Bucket wheel machine control method and device, medium, electronic equipment and program product

Abstract

The invention relates to a bucket wheel machine control method and device, a medium, electronic equipment and a program product, and relates to the field of bucket wheel machine control, and the method comprises the steps: collecting the operation data of a bucket wheel machine in real time through a sensor network; dynamically updating a digital twin model of the bucket wheel machine through the operation data; performing multi-objective optimization processing based on the digital twin model to obtain a control strategy of the bucket wheel machine; and based on the control strategy, the bucket wheel machine is controlled through self-adaptive model predictive control. Through construction of a digital twinborn model of the bucket wheel machine, real-time operation data fusion, multi-objective optimization and a self-adaptive control strategy, the bucket wheel machine can efficiently and stably operate in a complex operation environment, and dependence on manual operation is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of bucket wheel machine control, and in particular, to a bucket wheel machine control method, device, medium, electronic equipment and program product. Background Art

[0002] Bucket wheel excavators are large-scale mechanical equipment widely used in industries such as mining, power and ports, mainly used for excavation, transportation and loading and unloading of materials. With the development of industrial automation, the requirements for the operating efficiency, energy consumption control and safety performance of bucket wheel excavators are getting higher and higher.

[0003] The control system of traditional bucket wheel excavators mainly relies on manual operation or semi-automatic methods, and operators need to make manual adjustments based on experience and real-time monitoring data. This operation mode not only requires a high level of technical skills from operators, but also has problems such as manual operation prone to errors, low efficiency, and high energy consumption. Especially when facing complex working conditions and emergencies, manual operation is difficult to make timely and accurate adjustments, which can easily lead to equipment overload, frequent failures, and even safety accidents. In addition, traditional control systems usually lack all-round monitoring and analysis of the operating status of bucket wheel excavators, and cannot obtain and process key operating data of equipment in real time, resulting in difficulty in timely warning and prevention of equipment failures, increasing maintenance and operating costs.

[0004] When dealing with the needs of bucket wheel excavators for energy consumption, stability and intelligent management, existing technologies often fail to achieve comprehensive optimization control. Traditional methods lack the ability to optimize multiple objectives, making it difficult to minimize energy consumption and extend equipment life while ensuring efficient operation of the equipment. At the same time, existing control systems generally lack adaptability and cannot be dynamically adjusted based on real-time operating data, making it difficult for equipment to maintain optimal operating conditions in complex and changing environments. In addition, current bucket wheel excavator control technology still faces major challenges in achieving unmanned operation, and the system's intelligence level is insufficient, which cannot effectively reduce reliance on manual operations, limiting the improvement of the automation and intelligence level of bucket wheel excavators.

[0005] To sum up, the existing technology still has many defects and shortcomings in the intelligent control of bucket wheel excavators. There is an urgent need for a solution based on advanced technology that can achieve efficient, stable and intelligent control of bucket wheel excavators, reduce dependence on manual operation, and improve the overall performance and operational efficiency of the equipment. Summary of the invention

[0006] In order to overcome the problems existing in the related art, the present disclosure provides a bucket wheel machine control method, device, medium, electronic equipment and program product.

[0007] According to a first aspect of an embodiment of the present disclosure, a bucket wheel machine control method is provided, comprising: Collect bucket wheel machine operation data in real time through sensor network; Dynamically updating the digital twin model of the bucket wheel machine through the operating data; Performing multi-objective optimization processing based on the digital twin model to obtain a control strategy for the bucket wheel excavator; Based on the control strategy, the bucket wheel machine is controlled by adaptive model predictive control.

[0008] Optionally, the steps of establishing the digital twin model include: Establishing a structural mechanics sub-model of the bucket wheel machine based on the finite element method; A dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation; Establishing a thermodynamic sub-model of the bucket wheel machine based on a heat conduction equation; The digital twin model is obtained by performing multi-physical field coupling based on the structural mechanics sub-model, the dynamics sub-model and the thermodynamics sub-model.

[0009] Optionally, establishing a structural mechanics sub-model of the bucket wheel machine based on the finite element method comprises: The bucket wheel machine is meshed based on the finite element method, and a mathematical sub-model of stress and deformation is established according to the meshing result, the material properties of the bucket wheel machine and the boundary conditions as the mechanical sub-model.

[0010] Optionally, the dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation, including: A dynamic sub-model based on at least one of mass distribution, inertia characteristics, damping, stiffness and external force of the bucket wheel machine is established through the Lagrangian equation.

[0011] Optionally, a thermodynamic sub-model of the bucket wheel machine is established based on a heat conduction equation, including: Based on the heat conduction equation, the temperature distribution and thermal stress of the bucket wheel excavator during operation are simulated to obtain the thermodynamic sub-model.

[0012] Optionally, the multi-physics field coupling includes: The structural mechanics sub-model is coupled with the dynamics sub-model; The structural mechanics sub-model and the thermodynamics sub-model are coupled; The kinetic sub-model and the thermodynamic sub-model are coupled.

[0013] Optionally, dynamically updating the digital twin model through the operating data includes: inputting the operating data into the digital twin model; The Kalman filter is used to dynamically update the digital twin model.

[0014] Optionally, the multi-objective optimization process is performed based on the digital twin model to obtain a control strategy for the bucket wheel machine, including: Taking energy consumption, vibration and temperature control as optimization targets, constructing the objective function of the multi-objective optimization; Determining the constraint conditions of the multi-objective optimization based on the operating conditions and safety limits of the bucket wheel machine; Based on the objective function and the constraint conditions, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization calculation to obtain the control strategy.

