Remote unattended control system and method for bucket-wheel stacker-reclaimer

Abstract

The invention relates to the field of automatic reclaimers, and particularly discloses a remote unattended control system and method for a bucket-wheel stacker-reclaimer, which utilizes a material level radar deployed at the head of a cantilever belt of the bucket-wheel stacker-reclaimer to monitor the vertical distance between the head of the belt and the surface of a coal pile in real time, and determines the position of the coal pile on the basis of the error between the actual distance and the preset distance. And the PLC is used for controlling the adjustment amount of the pitch angle of the cantilever of the bucket-wheel stacker-reclaimer. Meanwhile, in the material level radar distance measuring process, in order to improve the environmental adaptability and measurement accuracy of radar waves, environmental parameter data are further collected in real time through a multi-source sensor, a deep learning algorithm is introduced to conduct deep time sequence analysis on environmental parameters, and the radar transmitting power is intelligently adjusted based on the dynamic interaction change of the multi-source environmental parameters. In this way, dynamic compensation of radar wave propagation characteristics can be achieved, the influence of environmental factors on radar ranging precision is reduced, and therefore the automatic operation precision and safety of the bucket-wheel stacker-reclaimer are improved.

Description

Technical Field

[0001] The present application relates to the technical field of automatic material handling machines, and particularly to a remote unattended control system and method for a bucket wheel stacker-reclaimer. Background Art

[0002] As a key device in modern large-scale bulk material yards, the improvement of the automation and intelligence level of the bucket wheel stacker-reclaimer is of great significance for improving production efficiency and reducing operating costs. The control of traditional bucket wheel stacker-reclaimers mostly relies on on-site operations, which not only increases the workload and complexity of personnel, but also may pose a threat to the health of personnel due to the environment of the enclosed coal yard. In this regard, the invention patent with the publication number CN117088070A discloses a bucket wheel remote control method and system. First, it stratifies the coal stack and sets the parameters of the bucket wheel (such as coal taking points, stacking points, left and right boundaries, etc.), then starts the automatic positioning and operation program, uses a level radar to monitor the real-time height of the coal stack, and performs remote full-automatic control of coal taking and stacking according to the preset parameters, greatly reducing the need for human intervention. At the same time, during the operation process, this bucket wheel remote control method also supports fine-tuning the angle of the stacking or coal taking boundary and correcting parameter deviations to improve the operation accuracy and efficiency.

[0003] However, in the prior art, for the fine-tuning of the angle of the stacking or coal taking boundary and the correction of parameter deviations, it is mainly carried out by the operator manually setting and fine-tuning on the user interface of the control system. This not only depends on the experience and skills of the operator, but is also easily affected by human errors, resulting in limitations in the improvement of operation accuracy and efficiency. In addition, in the actual yard environment, changes in environmental factors such as ambient temperature and humidity will affect the propagation characteristics of radar waves, thereby affecting the monitoring accuracy of the level radar for the height of the coal stack. This will not only affect the accurate judgment of the position of the coal stack by the bucket wheel stacker-reclaimer, but may also cause safety accidents such as equipment collisions.

[0004] Therefore, an optimized remote unattended control system and method for a bucket wheel stacker-reclaimer are expected. Summary of the Invention

[0005] Embodiments of the present application aim to solve at least one of the technical problems existing in the prior art, and provide a remote unattended control system and method for a bucket wheel stacker-reclaimer. During the automatic stacking and reclaiming operation, a level radar deployed at the head of the cantilever belt of the bucket wheel stacker-reclaimer is used to continuously monitor the vertical distance between the head of the belt and the surface of the coal pile, and based on the error between the actual distance and the preset distance, the PLC controller is used to control the adjustment amount of the cantilever pitch angle of the bucket wheel stacker-reclaimer. At the same time, during the ranging process of the level radar, in order to improve the environmental adaptability and measurement accuracy of the radar wave, environmental parameter data is further collected in real time by multi-source sensors, and a deep learning algorithm is introduced to perform in-depth time series analysis on the environmental parameters, so as to intelligently adjust the radar transmission power based on the dynamic interaction changes of the multi-source environmental parameters. In this way, dynamic compensation for the propagation characteristics of the radar wave can be realized, reducing the influence of environmental factors on the radar ranging accuracy, thereby improving the automation operation accuracy and safety of the bucket wheel stacker-reclaimer.

[0006] On the one hand, embodiments of the present application provide a remote unattended control method for a bucket wheel stacker-reclaimer, including: stratifying the coal stack and setting the parameters of the bucket wheel machine; starting remote control, entering the automatic reclaiming mode, and selecting a coal stack for coal reclaiming; or entering the automatic stacking mode, setting an existing stacking point or creating a new stacking point; performing angle fine-tuning and parameter deviation correction on the stacking or reclaiming boundary.

[0007] Performing angle fine-tuning and parameter deviation correction on the stacking or reclaiming boundary includes:

[0008] Measuring the vertical distance between the head of the cantilever belt and the surface of the coal pile by using a non-contact level radar, and the non-contact level radar is installed at the head of the cantilever belt;

[0009] Extracting the preset vertical distance from the background database;

[0010] Calculating the difference between the vertical distance and the preset vertical distance to obtain the radar distance error;

[0011] Inputting the radar distance error into a cantilever pitch angle controller based on a PLC controller to obtain a control instruction, and the control instruction includes the adjustment amount of the cantilever pitch angle.

[0012] Optionally, measuring the vertical distance between the head of the cantilever belt and the surface of the coal pile by using a non-contact level radar, and the non-contact level radar is installed at the head of the cantilever belt, includes:

[0013] Obtaining a time queue of environmental parameters collected by a temperature and humidity sensor, and the environmental parameters include environmental temperature and environmental humidity;

[0014] Extract the environmental temperature time-series features and environmental humidity time-series features from the time queue of the environmental parameters to obtain the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features;

[0015] Perform in-depth collaborative analysis of the environmental parameters on the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features to obtain the implicit encoding vectors of the in-depth collaborative time-series features of the environmental parameters;

[0016] Based on the implicit encoding vectors of the in-depth collaborative time-series features of the environmental parameters, correct the current radar transmission power to obtain the corrected radar transmission power.

[0017] Optionally, extracting the environmental temperature time-series features and environmental humidity time-series features from the time queue of the environmental parameters to obtain the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features includes:

[0018] Use the environmental parameter time-series feature extractor based on the LSTM model to perform time-series encoding on the time queue of environmental temperature and the time queue of environmental humidity respectively to obtain the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features.

