Engineering machinery loading matching method, device, equipment and medium

Abstract

The invention provides an engineering machinery loading matching method, device and equipment and a medium, and relates to the technical field of engineering machinery. The method comprises the following steps: acquiring first positioning information of a target mine car and second positioning information of a plurality of engineering machinery; analyzing the first positioning information, and fitting to obtain a backing track of the target mine car; determining a vertical distance from each engineering machine to the backing track according to the backing track and the second positioning information of the plurality of engineering machines; performing frequency domain analysis on the second positioning information of the plurality of engineering machines to obtain frequency domain characteristics of each engineering machine; and based on the vertical distance and the frequency domain characteristics of each engineering machine, determining a target engineering machine matched with the loading of the target mine car in the plurality of engineering machines. According to the method, the accuracy and reliability of matching identification of loading of the engineering machinery and the mine car are improved.

Description

Technical Field

[0001] This application relates to the field of engineering machinery technology, and in particular to a method, device, equipment and medium for matching engineering machinery to vehicles. Background Technology

[0002] In open-pit coal mining, multiple excavators and mine cars work together to complete ore extraction through processes such as excavation, loading, and transportation. The matching relationship between the excavators and mine cars is crucial for measurement work.

[0003] In related technologies, matching the relationship between excavators and mine cars in open-pit coal mines mainly relies on the following two methods: First, judgment is based on positioning information, the stopped state of the mine car, and vibration signals. This involves inferring loading events by detecting whether the mine car has stopped moving and whether it exhibits a specific vibration pattern. Second, matching is based on video recognition. This involves capturing on-site video through cameras and using image recognition technology to extract the excavator's serial number or behavioral characteristics to match the loading relationship. However, methods based on positioning and vibration signals are susceptible to interference from multiple devices clustered together (e.g., multiple mine cars and excavators operating at close range), leading to overlapping positioning or signal confusion. Furthermore, vibrations from external impacts (e.g., blasting, mechanical collisions) can easily be misjudged as loading vibrations, causing matching errors. Video recognition methods require additional hardware such as cameras and vibration sensors, increasing cost and system complexity. Moreover, the recognition rate is limited by environmental factors (e.g., insufficient light, dust obstruction, weather conditions), and it is difficult to clearly capture the excavator's serial number while the mine car is in motion, resulting in reduced recognition reliability.

[0004] Therefore, there is a need for a vehicle matching solution for engineering machinery that can improve the accuracy and reliability of vehicle matching identification. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and medium for matching construction machinery with mining trucks, which can improve the accuracy and reliability of matching and identifying construction machinery with mining trucks.

[0006] In a first aspect, embodiments of this application provide a method for matching engineering machinery to a vehicle, including:

[0007] Obtain the first location information of the target mining truck and the second location information of multiple construction machinery;

[0008] Analyze the first positioning information and fit the reversing trajectory of the target mining truck to obtain the trajectory.

[0009] Based on the reversing trajectory and the second positioning information of the multiple construction machines, determine the vertical distance of each construction machine from the reversing trajectory;

[0010] Frequency domain analysis is performed on the second positioning information of the multiple construction machines to obtain the frequency domain characteristics of each construction machine;

[0011] Based on the vertical distance and frequency domain characteristics of each piece of engineering machinery, a target engineering machinery that matches the loading of the target mining truck is determined from among the multiple pieces of engineering machinery.

[0012] In one possible implementation, determining the target mining machinery that matches the loading of the target mining truck from among the multiple mining machines, based on the vertical distance and frequency domain characteristics of each mining machine, includes:

[0013] The vertical distance and frequency domain features of each engineering machine are input into the loading pattern recognition model. In the loading pattern recognition model, the loading matching probability between each engineering machine and the target mining truck is obtained based on the weights of the learned vertical distance and frequency domain features and the loading matching probability, respectively.

[0014] The engineering machinery with the highest loading matching probability is taken as the target engineering machinery for loading and matching with the target mining truck.

[0015] In one possible implementation, the weights are determined based on an attention mechanism.

[0016] In one possible implementation, determining the vertical distance from each piece of construction machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of the multiple construction machinery includes:

[0017] Based on the first positioning information and the second positioning information, multiple candidate engineering machines that may be loaded onto the target mining truck are selected from the multiple engineering machines.

