High-voltage variable-frequency power supply thermal management control method for improving energy efficiency

Abstract

The invention relates to the technical field of power supply thermal management control, and discloses a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency, and the method comprises the following steps: carrying out the order reduction processing in combination with a solar high-temperature thermal power generation system, and obtaining a low-dimensional model; carrying out data fusion by using Gaussian process regression and a Kalman filtering algorithm, and reconstructing temperature field information of the system; establishing a multi-objective optimization function, and dynamically adjusting a weight optimization objective; generating a control parameter sequence by using an improved particle swarm optimization algorithm, and adjusting a control decision in real time through iterative optimization; the optimized control parameters are input into a multi-rate hierarchical control system for division execution; and detecting a fault type and switching to a corresponding fault-tolerant control mode. According to the method, a multi-physical field coupling model and an intrinsic orthogonal decomposition technology are combined, an accurate coupling model of an electromagnetic field, a temperature field and a flow field in the high-voltage variable-frequency power generation system is established, through order reduction processing, the dimension of the model is reduced, the calculation complexity is remarkably reduced, and the calculation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply thermal management control, and in particular to a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency. Background Art

[0002] As a key component of modern industrial and energy systems, high-voltage variable-frequency power supplies are widely used in fields such as power generation, chemical engineering, and mining. Their primary function is to precisely control power by adjusting voltage and frequency to meet energy demands under varying loads and operating conditions. With the advancement of industrial automation and increasingly stringent energy conservation and emission reduction requirements, the energy efficiency and stability of high-voltage variable-frequency power supplies have become key factors in ensuring efficient system operation.

[0003] Existing thermal management technologies primarily rely on temperature or flow field models, adjusting cooling systems through simplified numerical analysis of temperature changes or the cooling effects of fluids. Common cooling methods include air cooling and liquid cooling, which typically maintain power supply equipment temperatures within a safe range by adjusting fan speed and liquid flow.

[0004] However, existing thermal management control technologies only analyze the temperature field or flow field independently, lacking comprehensive consideration of the coupling between the electromagnetic field, temperature field, and flow field. This results in low model accuracy and makes it difficult to fully reflect the thermal state of the system. Secondly, traditional multi-objective optimization methods usually focus only on optimizing a single objective, neglecting the comprehensive optimization of multiple objectives. Therefore, the present invention provides a high-voltage variable-frequency power supply thermal management control method that improves energy efficiency to address the shortcomings of the existing technology. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a high-voltage variable-frequency power supply thermal management control method to improve energy efficiency, which solves the problems of existing single physical field analysis, lack of multi-field coupling, insufficient accuracy and insufficient multi-objective optimization.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A high-voltage variable-frequency power supply thermal management control method for improving energy efficiency, comprising the following steps:

[0007] Based on the principles of electromagnetics, heat conduction, and fluid mechanics, and combined with the structure and operating environment of the solar high-temperature thermal power generation system, a coupled model of electromagnetic field, temperature field, and flow field is established. The order reduction is performed through intrinsic orthogonal decomposition to obtain a low-dimensional model.

[0008] Based on the obtained low-dimensional model, temperature sensors, heat flow sensors, and flow velocity sensors are placed at different locations in the solar thermal power generation system to collect data from the power generation system. The collected data is then fused using Gaussian process regression and Kalman filtering algorithms to reconstruct the temperature field of the power generation system.

[0009] Through the reconstructed temperature field information, a multi-objective optimization function is established, which comprehensively considers the temperature difference, cooling power, temperature field uniformity and thermal energy storage efficiency goals, dynamically adjusts the weights, and optimizes the target priority in real time;

[0010] Based on the established multi-objective optimization function, an improved particle swarm optimization algorithm is used to generate a control parameter sequence. The control parameters are optimized iteratively through the particle swarm, and the control decision is adjusted according to the real-time data and prediction results.

[0011] The optimized control parameters are input into the multi-rate hierarchical control system, which is divided into three parts: the high-speed loop, the medium-speed loop, and the low-speed loop. The data is synchronized through the state buffer.

[0012] By executing the control process in real time, the system status is monitored and the type of fault in the power generation system is detected, and the corresponding fault-tolerant control mode is switched according to the type of fault.

[0013] Preferably, the establishment of the electromagnetic field, temperature field and flow field coupling model includes the following steps:

[0014] By combining the light-to-heat conversion process of solar high-temperature thermal power generation systems, heat conduction and fluid mechanics principles, the mutual coupling between light radiation, temperature field and cooling flow field is first considered in the physical model;

[0015] Apply partial differential equations to describe the coupling relationship between light radiation, temperature, and fluid fields, and calculate the transient response of each physical field, focusing on the heat conduction and heat energy recovery processes of solar collectors, thermal energy storage systems, and heat exchangers;

[0016] The obtained high-dimensional coupled equations are reduced in order using the intrinsic orthogonal decomposition method to retain the main physical characteristics, reduce the amount of calculation, and obtain a low-dimensional photothermal conversion-temperature field-flow field coupling model.

[0017] Preferably, the fusing of the collected data using Gaussian process regression and Kalman filter algorithm comprises the following steps:

[0018] After obtaining the low-dimensional model, temperature sensors, heat flow sensors, and flow velocity sensors are placed at different locations in the solar high-temperature thermal power generation system to collect system status information in real time, focusing on the status of the collector, heat exchanger, and thermal energy storage system;

[0019] The Gaussian process regression algorithm is used to spatially interpolate the sensor data to infer the precise values ​​of the temperature field and flow field, ensuring accurate reconstruction of the collector surface temperature and heat exchange efficiency.

[0020] Combined with the Kalman filter algorithm, the sensor data is dynamically updated in time series to reconstruct the temperature field of the solar power generation system and adapt to changes in weather and light intensity.

[0021] Preferably, the establishing of the multi-objective optimization function comprises the following steps:

[0022] Based on the reconstructed temperature field information, a multi-objective optimization function is established to simultaneously optimize the temperature difference, cooling power, temperature field uniformity, and thermal energy storage efficiency.

