A method and system for counting the transport of intelligent mining trucks

Abstract

This application relates to the field of data processing, specifically to a method and system for counting the transportation of intelligent mining trucks. The method includes: calculating the overall transportation effectiveness based on acquired transportation process information; comparing the overall transportation effectiveness with a preset threshold; counting if the effectiveness exceeds the threshold, and not counting otherwise; calculating the node similarity between the transportation process to be counted and historically counted transportation processes; calculating the trajectory similarity between the transportation process to be counted and historically counted transportation processes; using the product of node similarity and trajectory similarity as the trajectory effectiveness; processing the transportation process to be counted and historically counted transportation processes to obtain a differential weight sequence; calculating the transportation effectiveness based on the trajectory effectiveness and the differential weight sequence; calculating the transportation effectiveness of the transportation process to be counted under each historically counted transportation process, and then calculating the overall transportation effectiveness. This application improves the accuracy of effective transportation counting for intelligent mining trucks.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method and system for counting the transport of intelligent mining trucks. Background Technology

[0002] Intelligent mining truck transport counting refers to the accurate monitoring and counting of mining truck transport processes through automation technology, and is widely used in open-pit mines, underground mines, and other scenarios. Traditional mining area transport counting mainly relies on manual recording or manual verification, which is inefficient and prone to omissions, overcounts, or human errors, especially in large mining areas or multi-lane scenarios.

[0003] Existing technologies match the trajectories of mining trucks with historical valid transport trajectories or record the number of times a mining truck passes through using pressure sensors and then count the trips. Since a valid transport activity includes mining, transporting, and unloading, existing technologies rely on a single trajectory node and the dwell time of the mining truck during mining and unloading to match the trajectories, ignoring whether the mining truck has completed the unloading process. This results in the phenomenon of miscounting transport when a mining truck is idle during mining and unloading and is still considered a valid transport. Summary of the Invention

[0004] To address the problem in existing technologies that ignore whether mining trucks have completed unloading, resulting in erroneous counting of transportation even when empty mining trucks are still considered to be in valid transport, this application provides a transportation counting method and system for intelligent mining trucks. By processing data to calculate the overall transportation effectiveness of the transportation process, this method achieves more efficient and accurate counting and statistics of the mining truck transportation process.

[0005] Firstly, this application provides a transportation counting method for intelligent mining trucks, employing the following technical solution:

[0006] Based on the acquired transportation process information, the overall transportation effectiveness is calculated, and the overall transportation effectiveness is compared with a preset threshold. If it is greater than the threshold, it is counted; otherwise, it is not counted.

[0007] The transportation process information includes: the trajectory sequence, weight sequence, and node sequence for each transportation process; the nodes include mining points, waypoints, and unloading points.

[0008] The calculation of the overall transportation efficiency includes: calculating the node similarity between the node sequence of the transportation process to be counted and the node sequence of the historically counted transportation processes;

[0009] The intersection of the trajectory of the transportation process to be counted with the trajectory of the historically counted transportation process is used as the cutting point. The trajectory sequence of the transportation process to be counted is divided into multiple first trajectory subsequences, and the trajectory sequence of the historically counted transportation process is divided into multiple second trajectory subsequences. The trajectory similarity between the transportation process to be counted and the historically counted transportation process is calculated based on the first trajectory subsequences and the second trajectory subsequences.

[0010] The product of node similarity and trajectory similarity is used as the trajectory validity; the weight sequence of the transportation process to be counted is differentially processed with the weight sequence of the historically counted transportation processes to obtain their respective differential weight sequences.

[0011] The transportation efficiency is calculated based on the trajectory efficiency and differential weight sequence; the transportation efficiency of the transportation process to be counted is calculated under each historically counted transportation process, and then the overall transportation efficiency of the current transportation process to be counted is calculated.

[0012] Furthermore, the node sequence starts from the mining point, passes through the path points, and ends at the unloading point.