[0015] Optionally, controlling the bucket wheel machine by adaptive model predictive control based on the control strategy includes: Establishing a state space model describing the dynamic behavior of the bucket wheel machine; Optimizing the control strategy based on the state space model to obtain a target control strategy; The bucket wheel machine is controlled by the target control strategy.

[0016] Optionally, after establishing the state space model describing the dynamic behavior of the bucket wheel machine, the method further comprises: The parameters of the state-space model are updated online through an adaptive mechanism.

[0017] According to a second aspect of an embodiment of the present disclosure, there is provided a bucket wheel machine control device, comprising: A collection module is used to collect the operation data of the bucket wheel machine in real time through a sensor network; An updating module, used for dynamically updating the digital twin model of the bucket wheel machine through the operating data; A processing module, used for performing multi-objective optimization processing based on the digital twin model to obtain a control strategy for the bucket wheel machine; A control module is used to control the bucket wheel machine through adaptive model predictive control based on the control strategy.

[0018] According to a third aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, wherein the program instructions, when executed by a processor, implement the steps of the bucket wheel machine control method provided in the first aspect of the present disclosure.

[0019] According to a fourth aspect of an embodiment of the present disclosure, there is provided an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the bucket wheel machine control method provided in the first aspect of the present disclosure.

[0020] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the bucket wheel machine control method provided in the first aspect of the present disclosure.

[0021] In the above technical solution, the operation data of the bucket wheel machine is collected in real time through the sensor network; the digital twin model of the bucket wheel machine is dynamically updated through the operation data; multi-objective optimization processing is performed based on the digital twin model to obtain the control strategy of the bucket wheel machine; based on the control strategy, the bucket wheel machine is controlled through adaptive model predictive control. By constructing a digital twin model of the bucket wheel machine, real-time operation data fusion, multi-objective optimization and adaptive control strategy, the bucket wheel machine can operate efficiently and stably in a complex operating environment, reducing dependence on manual operation.

[0022] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The present invention is a flow chart of a bucket wheel machine control method according to an exemplary embodiment.

[0024] Figure 2 It is a flowchart of establishing a digital twin model according to an exemplary embodiment.

[0025] Figure 3 The present invention is a flow chart of a bucket wheel machine control method according to an exemplary embodiment.

[0026] Figure 4 The present invention is a flow chart of a bucket wheel machine control method according to an exemplary embodiment.

[0027] Figure 5 The present invention is a flow chart of a bucket wheel machine control method according to an exemplary embodiment.

[0028] Figure 6 is a block diagram of a bucket wheel machine control device 600 according to an exemplary embodiment.

[0029] Figure 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. DETAILED DESCRIPTION

[0030] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0031] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0032] Figure 1 FIG. 1 is a flow chart of a bucket wheel machine control method according to an exemplary embodiment. Figure 1 As shown, the method comprises the following steps: In step S11, the operation data of the bucket wheel machine is collected in real time through the sensor network.

[0033] For example, bucket wheel machines are large-scale mechanical equipment widely used in industries such as mining, electricity, and ports, and are mainly used for excavation, transportation, and loading and unloading of materials. The sensor network of the bucket wheel machine can be used to collect the operation data of the bucket wheel machine. In the embodiment described in the present disclosure, the deployment and data collection steps of the sensor network include: 1) Sensor layout and installation: Multiple types of sensors are arranged at key parts of the bucket wheel excavator, including one or more of temperature sensors, acceleration sensors, stress sensors and position sensors; Among them, temperature sensors are installed in motors, bearings and other heat-prone components to monitor equipment temperature in real time and prevent overheating.

[0034] Acceleration sensor: It is arranged in the bucket wheel arm, bearing seat and other locations to obtain vibration signals for evaluating the mechanical vibration status of the equipment.

[0035] Stress sensors: Installed at key structural parts of bucket wheel machines, such as connection points and high stress areas, to measure stress and deformation of the equipment.

[0036] Position sensors: Used to monitor the displacement and speed of rotating parts, especially where precise position control is required.

[0037] 2) Sensor data collection and transmission: Through industrial communication networks such as 5G or LoRa, the collected sensor data can be transmitted to the data collection layer in real time.

[0038] Transmission protocol selection: Select a communication protocol with low latency and high bandwidth to ensure that sensor data can be transmitted in a timely manner and reduce the impact of data delays on model updates.

[0039] Data synchronization and timestamp marking: All sensor data are marked with a unified timestamp to ensure the synchronization between different types of sensor data and provide a basis for subsequent data fusion.

[0040] 3) Sensor data preprocessing: Preprocessing the raw data collected by the sensor can improve data quality and reliability; For example, sensor data pre-processing may include; De-noising: The sensor signal is de-noised using the wavelet transform method. Wavelet transform can effectively extract the main features of the signal and eliminate high-frequency noise components.

[0041] Anomaly detection: Anomaly detection is performed through cluster analysis. Sensor data is clustered, and outliers are identified and removed based on data distribution characteristics to improve data reliability.

[0042] Data standardization: Standardize all sensor data and convert the data into a unified dimension and range to ensure the consistency of subsequent data fusion and model input.

[0043] 4) Sensor data fusion: The pre-processed multi-source data can be fused using Bayesian network and neural network fusion methods to construct a unified state estimation.

[0044] Among them, Bayesian network fusion is used to integrate temperature, vibration and stress data, and estimate the equipment status through Bayesian theorem:

[0045] in, is the assumed state (such as normal or abnormal equipment), is the fused sensor data.

[0046] Neural network fusion: The accuracy and robustness of data fusion can be further enhanced by extracting complex relationships in the data through deep neural networks.

