Photovoltaic inverter heat dissipation adjustment control system

Abstract

The invention relates to the technical field of power electronics, in particular to a photovoltaic inverter heat dissipation adjustment control system. Comprising a multi-mode state prediction module which is used for receiving environment data collected in real time and historical working state data of an inverter and predicting predicted junction temperatures in one or more time steps in the future; the collaborative optimization decision module is used for receiving the predicted junction temperature and obtaining an optimal control parameter combination and an expected steady-state junction temperature; the feed-forward control execution module is used for receiving the optimal control parameter combination and setting the optimal fan rotating speed in the optimal control parameter combination as a reference set value of the cooling system rotating speed controller; the feedback correction module is used for obtaining a fan rotating speed correction value; and the instruction synthesizing and sending module is used for sending the final target rotating speed instruction to a bottom-layer speed controller of the fan. According to the system, the problems of temperature overshoot and frequent start and stop of a heat dissipation system caused by traditional passive response type control are avoided, and the stability of system operation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power electronics, in particular to a photovoltaic inverter heat dissipation regulation control system. BACKGROUND

[0002] In the current photovoltaic power generation system, the inverter as the core power conversion device, its operation efficiency, reliability and service life are crucial to the economic benefit of the whole system; the junction temperature of the power semiconductor device is the key factor affecting the above performance indicators, so accurate temperature regulation must be carried out through the heat dissipation system; the traditional heat dissipation control strategy is mostly passive response, that is, the fan speed and other heat dissipation measures are adjusted according to the real-time monitored temperature feedback; this method fails to systematically weigh the complex coupling and conflict relationship among power generation benefits, heat dissipation power consumption and long-term reliability of the device, often leading to unreasonable resource allocation and difficulty in maximizing the comprehensive net benefit of the system throughout its life cycle. In the prior art, although some heat dissipation control methods introduce simple prediction models or multi-objective control ideas, there are generally problems of low prediction accuracy of future working conditions and single optimization dimension; for example, most control strategies separate the heat dissipation system from the working point of the inverter, such as switching frequency and MPPT strategy, and control them independently, ignoring the strong coupling between them, resulting in optimization results limited to local optimum and unable to realize overall performance improvement at the system level; in addition, in the face of dramatic dynamic changes in environmental factors such as light and environmental temperature, the traditional method lacks a forward-looking pre-regulation mechanism, which easily causes temperature overshoot or frequent start-stop problems, not only increasing unnecessary energy consumption, but also accelerating the thermal fatigue aging of power devices. Therefore, how to provide a photovoltaic inverter heat dissipation regulation control method capable of forward-looking prediction of thermal load and collaborative optimization of multiple control variables is a problem that those skilled in the art need to solve. SUMMARY

