data sampling frequency of the three-dimensional sensor is set; Based on the data sampling frequency, the three-dimensional sensor is used to collect multi-dimensional real-time operation data of the shovel loader during the mine blast pile shoveling process, and the multi-dimensional real-time operation data includes angle, angular velocity and acceleration.

3. The method for calculating the efficiency of mine blasting pile shoveling based on multidimensional data according to claim 1 is characterized in that: The method of obtaining the multimodal fusion feature information data of the scraper based on the multidimensional real-time operation data includes: Preprocessing the multi-dimensional real-time operation data to obtain multi-dimensional real-time operation characteristic data of the scraper; The multi-dimensional real-time operation characteristic data is subjected to data fusion to obtain multi-modal fusion characteristic information data of the scraper.

4. The method for calculating the efficiency of mine blast pile shoveling based on multidimensional data according to claim 3 is characterized in that: The step of fusing the multi-dimensional real-time operation feature data to obtain multi-modal fusion feature information data of the scraper includes: ； in, is the comprehensive feature of multimodal fusion. is the traversal count flag, It is the dynamic weighting coefficient of multi-dimensional real-time running characteristic data. Run feature data in real-time for multiple dimensions.

5. The method for calculating the efficiency of mine blasting pile shoveling based on multidimensional data according to claim 1 is characterized in that: The step of obtaining a comprehensive feature vector based on the multimodal fusion feature information data, thereby identifying a complete action cycle of the scraper, includes: ； in, is the comprehensive feature vector, Indicates the angle change amplitude, Indicates the speed of angle change, is the mean angular velocity, is the standard deviation of angular velocity, is the mean acceleration, is the peak acceleration.

6. A mine blast pile shoveling efficiency statistics system based on multidimensional data, characterized in that: The system includes an input device, an output device, a processor and a memory, wherein the input device, the output device, the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the mine blasting pile shoveling efficiency statistics method based on multidimensional data as described in any one of claims 1-5.

Images