[0047] Through the above steps 1-4, efficient collection and preprocessing of sensor data can be achieved, providing high-quality input data for the dynamic update of the digital twin model.

[0048] In step S12, the digital twin model of the bucket wheel machine is dynamically updated using the operating data.

[0049] Exemplarily, a digital twin model is a virtual model that accurately reflects the characteristics, state and behavior of its corresponding physical entity. This model can be extended to simulate complex physical systems and can interact with users to predict the future state of physical entities. The definition of digital twin is to use data such as physical models, sensor updates and operation history, integrate multi-disciplinary, multi-physical quantities, multi-scale and multi-probability simulation processes, and complete mapping in virtual space to reflect the full life cycle process of the corresponding physical equipment. It can also be defined as a digital model of existing or future physical entity objects, which can perceive, diagnose and predict the state of physical entity objects in real time through actual measurement, simulation and data analysis, regulate the behavior of physical entity objects through optimization and instructions, and evolve itself through mutual learning between related digital models. Therefore, the digital twin model of the bucket wheel machine can be dynamically updated by establishing the digital twin model and using the operation data as the input of the digital twin model.

[0050] Alternatively, if Figure 2 As shown, the steps of establishing the digital twin model may include: In step S21, a structural mechanics sub-model of the bucket wheel machine is established based on the finite element method.

[0051] Exemplarily, in the embodiments described in the present disclosure, a digital twin model of a bucket wheel machine can be constructed through multi-physics modeling. The digital twin model can integrate the three key sub-models of the bucket wheel machine's structural mechanics sub-model, dynamics sub-model, and thermodynamics to comprehensively describe the operating state of the bucket wheel machine and its response behavior under different working conditions. Among them, multi-physics modeling is the core step in realizing digital twin technology. By coupling the interaction of multiple sub-model physical fields, an accurate simulation environment can be provided for subsequent optimization control and dynamic adjustment.

[0052] Optionally, the bucket wheel machine is meshed based on the finite element method, and a mathematical sub-model of stress and deformation is established according to the meshing result, the material properties of the bucket wheel machine and boundary conditions as the mechanical sub-model.

[0053] For example, finite element analysis (FEM) is a numerical calculation method that approximates the control equations of engineering problems by discretizing continuous engineering structures (such as machinery, civil structures, circuits, etc.) into a finite number of small units. This method is widely used in engineering fields, including but not limited to structural analysis, thermal analysis, fluid dynamics analysis, electromagnetic field analysis, etc. Among them, the purpose of meshing is to discretize continuous entities into a finite number of small units for computer calculations. For example, the unit size, shape and distribution can be set, and local mesh refinement can be performed on specific areas to capture complex stress and deformation conditions. Material properties refer to specifying material properties for each unit according to the bucket wheel, such as elastic modulus, Poisson's ratio, density, thermal conductivity, etc. These parameters are crucial for calculating stress and deformation. Boundary conditions and load application refer to defining the boundary conditions of the bucket wheel, such as fixed support, rotating boundary, etc., and the loads acting on the bucket wheel, such as gravity, working load, etc. These conditions and loads will affect the stress and deformation distribution of the bucket wheel.

[0054] For example, in the embodiments described in the present disclosure, the bucket wheel machine can be meshed using the finite element method, and a structural mechanics sub-model of stress and deformation can be established based on material properties and boundary conditions. This model is used to predict the stress distribution and structural deformation of the bucket wheel machine under different loads to ensure the safety of the equipment under various working conditions. The basic equation of the structural mechanics sub-model can be expressed as an equilibrium equation:

[0055] in, is the stress tensor, For physical strength, is the density, is the displacement vector. By calculating the stress and displacement of the grid nodes, the deformation and stress distribution of each part of the bucket wheel machine under load can be obtained.

[0056] In step S22, a dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation.

[0057] Optionally, a dynamic sub-model based on at least one of mass distribution, inertia characteristics, damping, stiffness and external force of the bucket wheel machine is established through the Lagrangian equation.

[0058] For example, the dynamic sub-model can use a multi-rigid body dynamics method to describe the motion behavior of each component of the bucket wheel. The dynamic sub-model is established by the Lagrangian equation, which takes into account factors such as the mass distribution, inertia characteristics, damping, stiffness and external forces of the bucket wheel to accurately simulate the dynamic response of the equipment. For example, the expression of the Lagrangian equation of the dynamic sub-model can be:

[0059] in, is the mass matrix, is the damping matrix, is the stiffness matrix, are generalized coordinates, is the external force vector. This equation can be used to describe the motion state of a bucket wheel machine under different external forces, including dynamic parameters such as speed and acceleration.

[0060] In step S23, a thermodynamic sub-model of the bucket wheel machine is established based on the heat conduction equation.

[0061] Optionally, based on the heat conduction equation, the temperature distribution and thermal stress of the bucket wheel machine during operation are simulated to obtain the thermodynamic sub-model.

[0062] For example, the thermodynamic submodel can simulate the temperature distribution and thermal stress of the bucket wheel machine during operation based on the heat conduction equation. The thermodynamic submodel can predict the impact of temperature changes on equipment performance, especially in high load or high temperature environments, where the impact of temperature on material strength and equipment life is particularly critical. The heat conduction equation can be expressed as:

[0063] in, is the density, is the specific heat capacity, is the thermal conductivity, is the temperature, The formula can be used to calculate the temperature field of each part of the bucket wheel machine, determine the impact of temperature on the operation of the equipment, and take corresponding control measures.