[0018] Based on the reversing trajectory and the second positioning information of the candidate construction machinery, the vertical distance from the candidate construction machinery to the reversing trajectory is determined.

[0019] In one possible implementation, the step of screening multiple candidate construction machinery that may be used to load the target mining truck from among the multiple construction machinery based on the first positioning information and the second positioning information includes:

[0020] Based on the loading time of the target mining truck and the preset duration, determine the target time before the loading time;

[0021] Based on the first positioning information and the second positioning information, determine the Euclidean distance between the multiple engineering machines and the target mining truck at the target time;

[0022] Among the multiple construction machinery vehicles, those that meet the distance requirements according to the European distance are selected as multiple candidate construction machinery vehicles that may be loaded onto the target mining truck.

[0023] In one possible implementation, the step of performing frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery includes:

[0024] Fourier transform is used to perform frequency domain analysis on the second positioning information of the engineering machinery to obtain the frequency domain characteristics of the engineering machinery.

[0025] In one possible implementation, the step of performing frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery includes:

[0026] Wavelet transform is used to perform frequency domain analysis on the second positioning information of the engineering machinery to obtain the frequency domain characteristics of the engineering machinery.

[0027] Secondly, embodiments of this application provide a vehicle-mounted matching device for engineering machinery, comprising:

[0028] The acquisition module is used to acquire the first positioning information of the target mining truck and the second positioning information of multiple engineering machinery.

[0029] The processing module is used to analyze the first positioning information and fit the reversing trajectory of the target mining truck; determine the vertical distance of each piece of engineering machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of the multiple engineering machines; perform frequency domain analysis on the second positioning information of the multiple engineering machines to obtain the frequency domain characteristics of each engineering machine; and determine the target engineering machine that matches the loading of the target mining truck among the multiple engineering machines based on the vertical distance and frequency domain characteristics of each engineering machine.

[0030] Thirdly, embodiments of this application provide an electronic device, including:

[0031] The processor, and the memory that is in communication with the processor;

[0032] Memory is used to store instructions that the computer executes;

[0033] The processor is configured to execute computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect described above.

[0035] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the first aspect and / or various possible implementations of the first aspect as described above.

[0036] This application provides a method, apparatus, equipment, and medium for matching engineering machinery loading onto and off target mining trucks. It can fit the reversing trajectory of the target mining truck based on its first positioning information to characterize the loading action. The shortest distance between the engineering machinery and the target mining truck can be determined based on the vertical distance between each piece of engineering machinery and its reversing trajectory. The motion state patterns of each piece of engineering machinery can be effectively mined based on its frequency domain characteristics, thereby determining its working mode. This allows for accurate identification of the target engineering machinery from among multiple machines, matching it with the target mining truck, based on the vertical distance and frequency domain characteristics of each machine. By fusing and analyzing multi-source data such as positioning information, reversing trajectory, and frequency domain characteristics, precise matching of the loading relationship between engineering machinery and mining trucks can be achieved. This effectively avoids interference from multiple devices and external signals, reducing the false positive rate. Furthermore, it is unaffected by environmental factors, adapting to various complex environments and improving environmental robustness, thus significantly improving the accuracy and reliability of the matching and identification of engineering machinery and mining truck loading. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0038] Figure 1 This is a system architecture diagram of an embodiment of this application;

[0039] Figure 2 This is a flowchart of a method for matching engineering machinery to vehicles according to an embodiment of this application;

[0040] Figure 3 This is a schematic diagram of frequency domain analysis according to an embodiment of this application;

[0041] Figure 4 This is a schematic diagram of the structure of an engineering machinery loading and matching device according to an embodiment of this application;

[0042] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0043] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0044] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0045] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0046] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0047] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0048] The engineering machinery loading and matching method, device, equipment and medium of this application can be used in the field of engineering machinery, and can also be used in any field other than engineering machinery, such as equipment matching, etc. The application field of the engineering machinery loading and matching method, device, equipment and medium of this application is not limited.