[0023] The multi-objective optimization function is expressed as:

[0024] J(t)=α·max(ΔT)+β·∫P cool dt+γ·σ T ;

[0025] Where ΔT is the maximum temperature difference in the system, P cool is the system cooling power, σ T is the uniformity of the temperature field, α, β, γ are the dynamically adjusted weight coefficients, dt is the time step, and J(t) is the value of the multi-objective optimization function;

[0026] The weight coefficient is dynamically adjusted according to real-time working conditions and environmental change factors, especially optimized according to light intensity, ambient temperature and system load conditions.

[0027] Preferably, the method of generating the control parameter sequence using the improved particle swarm optimization algorithm comprises the following steps:

[0028] In the particle swarm optimization algorithm, the initial position and velocity of each particle in the population are first set, and the fitness of the current particle is calculated. The fitness function is defined based on the temperature field, cooling power, and thermal energy storage target;

[0029] At each iteration, the particle's velocity and position are updated, where the particle's velocity update equation is:

[0030]

[0031] in, represents the updated velocity value of particle i in the k+1 generation, ω is the inertia weight, c1, c2, c3 are constant acceleration factors, and pbest i is the best position that particle i reaches in the historical search, is the current position of particle i in the kth generation, gbest is the global best position found by all particles in the current generation, r1, r2, r3 are the coefficients in the particle velocity update equation, is the gradient term of the cost function, and the inertia weight ω is adjusted according to the convergence requirements of the algorithm;

[0032] Through multiple particle swarm iterations, a set of optimized control parameters is finally obtained to adapt to the regulation of solar collectors and heat exchangers under different lighting conditions.

[0033] Preferably, inputting the optimized control parameters into the multi-rate hierarchical control system comprises the following steps:

[0034] Inputting the optimized control parameters into a multi-rate hierarchical control system, wherein the multi-rate hierarchical control system includes a high-speed loop, a medium-speed loop, and a low-speed loop;

[0035] The high-speed loop performs real-time particle swarm optimization control parameter calculations to regulate the operation of the collector and cooling system. The medium-speed loop dynamically predicts the thermal field model of the power generation system and regulates the heat release of the thermal energy storage system. The low-speed loop is responsible for performing physical driving and cooling operations.

[0036] The data of each loop is synchronized through the status buffer area to make the control operations of each loop coordinated and consistent.

[0037] Preferably, switching to a corresponding fault-tolerant control mode according to the fault type includes the following steps:

[0038] By monitoring the real-time status of the system, the residual detection mechanism is used to determine whether there is a fault. If the system detects the type of fault, the fault-tolerant control mode is triggered;

[0039] In the event of a sensor failure, model predictive control is used to replace the function of the damaged sensor and control the thermal management process through the estimated value;

[0040] In the event of an actuator failure, the system switches to safe mode and controls the system operation via set limits.

[0041] Preferably, the step of reducing the obtained high-dimensional coupled equations by the proper orthogonal decomposition method includes:

[0042] The snapshot matrix X=[x1,x2,…,x m ], where X represents the snapshot matrix of state variables collected at time, each Indicates the state of the power generation system at a certain moment, x i represents the state of the power generation system at the i-th moment, and n represents the state variable dimension of the power generation system;

[0043] Perform singular value decomposition on the snapshot matrix:

[0044] X=U∑V T ;

[0045] Among them, U is the left singular vector matrix, ∑ is the singular value diagonal matrix, V Tis the transpose of the right singular vector matrix;

[0046] Select the first r main modes to form the dimensionality reduction basis Φ=[u1,u2,…,u r ], projecting the high-dimensional system state into a low-dimensional subspace:

[0047] x(t)≈Φa(t);

[0048] Where r represents the number of principal components, Φ=[u1,u2,…,u r ] represents the most representative basis vector extracted from the original state data, a(t) is the low-dimensional state variable, Φ is the POD modal matrix, and x(t)≈Φa(t) indicates the POD method.

[0049] Preferably, the dynamic adjustment of the weight coefficient is driven by the Lyapunov guidance strategy, and the adjustment formula is:

[0050]

[0051] Among them, α, β, and γ represent the three dynamic weight factors in multi-objective optimization. Indicates the rate at which these three weights change over time, k1, k2, k3>0 is the adjustment factor, Represents the partial derivative of the optimization objective function with respect to each sub-objective.

[0052] A high-voltage variable-frequency power supply thermal management control system for improving energy efficiency is also provided, including:

[0053] The multi-physics modeling and order reduction module is used to establish a coupled model of electromagnetic field, temperature field and flow field based on the principles of electromagnetics, heat conduction and fluid mechanics, combined with the system structure and operating conditions, and perform model order reduction based on the intrinsic orthogonal decomposition method;

[0054] The sensor acquisition and temperature rise detection module is used to place temperature sensors, heat flow sensors, and flow velocity sensors on key components and overheat-sensitive areas of the solar thermal power generation system. It collects multi-point operating data and integrates and analyzes it through Gaussian process regression and Kalman filter algorithms;

[0055] The thermal safety assessment and protection strategy module is used to combine the real-time temperature field reconstruction results with the historical thermal runaway characteristic curve to determine whether the preset temperature protection threshold has been reached, construct a multi-objective protection function, and form a dynamic safety control strategy;

[0056] The control parameter optimization generation module is used to generate control parameter sequences based on thermal safety control strategies through an improved particle swarm algorithm, and introduces temperature rise weighting factors and gradient feedback to improve control accuracy;

[0057] A multi-rate thermal control execution module receives optimized control parameters and executes them hierarchically according to the high-speed, medium-speed, and low-speed control strategies, while utilizing a state buffer to synchronize control data across rates.

[0058] The fault identification and redundant fault-tolerance module is used to identify and locate sensor failures, actuator failures or temperature anomalies that may occur during system operation, and switch to model prediction fault-tolerant control mode or enable redundant equipment according to the fault type.

[0059] The present invention provides a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency. It has the following beneficial effects:

[0060] 1. This paper combines a multi-physics field coupling model with intrinsic orthogonal decomposition technology to establish an accurate coupling model of the electromagnetic field, temperature field, and flow field in a high-voltage variable-frequency power generation system. This model can accurately simulate the mutual influence between different physical fields, especially the impact of electromagnetic field changes on temperature distribution and fluid flow. Through order reduction processing, the dimensionality of the model is reduced, the computational complexity is significantly reduced, and the computational efficiency is improved. It can comprehensively consider the coupling effects of multiple physical fields in the system, avoiding the high computational cost and low efficiency problems caused by complex interactions in the existing technology.