[0064] In step S24, multi-physical field coupling is performed based on the structural mechanics sub-model, the dynamics sub-model and the thermodynamics sub-model to obtain the digital twin model.

[0065] For example, after the construction of the structural mechanics sub-model, the dynamics sub-model and the thermodynamics sub-model is completed, the structural mechanics, dynamics and thermodynamics sub-models can be coupled to multiple physical fields. Multi-physical field coupling enables each model to synchronously calculate and reflect the complex operating state of the actual equipment by defining the interaction interface and interaction effect between each physical field.

[0066] Optionally, the multi-physics coupling includes: The structural mechanics sub-model is coupled with the dynamics sub-model; The structural mechanics sub-model is coupled to the thermodynamics sub-model; The kinetic sub-model and the thermodynamic sub-model are coupled.

[0067] Exemplarily, the multi-physics coupling can be expressed by the following set of equations: The structural mechanics submodel is coupled to the dynamics submodel:

[0068] in, is the mass matrix, is the damping matrix, is the stiffness matrix, are generalized coordinates, is the external force vector, is the stress tensor, is the normal vector, and the integral is at the coupling interface This equation can reflect the influence of structural deformation on dynamic response.

[0069] The structural mechanics sub-model is coupled to the thermodynamics sub-model:

[0070] in, is the stress tensor, For physical strength, is the density, is the displacement vector, is the thermal expansion coefficient, which reflects the influence of temperature field on structural stress and deformation. is the temperature field.

[0071] The kinetic submodel is coupled to the thermodynamic submodel:

[0072] in, is the mass matrix, is the damping matrix, is the stiffness matrix, are generalized coordinates, is the external force vector, is the temperature-dependent damping matrix, is the friction heat generation coefficient. This equation reflects the influence of the heat generation effect in the dynamic process on the operation of the equipment.

[0073] In addition, numerical solution methods, such as finite element-finite difference hybrid method or multi-grid method, can be used to solve the coupled equations and obtain the linkage response of each physical field. The solution results are integrated into the digital twin model, and through continuous data feedback and model correction, the digital twin model can accurately reflect the actual operating status of the bucket wheel machine. In summary, multi-physical field modeling and coupling can achieve a full range of simulation of the bucket wheel machine's operating status, providing an accurate simulation environment for subsequent optimization control and dynamic adjustment.

[0074] Alternatively, if Figure 3 As shown, step S12 may include the following steps: In step S121, the operating data is input into the digital twin model.

[0075] In step S122, a Kalman filter is used to dynamically update the digital twin model.

[0076] For example, the sensor data collected in real time can dynamically update the digital twin model to ensure the synchronization of the virtual model with the actual equipment status. Dynamic update is a key link in digital twin technology. Through continuous data input and model correction, the digital twin model can reflect the operating status of the bucket wheel excavator in real time, thus providing a reliable basis for subsequent optimization control and adaptive decision-making.

[0077] In the embodiment described in the present disclosure, the specific steps of dynamically updating the digital twin model using the operating data include: The operating data is input into each sub-model of the digital twin model, including structural mechanics, dynamics and thermodynamics sub-models, to comprehensively utilize multi-source data through data fusion technology to improve the accuracy and response speed of the model.

[0078] The Kalman filter is used to dynamically update the digital twin model and the model parameters are corrected using real-time data to reduce the error between the model prediction and the actual state. The state estimation and update equation of the Kalman filter is:

[0079]

[0080]

[0081] in, For in time The posterior state estimate of For in time The prior state estimate of is the actual measured value, is the measurement matrix, is the Kalman gain, For in time The posterior error covariance of For in time The prior error covariance of is the observation noise covariance matrix, is the identity matrix.

[0082] In addition, dynamic updates to the digital twin model also include: Model correction and multi-field synchronous adjustment: synchronous correction of structural mechanics, dynamics and thermodynamics sub-models to reflect the current operating status of the equipment. Structural mechanics sub-model correction is achieved by adjusting the stress and deformation parameters of the nodes, the dynamics sub-model is adjusted by updating the mass, damping and stiffness matrix parameters, and the thermodynamics sub-model adjusts the thermal conductivity and heat source parameters according to temperature changes. Among them, structural mechanics model correction: according to real-time stress and deformation data, adjust the boundary conditions and material parameters of the model to ensure that the model output is consistent with the actual state. Dynamic model correction: using velocity and acceleration data, adjust the damping and stiffness parameters in the dynamic model in real time to match the motion characteristics of the actual equipment. Thermodynamic model correction: through temperature data input, adjust the thermal conductivity and internal heat source in the heat conduction equation to reflect the changes in the thermal state of the equipment.

[0083] Multi-physics coupling adjustment: By iteratively solving the multi-physics coupling equations, the interactions between the sub-models are coordinated so that the coupled digital twin model can reflect the linkage effects between the physical fields. Coupling adjustment includes: Coupling of stress and temperature fields: Adjusting the effect of thermal stress on structural deformation to ensure that thermodynamic changes accurately reflect structural mechanics. Coupling of dynamics and thermodynamics: Combining the effect of temperature on damping and stiffness, the dynamic response is adjusted to accurately describe the effect of temperature on the motion behavior of the device.

[0084] Model accuracy assessment and continuous updating: Compare real-time data with model prediction data, and evaluate the accuracy of the model through error assessment indicators (such as mean square error). If the error exceeds the set threshold, the self-correction mechanism is triggered to further adjust the model parameters to ensure the high accuracy and stability of the digital twin model.