[0013] Furthermore, the node similarity is calculated by dividing the number of nodes where the trajectory of the transportation process to be counted intersects with that of the historically counted transportation processes by the ratio of the number of nodes traversed by the trajectory of the transportation process to be counted and that of the historically counted transportation processes by the ratio of the number of identical node pairs traversed by ...

[0014] A node pair represents a directional path formed by two adjacent nodes.

[0015] Furthermore, the method for calculating the trajectory similarity of the transportation process to be counted relative to the historically counted transportation processes based on the first trajectory subsequence and the second trajectory subsequence is as follows: calculate the DTW distance between each first trajectory subsequence and the corresponding second trajectory subsequence, calculate the mean of all DTW distances, take the negative of the mean and perform negative correlation normalization to obtain the trajectory similarity.

[0016] Furthermore, the differential weight sequence includes a mining differential weight sequence, a transportation differential weight sequence, and an unloading differential weight sequence.

[0017] Furthermore, the calculation of transportation efficiency based on trajectory effectiveness and differential weight sequence includes: calculating the DTW distance between the mining differential weight sequence of the transportation process to be counted and the mining differential weight sequence of historically counted transportation processes; calculating the DTW distance between the unloading differential weight sequences of the two transportation processes; calculating the difference between the standard deviation of the transportation differential weight sequence of the transportation process to be counted and the standard deviation of the transportation differential weight sequence of historically counted transportation processes; and calculating and using an exponential function to obtain the corresponding weight change trend based on the difference between the corresponding mining differential weight sequence DTW distance, unloading differential weight sequence DTW distance, and transportation differential weight sequence standard deviation.

[0018] The sum of the trajectory effectiveness and the corresponding weight change trend is taken as the transportation effectiveness of the transportation process to be counted, compared with the historically counted transportation processes.

[0019] Furthermore, the transportation efficiency of the transportation process to be counted under each historically counted transportation process is taken, and the mean value of each transportation efficiency is calculated after normalization as the comprehensive transportation efficiency of the current transportation process to be counted.

[0020] Secondly, this application provides a transportation counting system for intelligent mining trucks, which adopts the following technical solution:

[0021] A transportation counting system for an intelligent mining truck includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the transportation counting method for an intelligent mining truck as described above is implemented.

[0022] This application has the following technical effects:

[0023] This application calculates the node similarity between the transportation process to be counted and historically counted transportation processes. By combining nodes and node pairs, it can perform ordered similarity calculations considering the order in which mining trucks visit nodes, avoiding the phenomenon of miscounting transportation effectiveness due to relying solely on nodes, where visited nodes may have high similarity but the actual order of node visits differs. Secondly, this application considers both nodes and trajectories to ensure the arrival of key nodes and the rationality of the trajectory path, avoiding the misclassification of abnormal and incomplete transportation behaviors as valid transportation. Furthermore, this application considers the mining and unloading behavior of mining trucks at the mining and unloading points and the impact of road conditions on weight fluctuations during transportation, avoiding the phenomenon of miscounting empty mining trucks and identifying abnormal mining and unloading behaviors during transportation. This application significantly improves the accuracy of valid transportation counting for intelligent mining trucks. Attached Figure Description

[0024] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description in conjunction with the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0025] Figure 1 This is a flowchart of a transportation counting method for an intelligent mining truck provided in an embodiment of this application;

[0026] Figure 2 This is a schematic diagram of trajectory nodes provided in an embodiment of this application;

[0027] Figure 3 This is a schematic diagram of transportation trajectory segmentation provided in the embodiments of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] This application discloses a transportation counting method for intelligent mining trucks, referring to... Figure 1 The steps include:

[0030] S101: Collect information on the current transportation process to be counted and the transportation process information that has been counted in the past.

[0031] Specifically, the transportation process information includes: a trajectory sequence, a weight sequence, and a node sequence corresponding to each transportation process; the nodes include mining points, path points, and unloading points; the node sequence starts from the mining point, passes through the path points, and ends at the unloading point.