[0049] The engineering machinery loading and matching method, device, equipment and medium of this application can be applied to the matching of loading relationship between engineering machinery and mine cars in mining scenarios such as open-pit coal mines. As long as the engineering machinery is equipped with a positioning module, the engineering machinery loading and matching method, device, equipment and medium of this application can be applied.

[0050] In open-pit coal mining, multiple excavators and mine cars work together to complete ore extraction through processes such as excavation, loading, and transportation. The matching relationship between the excavators and mine cars is crucial for measurement work.

[0051] In related technologies, the matching of the relationship between excavators and mine car loading in open-pit coal mines mainly relies on the following two methods:

[0052] (i) Judgment is made based on positioning information, the stopping status of the mine car and vibration signals. The loading event is inferred by detecting whether the mine car has stopped moving and whether a specific vibration pattern has been generated.

[0053] (ii) Matching based on video recognition: On-site video is collected by camera, and image recognition technology is used to extract excavator number or behavioral characteristics, and then the loading relationship is matched.

[0054] However, the accuracy and reliability of both methods for vehicle matching identification are not high.

[0055] (i) Methods based on positioning and vibration signals are susceptible to interference from multiple devices clustered together (such as multiple mining trucks and excavators operating in close proximity), leading to overlapping positioning or signal confusion. At the same time, vibrations generated by external impacts on site (such as blasting or mechanical collisions) are easily misjudged as loading vibrations, resulting in matching errors.

[0056] (ii) Video recognition methods require additional hardware such as cameras and vibration sensors, which increases costs and system complexity. Furthermore, the recognition rate is limited by environmental factors (such as insufficient light, dust obstruction, and weather conditions). It is difficult to clearly capture the excavator number when the mining truck is in motion, which reduces the reliability of recognition.

[0057] Based on the above-mentioned technical problems, the inventive concept of this application is to provide a vehicle matching solution for engineering machinery that can improve the accuracy and reliability of vehicle matching identification.

[0058] This application provides a method, apparatus, equipment, and medium for matching engineering machinery loading onto and off target mining trucks. It can fit the reversing trajectory of the target mining truck based on its first positioning information to characterize the loading action. The shortest distance between the engineering machinery and the target mining truck can be determined based on the vertical distance between each piece of engineering machinery and its reversing trajectory. The motion state patterns of each piece of engineering machinery can be effectively mined based on its frequency domain characteristics, thereby determining its working mode. This allows for accurate identification of the target engineering machinery from among multiple machines, matching it with the target mining truck, based on the vertical distance and frequency domain characteristics of each machine. By fusing and analyzing multi-source data such as positioning information, reversing trajectory, and frequency domain characteristics, precise matching of the loading relationship between engineering machinery and mining trucks can be achieved. This effectively avoids interference from multiple devices and external signals, reducing the false positive rate. Furthermore, it is unaffected by environmental factors, adapting to various complex environments and improving environmental robustness, thus significantly improving the accuracy and reliability of the matching and identification of engineering machinery and mining truck loading.

[0059] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0060] Figure 1 This is a system architecture diagram of an embodiment of this application, such as... Figure 1 As shown, the electronic device can communicate with the positioning modules of the target mining truck and the engineering machinery respectively to obtain the first positioning information of the target mining truck and the second positioning information of multiple engineering machinery; analyze the first positioning information to fit and obtain the reversing trajectory of the target mining truck; determine the vertical distance of each engineering machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of multiple engineering machinery; perform frequency domain analysis on the second positioning information of multiple engineering machinery to obtain the frequency domain characteristics of each engineering machinery; and determine the target engineering machinery that matches the target mining truck among the multiple engineering machinery based on the vertical distance and frequency domain characteristics of each engineering machinery.

[0061] Figure 2 This is a flowchart illustrating a method for matching and loading construction machinery onto a vehicle, according to an embodiment of this application. This embodiment describes the method using an electronic device as the executing entity. Figure 2 As shown, the method for matching construction machinery to vehicles may include the following steps:

[0062] S201: Obtain the first positioning information of the target mining truck and the second positioning information of multiple engineering machinery.

[0063] In this embodiment, the electronic device can be a terminal device such as a mobile phone or computer, or a server device such as a physical server or cloud server, or an integrated terminal-server device, as long as the electronic device can perform data acquisition and calculation.