[0085] In summary, the above steps can realize the dynamic update of the digital twin model, so that the virtual model can accurately and real-time reflect the operating status of the bucket wheel machine. This update process ensures the synchronization between the model and the actual equipment status, and provides reliable real-time data support for subsequent multi-objective optimization and adaptive control.

[0086] In step S13, multi-objective optimization processing is performed based on the digital twin model to obtain the control strategy of the bucket wheel excavator.

[0087] For example, multi-objective optimization based on the digital twin model can achieve comprehensive control of the bucket wheel machine's operating status. By optimizing key indicators such as energy consumption, vibration and temperature, multiple optional control strategies can be generated, so that the bucket wheel machine's operating plan can be flexibly adjusted under different operating conditions.

[0088] Alternatively, if Figure 4 As shown, step S13 may include the following steps: In step S131, the objective function of the multi-objective optimization is constructed with energy consumption, vibration and temperature control as optimization targets.

[0089] For example, a multi-objective optimization problem can be constructed with energy consumption, vibration and temperature control as optimization targets, and the objective function can be defined as:

[0090] in, represents the energy consumption function, describing the electric energy consumption of bucket wheel machine under different operating conditions; Represents the vibration amplitude function, which is used to evaluate the impact of mechanical vibration on the equipment; Represents the temperature control function, which is used to keep the device running within a safe temperature range. Control variable These include operating variables such as speed, load and cooling parameters.

[0091] In step S132, the constraints of the multi-objective optimization are determined based on the operating conditions and safety limits of the bucket wheel machine.

[0092] For example, to ensure that the optimization process meets the actual working conditions, it is necessary to set the physical constraints and safety limits of the bucket wheel machine operation as the constraints of the multi-objective optimization, including:

[0093]

[0094] in, It is an inequality constraint, which is used to limit the upper and lower limits of the control variable, such as the maximum and minimum values ​​of the speed; Equality constraints are used to maintain equilibrium conditions of the system, such as energy conservation or material flow balance.

[0095] In step S133, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization calculation based on the objective function and the constraint conditions to obtain the control strategy.

[0096] Exemplarily, the non-dominated sorting genetic algorithm II can perform multi-objective optimization calculations, and the specific steps include: Initialize the population: randomly generate a set of control variable vectors , forming the initial population.

[0097] Fitness evaluation: For each individual in the population, the fitness value is calculated according to the objective function to evaluate its performance in terms of energy consumption, vibration and temperature control.

[0098] Non-dominated sorting: Sort the population according to the Pareto dominance relationship, assign individuals to different non-dominated frontiers, and divide them into levels according to the superiority of individuals.

[0099] Crowding calculation: Calculate the crowding distance of each individual to maintain the diversity of the population and prevent premature convergence.

[0100] Selection, crossover and mutation: According to non-dominated sorting and crowding, the parent generation is selected through tournament selection to perform crossover and mutation operations to generate a new offspring population. The crossover and mutation formulas are as follows:

[0101]

[0102] in, is the velocity of the particle, For location, is the inertia weight, is the learning factor, is a random number, is the optimal position of an individual, is the global optimal position.

[0103] Iterative optimization process: Repeat the steps of fitness evaluation, non-dominated sorting, crowding calculation and selection, crossover, mutation, etc., optimize the population generation by generation until the preset termination condition is reached, such as the maximum number of iterations or the stability of the Pareto front, and obtain the final multi-objective optimization solution set.

[0104] Strategy screening and application: Select a set of optimized control strategies from the final Pareto frontier, conduct adaptability evaluation based on the current bucket wheel machine operating conditions, and select the most suitable control strategy. The selection steps include: 1) Evaluation of operating conditions: Obtain current equipment status: Obtain the current bucket wheel machine operation data in real time from the sensor network and digital twin model, including: Load status: such as the current load and rotation speed of the bucket wheel excavator.

[0105] Environmental conditions: including ambient temperature, humidity and other external conditions that may affect the performance of the device.

[0106] Equipment health status: Evaluate the current health status of the equipment by real-time monitoring of key equipment components such as vibration, temperature and stress of bearings and motors.

[0107] 2) Optimize control strategy adaptability evaluation: Matching strategies with operating conditions: Match the current operating conditions with each optimization control strategy in the Pareto frontier. Each control strategy contains different control variable configurations, such as speed, cooling intensity, load adjustment, etc.

[0108] Calculate the adaptability score: Perform a comprehensive adaptability score on each strategy based on the current operating conditions. The scoring criteria include energy consumption, vibration, and temperature performance. The adaptability score formula is:

[0109] in, For the The comprehensive score of each control strategy, Respectively The energy consumption, vibration and temperature objective function values ​​under each strategy are: It is the weight coefficient of the corresponding target, which is set according to the current operation priority and actual needs.

[0110] 3) Select the optimal control strategy: Score sorting: Sort the scores of all strategies and select the strategy with the highest score as the optimal strategy under the current operating conditions.

[0111] Redundancy check: Perform a redundancy check on the selected optimal strategy to ensure that the actual execution will not exceed the equipment operating limits. If the speed or load required by the strategy exceeds the safe operating range of the equipment, a suboptimal strategy will be selected.

[0112] 4) Strategy application and execution: Apply the selected strategy: Convert the selected optimal control strategy into specific control instructions and send them to the controller of the bucket wheel excavator. The control instructions include adjusting the speed, adjusting the load, adjusting the cooling system, etc.

[0113] Real-time monitoring and feedback: During the strategy execution process, the response and actual operation status of the bucket wheel excavator are continuously monitored. Through the feedback mechanism, the execution results are compared with the expected effect of the strategy. If a large deviation is found, the strategy is adjusted immediately or the strategy is reselected.