[0061] 2. This invention utilizes a combined Gaussian process regression and Kalman filtering algorithm to optimize the prediction accuracy of temperature and flow fields in real time even when sensor data is incomplete or noisy. Through data fusion, the system can provide accurate temperature reconstruction information even when temperature sensors are erroneous or lost. This is superior to traditional single-sensor prediction methods, avoiding inaccurate temperature predictions caused by sensor failure or data loss, thereby improving the thermal management reliability of the system.

[0062] 3. The present invention utilizes a particle swarm optimization algorithm to dynamically generate a sequence of control parameters, achieving multi-objective optimization of temperature difference, cooling power, and temperature field uniformity in a high-voltage variable-frequency power supply system. The iterative optimization of the particle swarm optimization algorithm not only adjusts the control strategy based on real-time data and system prediction results, but also adapts to system load and environmental changes, optimizing thermal management, reducing energy consumption, and improving system stability. Compared to traditional fixed control strategies, the control scheme of the present invention is more flexible and precise, and can be dynamically adjusted as load and environmental conditions change, ensuring that the system remains within a safe temperature range.

[0063] 4. By combining residual analysis with model predictive control, this invention can identify sensor or actuator failures in real time and automatically switch to a fault-tolerant control mode. This mechanism enables the system to maintain temperature control functionality and prevent overheating caused by sensor or actuator failures. Compared to traditional fault-tolerant control methods, this invention dynamically adjusts the weights of optimization objectives to ensure stable system operation even in the event of device failure, preventing overheating or damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a flow chart of the method steps of the present invention;

[0065] Figure 2 This is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] Please see the attached Figure 1 The embodiment of the present invention provides a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency, comprising the following steps:

[0068] S1. Based on the principles of electromagnetics, heat conduction, and fluid mechanics, and in combination with the structure and operating environment of the solar high-temperature thermal power generation system, a coupled model of the electromagnetic field, temperature field, and flow field is established. The model is then reduced to a low-dimensional model through proper orthogonal decomposition.

[0069] S2. Based on the obtained low-dimensional model, temperature sensors, heat flow sensors, and flow velocity sensors are placed at different locations in the CSP system to collect data from the power generation system. The collected data are then fused using Gaussian process regression and Kalman filtering algorithms to reconstruct the temperature field of the power generation system.

[0070] S3. Establish a multi-objective optimization function based on the reconstructed temperature field information, comprehensively consider the temperature difference, cooling power, temperature field uniformity and thermal energy storage efficiency goals, dynamically adjust the weights, and optimize the goal priority in real time;

[0071] S4. Based on the established multi-objective optimization function, an improved particle swarm optimization algorithm is used to generate a control parameter sequence. The control parameters are optimized through particle swarm iteration, and the control decision is adjusted according to the real-time data and prediction results.

[0072] S5. Input the optimized control parameters into the multi-rate hierarchical control system, which is executed by the high-speed ring, the medium-speed ring, and the low-speed ring, and synchronizes the data through the state buffer;

[0073] S6. By executing the control process in real time, the system status is monitored and the type of fault in the power generation system is detected, and the corresponding fault-tolerant control mode is switched according to the type of fault.

[0074] Regarding step S1, in this embodiment, a coupled model of the electromagnetic field, temperature field, and flow field is first established based on the principles of electromagnetism, thermal conductivity, and fluid mechanics, combined with the specific design parameters of the high-voltage variable-frequency power supply. Generally, these physical fields influence each other. Changes in the electromagnetic field will cause changes in the distribution of the temperature field, while fluid flow affects the conduction and dissipation of heat. In high-voltage variable-frequency power supply systems, special attention must be paid to overheating protection and safety to ensure that the system can respond promptly and take effective protective measures in the event of temperature anomalies.

[0075] Specifically, the model building process includes the following aspects:

[0076] Establishing an electromagnetic field model: High-voltage variable-frequency power generation systems typically contain multiple power electronic devices, which generate strong electromagnetic fields during operation. To accurately simulate the performance of the power generation system, it is necessary to consider the impact of electromagnetic fields on the power equipment, particularly the effects of current fluctuations on motor windings and heat sources. During this process, the system needs to monitor electromagnetic field changes in real time to prevent electromagnetic interference and thermal damage caused by overload. This part of the model is described using Maxwell's equations from electromagnetics:

[0077]

[0078] in, represents the curl of the electric field E; E is the electric field strength; B is the magnetic field strength; represents the gradient operator; represents the partial derivative of the magnetic field B with respect to time; Indicates that the divergence of the magnetic field is zero.

[0079] Establishing a temperature field model: During the operation of a variable-frequency power supply, the heat exchange between electrical components and the air or coolant determines the distribution of the temperature field. This temperature field is determined by both heat conduction and convection processes and is typically modeled using a combination of heat conduction equations and fluid dynamics equations. Real-time monitoring of the temperature field is particularly important to prevent failures or safety risks caused by overheating. The distribution of the temperature field directly affects the effectiveness of thermal management strategies. This temperature field can be described by the following equation:

[0080]

[0081] Where ρ is density; c is specific heat capacity; k is thermal conductivity; T is temperature; Q is the heat source term; It represents the rate of change of temperature with time; Represents the diffusion of heat in space. The distribution of temperature field plays a vital role in the thermal management of power generation systems.

[0082] Establishing a flow field model: The fluid mechanics component primarily considers the effects of coolant flow. Changes in the flow field directly affect heat conduction and dissipation. Fluid flow follows the Navier-Stokes equations, which describe the laws of fluid motion. The flow rate and flow rate of the cooling fluid are particularly important to ensure that heat is removed promptly and to prevent heat accumulation and overheating. A flow field model typically takes the following form:

[0083]

[0084] Where v is the fluid velocity; p is the fluid pressure; μ is the dynamic viscosity of the fluid; F is the external force (such as gravity, etc.); Indicates the instantaneous rate of change of flow velocity; The change in velocity of particles due to motion; Indicates the direction and magnitude of acceleration caused by uneven pressure distribution; Represents the momentum diffusion caused by viscosity inside the fluid.