[0003] To solve the above technical problems, the present application discloses a photovoltaic inverter heat dissipation regulation control system, in particular, the technical scheme of the present application is: A photovoltaic inverter heat dissipation regulation control system, comprising: A multi-modal state prediction module for receiving real-time collected environmental data and inverter historical working state data, the environmental data including light intensity and environmental temperature, and the inverter historical working state data including current junction temperature and output power, and predicting the predicted junction temperature in one or more time steps in the future based on a preset discrete time dynamic thermal model; A collaborative optimization decision module for receiving the predicted junction temperature, solving and analyzing the switching frequency, MPPT disturbance strategy and fan speed based on a cost function with the goal of maximizing the system comprehensive net energy efficiency, to obtain the optimal control parameter combination and the expected steady-state junction temperature. a feedforward control execution module configured to receive the optimal control parameter combination, set the optimal fan rotating speed in the optimal control parameter combination as a reference set value of a rotating speed controller of the heat dissipation system, send the optimal switching frequency to a main control unit of the inverter for adjusting a driving signal frequency of the power device, and send the optimal MPPT perturbation strategy to a maximum power point tracking controller for updating core parameters thereof; a feedback correction module configured to monitor a deviation between the actual junction temperature and the expected steady-state junction temperature to obtain a fan rotating speed correction amount; an instruction synthesis and sending module configured to synthesize the reference set value and the fan rotating speed correction amount to obtain a final target rotating speed instruction, and send the final target rotating speed instruction to a bottom speed controller of the fan; Preferably, the multi-modal state prediction module is further configured to: fit and calibrate model coefficients of the discrete-time dynamic thermal model by using historical operation data collected offline through a system identification algorithm; update the correction term of the discrete-time dynamic thermal model in real time through an online adaptive algorithm; Preferably, the cost function unifies power generation income, heat dissipation cost and operation risk under a single optimization target, and the cost function specifically includes: a product term of the conversion efficiency and the input power, for representing the power generation income; a heat dissipation power consumption term, for representing the heat dissipation cost; a temperature penalty function term, for quantifying an equivalent power loss risk caused by excessively high junction temperature; Preferably, the temperature penalty function is configured to: compare the predicted junction temperature with a preset safety threshold; when the predicted junction temperature is lower than the safety threshold, the value of the temperature penalty function is set to zero; when the predicted junction temperature exceeds the safety threshold, the value of the temperature penalty function is set in an exponential form; Preferably, the collaborative optimization decision module is further configured to: solve the cost function by using a numerical optimization algorithm; Preferably, the feedback correction module is specifically configured to: adopt a proportional-integral controller; determine the deviation between the actual junction temperature and the expected steady-state junction temperature; calculate the fan rotating speed correction amount according to the deviation; Preferably, the calculation process of the final target rotating speed instruction is as follows: synthesize the optimal fan rotating speed and the fan rotating speed correction amount to obtain the final target rotating speed instruction; the final target rotating speed instruction is used to drive the fan.

[0004] Compared with the prior art, the present application has the following beneficial effects: 1、The system can predict the junction temperature change of the future key power device in a forward-looking manner by establishing a dynamic thermal model; this active adjustment method based on prediction effectively avoids the temperature overshoot and frequent start-stop problem of the heat dissipation system caused by traditional passive response control, and improves the stability of system operation; 2、The system builds a decision mechanism that unifies power generation income, heat dissipation cost and operation risk under a single optimization target; by cooperatively optimizing multiple interrelated control variables such as switching frequency, MPPT strategy and fan speed, it breaks through the limitations of independent decision-making in traditional control, and realizes the maximization of comprehensive electric energy net income in the whole cycle of the system; 3、The system introduces a temperature penalty function into the optimization target, which can quantify and avoid the aging risk of power devices caused by excessively high junction temperature; when the predicted temperature exceeds the safety threshold, this mechanism will significantly increase the risk cost, so as to pursue the immediate power generation efficiency while taking into account the long-term reliability of the equipment, effectively prolonging the service life of the inverter; 4、The system adopts a feedforward-feedback composite control architecture, combining the forward-looking nature of feedforward control with the accuracy of feedback correction; this architecture not only actively responds to predictable working condition changes, but also compensates for model errors and external unknown disturbances through real-time deviation correction, ensuring that the actual junction temperature accurately and stably tracks the dynamic target, significantly enhancing the control accuracy and robustness of the system. BRIEF DESCRIPTION OF DRAWINGS

[0005] The present application will be further explained in conjunction with the accompanying drawings and embodiments: Figure 1 is a flow chart of the system of the present application. DETAILED DESCRIPTION

[0006] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application will be further explained in detail in conjunction with specific embodiments.