[0019] Optionally, performing in-depth collaborative analysis of the environmental parameters on the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features to obtain the implicit encoding vectors of the in-depth collaborative time-series features of the environmental parameters includes:

[0020] Extract the core information of the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features respectively to obtain the core information anchor encoding vectors of the environmental temperature time-series features and the core information anchor encoding vectors of the environmental humidity time-series features;

[0021] Perform multi-granularity time-series response interaction encoding on the core information anchor encoding vectors of the environmental temperature time-series features and the core information anchor encoding vectors of the environmental humidity time-series features to obtain the implicit encoding vectors of the in-depth collaborative time-series features of the environmental parameters.

[0022] Optionally, extracting the core information of the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features respectively to obtain the core information anchor encoding vectors of the environmental temperature time-series features and the core information anchor encoding vectors of the environmental humidity time-series features includes:

[0023] Construct the semantic self-correlation association matrices of the implicit encoding vectors of the environmental temperature time-series features and the implicit encoding vectors of the environmental humidity time-series features to obtain the semantic self-correlation association matrix of the environmental temperature time-series features and the semantic self-correlation association matrix of the environmental humidity time-series features;

[0024] Input the environmental temperature time-series feature semantic autocorrelation association matrix and the environmental humidity time-series feature semantic autocorrelation association matrix into the core information anchoring network based on autocorrelation decoupling respectively to obtain the environmental temperature time-series feature core information anchoring coding vector and the environmental humidity time-series feature core information anchoring coding vector.

[0025] Optionally, perform multi-granularity time-series response interaction coding on the environmental temperature time-series feature core information anchoring coding vector and the environmental humidity time-series feature core information anchoring coding vector to obtain the environmental parameter deep collaborative time-series feature implicit coding vector, including:

[0026] Input the environmental temperature time-series feature core information anchoring coding vector and the environmental humidity time-series feature core information anchoring coding vector into the feature granularity response interaction encoder to obtain the environmental parameter feature granularity response interaction coding vector;

[0027] Input the environmental temperature time-series feature core information anchoring coding vector and the environmental humidity time-series feature core information anchoring coding vector into the feature value granularity response interaction encoder to obtain the environmental parameter feature value granularity response interaction coding vector;

[0028] Fuse the environmental parameter feature granularity response interaction coding vector and the environmental parameter feature value granularity response interaction coding vector to obtain the environmental parameter deep collaborative time-series feature implicit coding vector.

[0029] Optionally, fuse the environmental parameter feature granularity response interaction coding vector and the environmental parameter feature value granularity response interaction coding vector to obtain the environmental parameter deep collaborative time-series feature implicit coding vector, including:

[0030] Based on the environmental parameter feature granularity response interaction coding vector, perform per-position feature interaction gradient constraint correction on the environmental parameter feature value granularity response interaction coding vector to obtain an optimized environmental parameter feature value granularity response interaction coding vector;

[0031] Based on the optimized environmental parameter feature value granularity response interaction coding vector, perform feature distribution deviation correction on the environmental parameter feature granularity response interaction coding vector to obtain an optimized environmental parameter feature granularity response interaction coding vector;

[0032] Perform cascade fusion on the optimized environmental parameter feature value granularity response interaction coding vector and the optimized environmental parameter feature granularity response interaction coding vector to obtain the environmental parameter deep collaborative time-series feature implicit coding vector.

[0033] Optionally, based on the depth collaborative temporal feature implicit encoding vector of the environmental parameters, correcting the current radar transmission power to obtain the corrected radar transmission power includes:

[0034] Inputting the depth collaborative temporal feature implicit encoding vector of the environmental parameters into a correction coefficient generator based on a feedforward neural network model to obtain a radar transmission power correction coefficient;

[0035] Multiplying the radar transmission power correction coefficient by the current radar transmission power to obtain the corrected radar transmission power.

[0036] On the other hand, the present application provides a remote unattended control system for a bucket wheel stacker-reclaimer, including:

[0037] An actual vertical distance measurement module for using a non-contact level radar to measure the vertical distance between the head of the cantilever belt and the surface of the coal pile, and the non-contact level radar is installed at the head of the cantilever belt;

[0038] A preset vertical distance extraction module for extracting a preset vertical distance from a background database;

[0039] A radar distance error calculation module for calculating the difference between the vertical distance and the preset vertical distance to obtain a radar distance error;

[0040] A control instruction generation module for inputting the radar distance error into a cantilever pitch angle controller based on a PLC controller to obtain a control instruction, and the control instruction includes a cantilever pitch angle adjustment amount.

[0041] Compared with the prior art, the remote unattended control system and method for a bucket wheel stacker-reclaimer provided by the present application, during the automatic stacking and reclaiming operation process, uses a level radar deployed at the head of the cantilever belt of the bucket wheel stacker-reclaimer to real-time monitor the vertical distance between the head of the belt and the surface of the coal pile, and based on the error between the actual distance and the preset distance, uses a PLC controller to control the cantilever pitch angle adjustment amount of the bucket wheel stacker-reclaimer. At the same time, during the ranging process of the level radar, to improve the environmental adaptability and measurement accuracy of the radar wave, further collect environmental parameter data in real time through multi-source sensors, and introduce a deep learning algorithm to perform in-depth temporal analysis on the environmental parameters, so as to intelligently adjust the radar transmission power based on the dynamic interaction changes of multi-source environmental parameters. In this way, dynamic compensation for the radar wave propagation characteristics can be achieved, reducing the influence of environmental factors on the radar ranging accuracy, thereby improving the automation operation accuracy and safety of the bucket wheel stacker-reclaimer. Description of the Drawings

[0042] Figure 1 Is a flowchart of a remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0043] Figure 2 It is a flowchart of sub-step S1 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of data flow of sub-step S1 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0045] Figure 4 It is a flowchart of sub-step S13 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0046] Figure 5 It is a flowchart of sub-step S132 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0047] Figure 6 It is a flowchart of sub-step S14 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application;

[0048] Figure 7 It is a block diagram of the remote unattended control system for a bucket wheel stacker-reclaimer according to an embodiment of the present application. Detailed implementation manners

[0049] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0050] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0051] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in order. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0052] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0053] It should be noted that in the present application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the data is located and obtaining authorization from the owner of the corresponding device.

[0054] As mentioned in the above background art, Patent CN117088070A proposes a remote unattended control method and system for a bucket wheel stacker-reclaimer, which includes: stratifying the coal stack and setting the parameters of the bucket wheel machine. Start remote control, enter the automatic coal extraction mode, and select a coal stack for coal extraction. Or enter the automatic stacking mode, set an existing stacking point or create a new stacking point. Perform angle fine-tuning and parameter deviation correction on the stacking or coal extraction boundary.