[0032] Specifically, GPS and pressure sensors are used to collect location and weight data during transportation, and RFID readers are used to obtain the time when the mining truck passes each node. In this embodiment, GPS is used to obtain the location data of each node in the mining area and the location data of the mining truck during transportation, pressure sensors are used to obtain the weight data of the mining truck, and RFID readers are used to obtain the time when the mining truck passes each node. The GPS is placed on top of each mining truck, the pressure sensor is placed at the bottom of each mining truck bed, and the RFID tag is placed on the side of the mining truck for scanning by the reader. The nodes include mining points, unloading points, and waypoints. In this embodiment, the waypoint refers to the location of the center of an intersection in the mining area, including but not limited to T-shaped, cross-shaped, etc. Since multiple mining trucks are not used for transportation, multiple roads intersect within the transportation scenario for multi-vehicle transportation. An exemplary node is shown below for further understanding. Figure 2 As shown. The system obtains the location data, weight data, and arrival time at each node for multiple historically counted transportation processes of the mining truck, and obtains the location data, weight data, and arrival time at each node for the transportation process to be counted.

[0033] Specifically, for a transportation process, a trajectory sequence is obtained based on the location data during transportation, a weight sequence is obtained based on the weight data during transportation, and a node sequence is obtained based on the nodes encountered during transportation. A complete node sequence starts from the mining point, passes through the path points, and ends at the unloading point.

[0034] S102: Based on the current transport process to be counted and the first The transportation efficiency is calculated based on the transportation process information of each historically counted transportation process.

[0035] Specifically, an exemplary node sequence is as follows: This sequence represents , A node pair represents a directional path formed by two adjacent nodes.

[0036] Specifically, the node similarity between the node sequence of the transportation process to be counted and the node sequence of the previously counted transportation processes is calculated.

[0037] Specifically, the node similarity is calculated by dividing the number of nodes where the trajectory of the transportation process to be counted intersects with that of the historically counted transportation processes by the ratio of the number of nodes traversed by the trajectory of the transportation process to be counted and that of the historically counted transportation processes by the ratio of the number of identical node pairs traversed by ...

[0038] Specifically, for a transport process to be counted and the first The historical transport process has been counted. Node similarity is calculated based on the node sequence, using the following expression:

[0039]

[0040] in, This indicates the transportation process to be counted and the first... Node similarity of a historically counted transportation process This indicates the number of nodes where the trajectories of two transportation processes intersect. This represents the total number of nodes traversed by the trajectories of the two transportation processes. This represents the similarity of nodes in two unordered transportation processes. This indicates the number of the same node pairs experienced by two transportation processes. This represents the total number of node pairs experienced by the two transportation processes. This represents the similarity between nodes in two orderly transportation processes.

[0041] Specifically, the more similar the nodes traversed by two transportation trajectories, the more similar the two transportation processes are, and the greater the likelihood of effective transportation. Similarly, the more similar the order in which nodes are visited in two transportation trajectories, the more similar the two transportation processes are, and node pairs can represent the order in which nodes are visited. Since a single node is unordered, two trajectories visiting the same node cannot indicate similarity between the two trajectories. Furthermore, the complex and interwoven mining truck transportation paths can be separated by ordered node pairs, which can lead to similar paths becoming more distant. Visiting the same nodes does not necessarily mean the same direction of travel, nor does it guarantee the effectiveness of the transportation process; different node pairs do not necessarily mean different directions of travel, nor does it guarantee the ineffectiveness of the transportation process. Therefore, this application calculates node similarity by combining nodes and node pairs, taking into account the order in which mining trucks visit nodes for ordered similarity calculation. This avoids the phenomenon where relying solely on nodes leads to situations where visited nodes have high similarity but the actual order of node visits results in misclassification of transportation effectiveness.

[0042] Specifically, for a transport process to be counted and the first For each historically counted transportation process, the intersection points of the trajectories of two transportation processes are used as cutting points to segment the trajectory sequence of each transportation process. A single transportation process yields multiple trajectory subsequences. No segmentation is performed when the intersection point is a mining point or an unloading point. An exemplary segmentation method is shown below. Figure 3 As shown.