[0007] Example 1: Please refer to Figure 1 A photovoltaic inverter heat dissipation regulation control system, comprising: A multi-modal state prediction module for receiving real-time collected environmental data and inverter historical working state data, the environmental data including illumination intensity and environmental temperature, the inverter historical working state data including current junction temperature and output power, and predicting the predicted junction temperature in one or more time steps in the future based on a preset discrete-time dynamic thermal model; A cooperative optimization decision module is configured to receive the predicted junction temperature, and solve and analyze the switching frequency, the MPPT perturbation strategy and the fan rotating speed based on a cost function aiming at maximizing the comprehensive net energy efficiency of the system, so as to obtain an optimal control parameter combination and an expected steady-state junction temperature; A feedforward control execution module is configured to receive the optimal control parameter combination, and set the optimal fan rotating speed in the optimal control parameter combination as a reference set value of a heat dissipation system rotating speed controller; A feedback correction module is configured to monitor the deviation between the actual junction temperature and the expected steady-state junction temperature, so as to obtain a fan rotating speed correction amount; An instruction synthesis and sending module is configured to synthesize the reference set value and the fan rotating speed correction amount to obtain a final target rotating speed instruction, and send the final target rotating speed instruction to a bottom speed controller of the fan; The embodiment of the present application discloses a photovoltaic inverter heat dissipation regulation control system, which aims to maximize the comprehensive net energy yield of the inverter system in a whole cycle under the premise of ensuring the high reliability of power devices; the system comprises a multi-modal state prediction module, a cooperative optimization decision module, a feedforward control execution module and a feedback correction module, and through the cooperative work of the modules, the robust and accurate cooperative control of the photovoltaic inverter heat dissipation and working point is realized. The multi-modal state prediction module is configured to receive real-time collected environmental data and inverter historical working state data, and the purpose is to make forward-looking prediction on the junction temperature of the key power semiconductor of the inverter in the future; the environmental data received by the module includes the light intensity and the environmental temperature, and the inverter historical working state data includes the current junction temperature and the output power; the module is based on a preset, simplified discrete-time dynamic thermal model for real-time calculation, and the junction temperature of the key power semiconductor in one or more time steps in the future is predicted; the initial form of the discrete-time dynamic thermal model is derived from a first-order lumped parameter thermal model for describing the heat transfer process of the power module, and after linearization and discretization, it is constructed as:

[0008] Wherein: : predicted junction temperature, unit: Kelvin (K); : current junction temperature, unit: Kelvin (K), obtained by real-time collection through the internal temperature sensor of the inverter; : output power, unit: Watt (W), obtained by real-time collection through the internal power monitoring device of the inverter; : light intensity, unit: Watt per square meter (W / m²), obtained by real-time collection through the external environmental sensor of the photovoltaic array; : Ambient temperature, unit: Kelvin (K), real-time collected by external environment sensor; : Prediction step, unit: second (s), pre-set according to system control period; : Model coefficient, dimensionless parameter; : Model coefficient, unit: Kelvin per Watt (K / W); : Model coefficient, unit: Kelvin square meter per Watt (K·m² / W); : Model coefficient, dimensionless parameter; The values of these coefficients are fitted and calibrated by offline collected historical operation data using system identification algorithm, to reflect the thermal characteristics of a specific inverter; : Model coefficient, unit: Kelvin (K), representing the heat dissipation efficiency of the heat dissipation system; : A dimensionless heat dissipation function related to the current fan speed, for example, it can be a simple linear or polynomial function, used to represent the contribution of fan speed to cooling, its value range is usually [0, 1]; for example, it can be a normalized polynomial function, such as

[0009] Wherein: is the maximum fan speed, coefficient Calibrated by experiment; : Correction term, unit: Kelvin (K); this correction term is updated in real time by online adaptive algorithm, to compensate for the long-term drift of the model due to changes in working conditions; The predicted junction temperature calculated by this model is taken as the core information, transmitted to the collaborative optimization decision module; The collaborative optimization decision module is connected to the output end of the multi-modal state prediction module, and its core purpose is to unify the three conflicting performance indicators of power generation benefit, heat dissipation cost and operation risk under a single optimization target, to maximize the comprehensive net energy efficiency of the system; this module receives the predicted junction temperature , and based on the cost function with the goal of maximizing the comprehensive net energy efficiency of the system, solves and analyzes the switching frequency, MPPT disturbance strategy and fan speed, to obtain a set of optimal control parameter combinations and the corresponding expected steady-state junction temperature under this optimal parameter; ​is the expected equilibrium temperature calculated by substituting the optimal control parameter combination into the system thermal model under the current environmental condition. Specifically, the steady-state temperature can be obtained by solving the steady-state equation of the system thermal model, i.e., setting the predicted junction temperature in the dynamic thermal model equal to the current junction temperature , and substituting the system state corresponding to the current environmental data and the optimal control parameter combination, so as to solve the expected steady-state junction temperature ; the solving expression is as follows:

[0010] The output ends of the feedforward control execution module and the collaborative optimization decision module are connected, and the purpose is to realize prediction-based and forward-looking control. The optimal fan speed in the optimal control parameter combination output by the collaborative optimization decision module is directly used as the reference set value of the heat dissipation system speed controller; At the same time, the optimal switching frequency in the optimal control parameter combination is sent to the main control unit of the inverter for adjusting the driving signal frequency of the power device; and the optimal MPPT perturbation strategy is sent to the maximum power point tracking controller for updating the core parameters such as the perturbation step length; in this way, the system realizes comprehensive collaborative control of the power generation efficiency and the heat dissipation strategy; The function of the feedback correction module is to compensate for the deviation of the feedforward control to improve the control accuracy of the system. The module monitors the actual junction temperature collected by the internal temperature sensor of the inverter and the dynamic expected steady-state junction temperature output by the collaborative optimization decision module, and obtains the fan speed correction amount according to the deviation ; The instruction synthesis and sending module synthesizes the reference set value provided by the feedforward control execution module and the fan speed correction amount obtained by the feedback correction module to obtain a final target speed instruction integrated with feedforward prediction and feedback correction and having a clear physical meaning , and sends the instruction to the underlying speed controller of the fan to drive the fan; The embodiment of the present invention integrates four modules: multi-modal state prediction, collaborative optimization decision-making, feedforward control execution, and feedback correction to form a feedforward-feedback composite control architecture, thereby realizing robust and precise collaborative control of the heat dissipation and operating point of the photovoltaic inverter; the system can actively predict the upcoming thermal load changes and collaboratively optimize the switching frequency, MPPT strategy, and heat dissipation strategy at the system level, thereby avoiding the temperature overshoot and frequent start-stop problems caused by passive response in the existing technology, and maximizing the comprehensive net energy benefit of the inverter system within the entire cycle while ensuring the high reliability of the power devices.

[0011] Example 2: The modal state prediction module is also used to: Through the system identification algorithm, the model coefficients of the discrete time dynamic thermal model are fitted and calibrated using the historical operating data collected offline; The correction term of the discrete-time dynamic thermal model is updated in real time through an online adaptive algorithm; This embodiment further describes the method for determining the parameters of the model in the multimodal state prediction module based on the embodiment 1. The module uses the system identification algorithm to determine the model coefficients of the discrete time dynamic thermal model by fitting and calibrating the historical operation data collected offline. ; System identification algorithm refers to a method of building a mathematical model through input and output data, for example, through regression analysis, using known input quantities in offline historical data sets, such as light intensity , ambient temperature , output power , Current junction temperature and output, such as future junction temperature , solve and obtain the optimal model coefficient; In addition, the module also uses an online adaptive algorithm to adjust the correction term of the discrete time dynamic thermal model. Real-time updates are performed. Online adaptive algorithms, such as the least mean square (LMS) algorithm, dynamically adjust correction terms based on the deviation between actual measurements and model predictions during system operation to compensate for long-term model drift due to changes in operating conditions, thereby ensuring prediction accuracy. This combination of offline calibration and online adaptation recognizes and compensates for the physical fidelity sacrificed by using a simplified linear model to ensure real-time calculations. While ensuring computational efficiency, it compensates for nonlinear effects and model drift through real-time correction. By combining offline calibration and online adaptive update, the embodiment not only ensures the initial accuracy of the model, but also enables it to adapt to the changes in thermal characteristics of the photovoltaic system in different seasons, different weather conditions and long-term operation, greatly improving the robustness and accuracy of the junction temperature prediction, and providing a more reliable data basis for subsequent collaborative optimization decisions.