[0055] In the above remote unattended control method for a bucket wheel stacker-reclaimer, it is first necessary to comprehensively evaluate the coal stack, which includes understanding the basic physical dimensions such as the height, width, and length of the coal stack, and considering the internal density changes and possible non-uniformities. Through laser scanning technology to generate a three-dimensional model or using drone photography combined with image processing algorithms, detailed information of the coal stack can be obtained, and an accurate digital representation can be constructed to provide a basis for subsequent analysis. Based on these data, the coal stack is divided into several layers, and the thickness of each layer needs to comprehensively consider factors such as the operating range of the robotic arm, the excavation depth, and the maximum load-bearing capacity of the conveyor belt. Ideally, each layer should be thin enough to ensure efficient excavation, but not too thin to avoid increasing unnecessary operation times and energy consumption. Special attention should be paid to special areas near the ground or the top, because these places often have greater operation difficulties and risks. In order to ensure a smooth transition between layers, the specific positions and boundaries of each layer also need to be carefully planned to avoid the occurrence of faults or overlaps, which will affect the overall working efficiency.

[0056] After the coal stack is stratified, it enters the stage of setting the parameters of the bucket wheel stacker-reclaimer. During this process, it is necessary to determine the optimal set of operating parameters, covering multiple aspects such as the position of the bucket wheel, the feeding speed, and the slewing angle. Ensure that the bucket wheel can transition smoothly between layers to avoid equipment damage or material spillage caused by sudden movement. When formulating the bucket wheel trajectory, fully consider the actual undulation of the coal stack surface and reserve a certain safety margin. For example, when facing a coal stack with different heights, adjust the working path of the bucket wheel to adapt to the terrain changes while ensuring the consistency and continuity of the excavation effect. Reasonably adjust the feeding speed based on the differences in the characteristics of each layer of materials. For softer coal seams, the speed can be appropriately increased, while for harder parts, the rhythm needs to be slowed down to ensure the excavation effect while reducing wear. In addition, an appropriate slewing angle can not only improve work efficiency but also effectively reduce the load pressure on the machine. Therefore, based on the geometric shape of the coal stack and the surrounding environmental conditions, carefully calculate the optimal steering angle for each operating point. For example, in operations in narrow spaces, additional collision avoidance strategies need to be considered to prevent collisions with other facilities and ensure the safety and smoothness of the operation.

[0057] After the above preparatory work is completed, the next step is to start the remote control system and enter the automatic coal fetching mode or the automatic stacking mode. Through the user interface, the operator can easily switch the working mode, select a specific coal stack for coal fetching operations or set an existing stacking point for stacking. In the automatic coal fetching mode, the system will automatically locate to the designated coal stack according to the pre-set parameters and start the excavation operation. This process relies on the real-time data provided by high-precision sensors to ensure that the bucket wheel stacker-reclaimer operates at the correct position and angle. By real-time monitoring the state of the coal stack and the working conditions of the bucket wheel stacker-reclaimer, the system can dynamically adjust parameters such as the feeding speed and the excavation depth to cope with the changes in different layers of coal seams, ensuring the excavation efficiency and quality. This precise control not only improves work efficiency but also reduces energy consumption and extends the service life of the equipment.

[0058] When choosing to enter the automatic stacking mode, the operator can choose to use an existing stacking point or create a new one. If an existing stacking point is selected, simply select the corresponding coordinate position in the system to quickly start the stacking operation. When creating a new stacking point, specific geographical coordinates and parameters such as the desired height and shape need to be input. The system will automatically generate a stacking path based on this information to guide the bucket wheel stacker-reclaimer to stack according to the predetermined plan. Regardless of which mode, accurate data support is required to ensure the accuracy of the operation. For example, during the stacking process, use a non-contact level radar to real-time monitor the height of the coal pile and timely adjust the working state of the bucket wheel stacker-reclaimer to ensure the safety and efficiency of the stacking process. Through real-time data feedback, the system can continuously optimize the stacking path and parameters to ensure that each stacking reaches the best effect.

[0059] However, in the prior art, for the angular fine-tuning and parameter deviation correction of the stockpiling or coal-taking boundary, it is mainly manually set and fine-tuned by the operator on the user interface of the control system. This not only depends on the operator's experience and skills, but is also easily affected by human errors, resulting in limited improvement in operation accuracy and efficiency. In addition, in the actual yard environment, changes in environmental factors such as ambient temperature and humidity will affect the propagation characteristics of radar waves, and further affect the monitoring accuracy of the coal pile height by the level radar. This will not only affect the accurate judgment of the coal pile position by the bucket wheel stacker-reclaimer, but may also cause safety accidents such as equipment collisions. In view of the above technical problems, the present application proposes an optimized remote unattended control method for a bucket wheel stacker-reclaimer. During the automatic stacking and reclaiming operation process, it uses a level radar deployed at the head of the cantilever belt of the bucket wheel stacker-reclaimer to continuously monitor the vertical distance between the head of the belt and the surface of the coal pile, and based on the error between the actual distance and the preset distance, uses a PLC controller to control the adjustment amount of the cantilever pitch angle of the bucket wheel stacker-reclaimer. At the same time, during the ranging process of the level radar, in order to improve the environmental adaptability and measurement accuracy of the radar wave, environmental parameter data is continuously collected through multi-source sensors, and a deep learning algorithm is introduced to perform in-depth time-series analysis on the environmental parameters, so as to intelligently adjust the radar transmission power based on the dynamic interaction changes of multi-source environmental parameters. In this way, dynamic compensation for the radar wave propagation characteristics can be achieved, reducing the influence of environmental factors on the radar ranging accuracy, thereby improving the automation operation accuracy and safety of the bucket wheel stacker-reclaimer.

[0060] Figure 1 FIG. is a flowchart of a remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. As Figure 1 shown, the remote unattended control method for the bucket wheel stacker-reclaimer includes the steps of: S1, measuring the vertical distance between the head of the cantilever belt and the surface of the coal pile by using a non-contact level radar, and the non-contact level radar is installed at the head of the cantilever belt. S2, extracting a preset vertical distance from the background database. S3, calculating the difference between the vertical distance and the preset vertical distance to obtain a radar distance error. S4, inputting the radar distance error into a cantilever pitch angle controller based on a PLC controller to obtain a control instruction, and the control instruction includes an adjustment amount of the cantilever pitch angle.