[0064] In this embodiment, the construction machinery can be equipment related to loading operations of mining trucks, such as excavators, and no restrictions are imposed here.

[0065] In this embodiment, the multiple construction vehicles can be construction vehicles operating in the same working environment as the target mining truck.

[0066] In this embodiment, the first positioning information may be the latitude and longitude information of the target mining truck. The positioning module (GPS / BeiDou positioning) on ​​the target mining truck can collect the first positioning information of the target mining truck in real time and upload the first positioning information to the electronic device.

[0067] In this embodiment, the second positioning information can be the latitude and longitude information of the construction machinery. The positioning module (GPS / BeiDou positioning) of each construction machinery can obtain the second positioning information of the construction machinery in real time and upload the second positioning information to the electronic device.

[0068] In this embodiment, the sampling frequency of the first positioning information and the second positioning information can be flexibly set by those skilled in the art according to actual conditions. For example, it can be 1Hz, and no restrictions are imposed here.

[0069] S202: Analyze the first positioning information and fit the reversing trajectory of the target mining truck.

[0070] In this embodiment, the loading operation of the mine car requires a reversing operation. Therefore, the loading operation of the target mine car can be accurately identified based on the reversing trajectory of the target mine car.

[0071] In this embodiment, the loading event of the target mine car has already occurred. Therefore, the loading point of the target mine car is known. The loading point of the target mine car can be used as the endpoint to deduce a certain number of data sampling points of the first positioning information (e.g., 10 data sampling points before the loading point) and curve fitting can be performed to obtain the reversing trajectory of the target mine car (e.g., a cubic polynomial curve, or other curves, without any restrictions).

[0072] S203: Based on the reversing trajectory and the second positioning information of multiple construction machines, determine the vertical distance of each construction machine from the reversing trajectory.

[0073] In this embodiment, after determining the reversing trajectory, a certain time before the loading time of the target mining truck can be determined (for example, the time corresponding to the first data sampling point in the trajectory, i.e., the time of the 10th data sampling point backwards), and the vertical distance from each piece of engineering machinery to the reversing trajectory at that time can be calculated.

[0074] S204: Perform frequency domain analysis on the second positioning information of multiple construction machines to obtain the frequency domain characteristics of each construction machine.

[0075] In this embodiment, for each of the multiple construction machines, the time sequence of the second positioning information of the construction machine before the loading time of the target mine truck can be determined, and the frequency domain analysis of the time sequence can be performed to obtain the amplitude spectrum of the construction machine. The relevant features of the amplitude spectrum can be extracted as the frequency domain features of the construction machine.

[0076] In this embodiment, when the construction machinery and the mining truck cooperate to carry out loading operations, the construction machinery has certain motion state patterns. By performing frequency domain analysis on the second positioning information of the construction machinery, the motion state patterns of the construction machinery can be fully explored. The frequency domain features can supplement and improve the identification of the construction machinery's working mode (whether it is loading mode).

[0077] S205: Based on the vertical distance and frequency domain characteristics of each piece of engineering machinery, determine the target engineering machinery that matches the loading of the target mining truck among multiple pieces of engineering machinery.

[0078] In this embodiment, a pre-trained classification model can be used to analyze the vertical distance and frequency domain characteristics of each engineering machine to determine the probability of matching each engineering machine with the target mining truck.

[0079] In this embodiment, the smaller the vertical distance from the construction machinery to the reversing trajectory, the closer it is to the target mining truck, and the greater the probability that it is the target construction machinery that matches the loading of the target mining truck. Furthermore, the frequency domain characteristics of the construction machinery can supplement and improve the identification of its working mode (whether it is in loading mode). Therefore, by analyzing the vertical distance and frequency domain characteristics of each construction machinery, the target construction machinery that matches the loading of the target mining truck can be accurately determined from among multiple construction machinery.