[0085] Time-Varying Characteristics and Dynamic Response: As voltage and load change, the power generation system's electromagnetic characteristics, temperature distribution, and cooling effectiveness change dynamically. Therefore, when building a model, the system's time-varying characteristics must be considered to ensure the model can adapt to changes in different operating conditions. Especially in high-load or low-temperature environments, the system's response must be highly flexible and accurate to avoid failures caused by temperature anomalies or overloads.

[0086] By establishing the aforementioned physical model, the coupling between the electromagnetic field, temperature field, and flow field can be accurately simulated and solved. It is important to note that the electromagnetic characteristics, temperature distribution, and cooling effect of the power generation system will change dynamically with changes in voltage and load. Therefore, when establishing the model, it is also necessary to consider the time-varying characteristics of the system so that the model can adapt to changes under different operating conditions.

[0087] In some embodiments, the proper orthogonal decomposition (POD) method is used to reduce the order of the high-dimensional coupled equations. By collecting snapshots of the state variables of the coupled model in time, a snapshot matrix is ​​formed:

[0088] X=[x1,x2,…,xm];

[0089] Where X is the snapshot matrix; x i(where i = 1, 2, ..., m) represents the state vector of the system at the i-th time step; m is the number of snapshots; each x i Represents the state vector of the power generation system at a certain moment. By performing singular value decomposition (SVD) on the matrix:

[0090] X=U∑V T ;

[0091] Among them, U is the left singular vector matrix; ∑ is the singular value diagonal matrix; V T is the transpose of the right singular vector matrix.

[0092] Extract the main features U from it and select the top r modes to form the dimensionality reduction base:

[0093] Φ=[u1,u2,…,u r ];

[0094] Among them, Φ is the reduced-dimensional modal basis matrix; u i (where i = 1, 2, ..., n); r is the number of selected main modes.

[0095] By projecting the high-dimensional state onto a low-dimensional subspace, the state variables of the low-dimensional system are obtained, significantly reducing computational complexity. This reduced-order model not only improves the efficiency of the numerical solution but also ensures accurate thermal management of the high-voltage variable-frequency power supply system under different operating conditions.

[0096] In this embodiment, the established electromagnetic field, temperature field and flow field coupling model provides basic data support for subsequent multi-objective optimization and thermal safety protection. Through the dynamic optimization and updating of the model, the system can monitor and reflect the thermal state of the power generation system in real time. When the temperature is abnormal or overloaded, it can respond in time and trigger the overheating protection mechanism, thereby ensuring that the system is always within the safe operating range.

[0097] In step S2, this embodiment utilizes Gaussian process regression (GPR) and Kalman filtering algorithms to process sensor data, improving the accuracy of reconstructing the power generation system's temperature and flow fields. This provides more accurate real-time data support for subsequent thermal management and control, particularly for overheat protection and fault diagnosis. The data fusion process integrates data collected by multiple sensors (such as temperature sensors and flow rate sensors), further optimizing temperature and flow field predictions through mathematical modeling, and providing data support for overheat warnings and thermal protection responses.

[0098] The data of temperature, flow rate and other related parameters collected by sensors are usually affected by noise, sensor errors, system anomalies, etc. Therefore, Gaussian process regression and Kalman filtering algorithms must be used to eliminate noise, compensate for data loss, and enhance the system's response to fault warnings.

[0099] Specifically, the combination of Gaussian process regression and Kalman filtering provides a powerful data fusion method:

[0100] Gaussian Process Regression (GPR): A nonparametric regression method based on Bayesian theory, GPR is widely used to solve regression problems caused by factors such as noise and incomplete data. It can help the system process sensor errors and predict the changing trends of temperature and flow fields in real time, ensuring a timely response to thermal runaway. The specific regression model can be expressed as the following equation:

[0101]

[0102] Where y(x) is the predicted temperature value; K(x, X) is the kernel function matrix, which represents the similarity between the test point and the training point; K(X, X) is the kernel function matrix between the training set itself; I is the identity matrix; is the noise variance; y is the temperature value of the training data; X is the training data point.

[0103] Kalman Filter: A recursive optimization estimation method widely used for state estimation in dynamic systems. It effectively adjusts temperature field estimates during real-time monitoring, optimizing fault warning and overheating protection. Kalman filtering combines historical estimates with new observations to minimize error covariance, enhancing the system's dynamic prediction capabilities for temperature changes and ensuring real-time response to temperature anomalies and faults. The basic formula for Kalman filtering is as follows:

[0104]

[0105] in, is the estimated value at the kth moment, is the predicted value based on previous data, K k is the Kalman gain, z k is the new observation value at the Kth moment, H k is the observation matrix.

[0106] By combining the advantages of GPR and Kalman filtering algorithms, this method effectively leverages the unique characteristics of sensor data, reduces noise interference, and improves the accuracy of temperature and flow field reconstruction. During real-time dynamic monitoring, the data fusion method provides precise input data for subsequent control strategies, enabling the system to intelligently adjust to different operating conditions, ensuring a balanced temperature distribution and preventing system failures caused by overheating.

[0107] In particular, data fusion technology can effectively monitor sensor data anomalies and provide early warning of overheating failures. For example, when certain sensors fail or data is lost, the system can reconstruct an accurate prediction of the temperature field through data fusion and trigger fault-tolerant control through redundancy mechanisms to ensure stable system operation. Furthermore, after data fusion, the system can accurately predict temperature trends within the power supply and adjust the cooling system's operating status accordingly to prevent thermal runaway.

[0108] In step S3, this embodiment constructs a multi-objective optimization function to comprehensively optimize the system's thermal management indicators, specifically incorporating overheat protection and fault response requirements. Specifically, the optimization function not only focuses on a single objective but also simultaneously considers three important parameters: temperature difference, cooling power, and temperature field uniformity. By dynamically adjusting the weight coefficients of each objective, the optimization process automatically adjusts the priority of optimization objectives based on the requirements of different operating states, thereby achieving optimal thermal management results under different environmental and load conditions, ensuring that the system can respond promptly and implement fault protection measures in the event of temperature anomalies.