[0061] In the above remote unattended control method for a bucket wheel stacker-reclaimer, in step S1, a non-contact level radar is used to measure the vertical distance between the head of the cantilever belt and the surface of the coal pile, and the non-contact level radar is installed at the head of the cantilever belt. It should be understood that the vertical distance between the head of the cantilever belt and the surface of the coal pile refers to the straight-line length from the measurement point installed at the head of the cantilever belt, vertically downward to the surface of the coal pile during the operation of the bucket wheel stacker-reclaimer. During actual operation, this vertical distance is dynamically changing and has an important impact on the coal-taking and coal-stacking operations of the bucket wheel stacker-reclaimer. For example, during coal-taking, if this vertical distance is too large, the bucket wheel may not be able to effectively take coal, resulting in low coal-taking efficiency. If this vertical distance is too small, the bucket wheel may collide with the coal pile, damaging the equipment. During coal-stacking, improper distance control will cause uneven coal-stacking, affecting the stability of the coal pile and subsequent use. Therefore, in order to ensure the efficient and safe operation of the bucket wheel stacker-reclaimer, this application uses a level radar installed at the head of the cantilever belt of the bucket wheel stacker-reclaimer to continuously monitor the vertical distance between the head of the belt and the surface of the coal pile, so as to dynamically adjust the cantilever pitch angle of the bucket wheel stacker-reclaimer based on the distance monitoring results, correct the position error during the operation, and ensure the operation accuracy of the bucket wheel stacker-reclaimer. Among them, Figure 2 FIG. is a flowchart of sub-step S1 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. Figure 3 FIG. is a schematic diagram of data flow of sub-step S1 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. As Figure 2 and Figure 3 shown, step S1 includes steps: S11, obtaining a time queue of environmental parameters collected by a temperature and humidity sensor, where the environmental parameters include environmental temperature and environmental humidity. S12, extracting the environmental temperature time series feature and the environmental humidity time series feature from the time queue of the environmental parameters to obtain an environmental temperature time series feature implicit coding vector and an environmental humidity time series feature implicit coding vector. S13, performing in-depth collaborative analysis of environmental parameters on the environmental temperature time series feature implicit coding vector and the environmental humidity time series feature implicit coding vector to obtain an environmental parameter in-depth collaborative time series feature implicit coding vector. S14, based on the environmental parameter in-depth collaborative time series feature implicit coding vector, correcting the current radar transmission power to obtain the corrected radar transmission power.

[0062] Specifically, in step S11, a time queue of environmental parameters collected by a temperature and humidity sensor is obtained. The environmental parameters include environmental temperature and environmental humidity. In particular, in the actual yard environment, the dynamic changes in environmental temperature and humidity will greatly interfere with the propagation characteristics of radar waves, thereby affecting the monitoring accuracy of the coal pile height by the level radar. Specifically, temperature changes will affect the density and dielectric constant of air, thereby changing the propagation path and speed of radar waves. An increase in humidity may lead to increased absorption and scattering of radar waves, causing signal attenuation. Usually, high-power radar transmission can enhance the propagation distance and penetration ability of radar waves to cope with environmental interference. However, excessive transmission power will not only increase energy consumption but also may cause interference to the surrounding environment and other equipment. Therefore, in order to improve the stability and accuracy of radar ranging under different environmental conditions, the present application further uses the temperature and humidity sensor to collect the time queue data of environmental temperature and environmental humidity to comprehensively master the dynamic change law of environmental temperature and humidity, and dynamically adjust the transmission power of the level radar based on this to ensure that the radar waves emitted by the level radar can accurately reach the target surface, return a stable echo signal, and at the same time reduce unnecessary energy consumption, thereby improving the accuracy and reliability of radar measurement.

[0063] Specifically, first, appropriate temperature and humidity sensors need to be selected. These sensors need to have characteristics such as high precision, good response speed, and long-term stability to ensure the authenticity and reliability of the collected data. In actual operation, according to different on-site environmental conditions, multiple sensors may need to be installed to cover the entire working area to ensure the comprehensiveness of data collection. For example, in a large bulk material yard, due to the vast site and possible local microclimate differences, reasonable distribution of sensors can effectively capture the temperature and humidity changes at different positions, avoiding deviations caused by single-point measurement.

[0064] After the sensors are selected, physical connection and power supply settings are carried out. Each type of sensor usually comes with a detailed installation guide. Follow the instructions in the manual to complete the wiring work to ensure stable and reliable power supply. At the same time, considering the quality and distance limitations of signal transmission, a signal amplifier or converter may be needed to enhance the signal strength when necessary to ensure that the data is accurately transmitted to the control system. During this process, it is necessary to pay attention to protecting the lines from external interference, such as using shielded cables and reasonably planning the wiring path to reduce the impact of electromagnetic interference on data accuracy.

[0065] After completing the hardware connection, enter the software configuration phase. First, new devices need to be added to the control system, and the corresponding communication protocols and address information need to be set. Modern industrial control networks mostly adopt standard communication protocols such as Modbus, Profibus, etc. These protocols define the data exchange format and access rules, facilitating the interconnection and interoperability of devices from different brands. According to the specific sensor model used and its supported communication methods, relevant parameters need to be correctly configured within the control system to ensure that the data stream from the sensor can be read smoothly. In addition, the sampling frequency needs to be adjusted according to specific application scenarios, that is, how often data collection is performed. An overly high sampling rate may cause an increased burden on the system, while an overly low rate may not be able to reflect environmental changes in a timely manner. Therefore, a balance needs to be found to meet actual requirements.

[0066] At this time, the control system will automatically initiate requests according to the preset sampling frequency, asking each sensor for the current environmental temperature and humidity values. After each query, the data returned by the sensor will be encapsulated into a message packet in a specific format, containing key information such as timestamp, temperature value, humidity value, etc., and then transmitted back to the control system through the established communication link. It should be noted that during the entire transmission process, any delay or loss may affect the accuracy of the final result. Therefore, effective error correction mechanisms need to be adopted, such as cyclic redundancy check (CRC) technology to detect and correct transmission errors and ensure data integrity.

[0067] As time goes by, the system will continuously accumulate a large amount of raw data, forming a continuous time series. This time series records the specific values of environmental temperature and humidity at each moment, constituting the basic material for subsequent analysis. To facilitate the management and utilization of these data, a dedicated space is usually allocated in the database for storage. Designing a reasonable database structure is the key to ensuring efficient data access and storage, generally including table structure design, index creation, etc. For temperature and humidity data, date-based partitioning storage can be considered, which can not only improve query efficiency but also facilitate future archiving and sorting. At the same time, to cope with the possible problem of a sharp increase in data volume, an expansion strategy needs to be planned in advance, such as adding storage nodes or adopting a distributed storage solution, etc.

[0068] In addition to basic data collection, attention also needs to be paid to how to improve the overall robustness and flexibility of the system. For example, in the face of sudden situations such as sensor failures or network interruptions, corresponding emergency measures should be in place to ensure the continuity of data collection. A common approach is to set up backup sensors, which automatically switch to the backup state to continue working when the main sensor fails. Or enable the local cache function when the network is unstable to temporarily store the data that cannot be uploaded in a timely manner and then upload it to the server after the connection is restored.