[0080] In this embodiment, the reversing trajectory of the target mining truck can be fitted based on the first positioning information of the target mining truck to characterize its loading action. The shortest distance between the engineering machinery and the target mining truck can be determined based on the vertical distance between each piece of machinery and its reversing trajectory. The motion state patterns of each piece of machinery can be effectively mined based on its frequency domain characteristics, thereby determining its working mode. This allows for accurate identification of the target engineering machinery that matches the loading of the target mining truck from among multiple machines, based on the vertical distance and frequency domain characteristics of each machine. By fusing and analyzing multi-source data such as positioning information, reversing trajectory, and frequency domain characteristics, precise matching of the loading relationship between engineering machinery and mining trucks can be achieved. This effectively avoids interference from multiple devices and external signals, reducing the false positive rate. Furthermore, it is unaffected by environmental factors, adapting to various complex environments and improving environmental robustness, thus greatly improving the accuracy and reliability of the matching and identification of engineering machinery and mining truck loading.

[0081] In one possible implementation, step S205, based on the vertical distance and frequency domain characteristics of each piece of engineering machinery, determines the target engineering machinery that matches the loading of the target mining truck among multiple pieces of engineering machinery, and may include:

[0082] S11: Input the vertical distance and frequency domain features of each engineering machine into the loading pattern recognition model. In the loading pattern recognition model, based on the weights of the learned vertical distance and frequency domain features and the loading matching probability, the loading matching probability of each engineering machine and the target mining truck is obtained according to the vertical distance and frequency domain features.

[0083] S12: Select the engineering machinery with the highest loading matching probability as the target engineering machinery for loading and matching with the target mining truck.

[0084] In this embodiment, the loading pattern recognition model can identify the working mode of the construction machinery (whether it is a loading mode). The input is the vertical distance and frequency domain features of the construction machinery, and the output is the loading matching probability between the construction machinery and the mining truck.

[0085] In this embodiment, the loading pattern recognition model can be trained by a classification model. The training samples can be labeled sample data. The labels can be the loading matching relationship (match / mismatch) between the construction machinery and the mining truck. The sample data can include the vertical distance and frequency domain features of the construction machinery (and the reversing trajectory of the mining truck).

[0086] In this embodiment, the loading pattern recognition model can be obtained by iteratively training with the objective function of minimizing cross-entropy loss and L1 regularization, and optimizing the model parameters. During the training process, linear weighting can be introduced into the model so that the model learns the weights of vertical distance and frequency domain features with the loading matching probability, and has the ability to learn weights.

[0087] In this embodiment, the frequency domain characteristics may include, but are not limited to, the main frequency amplitude, spectral entropy, low-frequency energy ratio, number of peaks, etc. Those skilled in the art can set them flexibly according to actual conditions, and no restrictions are imposed here.

[0088] In this embodiment, when there are multiple frequency domain features, each frequency domain feature can correspond to a different weight.

[0089] In this embodiment, the classification model can be iteratively trained based on labeled sample data, and linear weighting is introduced during the training process, enabling the trained loading pattern recognition model to possess pattern recognition and weight learning capabilities. In practical applications, the vertical distance and frequency domain features of each piece of machinery are input into the loading pattern recognition model to obtain the loading matching probability between each piece of machinery and the target mining truck. Based on the machinery with the highest loading matching probability, the target machinery matching the target mining truck can be accurately identified. This method is unaffected by environmental factors, adapts to various complex environments, and improves environmental robustness.

[0090] In one possible implementation, the weights in step S11 above can be determined based on an attention mechanism.

[0091] In this embodiment, during the training process of the loading pattern recognition model, an attention mechanism can be used instead of linear weighting, allowing the model to dynamically adjust the weights of vertical distance and various frequency domain features, thereby improving the robustness and performance of the model and further enhancing the accuracy and reliability of the matching and recognition of engineering machinery and mining truck loading.

[0092] In one possible implementation, step S203, which determines the vertical distance from each piece of construction machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of multiple construction machinery, may include:

[0093] S21: Based on the first and second positioning information, select multiple candidate engineering machines that may be used to load the target mining truck from among multiple engineering machines.

[0094] S22: Based on the reversing trajectory and the second positioning information of the candidate construction machinery, determine the vertical distance from the candidate construction machinery to the reversing trajectory.

[0095] In this embodiment, before determining the vertical distance of each piece of engineering machinery to the reversing trajectory, multiple pieces of engineering machinery can be screened based on the first positioning information and the second positioning information. Only the loading matching probability of the candidate engineering machinery and the target mining truck is calculated. While reducing the amount of calculation, it can also effectively eliminate the interference of multiple equipment clusters and reduce the misjudgment rate.

