Automatic stabilizing system for stacker cantilever support

Abstract

The invention discloses an automatic stabilizing system for a stacker cantilever support, and relates to the technical field of stacker equipment, the system comprises the following components: a data acquisition module, a data analysis and prediction module, an automatic control module and a fault diagnosis and early warning module; the operation data of the cantilever support is acquired in real time through the data acquisition module, the data analysis and prediction module predicts the instability condition of the cantilever support by using an advanced algorithm, the automatic control module rapidly executes stable operation according to a prediction result, and compared with traditional manual monitoring and manual adjustment, the intelligent control mode has the advantages that the stability is high, and the stability is high. The unsteady state of the cantilever support can be dealt with more timely and accurately, so that the stability and safety of the cantilever support in the working process are remarkably improved, in addition, the system further has the fault diagnosis and early warning functions, early warning can be given out before faults occur, accidents are avoided, and safe operation of the stacker is further guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of stacker equipment, and particularly to an automatic stabilization system for the boom of a stacker. Background Art

[0002] During the operation of a stacker, the boom, as one of its core components, undertakes the key tasks of material transportation and stacking. However, due to the complex and changeable working environment, the boom is often affected by various external forces and vibrations during operation, resulting in challenges to its stability. To ensure the efficient and stable operation of the stacker, it is particularly important to carry out stabilization control on the boom.

[0003] Traditional technologies have deficiencies. Firstly, traditional methods often rely on manual experience and historical data for judgment, lacking real-time performance and accuracy, and it is difficult to predict the unstable state of the boom in a timely and accurate manner. Secondly, traditional stabilization control systems perform poorly in dealing with complex working conditions and sudden changes, and are unable to quickly adjust control strategies to adapt to the actual operating state of the boom. In addition, traditional systems also have limitations in energy consumption management and fault diagnosis, and it is difficult to achieve efficient energy utilization and early warning of faults.

[0004] In summary, traditional technologies have many deficiencies in the predictive stabilization control of the boom of a stacker, and it is difficult to meet the high requirements of modern industry for the stability and safety of equipment. Therefore, it is particularly important to develop an automatic stabilization system for the boom of a stacker. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the existing technology, and provide an automatic stabilization system for the boom of a stacker, which can achieve comprehensive and accurate monitoring of the boom state and timely and effective stabilization control through real-time data acquisition, advanced algorithm prediction, intelligent control, and fault diagnosis and early warning functions.

[0006] To solve the above technical problems, the present invention provides the following technical solution: an automatic stabilization system for the boom of a stacker, which system includes the following components: a data acquisition module, a data analysis and prediction module, an automatic control module, and a fault diagnosis and early warning module;

[0007] The data acquisition module: is configured at the root, front end, and key connection points of the boom body, and includes an adaptive sensor array, and the sensor array includes:

[0008] High-precision stress sensors, arranged at the root of the boom;

[0009] Displacement sensors, arranged at the front end of the boom;

[0010] An acceleration sensor is arranged at the joint of the cantilever frame;

[0011] The layout of the sensor is determined through finite element analysis and actual working condition tests, and the acquisition parameters are dynamically adjusted to collect real-time data of the cantilever frame of the stacker-reclaimer and obtain historical operation data;

[0012] The data analysis and prediction module: is fixed in the control box of the cantilever frame body, receives the signals of the data acquisition module, executes the spatio-temporal convolutional attention fusion prediction algorithm, and outputs the prediction results of the unstable state of the cantilever frame;

[0013] The automatic control module: includes a hydraulic drive component and a motor adjustment component, generates control instructions according to the prediction results, and drives the hydraulic system of the cantilever frame to perform attitude adjustment;

[0014] The fault diagnosis and early warning module: is integrated into the display terminal of the control box, monitors the operating states of all components of the system in real time, diagnoses faults and issues early warnings in a timely manner.

[0015] Furthermore, the data acquisition module adopts an adaptive sensor array layout technology. At different parts of the cantilever frame, according to its force characteristics and structural importance, the types and quantities of sensors are dynamically adjusted. At the root of the cantilever frame, due to bearing large bending moments and torques, high-precision pressure sensors and strain sensors are densely arranged. The accuracy of the pressure sensor can reach ±0.05 N, and the accuracy of the strain sensor is ±0.5 με. At the front end of the cantilever frame, displacement sensors and inclination sensors are mainly arranged. The resolution of the displacement sensor reaches 0.005 mm, and the accuracy of the inclination sensor is ±0.02°. The layout strategy of the sensors is determined by combining finite element analysis and actual working condition tests. According to the stress-strain distribution and deformation trend of the cantilever frame under different working conditions, the positions and parameters of the sensors are adjusted in real time to ensure that the collected data comprehensively and accurately reflects the state of the cantilever frame.