[0069] In the entire data acquisition process, security is also a factor that cannot be ignored. Especially in application scenarios involving remote monitoring and data transmission, it is particularly important to ensure that data is not illegally tampered with or stolen. To this end, encryption technology can be used to protect the data in transmission and prevent security threats such as man-in-the-middle attacks. At the same time, strict control should be exercised in user access rights management, and only necessary personnel should be granted the right to view and operate to avoid leakage of sensitive information. By establishing a sound security protection system, comprehensive protection can be provided for the data acquisition process.

[0070] Specifically, in step S12, the environmental temperature time series feature and the environmental humidity time series feature are extracted from the time queue of the environmental parameters to obtain an environmental temperature time series feature implicit coding vector and an environmental humidity time series feature implicit coding vector. It should be understood that this application takes into account that environmental temperature and humidity are continuously changing physical quantities with certain time series change characteristics. Therefore, in order to better capture the dynamic patterns of environmental changes, this application further uses deep learning technology to extract the environmental temperature time series feature and the environmental humidity time series feature from the time queue of the environmental parameters to obtain an environmental temperature time series feature implicit coding vector and an environmental humidity time series feature implicit coding vector. In a specific example of this application, an environmental parameter time series feature extractor based on the LSTM model is used to perform time series encoding on the time queue of environmental temperature and the time queue of environmental humidity respectively to obtain the environmental temperature time series feature implicit coding vector and the environmental humidity time series feature implicit coding vector. Those of ordinary skill in the art should know that the LSTM model is a special recurrent neural network (RNN) specifically designed to learn dependencies over long time intervals. It controls the information flow by introducing so-called "gates", including an input gate, a forget gate, and an output gate, enabling the model to selectively remember or forget information, thereby effectively capturing long-term dependencies and dynamic patterns in time series data. When dealing with continuously changing physical quantities such as environmental temperature and humidity, the LSTM model can accurately identify complex patterns and trends in the data, and then generate more accurate environmental temperature time series feature implicit coding vectors and environmental humidity time series feature implicit coding vectors, providing strong data support for subsequent analysis.

[0071] Specifically, in step S13, the environmental temperature time-series feature implicit encoding vector and the environmental humidity time-series feature implicit encoding vector are subjected to in-depth collaborative analysis of environmental parameters to obtain an in-depth collaborative time-series feature implicit encoding vector of environmental parameters. It should be understood that in practical applications, there is a certain correlation between environmental temperature and environmental humidity, and the effects of both on the radar wave propagation characteristics have a certain synergistic effect. Therefore, in order to more accurately describe the interaction between multi-dimensional environmental factors, the present application further performs in-depth collaborative analysis on the environmental temperature time-series feature implicit encoding vector and the environmental humidity time-series feature implicit encoding vector. By refining the core information of the environmental temperature time-series feature and the environmental humidity time-series feature and performing multi-level interactive response modeling analysis, the deep interaction between environmental temperature and environmental humidity is captured, so as to more accurately evaluate the comprehensive influence of environmental temperature and humidity on the radar wave propagation characteristics. Among them, Figure 4 is a flowchart of sub-step S13 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. As Figure 4 shown, step S13 includes the steps of: S131, respectively extracting the core information of the environmental temperature time-series feature implicit encoding vector and the environmental humidity time-series feature implicit encoding vector to obtain an environmental temperature time-series feature core information anchored encoding vector and an environmental humidity time-series feature core information anchored encoding vector. S132, performing multi-granularity time-series response interactive encoding on the environmental temperature time-series feature core information anchored encoding vector and the environmental humidity time-series feature core information anchored encoding vector to obtain the in-depth collaborative time-series feature implicit encoding vector of environmental parameters.

[0072] More specifically, in a specific example of the present application, step S131 includes: First, constructing a semantic self-correlation association matrix of the environmental temperature time-series feature implicit encoding vector and the environmental humidity time-series feature implicit encoding vector to obtain an environmental temperature time-series feature semantic self-correlation association matrix and an environmental humidity time-series feature semantic self-correlation association matrix, which is expressed by the formula:

[0073]

[0074] where, (·) T represents the transpose of a vector, v 1 represents the environmental temperature time-series feature implicit encoding vector, v 2 represents the environmental humidity time-series feature implicit encoding vector, M 1 represents the environmental temperature time-series feature semantic self-correlation association matrix, M 2 represents the environmental humidity time-series feature semantic self-correlation association matrix, is a linear mapping function.

[0075] That is, the present application first constructs a semantic autocorrelation association matrix of the environmental temperature time-series feature implicit encoding vector and the environmental humidity time-series feature implicit encoding vector to reveal the internal association structure of the environmental temperature time-series feature and the environmental humidity time-series feature respectively, so as to better understand the internal logic of the environmental temperature and environmental humidity changing over time. In a specific implementation, the mutual association between the constituent feature parts in the vector can be made explicit through an outer product operation to generate a semantic autocorrelation association matrix of the environmental temperature time-series feature and a semantic autocorrelation association matrix of the environmental humidity time-series feature, thereby capturing the internal semantic association pattern while retaining the global time-series structure of the environmental temperature and environmental humidity.

[0076] Then, the semantic autocorrelation association matrix of the environmental temperature time-series feature and the semantic autocorrelation association matrix of the environmental humidity time-series feature are respectively input into the core information anchoring network based on autocorrelation decoupling to obtain the core information anchoring encoding vector of the environmental temperature time-series feature and the core information anchoring encoding vector of the environmental humidity time-series feature, which is expressed by the formula:

[0077]

[0078] where, f Anchor (·) represents the core information anchoring network, decouple(·) represents the decoupling function, x 11 , x 1w , x 1i and x 1n respectively represent the 1st, 2nd, i-th and n-th row vectors in the semantic autocorrelation association matrix of the environmental temperature time-series feature, n is the number of rows of the semantic autocorrelation association matrix of the environmental temperature time-series feature, x 21 , x 22 , x 2i and x 2n respectively represent the 1st, 2nd, i-th and n-th row vectors in the semantic autocorrelation association matrix of the environmental humidity time-series feature, W 1i and W 2i respectively represent the environmental temperature time-series feature weight matrix and the environmental humidity time-series feature weight matrix, b 1i and b 2i respectively represent the environmental temperature time-series feature bias vector and the environmental humidity time-series feature bias vector, represents matrix multiplication, e 1i represents the environmental temperature time-series feature importance scoring factor corresponding to x 1i , e 2i represents the environmental humidity time-series feature importance scoring factor corresponding to x 2i , represents the environmental temperature local time-series feature importance scoring conversion vector, Represents the conversion vector of the importance score of the local temporal features of the environmental humidity, a 1i Represents e 1i The corresponding normalized importance score factor of the temporal features of the environmental temperature, a 2i Represents e 2i The corresponding normalized importance score factor of the temporal features of the environmental humidity, Sigmoid(·) represents the sigmoid function, c 1 Represents the core information anchoring coding vector of the temporal features of the environmental temperature, c 2 Represents the core information anchoring coding vector of the temporal features of the environmental humidity.