[0096] In one possible implementation, step S21, which involves selecting multiple candidate mining machines from among multiple mining machines that may be used to load the target mining truck based on the first and second positioning information, may include:

[0097] S31: Determine the target time before the loading time based on the loading time of the target mine car and the preset duration.

[0098] S32: Based on the first positioning information and the second positioning information, determine the Euclidean distance between the multiple engineering machines and the target mining truck at the target time.

[0099] S33: Among multiple construction machinery, those that meet the distance requirements according to the European distance are selected as multiple candidate construction machinery that may be used to load the target mining truck.

[0100] In this embodiment, the preset duration can be flexibly set by those skilled in the art according to actual conditions. For example, the duration for 10 data sampling points is not limited here.

[0101] In this embodiment, the loading event of the target mining truck has already occurred. Therefore, the loading time of the target mining truck is known. The target time can be a time point (e.g., the sampling time of 10 data points) before the loading time.

[0102] In this embodiment, the Euclidean distance meets the distance requirement, which can be that the Euclidean distance is less than a preset distance threshold. Those skilled in the art can flexibly set the distance threshold according to actual conditions, for example, it can be 50m, and no restrictions are imposed here.

[0103] In this embodiment, by determining the target time before the loading time, the positioning information of the target mine car at the target time can be determined from the first positioning information. The positioning information of each piece of machinery can be determined based on the second positioning information. Based on the positioning information of the mine car and each piece of machinery, the Euclidean distances between the multiple pieces of machinery and the target mine car can be calculated. Since the machinery cannot be too far away when loading the mine car, the candidate machinery that may be used to load the target mine car can be accurately selected based on the Euclidean distances between the multiple pieces of machinery and the target mine car.

[0104] In one possible implementation, step S204 above, which performs frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery, may include:

[0105] Fourier transform is used to perform frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery.

[0106] In this embodiment, the frequency domain characteristics may include, but are not limited to, the main frequency amplitude, spectral entropy, low-frequency energy ratio, number of peaks, etc. Those skilled in the art can set them flexibly according to actual conditions, and no restrictions are imposed here.

[0107] In this embodiment, the second positioning information of the construction machinery can be time-series data composed of positioning information of the construction machinery at different sampling times.

[0108] In this embodiment, the low-frequency energy can be flexibly set according to actual conditions, for example, 0-0.5Hz, without any restrictions.

[0109] In this embodiment, the number of peaks can be the number of times a certain peak appears in the spectrum. Peaks that are greater than or equal to 70% (or other proportions) of the maximum peak can be regarded as the same peak. The number of peaks can be used to count the number of times the same peak appears.

[0110] For example, Figure 3 This is a schematic diagram of frequency domain analysis according to an embodiment of this application, as shown below. Figure 3 As shown, Figure 3 (a) shows the relationship between the latitude / longitude offset of the construction machinery and time before frequency domain analysis, assuming the construction machinery and mine car loading are not matched; (b) shows the relationship between the latitude / longitude offset of the construction machinery and time after frequency domain analysis, assuming the construction machinery and mine car loading are not matched; (c) shows the relationship between the latitude / longitude offset of the construction machinery and time before frequency domain analysis, assuming the construction machinery and mine car loading are matched; (d) shows the relationship between the latitude / longitude offset of the construction machinery and time after frequency domain analysis, assuming the construction machinery and mine car loading are matched. Figure 3 As shown in (a) and (c), the latitude / longitude offset of the construction machinery changes differently with time depending on whether the machinery and the mining truck are matched or not. Figure 3 As shown in (b) and (d), the frequency domain features extracted after frequency domain analysis are different depending on whether the engineering machinery and the mining truck are matched or not.

[0111] In this embodiment, Fourier transform can be used to perform frequency domain analysis on the second positioning information of the construction machinery. After removing the DC component, the normalized amplitude spectrum is calculated, and the amplitude spectrum is analyzed to obtain the main frequency amplitude, spectral entropy, low-frequency energy ratio, peak number, etc., which can characterize the frequency domain features of the motion state law of the construction machinery.