[0016] Even further, the data analysis and prediction module uses the spatio-temporal convolutional attention fusion prediction algorithm. First, spatio-temporal convolutional processing is performed on the collected time series data and spatial position data. The time convolutional layer uses causal convolution to ensure that future data is not relied on during prediction. The size and stride of its convolutional kernel are determined through multiple experiments according to the time characteristics of the data. The spatial convolutional layer constructs a spatial adjacency matrix based on the physical positions of the sensors on the cantilever frame and performs graph convolutional operations to extract spatial features. Then, an attention mechanism is introduced to calculate the attention weights of different feature dimensions. Let the feature vector after spatio-temporal convolution be F = [f1, f2, …, f n , and the calculation formula for the attention weight is:

[0017]

[0018] Among them, β is a trainable parameter, which is optimized during the training process through the backpropagation algorithm. The final prediction result is output through the fully connected layer. This algorithm can effectively fuse spatio-temporal features and improve the prediction accuracy of the unstable conditions of the cantilever rack.

[0019] Furthermore, the automatic control module adopts a strategy based on fuzzy adaptive sliding mode control, introducing a fuzzy logic controller to adaptively adjust the sliding mode surface parameters. First, define the sliding mode surface function S(x), where x is the state variable of the cantilever rack. According to the real-time state and control objective of the cantilever rack, the gain coefficient k of the sliding mode surface and the boundary layer thickness ∈ of the switching function are adjusted through the fuzzy logic controller. The input of the fuzzy logic controller is the deviation e between the state variable of the cantilever rack and the set value and the deviation change rate The output is the adjustment amount of k and ∈. The fuzzy rules are determined based on expert experience and a large amount of experimental data. When the deviation e is large and the deviation change rate is also large, increase the gain coefficient k to accelerate the system response speed. When the deviation e is small, reduce the boundary layer thickness ∈ to improve the control accuracy, thereby achieving stable and precise control of the cantilever rack.

[0020] Furthermore, the fault diagnosis and early warning module adopts a fault diagnosis method based on deep learning and information fusion, constructs a multi-modal deep learning model, and fuses the time domain, frequency domain, and time-frequency domain features of the sensors. First, the original data collected by the sensors is converted into frequency domain and time-frequency domain features through the fast Fourier transform and wavelet transform methods. Then, the time domain, frequency domain, and time-frequency domain features are respectively input into different convolutional neural network branches for feature extraction. The outputs of each branch are fused through the fully connected layer, and then the fault type and location are judged through the classifier. For the fault diagnosis of the support structure, by analyzing the time domain waveform, frequency domain spectrum, and wavelet energy distribution in the time-frequency domain of the vibration sensor, it is possible to accurately judge whether it is a bolt loosening, component wear, or structural crack fault of the support structure, and trace the fault cause through the fault tree analysis method. When a fault is detected, timely early warning is carried out through various methods, such as displaying the fault information on the large screen of the control center and sending push notifications to the mobile terminals of the maintenance personnel.

[0021] Furthermore, the system has an adaptive maintenance strategy based on reinforcement learning. During the operation of the system, taking the stable operation time, maintenance cost, and failure incidence rate of the cantilever rack as the reward function, the system automatically learns the optimal maintenance strategy using the deep Q-network algorithm. The maintenance actions include regular calibration of sensors, lubrication maintenance of actuators, and replacement of key components. The system selects the optimal maintenance action through the DQN model according to the current operating state and historical maintenance data. When the system detects abnormal fluctuations in the force on a certain part of the cantilever rack but has not reached the failure threshold, the DQN model arranges inspections and maintenance of the relevant components of that part in advance according to the learned strategy to avoid the occurrence of failures. At the same time, through continuous learning and optimization, the maintenance strategy can adapt to different working conditions and equipment aging degrees, reduce maintenance costs, and improve the reliability and service life of the equipment.