[0109] In some embodiments, the multi-objective optimization function can be expressed as the following mathematical model:

[0110] J(t)=α·max(ΔT)+β·∫P cool dt+γ·σ T ;

[0111] Where ΔT is the maximum temperature difference in the system; P cool is the system cooling power; σ T is the uniformity of the temperature field; α, β, and γ are dynamically adjusted weight coefficients; dt is the time step; and J(t) is the value of the multi-objective optimization function. The weight coefficients α, β, and γ for each objective are dynamically adjusted and updated in real time based on actual operating conditions (such as load changes and ambient temperature), ensuring that the optimization process meets thermal management requirements under different operating conditions.

[0112] In another embodiment, the weight coefficients can be adjusted using a Lyapunov-guided strategy to ensure that the system can respond promptly to temperature anomalies or load changes. In this case, the change pattern of the weight coefficients α, β, and γ is described by the following equation:

[0113]

[0114] Among them, α, β, and γ represent the three dynamic weight factors in multi-objective optimization; Indicates the rate at which these three weights change over time; k1, k2, k3>0 are adjustment factors; represents the partial derivatives of the optimization objective function with respect to each sub-objective. Through these equations, the optimization process can automatically adjust the weights of each optimization objective based on the real-time state of the system, thereby achieving more precise temperature control and energy efficiency improvement.

[0115] During the multi-objective optimization process, the first consideration is temperature difference, a key factor in determining whether there is local overheating in the power generation system. In high-voltage variable-frequency power generation systems, temperature difference often indicates uneven temperature distribution in key areas of the system, such as between power electronics and heat sinks. Excessive temperature difference can lead to equipment overheating or failure, so it is necessary to minimize this difference to maintain system stability and safety.

[0116] Secondly, cooling power is a key factor affecting system energy efficiency. While excessive cooling power can keep equipment operating at a safe temperature, excessive cooling consumption can reduce overall system energy efficiency. Therefore, the optimization process must not only control temperature differences but also balance cooling power consumption to avoid unnecessary energy waste and ensure rapid cooling system adjustments in the event of temperature anomalies.

[0117] Temperature field uniformity refers to the uniformity of the temperature distribution within a system. A uniform temperature field effectively prevents local overheating, thereby extending the life of the equipment and preventing damage from overload caused by uneven temperatures. Temperature field uniformity is another key optimization objective; optimizing this parameter can further improve system stability and reliability.

[0118] In practical applications, temperature differentials, cooling power, and temperature field uniformity interact with each other. For example, reducing temperature differentials may require increasing cooling power; while achieving temperature field uniformity may require adjusting the cooling system to optimize temperature distribution. To address this issue, the present invention dynamically adjusts weight coefficients to ensure that priorities change under different operating environments, thereby achieving the dual goals of precise temperature control and improved energy efficiency.

[0119] At the same time, after each optimization calculation, the system automatically adjusts the cooling system's operating state based on real-time temperature data and load changes. When the temperature reaches a set safety threshold, the system activates overheat protection mechanisms, such as increasing cooling power or adjusting the workload, to ensure the system remains in a safe state and prevent equipment damage caused by overheating.

[0120] In step S4, in this embodiment, a particle swarm optimization (PSO) algorithm is used to generate a control parameter sequence to optimize the thermal management and overheat protection performance of the high-voltage variable-frequency power supply system. PSO is a global optimization algorithm that simulates the foraging behavior of a flock of birds. It can find the optimal solution within a given search space and is particularly suitable for solving complex, high-dimensional problems, such as the multi-objective thermal management problem in high-voltage variable-frequency power generation systems.

[0121] The core of the particle swarm optimization algorithm is to find optimal control parameters that achieve thermal management objectives (such as temperature difference, cooling power, and temperature field uniformity) by simulating the movement and mutual learning of a swarm of particles. Particle swarm optimization not only focuses on energy efficiency but also considers system safety under abnormal operating conditions, particularly in overheating protection and fault-tolerant control. Through iterative optimization, the particle swarm optimization algorithm can provide the system with optimal control parameters, ensuring efficient operation under different load and environmental conditions and immediately initiating fault protection mechanisms in the event of temperature anomalies.

[0122] In the particle swarm optimization algorithm, the initial position and velocity of the particle swarm are set. Each particle corresponds to a set of control parameters. These control parameters directly affect the system's temperature management, including the cooling system's fan speed and coolant flow rate. Through iteration, particles adjust their positions based on their current fitness values ​​to find the optimal control parameters. The particle velocity update equation is:

[0123]

[0124] in, represents the updated value of the velocity of particle i in the k+1 generation; ω is the inertia weight; c1, c2, c3 are constant acceleration factors; pbest i is the best position that particle i reaches in the historical search; is the current position of particle i in the kth generation; gbest is the global best position found by all particles in the current generation; r1, r2, r3 are the coefficients in the particle velocity update equation; is the gradient term of the cost function; the inertia weight ω is adjusted according to the convergence requirements of the algorithm.

[0125] The fitness function of the particle is usually given by a multi-objective optimization function, which comprehensively considers multiple objectives such as temperature difference, cooling power and temperature field uniformity. The fitness function can be expressed as:

[0126] J(t)=α·max(ΔT)+β·∫P cool dt+γ·σ T ;

[0127] Where ΔT is the maximum temperature difference in the system; P cool is the system cooling power; σT is the uniformity of the temperature field; α, β, and γ are dynamically adjusted weight coefficients; dt is the time step; and J(t) is the value of the multi-objective optimization function. In this way, the particle swarm optimization algorithm can simultaneously optimize multiple thermal management objectives and adjust the priority of the optimization objectives based on the current operating status of the system.

[0128] During each particle swarm iteration, particles adjust control parameters based on their updated speed and position. These control parameters include specific operating parameters of the cooling system, such as fan speed and pump flow. These parameters directly influence the distribution of the temperature field, thereby achieving the optimization goal of reducing temperature differences, optimizing cooling power, and improving temperature field uniformity. Particularly under high loads or extreme environmental conditions, the particle swarm optimization algorithm can dynamically adjust cooling parameters to meet temperature control requirements while preventing overheating and avoiding thermal runaway.