[0112] In another possible implementation, step S204 above, which performs frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery, may include:

[0113] Wavelet transform is used to perform frequency domain analysis on the second positioning information of the construction machinery to obtain the frequency domain characteristics of the construction machinery.

[0114] In this embodiment, wavelet transform can be used instead of Fourier transform to perform frequency domain analysis on the second positioning information of the engineering machinery, and time-frequency analysis can be added to capture non-stationary signal features, thereby improving the accuracy and comprehensiveness of frequency domain features.

[0115] The following describes the engineering machinery loading and matching method of this application with a specific embodiment.

[0116] In one specific embodiment, the electronic device needs to measure the loading and matching relationship between the excavator and the mine car in an open-pit coal mine operation. Taking the target mine car A as an example, the specific loading and matching process is as follows;

[0117] The first step is for the electronic device to acquire the first positioning information collected by the positioning module of the target mining truck A, and the second positioning information collected by the positioning modules of multiple construction machines in the working condition.

[0118] The second step involves the electronic device determining the loading point of the target mining truck A, and using this loading point as the endpoint, it reverses the first positioning information of the previous 10 data sampling points, and then performs curve fitting to obtain the reversing trajectory of the target mining truck.

[0119] The third step involves the electronic equipment determining the loading time of the target mine car A, and determining the target time for the sampling duration of 10 data points prior to the loading time. It also determines the positioning information of the target mine car A and the positioning information of multiple engineering machines at the target time. Based on the positioning information of the mine car and the positioning information of multiple engineering machines, the Euclidean distance between the multiple engineering machines and the target mine car is calculated.

[0120] The fourth step involves the electronic equipment identifying multiple engineering machines that are less than 50 meters away from the target mining truck as potential candidates for loading the target mining truck.

[0121] Fifth, the electronic device determines the vertical distance from the candidate construction machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of the candidate construction machinery.

[0122] The sixth step involves using Fourier transform in the electronic device to perform frequency domain analysis on the second positioning information of the candidate engineering machinery, thereby obtaining the frequency domain characteristics of the candidate engineering machinery.

[0123] The seventh step involves the electronic device inputting the vertical distance and frequency domain features of each candidate engineering machinery into the loading pattern recognition model. In the loading pattern recognition model, based on the weights of the learned vertical distance and frequency domain features and the loading matching probability, the loading matching probability between each candidate engineering machinery and the target mining truck is obtained according to the vertical distance and frequency domain features.

[0124] The eighth step involves the electronic equipment selecting the candidate engineering machinery with the highest loading matching probability as the target engineering machinery for loading and matching with the target mining truck.

[0125] Figure 4 This is a schematic diagram of the structure of an engineering machinery loading and matching device according to an embodiment of this application, as shown below. Figure 4 As shown, the engineering machinery loading and matching device includes: an acquisition module 41, used to acquire the first positioning information of the target mining truck and the second positioning information of multiple engineering machinery; a processing module 42, used to analyze the first positioning information and fit the reversing trajectory of the target mining truck; determine the vertical distance of each engineering machinery to the reversing trajectory based on the reversing trajectory and the second positioning information of multiple engineering machinery; perform frequency domain analysis on the second positioning information of multiple engineering machinery to obtain the frequency domain characteristics of each engineering machinery; and determine the target engineering machinery that is matched with the target mining truck among the multiple engineering machinery based on the vertical distance and frequency domain characteristics of each engineering machinery.

[0126] The engineering machinery loading and matching device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0127] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application, as shown below. Figure 5 As shown, the electronic device includes: a processor 501 and a memory 502 communicatively connected to the processor 501; the memory 502 stores computer-executable instructions; the processor 501 executes the computer-executable instructions stored in the memory 502 to implement the steps of the engineering machinery loading and matching method in the above-described method embodiments.

[0128] In the aforementioned electronic device, the memory 502 and the processor 501 are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines, such as a bus connection. The memory 502 stores computer-executable instructions that implement data access control methods, including at least one software functional module that can be stored in the memory 502 in the form of software or firmware. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502.

[0129] The memory 502 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 502 stores programs, which are then executed by the processor 501 upon receiving execution instructions. Furthermore, the software programs and modules within the memory 502 may include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components.

[0130] Processor 501 can be an integrated circuit chip with signal processing capabilities. The aforementioned processor 501 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0131] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the steps of the various method embodiments of this application.