[0012] Embodiment 3 The cost function unifies power generation income, heat dissipation cost and operation risk under a single optimization objective, and the cost function specifically includes: a product term of conversion efficiency and input power, for representing power generation income; a heat dissipation power consumption term, for representing heat dissipation cost; a temperature penalty function term, for quantifying the risk of equivalent power loss due to excessively high junction temperature; The temperature penalty function is used to: compare the predicted junction temperature with a preset safety threshold; when the predicted junction temperature is lower than the safety threshold, the value of the temperature penalty function is set to zero; when the predicted junction temperature exceeds the safety threshold, the value of the temperature penalty function is set in an exponential form; The embodiment further discloses the composition details and specific implementation of the cost function adopted by the collaborative optimization decision module in the system of embodiment 1; the cost function aims to unify power generation income, heat dissipation cost and operation risk under a single optimization objective, and its expression is:

[0013] Among them: : cost function, unit: watt (W); : switching frequency, unit: hertz (Hz), calculated by the collaborative optimization decision module; : MPPT perturbation strategy, dimensionless, representing control parameters such as perturbation step size, perturbation direction, etc., calculated by the collaborative optimization decision module; here, the optimization is not a substitute for the real-time microsecond-level perturbation of the MPPT algorithm, but a minute-level dynamic optimization of its core superparameters to balance the tracking speed and steady-state efficiency in the long-term scale; : fan speed, unit: revolutions per minute (RPM), calculated by the collaborative optimization decision module; : weight coefficient, dimensionless, its value is pre-set according to economic and engineering factors such as electricity price and equipment life cycle cost; : conversion efficiency, dimensionless, its value is related to switching frequency and MPPT strategy; for example, conversion efficiency can be modeled as a function of switching loss related to switching frequency and steady-state tracking error related to MPPT strategy, its specific form can be obtained by offline calibration or theoretical modeling; for example, conversion efficiency can be modeled as a function containing switching loss and conduction loss, where switching loss is proportional to switching frequency , while MPPT strategy affects the steady-state tracking error of the system, and then affects the total output power; a simplified model can be

[0014] where, is the base efficiency, is the switching loss coefficient, unit is second s, represents the dimensionless equivalent efficiency loss determined by MPPT strategy ; these coefficients can be obtained by offline experimental calibration, for example, when MPPT strategy mainly refers to the perturbation step s, its corresponding power loss can be modeled as a function related to steady-state oscillation and dynamic tracking speed, its specific form is obtained by offline simulation or experimental data fitting; for example, when MPPT strategy mainly refers to the perturbation step , its corresponding dimensionless efficiency loss factor can be modeled as a function related to steady-state oscillation and dynamic tracking speed; It should be pointed out that this model is a simplified form, a more accurate conversion efficiency model will also contain terms related to the current junction temperature and output power , in this embodiment, the influence of these factors will be mainly compensated by the feedback correction link; : input power, unit is watt (W), real-time acquisition through the power monitoring device at the input end of the photovoltaic array; : heat dissipation power consumption, unit is watt (W), its value is related to fan speed; for example, according to the aerodynamics principle of the fan, the heat dissipation power consumption can be usually modeled as a function proportional to the third power of the fan speed, that is , where is the fan power consumption coefficient, which can be calibrated by consulting the fan specification manual or by actually testing the power of the fan, unit is watt per cubic revolution per minute ( ); : temperature penalty function, unit is watt (W); The cost function specifically includes the following three items: The product of conversion efficiency and input power : Used to characterize power generation benefits. Its purpose is to maximize the system output power by optimizing the switching frequency and MPPT strategy. Heat dissipation item : It is used to characterize the cooling cost. Its purpose is to minimize the energy consumption of the cooling system itself by optimizing the fan speed. Temperature penalty function : Used to quantify the equivalent power loss risk caused by excessively high junction temperature. Its purpose is to introduce a penalty for high junction temperature into the optimization objective, forcing the system to maintain the junction temperature within a safe range, thereby ensuring the reliability and service life of power devices; The temperature penalty function The specific rules are as follows: This function will predict the junction temperature and the preset safety threshold Compare; the safety threshold It is a fixed value pre-set based on the maximum safe operating temperature of the power device and a certain safety margin; when the junction temperature is predicted Below the safety threshold When the value of the temperature penalty function is set to zero, which means that within the safe temperature range, the system is not penalized due to temperature factors; when the predicted junction temperature Exceed When the value of the temperature penalty function is set to exponential form:

[0015] in: : The base penalty coefficient, measured in watts (W), is a preset constant with the dimension of power. This value is set to quantify the basic risk cost when the temperature just begins to exceed the safety threshold. Its value can be estimated based on economic factors such as component replacement costs and power generation losses caused by derating. For example, it can be set as a multiple of the maximum power consumption of the cooling system. : Characteristic temperature, in Kelvin (K). Its value is set based on the device reliability curve, such as the Arrhenius model, and is used to characterize the severity of the penalty growth. This value can be obtained by fitting the device lifetime data at different temperatures, for example, by determining the coefficient related to the device lifetime attenuation rate through regression analysis; The embodiment realizes the collaborative optimization of multiple control dimensions of the photovoltaic inverter by constructing a cost function which comprehensively considers power generation benefits, heat dissipation costs and operation risks; in particular, the design of the temperature penalty function quantitatively punishes the over-temperature risk, so that the optimization target not only pursues the immediate power generation efficiency, but also takes into account the long-term reliability of the equipment, effectively avoiding the risk of sacrificing the service life of the equipment in pursuit of short-term high benefits, thereby maximizing the comprehensive net power benefits of the photovoltaic system in the whole life cycle. It should be noted that the cost function in the embodiment mainly focuses on the balance between electric energy and heat energy; in a more complex implementation, the cost function can be further extended to include items such as EMI filter cost related to switching frequency, grid voltage fluctuation penalty related to MPPT disturbance, etc., thereby realizing more comprehensive system-level optimization.

[0016] Embodiment 4: The collaborative optimization decision module is further configured to: Solve the cost function by using a numerical optimization algorithm. The embodiment further discloses a specific method for the collaborative optimization decision module to solve the cost function in the system of embodiment 1; the module uses a numerical optimization algorithm to solve the cost function to obtain the optimal control parameter combination ; the numerical optimization algorithm refers to algorithms such as genetic algorithm, particle swarm optimization algorithm or simpler gradient descent method, etc.; the algorithm searches for the parameter combination that can maximize the cost function by iteratively searching in the preset control parameter space; for example, the search space can be set as: switching frequency , MPPT disturbance step , fan speed , which are determined by the specifications of the power device and the physical capabilities of the heat dissipation system; the optimization process is repeatedly performed in each decision-making period to adapt to the changing operating conditions; By using the numerical optimization algorithm, the embodiment can efficiently and accurately find the optimal solution among multiple interrelated control variables, avoiding the local optimization problem caused by independent decision-making of each control link in the traditional method, and ensuring the optimization of the overall performance of the system.

[0017] Embodiment 5: The feedback correction module is specifically configured to: Use a proportional-integral (PI) controller; Determine the deviation between the actual junction temperature and the expected steady-state junction temperature; According to the deviation, calculate the fan speed correction amount; The embodiment is based on the embodiment 1, and the embodiment further discloses a specific implementation manner of the feedback correction module; the module adopts a proportional-integral (PI) controller, and a purpose of the controller is to calculate a real-time correction amount according to a deviation between an actual junction temperature and an expected junction temperature; the controller determines the deviation between the actual junction temperature and the expected steady-state junction temperature . . . ; according to the deviation, a fan rotating speed correction amount is solved ; a calculation formula of the correction amount is as follows:

[0018] . : the fan rotating speed correction amount, unit: revolutions per minute (RPM); : a proportional coefficient, unit: RPM / K, and the proportional coefficient is obtained by experiment setting of a system in which feedforward control has been deployed; : an integral coefficient, unit: RPM / (K·s), and the integral coefficient is obtained by experiment setting of the system in which the feedforward control has been deployed; : a temperature error, unit: Kelvin (K); : an integral variable; The embodiment introduces the PI controller, so that the system can compensate for a deviation caused by an inaccurate model or an external unknown disturbance in the feedforward control in real time; the proportional term can quickly respond to a current deviation, and the integral term can eliminate a long-term steady-state error, thereby ensuring that the actual junction temperature accurately and stably tracks the dynamic expected steady-state junction temperature, and the robustness and control precision of the system are significantly improved.