[0043] Specifically, the intersection of the trajectory of the transportation process to be counted with the trajectory of the historically counted transportation process is used as the cutting point to divide the trajectory sequence of the transportation process to be counted into multiple first trajectory subsequences, and the trajectory sequence of the historically counted transportation process is divided into multiple second trajectory subsequences. The trajectory similarity of the transportation process to be counted relative to the historically counted transportation process is calculated based on the first trajectory subsequences and the second trajectory subsequences.

[0044] Specifically, the method for calculating the trajectory similarity of the transportation process to be counted relative to the historically counted transportation processes based on the first trajectory subsequence and the second trajectory subsequence is as follows: calculate the DTW (Dynamic Time Warping Distance) distance between each first trajectory subsequence and the corresponding second trajectory subsequence, calculate the mean of all DTW distances, take the negative of the mean and perform negative correlation normalization to obtain the trajectory similarity.

[0045] Specifically, for a transport process to be counted and the first For a historically counted transportation process, the validity of the trajectory is calculated based on the trajectory subsequence and node similarity. The calculation expression is as follows:

[0046]

[0047] in, This indicates the validity of the trajectory of the transportation process to be counted. This indicates the transportation process to be counted and the first... Node similarity of a historically counted transportation process Indicates the number of trajectory subsequences. This represents the first of the transportation processes to be counted. The trajectory subsequence and the first The first of the historically counted transportation processes DTW distance between trajectory subsequences This indicates the similarity of the trajectories of two transportation processes.

[0048] It is important to note that the trajectory sequence of the transportation process to be counted and the historically counted transportation processes are used as the cutting point to divide the trajectory sequence of the transportation process to be counted into multiple first trajectory subsequences, and the trajectory sequence of the historically counted transportation processes is divided into multiple second trajectory subsequences. That is, the starting point of each first trajectory subsequence and the corresponding second trajectory subsequence is the same, and the trajectory similarity is calculated in this way.

[0049] Specifically, due to the complex road conditions in mine truck transportation, relying solely on the trajectory can lead to valid counts being misjudged as invalid. For example, when a mine truck deviates from its historical trajectory due to road conditions, it is considered an invalid transport. Similarly, relying solely on nodes can lead to invalid counts being misjudged as valid. For instance, a mine truck may have encountered nodes similar to its historical trajectory but engaged in back-and-forth trips or temporary unloading, thus failing to complete the transport, yet it is still considered valid. Therefore, this application considers both nodes and trajectories to ensure the arrival of key nodes and guarantee a reasonable trajectory path, preventing abnormal and incomplete transport behaviors from being misjudged as valid transport.

[0050] Specifically, for a transport process to be counted and the first For each historically counted transportation process, the weight sequence is differentially processed to obtain a differential weight sequence. The differential weight sequence is then segmented according to time to obtain the mining differential weight sequence, the transportation differential weight sequence, and the unloading differential weight sequence.

[0051] Specifically, calculating the transportation effectiveness based on trajectory effectiveness and differential weight sequence includes: calculating the DTW distance between the mining differential weight sequence of the transportation process to be counted and the mining differential weight sequence of historically counted transportation processes; calculating the DTW distance between the unloading differential weight sequences of the two transportation processes; calculating the difference between the standard deviation of the transportation differential weight sequence of the transportation process to be counted and the standard deviation of the transportation differential weight sequence of historically counted transportation processes; calculating and using an exponential function to obtain the corresponding weight change trend based on the difference between the corresponding mining differential weight sequence DTW distance, unloading differential weight sequence DTW distance, and standard deviation of the transportation differential weight sequence; and taking the sum of trajectory effectiveness and the corresponding weight change trend as the transportation effectiveness of the transportation process to be counted compared with the historically counted transportation processes.