[0129] Furthermore, during the optimization process, the system not only prioritizes minimizing the temperature difference but also dynamically adjusts weighting coefficients using a particle swarm algorithm, ensuring that the priority of optimization objectives shifts in real time despite changes in load or environmental fluctuations. For example, optimizing the temperature difference may take precedence under high load conditions, while optimizing cooling power may take precedence under low load conditions. Through these adjustments, the system avoids unnecessary energy waste, ensures temperature safety, and promptly adjusts the cooling system's operating status to prevent overheating.

[0130] The power of the particle swarm optimization algorithm lies in its ability to continuously adjust control parameters based on real-time feedback, ensuring the system maintains optimal operating conditions under complex and dynamically changing operating conditions. For example, under high load conditions, the system may need to increase cooling power, while under low load conditions, cooling power can be reduced to save energy. This flexible adjustment ensures efficient thermal management and long-term system stability.

[0131] Using a particle swarm optimization algorithm, the system dynamically adjusts cooling parameters in real time while ensuring that overheat protection mechanisms remain active, preventing equipment damage caused by temperature anomalies. Furthermore, the algorithm optimizes the cooling system's energy efficiency, avoiding energy waste caused by inappropriate cooling power settings.

[0132] During the optimization process, the particle swarm optimization algorithm not only focuses on temperature control, but also involves system fault detection and fault-tolerant control. When a fault is found in the system operation (such as a temperature sensor failure or abnormal coolant flow), the optimization algorithm can automatically adjust the control parameters, such as switching to an alternative cooling path or adjusting the cooling power, to ensure that the equipment will not be damaged by overheating due to a single point of failure, thereby improving the fault tolerance and reliability of the system.

[0133] In step S5, in this embodiment, the optimized control parameters are input into the multi-rate hierarchical control system to ensure accurate execution in each different link. The multi-rate hierarchical control system mainly consists of three links: high-speed loop, medium-speed loop, and low-speed loop, each responsible for different tasks.

[0134] The high-speed loop is responsible for the system's high-frequency control tasks, primarily providing real-time regulation of modules that are extremely sensitive to temperature changes (such as power converters, power electronic switches, and heat sinks). Based on the latest control parameters output by the particle swarm optimization (PSO) algorithm, the high-speed loop rapidly executes control instructions for key components in the cooling system, such as fan speed and coolant pump speed, ensuring millisecond-level response in the event of overheating risks. Specifically, the control function of the high-speed loop can be expressed as:

[0135] u high =f high (P opt ,T real ,Δt);

[0136] Among them, u high is the control instruction of the high-speed loop; f high is the high-speed loop control function; P opt is the control parameter obtained by particle swarm optimization; T real is the actual temperature of the system; Δt is the control execution cycle.

[0137] The medium-speed loop is primarily responsible for the dynamic prediction of the power generation system's thermal field model, anticipating temperature field changes based on real-time data. In this phase, the system uses algorithms such as model predictive control (MPC) to simulate and predict temperature changes in the power generation system, combining feedback data from temperature sensors and heat flow sensors. Specifically, the control function of the medium-speed loop is:

[0138] u mid =f mid (T pred ,T real ,Δt);

[0139] Among them, u mid is the control instruction of the medium speed loop; f high is the high-speed loop control function; T pred is the predicted temperature field; T real is the current actual temperature; Δt is the control period. The medium-speed loop adjusts the control strategy based on the real-time temperature field prediction to reduce temperature deviation.

[0140] The low-speed loop is mainly aimed at long-term temperature control management at the physical level and the execution of device-level control actions, including the overall start-stop scheduling of the cooling system and the update of energy efficiency optimization strategies for power-level devices. The control function of the low-speed loop can be expressed as:

[0141] u low =f low (P cool ,T real ,Δt);

[0142] Among them, u low is the control instruction of the low-speed loop; f high is the high-speed loop control function; P cool is the cooling power or the status of the cooling equipment; T real is the current actual temperature; Δt is the control period.

[0143] To achieve consistency in timing, commands, and status across control loops, the system introduces a state cache synchronization mechanism to ensure consistency and coordination of data across loops:

[0144] Each control loop has a local status buffer, which regularly uploads its own control results and status indicators;

[0145] The buffer content includes current temperature, cooling status, warning status, control output, etc.

[0146] Before executing prediction and device management tasks, the medium-speed and low-speed rings prioritize reading the most recent status of the high-speed ring from the cache.

[0147] When command conflicts or rapidly changing trends occur (such as sudden temperature rise), the medium-speed ring can temporarily transfer some decision-making power to the high-speed ring to ensure that the real-time overheating emergency priority is maximized.

[0148] In step S6, in this embodiment, the monitoring system continuously assesses the system's health through real-time status monitoring and residual error detection, accurately determining whether there are sensor or actuator failures. Upon detecting a failure, the system immediately triggers the corresponding fault-tolerant control mode, ensuring thermal safety and stable operation of the power generation system, and preventing overheating risks caused by equipment failure.

[0149] When a sensor in the system fails, traditional sensor data is no longer reliable, so the system needs to adopt an alternative strategy. In some embodiments, the present invention replaces the function of the damaged sensor through model predictive control (MPC). Specifically, the system will use existing temperature field and flow field models, combined with known control parameters, to predict the temperature value or heat flow value during the sensor failure. This predicted value will be used to adjust the operation of the cooling equipment during the control process to ensure that the system's thermal management is not affected. The general form of model predictive control is:

[0150]

[0151] Among them, u MPC Predict control output for the model; Indicates that MPC selects a set of control strategies within the rolling prediction interval to minimize the cost function; T pred (k) is the predicted temperature value; T ref is the desired temperature value; T pred (k)-T ref 2 is the square loss term of temperature error; λ is the weight coefficient; u(k) is the control input; u previous is the control input at the previous moment; N is the number of prediction time steps. This formula enables the system to use the predicted temperature and known parameters to adjust the cooling control process in the event of a sensor failure.