[0079] Here, in order to remove redundancy and noise in the features and extract the temporal core features of the environmental temperature and environmental humidity, the present application uses a core information anchoring network based on autocorrelation decoupling to refine and purify the internal information of the features of the semantic autocorrelation association matrix of the environmental temperature temporal features and the semantic autocorrelation association matrix of the environmental humidity temporal features. By performing feature decoupling, local feature importance evaluation, and feature weighted aggregation on the two, the feature parts highly correlated with the core semantics in the semantic autocorrelation association matrix of the environmental temperature temporal features and the semantic autocorrelation association matrix of the environmental humidity temporal features are highlighted, and at the same time, redundant information is denoised, so as to realize the anchoring of the temporal core features of the environmental temperature and environmental humidity, and obtain the core information anchoring coding vector of the environmental temperature temporal features and the core information anchoring coding vector of the environmental humidity temporal features.

[0080] More specifically, in step S132, multi-granularity temporal response interaction coding is performed on the core information anchoring coding vector of the environmental temperature temporal features and the core information anchoring coding vector of the environmental humidity temporal features to obtain the implicit coding vector of the deep collaborative temporal features of the environmental parameters. Specifically, after completing the core information anchoring, the present application further performs interactive response modeling analysis on the core information anchoring coding vector of the environmental temperature temporal features and the core information anchoring coding vector of the environmental humidity temporal features to capture the deep interaction pattern between the environmental temperature and humidity. Here, the present application adopts a multi-level interactive response analysis method, and through in-depth analysis from two levels of feature granularity and feature value granularity, the interactive influence of the environmental temperature and humidity at different scales is revealed, and the interactive response relationship between the environmental temperature and humidity is modeled more precisely. Among them, Figure 5 Is the flowchart of sub-step S132 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. As Figure 5As shown, the step S132 includes the steps of: S1321, inputting the environmental temperature time-series feature core information anchored encoding vector and the environmental humidity time-series feature core information anchored encoding vector into a feature granularity response interaction encoder to obtain an environmental parameter feature granularity response interaction encoding vector. S1322, inputting the environmental temperature time-series feature core information anchored encoding vector and the environmental humidity time-series feature core information anchored encoding vector into a feature value granularity response interaction encoder to obtain an environmental parameter feature value granularity response interaction encoding vector. S1323, fusing the environmental parameter feature granularity response interaction encoding vector and the environmental parameter feature value granularity response interaction encoding vector to obtain the environmental parameter deep synchronous time-series feature implicit encoding vector.

[0081] In a specific example of the present application, the step S1321 is expressed by the formula:

[0082]

[0083] where tanh(·) represents the tanh function, W VT represents the environmental parameter interaction feature weight matrix, b VT represents the environmental parameter interaction feature bias vector, and E granular represents the environmental parameter feature granularity response interaction encoding vector.

[0084] That is, at the feature granularity level, a feature interaction layer is constructed based on a neural network architecture. By learning the feature combination relationship between the environmental temperature time-series feature core information anchored encoding vector and the environmental humidity time-series feature core information anchored encoding vector, the co-variation and interaction effects of the two in the feature space are captured, and an environmental parameter feature granularity response interaction encoding vector is generated.

[0085] In a specific example of the present application, the step S1322 is expressed by the formula:

[0086]

[0087] where E value represents the environmental parameter feature value granularity response interaction encoding vector.

[0088] That is, at the feature value granularity level, the time-series interaction modeling between environmental temperature and environmental humidity returns to more underlying numerical operations. By performing element-wise interaction response encoding on the environmental temperature time-series feature core information anchored encoding vector and the environmental humidity time-series feature core information anchored encoding vector, the subtle association and mutual dependence relationship between the two in the time-series change are characterized, and an environmental parameter feature value granularity response interaction encoding vector is generated.

[0089] In a specific example of the present application, the step S1323 is expressed by the formula:

[0090] V f = concat[E granular ; E value

[0091] where concat[·;·] represents the concatenation operation, and V f represents the implicit encoding vector of the environmental parameter depth collaborative time series features.

[0092] That is, in order to comprehensively consider the interaction response information at different levels, the present application cascades and fuses the environmental parameter feature granularity response interaction coding vector and the environmental parameter feature value granularity response interaction coding vector to generate the implicit encoding vector of the environmental parameter depth collaborative time series features, so as to more completely describe the dynamic changes and interactions of environmental factors and provide a more reliable data basis for the subsequent radar transmission power regulation.

[0093] Specifically, in a preferred example of the present application, the step S1323 includes: First, based on the environmental parameter feature granularity response interaction coding vector, perform position-by-position feature interaction gradient constraint correction on the environmental parameter feature value granularity response interaction coding vector to obtain an optimized environmental parameter feature value granularity response interaction coding vector, which is expressed by the formula:

[0094]

[0095] Then, based on the optimized environmental parameter feature value granularity response interaction coding vector, perform feature distribution deviation correction on the environmental parameter feature granularity response interaction coding vector to obtain an optimized environmental parameter feature granularity response interaction coding vector, which is expressed by the formula:

[0096]

[0097] Finally, perform cascade fusion on the optimized environmental parameter feature value granularity response interaction coding vector and the optimized environmental parameter feature granularity response interaction coding vector to obtain the implicit encoding vector of the environmental parameter depth collaborative time series features, which is expressed by the formula:

[0098] V f = concat[E granular '; E value ']

[0099] where E gi is the feature value at the i-th position in E granular , and E vi is E value ​The eigenvalue at the i-th position, cos(·) represents the cosine function, E gi ′ is E gi The corresponding optimized eigenvalue, E vi ′ is E vi The corresponding optimized eigenvalue, E granular ′ is the optimized environmental parameter feature granularity response interaction coding vector, E value ′ is the optimized environmental parameter eigenvalue granularity response interaction coding vector, V f Represents the environmental parameter depth collaborative time-series feature implicit coding vector.