[0052] Specifically, for a transport process to be counted and the first For each historically counted transportation process, the transportation efficiency is calculated based on the trajectory efficiency and the differential weight sequence. The calculation expression is as follows:

[0053]

[0054] in, This indicates the degree of transportation efficiency for the transportation process to be counted. This indicates the validity of the trajectory of the transportation process to be counted. This indicates the transportation process to be counted and the first... DTW distance between the mining differential weight sequences of two historically counted transportation processes. This indicates the transportation process to be counted and the first... DTW distance of the differential weight sequence of unloading ore for two historically counted transportation processes. This represents the standard deviation of the differential weight sequence of the transportation process to be counted and the first... The difference between the standard deviations of the differential weight sequences of a historically counted transportation process.

[0055] Specifically, regarding the effectiveness of transportation Normalization is performed to obtain the normalized transport efficiency. .

[0056] Specifically, the effectiveness of a mining truck transport is judged primarily by two aspects: the validity of the transport trajectory and whether mining and unloading were completed. Since the capacity of a mining truck is fixed and the mining and unloading operation mode is standardized, the increase or decrease of minerals within the truck during mining and unloading follows a certain trend. If a transport process is effective, the weight change trend within the truck during mining and unloading should be similar. Standard deviation measures the impact of road conditions on weight. If a transport process to be counted is effective, the weight fluctuation during transport should be similar in magnitude to the fluctuation of previously counted transport processes with similar road conditions. If the difference in standard deviation between two transport processes is large, it indicates abnormal mining and unloading behavior in the process to be counted, leading to abnormal weight fluctuations. A mining truck passing through mining and unloading points may not necessarily have performed mining or unloading; it could be in an empty state. Considering only the trajectory would lead to miscounting, as it may not have actually completed a transport. Compared to judging the effectiveness of transportation solely by the accessed node trajectories, the technical solution of this application considers the mining and unloading behavior of the mining truck at the mining and unloading point and the impact of road conditions on weight fluctuations during transportation. This can avoid the phenomenon of mining trucks being miscounted even when they are empty, and can also identify abnormal mining and unloading behaviors during transportation.

[0057] Specifically, based on the above operations, the normalized transportation efficiency of the transportation process to be counted under each historically counted transportation process is obtained.

[0058] S103: Calculate the transportation efficiency of the transportation process to be counted under each historically counted transportation process, and then calculate the overall transportation efficiency of the current transportation process to be counted.

[0059] Specifically, the transportation efficiency of the transportation process to be counted is taken from each historically counted transportation process, and the mean value is calculated after normalizing each transportation efficiency as the comprehensive transportation efficiency of the current transportation process to be counted.

[0060] Specifically, in this embodiment, due to the complexity of the trajectory during mine car transportation, which may involve actions such as stopping and changing lanes, determining the effectiveness of the next transportation process based on a single historically counted transportation process is subject to chance. Therefore, this application calculates the overall transportation effectiveness based on the normalized transportation effectiveness of the next transportation process under each historically counted transportation process. The expression for calculating the overall transportation effectiveness is as follows:

[0061]

[0062] in, This indicates the overall transportation efficiency of the transportation processes to be counted. This indicates the number of historically counted transportation processes. Indicates the first The normalized transport efficiency of the transport processes to be counted under a historically counted transport process.

[0063] S104: Compare the overall transportation effectiveness of the transportation process to be counted with a preset threshold. If it is greater than the threshold, it is counted; otherwise, it is not counted.

[0064] Specifically, in this embodiment, the preset threshold is 0.75. When the overall transportation effectiveness of the transportation process to be counted exceeds the preset threshold of 0.75, the transportation count of the mining car is increased by 1. If it is less than or equal to the preset threshold, it is considered an invalid transportation and is not counted.

[0065] This application also discloses a transportation counting system for intelligent mining trucks, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a transportation counting method for intelligent mining trucks according to this application.