[0022] Furthermore, a data transmission and preprocessing mechanism based on quantum encryption and edge computing is adopted between the data acquisition module and the data analysis and prediction module. At the data acquisition end, quantum key distribution technology is used to generate encryption keys to encrypt the acquired data to ensure the security of data transmission. At the same time, data preprocessing is carried out on edge devices, and data dimensionality reduction algorithms based on principal component analysis and independent component analysis are adopted to remove noise and redundant information. Let the original data matrix collected be X, and the dimensionality-reduced data matrix Y is obtained through PCA and ICA transformations. The transformation formula is: Y = W PCA ·W ICA ·X where W RCA and W ICA are the eigenvector matrices of PCA and ICA transformations respectively, which are obtained through the analysis and calculation of historical data. The preprocessed and encrypted data is then transmitted to the data analysis and prediction module to improve data transmission efficiency and analysis speed and reduce data transmission bandwidth requirements.

[0023] Furthermore, the automatic control module and other subsystems of the stacker-reclaimer construct a digital twin model of the stacker-reclaimer to real-time map the state and operation process of the physical device. The automatic control module conducts virtual control experiments in the digital twin model according to the results of the data analysis and prediction module, simulates the operating state of the stacker-reclaimer under different collaborative control strategies, evaluates the impact on the stability of the cantilever rack, selects the optimal collaborative control strategy through an optimization algorithm, and then sends the control instructions to the actual subsystems for execution. During the material conveying process, when the cantilever rack shows an unstable trend, the digital twin model is used to simulate and adjust the material conveying speed, flow rate, and landing position, as well as the actions of the traveling system and slewing system to find the best collaborative control plan to ensure the stability of the cantilever rack and improve the operation efficiency and quality of the stacker-reclaimer at the same time.

[0024] Furthermore, the system has an intelligent energy management and optimization function, which can monitor the energy consumption of each component of the system in real time. It adopts an energy distribution algorithm based on particle swarm optimization. According to the working state and prediction results of the cantilever rack, it dynamically adjusts the energy distribution. Suppose there are n energy-consuming components in the system, and the energy consumption of each component is P i , and the total energy consumption is P total . The goal is to minimize the total energy consumption on the premise of ensuring the stable operation of the cantilever rack. The energy consumption distribution weight w of each component is optimized through the PSO algorithm i , so that the total energy consumption reaches the minimum. The particle position in the PSO algorithm represents the energy consumption distribution weight of each component, and the particle velocity represents the adjustment amount of the weight. By continuously iterating and updating the position and velocity of the particles, the optimal energy distribution scheme is found. When the cantilever rack operates stably, the energy consumption of some non-critical components is reduced. When an unstable situation is predicted, the energy supply of the key actuators is preferentially guaranteed, realizing the efficient utilization of energy and the stable operation of the system.

[0025] Compared with the prior art, the automatic stabilization system for the cantilever rack of the stacker has the following

[0026] beneficial effects:

[0027] First, the system can obtain the operation data of the cantilever rack in real time through the data acquisition module. The data analysis and prediction module uses advanced algorithms to predict the unstable situation of the cantilever rack, and the automatic control module quickly executes the stabilization operation according to the prediction results. This intelligent control method can respond to the unstable state of the cantilever rack more timely and accurately compared with the traditional manual monitoring and manual adjustment, thus significantly improving the stability and safety of the cantilever rack during the working process. In addition, the system also has a fault diagnosis and early warning function, which can issue an early warning before a fault occurs, avoiding the occurrence of accidents and further ensuring the safe operation of the stacker.

[0028] Second, the system has an intelligent energy management and optimization function, which can dynamically adjust the energy distribution according to the working state and prediction results of the cantilever rack, realizing the efficient utilization of energy. This not only helps to reduce energy consumption and waste, but also can minimize the total energy consumption by optimizing the energy consumption distribution weight of each component on the premise of ensuring the stable operation of the cantilever rack. At the same time, the system also has an adaptive maintenance strategy based on reinforcement learning, which can select the optimal maintenance action according to the current operation state and historical maintenance data. This intelligent maintenance method can reduce the maintenance cost, improve the reliability and service life of the equipment, and bring greater economic benefits to the production and operation of the enterprise.