[0114] Dynamic adjustment of policies: If the operating conditions change significantly (such as a sudden increase in load or abnormality in equipment), the dynamic adjustment mechanism of the policy is triggered. By re-acquiring the current operating status and real-time evaluation, the policy is re-selected and applied to ensure the stability and optimization of the system.

[0115] In summary, through the multi-objective optimization method, the comprehensive control of bucket wheel machine energy consumption, vibration and temperature is achieved, and a variety of optimization control strategies are generated, which provides a variety of strategy options for subsequent adaptive control. This optimization process can ensure that the bucket wheel machine can respond flexibly under different operating conditions and realize efficient and safe unattended intelligent control.

[0116] In step S14, the bucket wheel machine is controlled by adaptive model predictive control based on the control strategy.

[0117] For example, adaptive model predictive control can adjust the control input of bucket wheel machine in real time to optimize the operation status of the equipment. Adaptive model predictive control combines the system's dynamic prediction and real-time optimization capabilities, and can dynamically adjust the control strategy according to real-time operation data, thereby achieving precise control and stable operation of bucket wheel machine under variable operating conditions.

[0118] Alternatively, if Figure 5 As shown, step S14 may include the following steps: In step S141, a state space model describing the dynamic behavior of the bucket wheel machine is established.

[0119] Exemplarily, in the embodiments described in the present disclosure, a state space model may be established for a bucket wheel machine to describe the dynamic behavior of the bucket wheel machine system.

[0120] The state space model includes state equations and output equations:

[0121]

[0122] in, is the state vector, representing the current state parameters of the system (such as displacement, velocity); For control input (such as speed adjustment, load change); for outputs (e.g. vibration level, temperature); is the system matrix, describing the system dynamics and control influence.

[0123] The optimization goal of the predictive control of the state space model is set to optimize the current control input by predicting the future system state. The optimization objective function is defined as:

[0124] in, For the predicted future output, is the reference trajectory used to define the expected system response; is the weighted matrix of the output deviation, indicating the penalty for the deviation; is the weighted matrix of the control input, which represents the penalty for the control intensity. By minimizing the objective function, the comprehensive optimization of output deviation and control cost can be achieved.

[0125] To ensure that the control input is physically feasible and safe, a set of constraints are set for the state-space model, covering control input limits, state constraints, and output constraints: Control input constraints:

[0126] in, and The minimum and maximum values ​​of the control input are used to limit the equipment operating parameters, such as the upper and lower limits of speed and load, to avoid exceeding the safe operating range of the equipment.

[0127] State constraints:

[0128] in, and It is the allowable range of the state variable and is used to control the operating state of the bucket wheel excavator, such as limiting the temperature within a safe range to prevent damage to the equipment due to overheating or low temperature.

[0129] Optionally, after step S141, the method may further include: The parameters of the state-space model are updated online through an adaptive mechanism.

[0130] Exemplarily, in order to cope with the nonlinear and time-varying characteristics that may occur during the operation of the bucket wheel machine, this embodiment may also introduce an adaptive mechanism to update the parameters of the state space model online through the recursive least squares method (RLS). The adaptive update steps include: Parameter vector update:

[0131] Gain matrix update:

[0132] in, Covariance matrix update:

[0133] in, is the model parameter vector, is the feature vector, is the actual observed output, is the gain matrix, is the covariance matrix, is the forgetting factor, which is used to control the weight of historical data.

[0134] By introducing the above-mentioned adaptive mechanism, the state-space model can dynamically adjust parameters to adapt to real-time changing operating conditions, ensuring the accuracy and effectiveness of the control strategy.

[0135] In step S142, the control strategy is optimized based on the state space model to obtain a target control strategy.

[0136] For example, based on the state space model or after completing the above adaptive update, the optimization solver can be used to solve the objective function to obtain the optimal control input at the current moment. The optimization solver uses a gradient-based optimization algorithm, such as gradient descent or Newton's method, to ensure the convergence and efficiency of the optimization process. The iterative process of the optimization solution is as follows:

[0137] in, For the The control input for the iteration is is the learning rate, is the objective function For control input gradient.

[0138] The optimized control input The control system applied to the bucket wheel machine adjusts the operating parameters of the equipment, such as speed and load, through the execution unit. At the same time, the response status of the bucket wheel machine is monitored in real time, the actual output is collected and fed back to the digital twin model, the deviation between the predicted value and the actual value is compared, and the control strategy is further optimized through feedback adjustment.

[0139] In summary, through adaptive model predictive control, the control input of the bucket wheel machine is adjusted in real time to ensure that the equipment can operate stably and efficiently under various complex working conditions. The introduction of this control method can enable the bucket wheel machine system to respond quickly to external disturbances, optimize the operating state, and achieve the goal of unmanned intelligent control.

[0140] In step S143, the bucket wheel machine is controlled by the target control strategy.

[0141] For example, by applying the control instructions optimized in step S142, the bucket wheel machine can be adjusted in real time according to the actual operating state, thereby ensuring the optimal operating state of the equipment under different working conditions. This step is the final execution link of the entire unattended intelligent control method. By implementing the aforementioned optimization strategy and control instructions, the automatic operation of the bucket wheel machine is realized.

[0142] In the embodiment described in the present disclosure, the specific steps of adjusting the operating state of the bucket wheel machine according to the optimized control instruction include: 1) Transmission and execution of control instructions: In step S142, the optimal control input is obtained by adaptive model predictive control The instructions are transmitted to the controller of the bucket wheel machine, which is responsible for converting these instructions into actual operations, including adjusting the speed, load, working status of the cooling system, etc. The control instructions received by the controller include:

[0143] in, , etc. represent the specific values ​​of different control parameters, such as speed setting, temperature control setting, etc. The controller executes these instructions and sends the corresponding operation signals to the execution unit of the equipment.