[0066] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0067] In this application, the aforementioned memory can be any tangible medium that contains or stores a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (DRAM), dynamic random access memory (DRAM), static random access memory (SRAM), etc., or any other medium that can be used to store desired information and can be accessed by an application program, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0068] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method of transport counting of a smart mine car, characterized by, The methods include: Based on the acquired transportation process information, the overall transportation effectiveness is calculated, and the overall transportation effectiveness is compared with a preset threshold. If it is greater than the threshold, it is counted; otherwise, it is not counted. The transportation process information includes: a trajectory sequence, a weight sequence, and a node sequence for each transportation process; the nodes include mining points, path points, and unloading points; the node sequence starts from the mining point, passes through the path points, and ends at the unloading point. The calculation of the overall transportation efficiency includes: calculating the node similarity between the node sequence of the transportation process to be counted and the node sequence of historically counted transportation processes; the expression for calculating node similarity is: ;in, This indicates the transportation process to be counted and the first... Node similarity of a historically counted transportation process This indicates the number of nodes where the trajectories of two transportation processes intersect. This represents the total number of nodes traversed by the trajectories of the two transportation processes. This represents the similarity of nodes in two unordered transportation processes. This indicates the number of the same node pairs experienced by two transportation processes. This represents the total number of node pairs experienced by the two transportation processes. The similarity of nodes in two transport processes is represented by the order of nodes; a node pair represents a directional path formed by two adjacent nodes. The intersection of the trajectory of the transportation process to be counted with the trajectory of the historically counted transportation process is used as the cutting point. The trajectory sequence of the transportation process to be counted is divided into multiple first trajectory subsequences, and the trajectory sequence of the historically counted transportation process is divided into multiple second trajectory subsequences. The trajectory similarity between the transportation process to be counted and the historically counted transportation process is calculated based on the first trajectory subsequences and the second trajectory subsequences. The product of node similarity and trajectory similarity is used as the trajectory validity; the weight sequence of the transportation process to be counted is differentially processed with the weight sequence of the historically counted transportation processes to obtain their respective differential weight sequences. The transportation efficiency is calculated based on the trajectory efficiency and differential weight sequence; the transportation efficiency of the transportation process to be counted is calculated under each historically counted transportation process, and then the overall transportation efficiency of the current transportation process to be counted is calculated. The expression for calculating the effectiveness of the trajectory is: ;in, This indicates the validity of the trajectory of the transportation process to be counted. This indicates the transportation process to be counted and the first... Node similarity of a historically counted transportation process Indicates the number of trajectory subsequences. This represents the first of the transportation processes to be counted. The trajectory subsequence and the first The first of the historically counted transportation processes DTW distance between each trajectory subsequence; The differential weight sequence includes the mining differential weight sequence, the transportation differential weight sequence, and the unloading differential weight sequence; The calculation of transportation effectiveness based on trajectory effectiveness and differential weight sequence includes: calculating the DTW distance between the mining differential weight sequence of the transportation process to be counted and the mining differential weight sequence of historically counted transportation processes; calculating the DTW distance between the unloading differential weight sequences of the two transportation processes; calculating the difference between the standard deviation of the transportation differential weight sequence of the transportation process to be counted and the standard deviation of the transportation differential weight sequence of historically counted transportation processes; calculating and using an exponential function to obtain the corresponding weight change trend based on the difference between the corresponding mining differential weight sequence DTW distance, unloading differential weight sequence DTW distance, and standard deviation of the transportation differential weight sequence; and taking the sum of trajectory effectiveness and the corresponding weight change trend as the transportation effectiveness of the transportation process to be counted compared with the historically counted transportation processes.

2. The intelligent mining truck transportation counting method according to claim 1, characterized in that, The transportation efficiency of the transportation process to be counted is taken from each historically counted transportation process. The average value of each transportation efficiency is calculated after normalization and is taken as the comprehensive transportation efficiency of the current transportation process to be counted.

3. A transportation counting system for intelligent mining trucks, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a transportation counting method for an intelligent mining vehicle according to claim 1 or 2.

Images