[0029] Other advantages, objectives, and features of the present invention will, to some extent, be elaborated in the subsequent description, and to some extent, will be obvious to those skilled in the art based on the examination of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a flowchart for realizing the functions of an automatic stabilization system for the boom of a stacker

[0032] Figure 2 It is a flowchart of the overall architecture of an automatic stabilization system for the boom of a stacker. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention objective, the following will, in conjunction with the drawings and preferred embodiments, detail the specific embodiments, structures, features, and their effects of the present invention as follows.

[0034] Embodiment 1

[0035] This embodiment describes that in a large port, a coal stacker is responsible for unloading coal from a transport ship and stacking it in a designated area. During the stacking operation, the stability of the boom of the stacker is crucial.

[0036] Adopting the adaptive sensor array layout technology, at the key stress points of the boom, such as the root and joint connection parts, stress sensors and displacement sensors are arranged according to the finite element analysis and the actual working condition test results. For example, at the root of the boom, due to the large stress, more high-precision stress sensors are arranged. These sensors collect the stress and strain data of the boom in real time as real-time data, and at the same time obtain historical operation data from the database, such as the boom state data under different stacking amounts and different operation durations.

[0037] Receiving the data from the data acquisition module, using the spatio-temporal convolutional attention fusion prediction algorithm. Assuming that the stress and strain data collected within a period of time is time series data, and the position information of the sensors on the boom is spatial position data, first perform spatio-temporal convolutional processing. The time convolutional layer uses causal convolution, and the spatial convolutional layer constructs a spatial adjacency matrix according to the sensor positions for graph convolutional operations. Let the feature vector after spatio-temporal convolution be F = [f1, f2,..., fn , calculate the attention weights through the attention mechanism:

[0038]

[0039] Among them, β is a trainable parameter, and finally the prediction result is output through a fully connected layer to judge whether the cantilever rack will be unstable. If it is predicted that the cantilever rack may be unstable 10 minutes later under the current working state, the system enters the next operation.

[0040] Adopt a strategy based on fuzzy adaptive sliding mode control, define the sliding mode surface function S(x), where x is the state variable of the cantilever rack (such as stress, displacement). According to the real-time state of the cantilever rack and the control target, use the deviation e between the state variable of the cantilever rack and the set value and the deviation change rate e as the input of the fuzzy logic controller to adjust the gain coefficient k of the sliding mode surface and the boundary layer thickness ∈ of the switching function. For example, when the deviation e is large and the deviation change rate is also large, the fuzzy logic controller increases the gain coefficient k so that the cantilever rack can return to the stable state faster, and performs a stabilizing operation on the cantilever rack by adjusting the pressure and flow rate of the hydraulic system.

[0041] Adopt a fault diagnosis method based on deep learning and information fusion. Convert the original data collected by the sensor into frequency domain and time-frequency domain features through fast Fourier transform and wavelet transform, and then input them into different convolutional neural network branches for feature extraction respectively. After the outputs of each branch are fused through a fully connected layer, the classifier judges the fault type and location. If it is detected that the sensor data at a certain joint of the cantilever rack is abnormal and is diagnosed as increased wear due to insufficient lubrication at the joint, the system immediately displays the fault information on the large screen of the control center and sends a push notification to the maintenance personnel's mobile terminal.

[0042] Embodiment 2

[0043] This embodiment describes a situation in the ore stockyard of a mine where a stacker is responsible for stacking the mined ore. Due to the large weight of the ore and the complex working environment, the cantilever rack of the stacker faces great challenges.

[0044] According to the force characteristics and structural importance of the cantilever rack of the mine stacker, the data acquisition module arranges displacement sensors and acceleration sensors at the parts of the cantilever rack prone to deformation, such as the front end of the cantilever, using the adaptive sensor array layout technology. The sensor layout is determined through finite element analysis and actual working condition tests, and the real-time displacement and acceleration data of the cantilever rack are collected in real time, and the data of the cantilever rack under different ore types and different stacking heights in historical operations are obtained.

[0045] The data analysis and prediction module uses a spatio-temporal convolutional attention fusion prediction algorithm to process the collected data, performs spatio-temporal convolution on the displacement, acceleration data of the time series and the sensor spatial position data. The temporal convolutional layer uses causal convolution, and the spatial convolutional layer constructs a spatial adjacency matrix for graph convolution. For the feature vector F = [f1, f2, …, f n , the weights are calculated according to the attention weight formula . β is optimized by the backpropagation algorithm. Finally, the fully connected layer outputs whether it is predicted that the cantilever rack will be unstable. If it is predicted that there may be a tilting risk after the cantilever rack continues to stack materials for 5 minutes, the subsequent control process is started.