[0152] When an actuator (such as a cooling fan or electric pump) fails, the system automatically switches to safe mode. In safe mode, the system strictly limits the adjustment range of the control input to prevent abnormal operation of the actuator due to the failure, which may cause the equipment to overheat or overcool, ensuring that the equipment operates within a safe temperature range. For example, the maximum limit of the control input can be expressed by the following formula:

[0153] u safe =min(max(u opt ,u min ),u max );

[0154] Among them, u safe It is the control input in safe mode; u opt is the optimized control parameter; u min and u max These are the minimum and maximum control input limits in safety mode. In this way, the system can ensure that even in the event of an actuator failure, the safe operating range will not be exceeded, ensuring the safety and stability of the power generation system.

[0155] The system monitors the operating status of each link in real time and uses a residual detection mechanism to identify faults. When the output of a sensor or actuator differs significantly from the predicted value, the residual detection mechanism issues an alarm and determines whether a fault exists. If the system confirms a fault, it automatically switches to the appropriate fault-tolerant control mode based on the fault type.

[0156] Specifically, in the system, the basic formula for residual detection is as follows:

[0157]

[0158] Where r(k) is the residual, y(k) is the actual output of the sensor or actuator, is the predicted output. If the residual r(k) exceeds a set threshold, the system identifies a fault and initiates the appropriate fault-tolerance mechanism. For sensor failures, the system activates model predictive control; for actuator failures, the system enters a safe mode, limiting control inputs.

[0159] A high-voltage variable-frequency power supply thermal management control system for improving energy efficiency described below and a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency described above may refer to each other.

[0160] Please see the attached Figure 2 The present invention also provides a high-voltage variable-frequency power supply thermal management control system for improving energy efficiency, comprising:

[0161] The multi-physics modeling and order reduction module is used to establish a coupled model of electromagnetic field, temperature field and flow field based on the principles of electromagnetics, heat conduction and fluid mechanics, combined with the system structure and operating conditions, and perform model order reduction based on the intrinsic orthogonal decomposition method;

[0162] The sensor acquisition and temperature rise detection module is used to place temperature sensors, heat flow sensors, and flow velocity sensors on key components and overheat-sensitive areas of the solar thermal power generation system. It collects multi-point operating data and integrates and analyzes it through Gaussian process regression and Kalman filter algorithms;

[0163] The thermal safety assessment and protection strategy module is used to combine the real-time temperature field reconstruction results with the historical thermal runaway characteristic curve to determine whether the preset temperature protection threshold has been reached, construct a multi-objective protection function, and form a dynamic safety control strategy;

[0164] The control parameter optimization generation module is used to generate control parameter sequences based on thermal safety control strategies through an improved particle swarm algorithm, and introduces temperature rise weighting factors and gradient feedback to improve control accuracy;

[0165] A multi-rate thermal control execution module receives optimized control parameters and executes them hierarchically according to the high-speed, medium-speed, and low-speed control strategies, while utilizing a state buffer to synchronize control data across rates.

[0166] The fault identification and redundant fault-tolerance module is used to identify and locate sensor failures, actuator failures or temperature anomalies that may occur during system operation, and switch to model prediction fault-tolerant control mode or enable redundant equipment according to the fault type.

[0167] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, so they will not be repeated here.

[0168] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A high-voltage variable-frequency power supply thermal management control method for improving energy efficiency, characterized in that: The following steps are involved: Based on the principles of electromagnetics, heat conduction, and fluid mechanics, and combined with the structure and operating environment of the solar high-temperature thermal power generation system, a coupled model of electromagnetic field, temperature field, and flow field is established. The order reduction is performed through intrinsic orthogonal decomposition to obtain a low-dimensional model. Based on the obtained low-dimensional model, temperature sensors, heat flow sensors, and flow velocity sensors are placed at different locations in the solar thermal power generation system to collect data from the power generation system. The collected data is then fused using Gaussian process regression and Kalman filtering algorithms to reconstruct the temperature field of the power generation system. Through the reconstructed temperature field information, a multi-objective optimization function is established, which comprehensively considers the temperature difference, cooling power, temperature field uniformity and thermal energy storage efficiency goals, dynamically adjusts the weights, and optimizes the target priority in real time; Based on the established multi-objective optimization function, an improved particle swarm optimization algorithm is used to generate a control parameter sequence. The control parameters are optimized iteratively through the particle swarm, and the control decision is adjusted according to the real-time data and prediction results. The optimized control parameters are input into the multi-rate hierarchical control system, which is divided into three parts: the high-speed loop, the medium-speed loop, and the low-speed loop. The data is synchronized through the state buffer. By executing the control process in real time, the system status is monitored and the type of fault in the power generation system is detected, and the corresponding fault-tolerant control mode is switched according to the type of fault.

2. The method for thermal management control of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, characterized in that: The establishment of the electromagnetic field, temperature field and flow field coupling model includes the following steps: By combining the light-to-heat conversion process of solar high-temperature thermal power generation systems, heat conduction and fluid mechanics principles, the mutual coupling between light radiation, temperature field and cooling flow field is first considered in the physical model; Apply partial differential equations to describe the coupling relationship between light radiation, temperature, and fluid fields, and calculate the transient response of each physical field, focusing on the heat conduction and heat energy recovery processes of solar collectors, thermal energy storage systems, and heat exchangers; The obtained high-dimensional coupled equations are reduced in order using the intrinsic orthogonal decomposition method to retain the main physical characteristics, reduce the amount of calculation, and obtain a low-dimensional photothermal conversion-temperature field-flow field coupling model.

3. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, wherein: The method of fusing the collected data using Gaussian process regression and Kalman filter algorithm includes the following steps: After obtaining the low-dimensional model, temperature sensors, heat flow sensors, and flow velocity sensors are placed at different locations in the solar high-temperature thermal power generation system to collect system status information in real time, focusing on the status of the collector, heat exchanger, and thermal energy storage system; The Gaussian process regression algorithm is used to spatially interpolate the sensor data to infer the precise values ​​of the temperature field and flow field, ensuring accurate reconstruction of the collector surface temperature and heat exchange efficiency. Combined with the Kalman filter algorithm, the sensor data is dynamically updated in time series to reconstruct the temperature field of the solar power generation system and adapt to changes in weather and light intensity.

4. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, wherein: The multi-objective optimization function is established and comprises the following steps: Based on the reconstructed temperature field information, a multi-objective optimization function is established to simultaneously optimize the temperature difference, cooling power, temperature field uniformity, and thermal energy storage efficiency. The multi-objective optimization function is expressed as: J(t)=α·max(ΔT)+β·∫P cool dt+γ·s T ; Where ΔT is the maximum temperature difference in the system, P cool is the system cooling power, σ T is the uniformity of the temperature field, α, β, γ are the dynamically adjusted weight coefficients, dt is the time step, and J(t) is the value of the multi-objective optimization function; The weight coefficient is dynamically adjusted according to real-time working conditions and environmental change factors, especially optimized according to light intensity, ambient temperature and system load conditions.

5. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, wherein: The method of generating a control parameter sequence using the improved particle swarm optimization algorithm comprises the following steps: In the particle swarm optimization algorithm, the initial position and velocity of each particle in the population are first set, and the fitness of the current particle is calculated. The fitness function is defined based on the temperature field, cooling power, and thermal energy storage target; At each iteration, the particle's velocity and position are updated, where the particle's velocity update equation is: in, represents the updated velocity value of particle i in the k+1 generation, ω is the inertia weight, c1, c2, c3 are constant acceleration factors, and pbest i is the best position that particle i reaches in the historical search, is the current position of particle i in the kth generation, gbest is the global best position found by all particles in the current generation, r1, r2, r3 are the coefficients in the particle velocity update equation, is the gradient term of the cost function, and the inertia weight ω is adjusted according to the convergence requirements of the algorithm; Through multiple particle swarm iterations, a set of optimized control parameters is finally obtained to adapt to the regulation of solar collectors and heat exchangers under different lighting conditions.

6. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, wherein: The step of inputting the optimized control parameters into the multi-rate hierarchical control system comprises the following steps: Inputting the optimized control parameters into a multi-rate hierarchical control system, wherein the multi-rate hierarchical control system includes a high-speed loop, a medium-speed loop, and a low-speed loop; The high-speed loop performs real-time particle swarm optimization control parameter calculations to regulate the operation of the collector and cooling system. The medium-speed loop dynamically predicts the thermal field model of the power generation system and regulates the heat release of the thermal energy storage system. The low-speed loop is responsible for performing physical driving and cooling operations. The data of each loop is synchronized through the status buffer area to make the control operations of each loop coordinated and consistent.

7. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 1, characterized in that: Switching to the corresponding fault-tolerant control mode according to the fault type includes the following steps: By monitoring the real-time status of the system, the residual detection mechanism is used to determine whether there is a fault. If the system detects the type of fault, the fault-tolerant control mode is triggered; In the event of a sensor failure, model predictive control is used to replace the function of the damaged sensor and control the thermal management process through the estimated value; In the event of an actuator failure, the system switches to safe mode and controls the system operation via set limits.

8. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 2, wherein: The order reduction processing of the obtained high-dimensional coupled equations by the eigenorthogonal decomposition method includes: The snapshot matrix X=[x1,x2,…,x m ], where X represents the snapshot matrix of state variables collected at time, each Indicates the state of the power generation system at a certain moment, x i represents the state of the power generation system at the i-th moment, and n represents the state variable dimension of the power generation system; Perform singular value decomposition on the snapshot matrix: X=U∑V T ; Among them, U is the left singular vector matrix, ∑ is the singular value diagonal matrix, V T is the transpose of the right singular vector matrix; Select the first r main modes to form the dimensionality reduction basis Φ=[u1,u2,…,u r ], projecting the high-dimensional system state into a low-dimensional subspace: x(t)≈Φa(t); Where r represents the number of principal components, Φ=[u1,u2,…,u r ] represents the most representative basis vector extracted from the original state data, a(t) is the low-dimensional state variable, Φ is the POD modal matrix, and x(t)≈Φa(t) indicates the POD method.

9. The method for controlling thermal management of a high-voltage variable-frequency power supply for improving energy efficiency according to claim 4, characterized in that: The dynamic adjustment of the weight coefficient is driven by the Lyapunov guidance strategy, and the adjustment formula is: Among them, α, β, and γ represent the three dynamic weight factors in multi-objective optimization. Indicates the rate at which these three weights change over time, k1, k2, k3>0 is the adjustment factor, Represents the partial derivative of the optimization objective function with respect to each sub-objective.

10. A high-voltage variable-frequency power supply thermal management control system for improving energy efficiency, applied to a high-voltage variable-frequency power supply thermal management control method for improving energy efficiency according to any one of claims 1 to 9, characterized in that: include: The multi-physics modeling and order reduction module is used to establish a coupled model of electromagnetic field, temperature field and flow field based on the principles of electromagnetics, heat conduction and fluid mechanics, combined with the system structure and operating conditions, and perform model order reduction based on the intrinsic orthogonal decomposition method; The sensor acquisition and temperature rise detection module is used to place temperature sensors, heat flow sensors, and flow velocity sensors on key components and overheat-sensitive areas of the solar thermal power generation system. It collects multi-point operating data and integrates and analyzes it through Gaussian process regression and Kalman filter algorithms; The thermal safety assessment and protection strategy module is used to combine the real-time temperature field reconstruction results with the historical thermal runaway characteristic curve to determine whether the preset temperature protection threshold has been reached, construct a multi-objective protection function, and form a dynamic safety control strategy; The control parameter optimization generation module is used to generate control parameter sequences based on thermal safety control strategies through an improved particle swarm algorithm, and introduces temperature rise weighting factors and gradient feedback to improve control accuracy; A multi-rate thermal control execution module receives optimized control parameters and executes them hierarchically according to the high-speed, medium-speed, and low-speed control strategies, while utilizing a state buffer to synchronize control data across rates. The fault identification and redundant fault-tolerance module is used to identify and locate sensor failures, actuator failures or temperature anomalies that may occur during system operation, and switch to model prediction fault-tolerant control mode or enable redundant equipment according to the fault type.

Images