[0132] An embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the various method embodiments of this application.

[0133] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0134] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0135] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0136] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0137] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0138] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

[0139] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An engineered machine loading matching method, characterized by, The method comprises the following steps: obtaining first positioning information of a target mine car and second positioning information of a plurality of engineering machines; analyzing the first positioning information to fit a reversing trajectory of the target mine car; determining the perpendicular distance of each engineering machine to the reversing trajectory according to the reversing trajectory and the second positioning information of the plurality of engineering machines; performing frequency domain analysis on the second positioning information of the plurality of engineering machines to obtain the frequency domain characteristics of each engineering machine; determining a target engineering machine that matches the target mine car for loading based on the perpendicular distance and the frequency domain characteristics of each engineering machine.

2. The method of claim 1, wherein, The method of determining a target engineering machine that matches the target mine car for loading based on the perpendicular distance and the frequency domain characteristics of each engineering machine comprises: inputting the perpendicular distance and the frequency domain characteristics of each engineering machine into a loading mode recognition model, and obtaining the loading matching probability of each engineering machine and the target mine car based on the learned weights of the perpendicular distance and the frequency domain characteristics and the loading matching probability in the loading mode recognition model; selecting the engineering machine corresponding to the maximum loading matching probability as the target engineering machine that matches the target mine car for loading.

3. The method of claim 2, wherein, The weights are determined based on an attention mechanism.

4. The engineering machine loading matching method according to any one of claims 1 to 3, characterized by, The method of determining the perpendicular distance of each engineering machine to the reversing trajectory according to the reversing trajectory and the second positioning information of the plurality of engineering machines comprises: selecting a plurality of candidate engineering machines that are likely to load the target mine car from the plurality of engineering machines based on the first positioning information and the second positioning information; determining the perpendicular distance of the candidate engineering machines to the reversing trajectory based on the reversing trajectory and the second positioning information of the candidate engineering machines.

5. The method of claim 4, wherein, The method of selecting a plurality of candidate engineering machines that are likely to load the target mine car from the plurality of engineering machines based on the first positioning information and the second positioning information comprises: determining a target time before the loading time of the target mine car based on the loading time of the target mine car and a preset time length; determining the Euclidean distance between the plurality of engineering machines and the target mine car at the target time based on the first positioning information and the second positioning information; selecting the engineering machines corresponding to the Euclidean distances that meet the distance requirement as the plurality of candidate engineering machines that are likely to load the target mine car from the plurality of engineering machines.

6. The engineering machine loading matching method according to any one of claims 1 to 3, characterized by, The method of performing frequency domain analysis on the second positioning information of the engineering machine to obtain the frequency domain characteristics of the engineering machine comprises: performing frequency domain analysis on the second positioning information of the engineering machine by using Fourier transform to obtain the frequency domain characteristics of the engineering machine.

7. The construction machine loading matching method according to any one of claims 1 to 3, characterized by, The method of performing frequency domain analysis on the second positioning information of the engineering machine to obtain the frequency domain characteristics of the engineering machine comprises: performing frequency domain analysis on the second positioning information of the engineering machine by using wavelet transform to obtain the frequency domain characteristics of the engineering machine.

8. An engineered machine loading matching device, characterized by, The method comprises the following steps: an acquisition module configured to obtain first positioning information of a target mine car and second positioning information of a plurality of engineering machines; The processing module is configured to analyze the first positioning information, fit a reverse trajectory of the target mine car, determine a perpendicular distance from each engineering machine to the reverse trajectory according to the reverse trajectory and second positioning information of the multiple engineering machines, perform frequency domain analysis on the second positioning information of the multiple engineering machines to obtain frequency domain features of each engineering machine, and determine a target engineering machine matching loading of the target mine car from the multiple engineering machines based on the perpendicular distance and the frequency domain features of each engineering machine.

9. An electronic device, comprising: Comprise: a processor, and a memory connected to the processor in communication; the memory is configured to store computer execution instructions; the processor is configured to execute the computer execution instructions stored in the memory, so that the processor executes the engineering machine loading matching method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to realize the engineering machine loading matching method in any one of claims 1 to 7.

Images