[0046] The automatic control module adopts a fuzzy adaptive sliding mode control strategy, defines the sliding mode surface function S(x), where x is the cantilever rack state variable (displacement, acceleration). The deviation e between the cantilever rack state variable and the set value and the deviation change rate are used as the inputs of the fuzzy logic controller to adjust the sliding mode surface gain coefficient k and the switching function boundary layer thickness ∈. For example, when the displacement deviation e is large and the deviation change rate e is small, the fuzzy logic controller appropriately reduces k to avoid overly drastic control actions, and stabilizes the cantilever rack by adjusting the motor speed and torque.

[0047] The fault diagnosis and warning module constructs a multi-modal deep learning model, converts the original sensor data into frequency domain and time-frequency domain features through fast Fourier transform and wavelet transform, respectively inputs different convolutional neural network branches to extract features, and the outputs of each branch are fused by the fully connected layer and then judged by the classifier for faults. If abnormal vibration is detected in a certain support component of the cantilever rack, it is diagnosed as component looseness, and the system promptly displays the fault information in the control center and notifies the maintenance personnel.

[0048] The above is only a preferred embodiment of the present invention, and does not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An automatic stabilization system for the boom of a stacking machine, characterized in that, The system includes the following components: a data acquisition module, a data analysis and prediction module, an automatic control module, and a fault diagnosis and warning module; The data acquisition module: is configured at the root, front end, and key connection points of the cantilever frame body, and includes an adaptive sensor array. The sensor array includes: High-precision stress sensors, arranged at the root of the cantilever frame; Displacement sensors, arranged at the front end of the cantilever frame; Acceleration sensors, arranged at the joint of the cantilever frame; The layout of the sensors is determined through finite element analysis and actual working condition tests, and the acquisition parameters are dynamically adjusted to collect real-time data of the stacker-reclaimer cantilever frame and obtain historical operation data; The data analysis and prediction module: is fixed in the control box of the cantilever frame body, receives the signals from the data acquisition module, executes the spatio-temporal convolutional attention fusion prediction algorithm, and outputs the prediction results of the unstable state of the cantilever frame; The automatic control module: includes a hydraulic drive component and a motor adjustment component, generates control instructions according to the prediction results, and drives the hydraulic system of the cantilever frame to perform attitude adjustment; The fault diagnosis and warning module: monitors the operating states of all components of the system in real time, diagnoses faults, and issues warnings in a timely manner.

2. The automatic stabilization system for the boom of a stacking machine according to claim 1, characterized in that, The data acquisition module adopts the adaptive sensor array layout technology. At different parts of the cantilever frame, according to its force characteristics and structural importance, the types and quantities of sensors are dynamically adjusted. The layout strategy of the sensors is determined by combining finite element analysis and actual working condition tests. According to the stress-strain distribution and deformation trend of the cantilever frame under different working conditions, the positions and parameters of the sensors are adjusted in real time.

3. An automatic stabilization system for the boom of a stacking machine according to claim 1, characterized in that, The data analysis and prediction module uses a spatio-temporal convolutional attention fusion prediction algorithm. First, spatio-temporal convolutional processing is performed on the collected time series data and spatial location data. The temporal convolutional layer uses causal convolution, and the spatial convolutional layer constructs a spatial adjacency matrix based on the physical positions of the sensors on the cantilever rack for graph convolution operations to extract spatial features. Then, an attention mechanism is introduced to calculate the attention weights of different feature dimensions. Let the feature vector after spatio-temporal convolution be F = [f1, f2, …, f n , and the calculation formula for the attention weight is: Among them, β is a trainable parameter, which is optimized through the backpropagation algorithm during the training process. The final prediction result is output through the fully connected layer. This algorithm can effectively fuse spatio-temporal features and improve the prediction accuracy of the unstable situation of the cantilever frame.

4. An automatic stabilization system for the boom of a stacker, according to claim 1, characterized in that, The automatic control module adopts a strategy based on fuzzy self-adaptive sliding mode control. A fuzzy logic controller is introduced to adaptively adjust the sliding mode surface parameters. First, the sliding mode surface function S(x) is defined, where x is the state variable of the cantilever rack. According to the real-time state and control objective of the cantilever rack, the gain coefficient k of the sliding mode surface and the boundary layer thickness ∈ of the switching function are adjusted through the fuzzy logic controller. The inputs of the fuzzy logic controller are the deviation e between the state variable of the cantilever rack and the set value and the deviation change rate and the outputs are the adjustment amounts of k and ∈.