[0144] 2) Real-time monitoring and data feedback: During the execution of control instructions, the response status of the bucket wheel excavator is monitored in real time through the sensor network, and key operating data including equipment speed, vibration level, temperature distribution, etc. are collected. These data will be used to evaluate the control effect and fed back to the digital twin model. The real-time monitoring formula is expressed as:

[0145] in, For the monitored system output, Represents the functional relationship between system state and control input.

[0146] 3) Feedback adjustment mechanism: Based on the real-time monitoring data, the actual operating status of the equipment is compared with the predicted status in the digital twin model to calculate the output error. If the error is within the allowable range, the current control strategy will continue to be executed; if the error exceeds the threshold, the feedback adjustment mechanism will be triggered. The main steps of feedback adjustment include: Error calculation:

[0147] in, The actual output With reference output By analyzing the size and trend of the error, the effectiveness of the current control strategy can be judged.

[0148] Adjust control instructions: According to the size and direction of the error, adjust the control input accordingly to reduce the error. The adjusted control input is:

[0149] in, is the correction amount calculated based on the error. The adjusted instruction is retransmitted to the controller to execute the new operation command.

[0150] 4) Implementation of closed-loop control: Through continuous monitoring and feedback, a closed-loop control system is formed to continuously optimize the operation status of the bucket wheel excavator. The cycle process of closed-loop control can be expressed as:

[0151] In each closed-loop cycle, the system updates the control strategy based on the latest feedback data to cope with changes in the external environment and fluctuations in equipment status.

[0152] 5) System performance evaluation and self-correction: Regularly evaluate the overall performance of the system and analyze the long-term effects of the control strategy. Performance evaluation indicators include energy consumption, equipment life, operating efficiency, etc. If the system performance is found to be declining or the equipment status is abnormal, the self-correction mechanism is triggered to correct and optimize the digital twin model and control strategy as a whole. The self-correction process includes: Model parameter update: The parameters of the digital twin model are fully re-evaluated and updated to ensure that the model accurately reflects the current status of the equipment.

[0153] Strategy optimization: Re-execute the multi-objective optimization step (S4) to generate a new optimization control strategy and replace the strategy that is no longer applicable.

[0154] By executing optimized control instructions and making real-time feedback adjustments, the bucket wheel excavator can maintain the best state in a complex and changing operating environment. The introduction of this closed-loop control system enables the system to have adaptive and self-optimization capabilities, significantly improving the effect of unmanned intelligent control.

[0155] In summary, in the embodiments disclosed in the present invention, the bucket wheel machine unattended intelligent control method based on digital twin technology realizes real-time monitoring, precise modeling, dynamic optimization and adaptive control of the bucket wheel machine operating status, ensuring stable and efficient operation of the equipment under complex and changeable working conditions. Through multi-physics field modeling, real-time data fusion and multi-objective optimization, the system can generate a variety of control strategies and adaptively adjust them, significantly improving the operating efficiency of the bucket wheel machine, reducing energy consumption, and reducing the failure rate, while reducing dependence on manual intervention, and realizing true unattended and intelligent management.

[0156] In the above technical solution, the operation data of the bucket wheel machine is collected in real time through the sensor network; the digital twin model of the bucket wheel machine is dynamically updated through the operation data; multi-objective optimization processing is performed based on the digital twin model to obtain the control strategy of the bucket wheel machine; based on the control strategy, the bucket wheel machine is controlled through adaptive model predictive control. By constructing a digital twin model of the bucket wheel machine, real-time operation data fusion, multi-objective optimization and adaptive control strategy, the bucket wheel machine can operate efficiently and stably in a complex operating environment, reducing dependence on manual operation.

[0157] Figure 6 FIG. 6 is a block diagram of a bucket wheel machine control device 600 according to an exemplary embodiment. Figure 6 As shown, the device 600 includes: a collection module 610, an update module 620, a processing module 630 and a control module 640; The acquisition module 610 is used to collect the operation data of the bucket wheel machine in real time through the sensor network; The updating module 620 is used to dynamically update the digital twin model of the bucket wheel machine through the operating data; The processing module 630 is used to perform multi-objective optimization processing based on the digital twin model to obtain a control strategy for the bucket wheel machine; The control module 640 is used to control the bucket wheel machine through adaptive model predictive control based on the control strategy.

[0158] Optionally, the steps of establishing the digital twin model include: The structural mechanics sub-model of the bucket wheel machine is established based on the finite element method; The dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation; The thermodynamic sub-model of the bucket wheel machine is established based on the heat conduction equation; The digital twin model is obtained by performing multi-physical field coupling based on the structural mechanics sub-model, the dynamics sub-model and the thermodynamics sub-model.

[0159] Optionally, the bucket wheel machine is meshed based on the finite element method, and a mathematical sub-model of stress and deformation is established according to the meshing result, the material properties of the bucket wheel machine and boundary conditions as the mechanical sub-model.

[0160] Optionally, a dynamic sub-model based on at least one of mass distribution, inertia characteristics, damping, stiffness and external force of the bucket wheel machine is established through the Lagrangian equation.

[0161] Optionally, based on the heat conduction equation, the temperature distribution and thermal stress of the bucket wheel machine during operation are simulated to obtain the thermodynamic sub-model.