[0100] Here, the present application considers that the difference between the modeling representations of the feature granularity interaction and the eigenvalue granularity interaction between the environmental temperature and the environmental humidity may cause unstable perturbations in the feature manifold interface of the environmental parameter depth collaborative time-series feature implicit coding vector with multi-granularity information expression after fusion. Therefore, preferably, the present application further uses the environmental parameter eigenvalue granularity response interaction coding vector as an extensibility constraint representation to model the interface shape perturbation deviation of the overall feature interaction distribution during the diffusion process of each eigenvalue, that is, uses the interaction interface gradient under each eigenvalue granularity as a perturbation contribution factor to determine the growth index stabilization contribution of the gradient diffusion under eigenvalue interdependence, so as to achieve the growth mode gradient correction dominated by perturbation stabilization and improve the manifold interface stability of the environmental parameter depth collaborative time-series feature implicit coding vector.

[0101] Figure 6 Is a flowchart of sub-step S14 of the remote unattended control method for a bucket wheel stacker-reclaimer according to an embodiment of the present application. As Figure 6 Shown, the step S14 includes steps: S141, inputting the environmental parameter depth collaborative time-series feature implicit coding vector into a correction coefficient generator based on a feedforward neural network model to obtain a radar transmission power correction coefficient. S142, multiplying the radar transmission power correction coefficient by the current radar transmission power to obtain the corrected radar transmission power.

[0102] More specifically, in step S141, the depth collaborative temporal feature implicit encoding vector of the environmental parameters is input into a correction coefficient generator based on a feedforward neural network model to obtain a radar transmission power correction coefficient. Specifically, the feedforward neural network model performs non-linear transformation and feature extraction on the depth collaborative temporal feature implicit encoding vector of the environmental parameters through multiple hidden layers to gradually learn the high-order non-linear correlation between the environmental features and the radar transmission power, thereby mapping the depth collaborative temporal feature implicit encoding vector of the environmental parameters to the prediction space of the radar transmission power correction coefficient, and outputting a quantitative representation of the influence degree of the current environment on the radar wave propagation loss, that is, the radar transmission power correction coefficient.

[0103] More specifically, in step S142, the radar transmission power correction coefficient is multiplied by the current radar transmission power to obtain the corrected radar transmission power. That is, by multiplying the radar transmission power correction coefficient by the current radar transmission power, the propagation loss caused by environmental factors is compensated to obtain the corrected radar transmission power, so as to ensure that the radar signal can still maintain stable and efficient transmission under complex and changeable environmental conditions, and improve its detection performance and stability in different environments.

[0104] In the above remote unattended control method for a bucket wheel stacker-reclaimer, in step S2, a preset vertical distance is extracted from the background database. It should be understood that the preset vertical distance refers to the ideal vertical distance between the head of the cantilever belt and the surface of the coal pile preset according to the actual situation of the coal pile and the operation requirements before the bucket wheel stacker-reclaimer operates. This preset vertical distance is an important parameter for the automated operation of the bucket wheel stacker-reclaimer. During the actual operation, by comparing the actual vertical distance measured by the level radar with the preset vertical distance in real time, it can be judged whether the operation position of the bucket wheel stacker-reclaimer is accurate, and then it can be decided whether to adjust the cantilever pitch angle.

[0105] In the above remote unattended control method for a bucket wheel stacker-reclaimer, in step S3, the difference between the vertical distance and the preset vertical distance is calculated to obtain a radar distance error. Here, the radar distance error reflects the deviation degree between the current operation position of the cantilever of the bucket wheel stacker-reclaimer and the ideal operation position, and is used to guide the calculation of the adjustment amount of the subsequent cantilever pitch angle.

[0106] In the above remote unattended control method of the bucket wheel stacker-reclaimer, in step S4, the radar distance error is input into the boom pitch angle controller based on the PLC controller to obtain a control instruction, and the control instruction includes the boom pitch angle adjustment amount. It should be understood that the PLC controller, as the core control unit of the bucket wheel stacker-reclaimer, based on the input radar distance error, through the proportional, integral, and differential control algorithm (PID control algorithm), comprehensively considers the magnitude, change trend, and error accumulation of the error, so as to calculate an appropriate control amount, that is, the boom pitch angle adjustment amount, to drive the boom to perform pitching motion, so as to ensure that the boom of the bucket wheel stacker-reclaimer can be quickly and accurately adjusted to the preset operation position, and achieve high-precision position control in the automated operation process.

[0107] In summary, the remote unattended control method of the bucket wheel stacker-reclaimer based on the embodiments of the present application is elucidated. During the automatic stacking and reclaiming operation process, the level radar deployed at the head of the boom belt of the bucket wheel stacker-reclaimer is used to continuously monitor the vertical distance between the head of the belt and the surface of the coal pile. Based on the error between the actual distance and the preset distance, the PLC controller is used to control the boom pitch angle adjustment amount of the bucket wheel stacker-reclaimer. At the same time, during the ranging process of the level radar, in order to improve the environmental adaptability and measurement accuracy of the radar wave, the environmental parameter data is further collected in real time through multi-source sensors, and a deep learning algorithm is introduced to perform in-depth time series analysis on the environmental parameters, so as to intelligently adjust the radar transmission power based on the dynamic interaction changes of the multi-source environmental parameters. In this way, the dynamic compensation of the radar wave propagation characteristics can be realized, the influence of environmental factors on the radar ranging accuracy can be reduced, and thus the automation operation accuracy and safety of the bucket wheel stacker-reclaimer can be improved.

[0108] Furthermore, the present application also provides a remote unattended control system for a bucket wheel stacker-reclaimer.

[0109] Figure 7 The block diagram of the remote unattended control system for the bucket wheel stacker-reclaimer according to the embodiments of the present application is shown in Figure 7 As shown, the remote unattended control system 100 for the bucket wheel stacker-reclaimer according to the embodiments of the present application includes: an actual vertical distance measurement module 110, which is used to measure the vertical distance between the head of the boom belt and the surface of the coal pile by using a non-contact level radar, and the non-contact level radar is installed at the head of the boom belt; a preset vertical distance extraction module 120, which is used to extract the preset vertical distance from the background database; a radar distance error calculation module 130, which is used to calculate the difference between the vertical distance and the preset vertical distance to obtain the radar distance error; a control instruction generation module 140, which is used to input the radar distance error into the boom pitch angle controller based on the PLC controller to obtain a control instruction, and the control instruction includes the boom pitch angle adjustment amount.

[0110] Here, those skilled in the art can understand that the specific operations of each module in the above remote unattended control system of the bucket wheel stacker-reclaimer have been introduced in detail in the description of the remote unattended control method of the bucket wheel stacker-reclaimer with reference to Figures 1 to 6 and thus, the repeated description thereof will be omitted.

[0111] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details to implement.

[0112] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any associated drawing marks in the claims should not be regarded as limiting the claimed rights.