5. The automatic stabilization system for the boom of a stacking machine according to claim 1, characterized in that, The fault diagnosis and warning module adopts a fault diagnosis method based on deep learning and information fusion, constructs a multi-modal deep learning model, and fuses the time domain, frequency domain, and time-frequency domain features of the sensors. First, the original data collected by the sensors is converted into frequency domain and time-frequency domain features through the fast Fourier transform and wavelet transform methods. Then, the time domain, frequency domain, and time-frequency domain features are respectively input into different convolutional neural network branches for feature extraction. The outputs of each branch are fused through the fully connected layer, and then the fault type and location are judged through the classifier. When a fault is detected, warnings are issued in a timely manner through various methods, such as displaying the fault information on the large screen in the control center and sending push notifications to the mobile terminals of maintenance personnel.

6. The automatic stabilization system for the boom of a stacking machine according to claim 1, characterized in that, The system has an adaptive maintenance strategy based on reinforcement learning. During the operation of the system, the stable operation time, maintenance cost, and failure rate of the cantilever frame are used as the reward function. The deep Q-network algorithm is used to let the system automatically learn the optimal maintenance strategy. The maintenance actions include regular calibration of sensors, lubrication and maintenance of actuators, and replacement of key components. The system selects the optimal maintenance action through the DQN model according to the current operating state and historical maintenance data.

7. An automatic stabilization system for the boom of a stacker, according to claim 1, characterized in that A data transmission and preprocessing mechanism based on quantum encryption and edge computing is adopted between the data acquisition module and the data analysis and prediction module. At the data acquisition end, quantum key distribution technology is used to generate encryption keys to encrypt the collected data. At the same time, data preprocessing is carried out on edge devices. A data dimensionality reduction algorithm based on principal component analysis and independent component analysis is adopted to remove noise and redundant information. Suppose the original data matrix collected is X, and the dimensionality-reduced data matrix Y is obtained through PCA and ICA transformations. The transformation formula is: Y = W PCA ·W ICA ·X where W RCA and W ICA are the eigenvector matrices of PCA and ICA transformations respectively. The preprocessed and encrypted data is then transmitted to the data analysis and prediction module, improving data transmission efficiency and analysis speed and reducing data transmission bandwidth requirements.

8. An automatic stabilization system for a boom of a stacking machine according to claim 1, characterized in that, The automatic control module and other subsystems of the stacker build a digital twin model of the stacker, which real-time maps the status and operation process of the physical device. According to the results of the data analysis and prediction module, the automatic control module conducts virtual control experiments in the digital twin model, simulates the operation status of the stacker under different cooperative control strategies, evaluates the impact on the stability of the cantilever frame, selects the optimal cooperative control strategy through an optimization algorithm, and then sends the control instructions to the actual subsystems for execution. During the material conveying process, when the cantilever frame shows an unstable trend, the digital twin model is used to simulate and adjust the material conveying speed, flow rate, and landing position, as well as the actions of the traveling system and slewing system to find the best cooperative control solution.

9. The automatic stabilization system for the boom of a stacker according to claim 1, wherein, The system has intelligent energy management and optimization functions, monitors the energy consumption of each component of the system in real time, and adopts an energy distribution algorithm based on particle swarm optimization. According to the working state and prediction results of the cantilever rack, it dynamically adjusts the energy distribution. Suppose there are n energy-consuming components in the system, and the energy consumption of each component is P i , and the total energy consumption is P total . The goal is to minimize the total energy consumption on the premise of ensuring the stable operation of the cantilever rack. The energy consumption distribution weights w of each component are optimized through the PSO algorithm i to minimize the total energy consumption . The particle position in the PSO algorithm represents the energy consumption distribution weight of each component, and the particle velocity represents the adjustment amount of the weight. By continuously iterating and updating the position and velocity of the particles, the optimal energy distribution scheme is found. When the cantilever rack is operating stably, the energy consumption of some non-critical components is reduced. When an unstable situation is predicted, the energy supply of the key actuators is prioritized

Images