[0019] Embodiment 6 A calculation process of the final target rotating speed instruction is as follows: The optimal fan rotating speed and the fan rotating speed correction amount are synthesized to obtain the final target rotating speed instruction; The final target rotating speed instruction is used to drive the fan. The embodiment is based on the embodiment 1, and the embodiment further specifically describes a calculation process of the final target rotating speed instruction; a control instruction finally applied to an execution mechanism of a heat dissipation system, such as a fan driver, is a final target rotating speed instruction that is integrated with feedforward prediction and feedback correction and has a clear physical meaning ; the instruction is synthesized by the optimal fan rotating speed provided by the feedforward control execution module and the fan rotating speed correction amount solved by the feedback correction module, and a synthesis formula of the instruction is as follows:

[0020] Final target speed instruction The bottom speed controller is sent to the fan, and the controller is responsible for generating a specific PWM signal or driving voltage to ensure that the actual fan speed accurately tracks the dynamic instruction, so as to drive the fan to work according to the optimized instruction of the system; The embodiment constructs a compound control structure with clear logic and easy implementation by taking the feedforward predicted optimal speed as the basis for active adjustment and using the feedback correction amount to compensate for the deviation in real time. This structure enables the system to maintain the advantages of foresight and initiative while using the accuracy of feedback to eliminate the influence of model errors and external disturbances, ensuring the accuracy and stability of control.

[0021] The system discloses a photovoltaic inverter heat dissipation regulation and control system, and the technical advantage lies in that a feedforward-feedback compound control architecture is constructed, which is essentially different from the passive response heat dissipation control mode in the prior art. The system realizes robust and accurate collaborative control of photovoltaic inverter heat dissipation and working point by integrating four core modules, i.e., multi-modal state prediction, collaborative optimization decision, feedforward control execution and feedback correction; The multi-modal state prediction module uses real-time environmental data and historical working state data to make forward-looking prediction of future junction temperature based on a discrete-time dynamic thermal model. The prediction model is initially calibrated by an offline system identification algorithm and the correction term is updated in real time by an online adaptive algorithm, which effectively compensates for the long-term drift of the model due to changes in working conditions, greatly improves the robustness and accuracy of junction temperature prediction, and provides a reliable data basis for subsequent optimization decisions; The collaborative optimization decision module unifies power generation income, heat dissipation cost and operation risk under a single optimization target, avoiding the local optimal problem caused by independent decision of each link in the traditional control. The module obtains the optimal control parameter combination by collaboratively analyzing the switching frequency, MPPT disturbance strategy and fan speed through solving the cost function. The cost function particularly includes a temperature penalty function term, which will grow exponentially when the predicted junction temperature exceeds the preset safety threshold. This enables the system to effectively quantify and avoid the power device loss risk caused by high junction temperature while pursuing immediate power generation efficiency, thereby taking into account the long-term reliability of the equipment and maximizing the comprehensive electric energy net income of the inverter system in the whole life cycle. The feedforward control execution module and the feedback correction module work together to form a control closed loop that is both forward-looking and precise. The feedforward control module directly uses the optimized optimal fan speed as the baseline setpoint, implementing proactive adjustment based on prediction, effectively avoiding the temperature overshoot and frequent starts and stops caused by passive response in existing technologies. The feedback correction module uses a proportional-integral (PI) controller to monitor the deviation between the actual junction temperature and the desired steady-state junction temperature in real time and calculate the fan speed correction. Finally, the system combines the optimal fan speed and the correction to generate a final target speed command with clear physical meaning. This composite control structure ensures that the actual junction temperature accurately and stably tracks the dynamically desired steady-state junction temperature, significantly enhancing the system's control accuracy and robustness, and effectively eliminating the impact of model errors and external unknown disturbances. In addition, the control system is robust. To address abnormal sensor conditions, such as zero or saturation, the system has built-in input data validity verification logic. When a sensor's measurement value is zero or saturated, the system switches to a conservative operating mode. Specifically, if the temperature sensor fails, the system will find a worst-case fan speed from a pre-stored safety operating curve based on current light intensity and output power, run the fan at full speed, and issue an alarm to the monitoring system. When the light or power sensor data is abnormal, the system will lock at a fixed, lower switching frequency and adopt a larger MPPT perturbation step to ensure tracking stability. At the same time, the fan speed will be set to a higher value, sacrificing some energy efficiency in exchange for absolute safety. It can switch to a conservative operating mode based on historical data and safety margins. When faced with drastic changes in operating conditions such as sudden changes in light, the feedforward control module can respond quickly, and the PI parameters of the feedback correction module have been carefully adjusted to effectively suppress overshoot and oscillation, ensuring a smooth transition of the system, thereby ensuring safe and stable operation under various complex and non-ideal operating conditions.