[0114] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0115] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A remote unattended control method for a bucket wheel stacker reclaimer, comprising: Layer the coal stack and set the parameters of the bucket wheel excavator; Start remote control, enter automatic material taking mode, and select the coal pile to take coal; Or enter the automatic stacking mode, set the existing stacking point or create a new stacking point; The angle of the material stacking or coal taking boundary is finely adjusted and the parameter deviation is corrected. The angle of the material stacking or coal taking boundary is finely adjusted and the parameter deviation is corrected, which includes: The vertical distance between the cantilever belt head and the coal pile surface is measured by using a non-contact material level radar, wherein the non-contact material level radar is installed on the cantilever belt head; Extract the preset vertical distance from the backend database; Calculating a difference between the vertical distance and the preset vertical distance to obtain a radar distance error; The radar distance error is input into a boom pitch angle controller based on a PLC controller to obtain a control instruction, wherein the control instruction includes a boom pitch angle adjustment amount.

2. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 1, characterized in that: The vertical distance between the cantilever belt head and the coal pile surface is measured by using a non-contact material level radar, wherein the non-contact material level radar is installed on the cantilever belt head, and comprises: Acquire a time queue of environmental parameters collected by a temperature and humidity sensor, wherein the environmental parameters include ambient temperature and ambient humidity; Extracting the time series features of the ambient temperature and the time series features of the ambient humidity from the time queue of the ambient parameters to obtain an ambient temperature time series feature implicit coding vector and an ambient humidity time series feature implicit coding vector; Performing an environmental parameter deep collaborative analysis on the environmental temperature time series feature implicit coding vector and the environmental humidity time series feature implicit coding vector to obtain an environmental parameter deep collaborative time series feature implicit coding vector; Based on the environmental parameter deep collaborative temporal feature implicit coding vector, the current radar transmit power is corrected to obtain a corrected radar transmit power.

3. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 2, characterized in that: Extracting the time series features of the ambient temperature and the time series features of the ambient humidity from the time queue of the ambient parameters to obtain an ambient temperature time series feature implicit coding vector and an ambient humidity time series feature implicit coding vector, including: The environmental parameter time series feature extractor based on the LSTM model is used to perform time series encoding on the time queue of the ambient temperature and the time queue of the ambient humidity respectively to obtain the ambient temperature time series feature implicit encoding vector and the ambient humidity time series feature implicit encoding vector.

4. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 3, characterized in that: Performing an environmental parameter deep collaborative analysis on the environmental temperature time series feature implicit coding vector and the environmental humidity time series feature implicit coding vector to obtain an environmental parameter deep collaborative time series feature implicit coding vector, including: Extracting core information of the ambient temperature time series feature implicit coding vector and the ambient humidity time series feature implicit coding vector respectively to obtain an ambient temperature time series feature core information anchor coding vector and an ambient humidity time series feature core information anchor coding vector; Multi-granularity temporal response interactive coding is performed on the core information anchor coding vector of the ambient temperature temporal feature and the core information anchor coding vector of the ambient humidity temporal feature to obtain the environmental parameter deep collaborative temporal feature implicit coding vector.

5. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 4, characterized in that: Extracting the core information of the ambient temperature time series feature implicit coding vector and the ambient humidity time series feature implicit coding vector respectively to obtain the ambient temperature time series feature core information anchor coding vector and the ambient humidity time series feature core information anchor coding vector, including: Constructing a semantic autocorrelation association matrix of the ambient temperature time series feature implicit coding vector and the ambient humidity time series feature implicit coding vector to obtain an ambient temperature time series feature semantic autocorrelation association matrix and an ambient humidity time series feature semantic autocorrelation association matrix; The ambient temperature time series feature semantic autocorrelation association matrix and the ambient humidity time series feature semantic autocorrelation association matrix are respectively input into the core information anchoring network based on autocorrelation decoupling to obtain the ambient temperature time series feature core information anchoring coding vector and the ambient humidity time series feature core information anchoring coding vector.

6. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 5, characterized in that: The anchor coding vector of the core information of the ambient temperature time series feature and the anchor coding vector of the core information of the ambient humidity time series feature are subjected to multi-granularity time series response interactive coding to obtain the implicit coding vector of the deep collaborative time series feature of the environmental parameters, including: Inputting the ambient temperature time series feature core information anchor coding vector and the ambient humidity time series feature core information anchor coding vector into a feature granularity response interactive encoder to obtain an environmental parameter feature granularity response interactive coding vector; Inputting the environmental temperature time series feature core information anchor coding vector and the environmental humidity time series feature core information anchor coding vector into the feature value granularity response interactive encoder to obtain the environmental parameter feature value granularity response interactive coding vector; The environmental parameter feature granularity response interactive coding vector and the environmental parameter feature value granularity response interactive coding vector are fused to obtain the environmental parameter deep collaborative temporal feature implicit coding vector.

7. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 6, characterized in that: The environmental parameter feature granularity response interactive coding vector and the environmental parameter feature value granularity response interactive coding vector are integrated to obtain the environmental parameter deep collaborative temporal feature implicit coding vector, including: Based on the environmental parameter characteristic granularity response interactive coding vector, performing position-by-position characteristic interaction gradient constraint correction on the environmental parameter characteristic value granularity response interactive coding vector to obtain an optimized environmental parameter characteristic value granularity response interactive coding vector; Based on the optimized environmental parameter characteristic value granularity response interactive coding vector, performing characteristic distribution deviation correction on the environmental parameter characteristic granularity response interactive coding vector to obtain an optimized environmental parameter characteristic granularity response interactive coding vector; The optimized environmental parameter feature value granularity response interactive coding vector and the optimized environmental parameter feature granularity response interactive coding vector are cascaded and fused to obtain the environmental parameter deep collaborative temporal feature implicit coding vector.

8. The remote unattended control method for a bucket wheel stacker and reclaimer according to claim 7, characterized in that: Based on the environmental parameter deep collaborative time series feature implicit coding vector, correcting the current radar transmit power to obtain a corrected radar transmit power, including: Inputting the environmental parameter deep collaborative time series feature implicit coding vector into a correction coefficient generator based on a feedforward neural network model to obtain a radar transmission power correction coefficient; The radar transmit power correction coefficient is multiplied by the current radar transmit power to obtain the corrected radar transmit power.

9. A remote unmanned control system for a bucket wheel stacker reclaimer, characterized in that: include: An actual vertical distance measurement module, used to measure the vertical distance between the cantilever belt head and the coal pile surface using a non-contact material level radar, wherein the non-contact material level radar is installed on the cantilever belt head; A preset vertical distance extraction module is used to extract the preset vertical distance from the background database; A radar distance error calculation module, used for calculating the difference between the vertical distance and the preset vertical distance to obtain a radar distance error; A control instruction generating module is used to input the radar distance error into a boom pitch angle controller based on a PLC controller to obtain a control instruction, wherein the control instruction includes a boom pitch angle adjustment amount.

Images