[0162] Optionally, the multi-physics coupling includes: The structural mechanics sub-model is coupled with the dynamics sub-model; The structural mechanics sub-model is coupled to the thermodynamics sub-model; The kinetic sub-model and the thermodynamic sub-model are coupled.

[0163] Optionally, the updating module 620 is used to: inputting the operating data into the digital twin model; The Kalman filter is used to dynamically update the digital twin model.

[0164] Optionally, the processing module 630 is used to: Taking energy consumption, vibration and temperature control as optimization targets, the objective function of the multi-objective optimization is constructed; Determining the constraints of the multi-objective optimization based on the operating conditions and safety limits of the bucket wheel machine; Based on the objective function and the constraint conditions, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization calculation to obtain the control strategy.

[0165] Optionally, the control module 640 is used to: Establish a state space model that describes the dynamic behavior of the bucket wheel machine; Optimize the control strategy based on the state space model to obtain a target control strategy; The bucket wheel machine is controlled by the target control strategy.

[0166] Optionally, the control module 640 is further configured to: The parameters of the state-space model are updated online through an adaptive mechanism.

[0167] In the above technical solution, the operation data of the bucket wheel machine is collected in real time through the sensor network; the digital twin model of the bucket wheel machine is dynamically updated through the operation data; multi-objective optimization processing is performed based on the digital twin model to obtain the control strategy of the bucket wheel machine; based on the control strategy, the bucket wheel machine is controlled through adaptive model predictive control. By constructing a digital twin model of the bucket wheel machine, real-time operation data fusion, multi-objective optimization and adaptive control strategy, the bucket wheel machine can operate efficiently and stably in a complex operating environment, reducing dependence on manual operation.

[0168] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0169] Figure 7 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 , a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0170] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned bucket wheel machine control method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. For example, these data may include instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0171] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned bucket wheel machine control method.

[0172] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned bucket wheel machine control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned bucket wheel machine control method.

[0173] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above bucket wheel machine control method when executed by the programmable device.

[0174] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0175] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0176] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A bucket wheel excavator control method, characterized in that: include: Collect bucket wheel machine operation data in real time through sensor network; Dynamically updating the digital twin model of the bucket wheel machine through the operating data; Performing multi-objective optimization processing based on the digital twin model to obtain a control strategy for the bucket wheel excavator; Based on the control strategy, the bucket wheel machine is controlled by adaptive model predictive control.

2. The method according to claim 1, characterized in that The steps of establishing the digital twin model include: Establishing a structural mechanics sub-model of the bucket wheel machine based on the finite element method; A dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation; Establishing a thermodynamic sub-model of the bucket wheel machine based on a heat conduction equation; The digital twin model is obtained by performing multi-physical field coupling based on the structural mechanics sub-model, the dynamics sub-model and the thermodynamics sub-model.

3. The method according to claim 2, characterized in that The method of establishing a structural mechanics sub-model of the bucket wheel machine based on the finite element method comprises: The bucket wheel machine is meshed based on the finite element method, and a mathematical sub-model of stress and deformation is established according to the meshing result, the material properties of the bucket wheel machine and the boundary conditions as the mechanical sub-model.

4. The method according to claim 2, characterized in that: The dynamic sub-model of the bucket wheel machine is established based on the Lagrange equation, including: A dynamic sub-model based on at least one of mass distribution, inertia characteristics, damping, stiffness and external force of the bucket wheel machine is established through the Lagrangian equation.

5. The method according to claim 2, characterized in that: The thermodynamic sub-model of the bucket wheel machine is established based on the heat conduction equation, including: Based on the heat conduction equation, the temperature distribution and thermal stress of the bucket wheel excavator during operation are simulated to obtain the thermodynamic sub-model.

6. The method according to claim 2, characterized in that The multi-physics coupling includes: The structural mechanics sub-model is coupled with the dynamics sub-model; The structural mechanics sub-model and the thermodynamics sub-model are coupled; The kinetic sub-model and the thermodynamic sub-model are coupled.

7. The method according to claim 1, characterized in that The dynamically updating the digital twin model through the operating data includes: inputting the operating data into the digital twin model; The Kalman filter is used to dynamically update the digital twin model.

8. The method according to claim 1, characterized in that The multi-objective optimization process based on the digital twin model is performed to obtain the control strategy of the bucket wheel machine, including: Taking energy consumption, vibration and temperature control as optimization targets, constructing the objective function of the multi-objective optimization; Determining the constraint conditions of the multi-objective optimization based on the operating conditions and safety limits of the bucket wheel machine; Based on the objective function and the constraint conditions, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization calculation to obtain the control strategy.

9. The method according to claim 1, characterized in that: The method of controlling the bucket wheel machine by adaptive model predictive control based on the control strategy includes: Establishing a state space model describing the dynamic behavior of the bucket wheel machine; Optimizing the control strategy based on the state space model to obtain a target control strategy; The bucket wheel machine is controlled by the target control strategy.

10. The method according to claim 9, characterized in that After establishing the state space model describing the dynamic behavior of the bucket wheel machine, the method further comprises: The parameters of the state space model are updated online through an adaptive mechanism.

11. A bucket wheel excavator control device, characterized in that: include: A collection module is used to collect the operation data of the bucket wheel machine in real time through a sensor network; An updating module, used for dynamically updating the digital twin model of the bucket wheel machine through the operating data; A processing module, used for performing multi-objective optimization processing based on the digital twin model to obtain a control strategy for the bucket wheel machine; A control module is used to control the bucket wheel machine through adaptive model predictive control based on the control strategy.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 10 are implemented.

13. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images