[0022] The above are only preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention; any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0023] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A photovoltaic inverter heat dissipation regulation control system, characterized in that: include: A multimodal state prediction module receives real-time collected environmental data, including light intensity and ambient temperature, and historical inverter operating state data, including current junction temperature and output power. Based on a preset discrete-time dynamic thermal model, it predicts the predicted junction temperature within one or more future time steps. The collaborative optimization decision module receives the predicted junction temperature and, based on a cost function aimed at maximizing the system's overall net energy efficiency, analyzes the switching frequency, MPPT perturbation strategy, and fan speed to determine the optimal control parameter combination and the desired steady-state junction temperature. A feedforward control execution module is used to receive an optimal control parameter combination, set the optimal fan speed in the optimal control parameter combination as a reference set value of the heat dissipation system speed controller, send the optimal switching frequency to the main control unit of the inverter for adjusting the drive signal frequency of the power device, and send the optimal MPPT disturbance strategy to the maximum power point tracking controller for updating its core parameters. The feedforward control execution module is used to receive an optimal control parameter combination, set the optimal fan speed in the optimal control parameter combination as a reference set value of the heat dissipation system speed controller; A feedback correction module is used to monitor the deviation between the actual junction temperature and the desired steady-state junction temperature to obtain a correction value for the fan speed; The instruction synthesis and sending module is used to synthesize the reference setting value and the fan speed correction amount to obtain the final target speed instruction, and send the final target speed instruction to the bottom speed controller of the fan.

2. A photovoltaic inverter heat dissipation regulation control system according to claim 1, characterized in that: The multimodal state prediction module is further used for: Through the system identification algorithm, the model coefficients of the discrete time dynamic thermal model are fitted and calibrated using the historical operating data collected offline; The correction terms of the discrete-time dynamic thermal model are updated in real time through an online adaptive algorithm.

3. A photovoltaic inverter heat dissipation regulation control system according to claim 1, characterized in that: The cost function unifies power generation revenue, heat dissipation cost and operation risk under a single optimization objective. The cost function specifically includes: The product of conversion efficiency and input power is used to characterize power generation benefits; Heat dissipation power consumption item, used to characterize heat dissipation cost; The temperature penalty function term is used to quantify the risk of equivalent power loss due to excessively high junction temperature.

4. A photovoltaic inverter heat dissipation regulation and control system according to claim 3, characterized in that: The temperature penalty function is used to: Compare the predicted junction temperature with the preset safety threshold; When the predicted junction temperature is lower than the safety threshold, the value of the temperature penalty function is set to zero; When the predicted junction temperature exceeds the safety threshold, the value of the temperature penalty function is set to an exponential form.

5. The photovoltaic inverter heat dissipation regulation and control system according to claim 1, characterized in that: The collaborative optimization decision module is also used to: A numerical optimization algorithm is used to solve the cost function.

6. A photovoltaic inverter heat dissipation regulation and control system according to claim 1, characterized in that: The feedback correction module is specifically used for: Use proportional-integral controller; Determine the deviation between the actual junction temperature and the desired steady-state junction temperature; Based on the deviation, the fan speed correction amount is calculated.

7. A photovoltaic inverter heat dissipation regulation and control system according to claim 1, characterized in that: The calculation process of the final target speed command is as follows: The optimal fan speed and the fan speed correction amount are combined to obtain the final target speed instruction; The final target speed command is used to drive the fan.

Images