Electrical equipment intelligent performance evaluation and management system for photovoltaic power station

Abstract

A photovoltaic power station-oriented electrical equipment intelligent performance evaluation and management system of the present invention belongs to the technical field of data processing, and comprises a data acquisition module used for acquiring environmental data, electrical data and operation state data of target electrical equipment in real time; the state evaluation module is used for determining the functional steady state deviation degree of the target electrical equipment on the basis of the data acquired by the data acquisition module and in combination with a preset functional steady state interval; the decision optimization module is used for generating an optimal control instruction according to the function steady state deviation degree and a preset reward function; and the control execution module is used for executing the optimal control instruction to regulate and control the operation state of the target electrical equipment, and a quantifiable equipment health state evaluation system is established.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an intelligent efficiency evaluation and management system for electrical equipment in photovoltaic power stations. Background Art

[0002] In the routine operation of photovoltaic power plants, the core objectives of management systems generally focus on maximizing instantaneous power generation efficiency and ensuring basic operational reliability. Technical solutions often employ algorithms such as maximum power point tracking (MPPT), aiming to extract maximum electrical energy under various environmental conditions. However, this aggressive control strategy, focused solely on short-term power generation, inevitably subjects key power electronic equipment, such as inverters, to severe cycles of electrical and thermal stress. Long-term stress accumulation accelerates the aging of components such as power semiconductors and capacitors within the equipment, shortening their effective service life and increasing long-term operation and maintenance costs. Existing technical solutions often perform passive assessments and maintenance only after equipment performance has significantly degraded, lacking a mechanism that can foresee and proactively manage the health of the equipment. Therefore, how to maintain equipment in the healthiest operating state through proactive intervention to minimize performance degradation while ensuring reasonable power generation returns is a technical issue that urgently needs to be addressed in this field. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants, so as to solve the problems raised in the above-mentioned background technology.

[0004] The technical solution of the present invention is, comprising: Data acquisition module, used to obtain environmental data, electrical data and operating status data of target electrical equipment in real time; a state assessment module for determining a functional steady-state deviation of the target electrical equipment based on the data acquired by the data acquisition module and in combination with a preset functional steady-state interval; A decision optimization module is used to generate optimal control instructions based on the functional steady-state deviation and a preset reward function; The control execution module is used to execute the optimal control instructions to regulate the operating status of the target electrical equipment.

[0005] Preferably, the state assessment module determines the functional steady-state deviation, including: The current value of the stress index is extracted from the data obtained by the data acquisition module; the preset functional steady-state interval is called, and the functional steady-state interval is defined by the preset optimal center value of the stress index and the preset safety range of the stress index; the preset weight coefficient is called; based on the current value of the stress index, the functional steady-state interval and the weight coefficient, the functional steady-state deviation is calculated and generated.

[0006] Preferably, the determination of the weight coefficient includes: In the preset digital twin model, systematic perturbations are performed on each stress indicator. Through accelerated simulation, the negative impact of each stress indicator on the predicted remaining service life of the equipment is quantified. Normalization is performed based on the degree of negative impact to determine the weight coefficient corresponding to each stress indicator.

[0007] Preferably, the decision optimization module generates the optimal control instruction, including: The functional steady-state deviation is used as the negative penalty term in the preset reward function. Based on the preset reward function, deep reinforcement learning tasks are used to search for the optimal control instructions for intervening in the target electrical equipment.

[0008] Preferably, the preset reward function includes: The instantaneous power generation efficiency term that represents the power generation revenue; The deviation from the functional steady state that characterizes the health status of the equipment; Penalties for grid violations to ensure grid friendliness.

[0009] Preferably, determining the instantaneous power generation efficiency item includes: Obtain the actual output power provided by the data acquisition module; call the preset digital twin model to calculate the theoretical maximum power under the current environmental conditions; determine the instantaneous power generation efficiency item by calculating the ratio of the actual output power to the theoretical maximum power.

[0010] Preferably, the determination of the grid violation penalty item includes: Comparing the output indicators of the target electrical equipment with the preset grid specifications; When the output index exceeds the limit, the grid violation penalty item is assigned a preset negative value; When the output indicator does not exceed the limit, the grid violation penalty item is assigned a value of zero.

[0011] Preferably, it also includes: The performance evaluation module is used to determine the predicted life under the steady-state control strategy composed of optimal control instructions based on the preset digital twin model, and to determine the predicted life under the standard control strategy. By calculating the ratio of the two, the decay inhibition factor that characterizes the long-term benefits of the steady-state control strategy is obtained.

[0012] Preferably, the performance evaluation module is further used to: Determine the actual output power guided by the optimal control command under this method; Determine the theoretical maximum power under current environmental conditions; Calculate the integral of the difference between the actual output power and the theoretical maximum power within the preset time; Calculate the integral of the theoretical maximum power within the preset time; By dividing the integral of the difference by the integral of the theoretical maximum power, the control efficiency loss rate that represents the short-term cost of the steady-state control strategy is determined. The present invention provides an intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants through improvements. Compared with the prior art, it has the following improvements and advantages: 1. This solution establishes a quantifiable equipment health assessment system. Through the health assessment module, the concept of functional steady-state deviation is introduced, imposing stronger penalties for larger health deviations. This functional steady-state deviation, calculated by combining the current stress indicator value provided by the data acquisition module with the preset functional steady-state interval, quantifies abstract equipment health into a precise, dimensionless scalar for the first time, providing a solid mathematical foundation for subsequent closed-loop control. 2. This solution's control priorities have a clear physical basis, ensuring that the allocation of weight coefficients is directly linked to the actual physical degradation mechanisms. This enables the decision-making optimization module to prioritize the suppression of the most critical damage factors, greatly improving the targetedness and efficiency of health management. This is unmatched by existing experience-based, indiscriminate control methods. 3. This solution achieves a dynamic optimal balance between power generation revenue and equipment health, ensuring that all optimization behaviors are carried out within the boundaries of grid safety regulations. Compared with the single, static control objectives of existing technologies, the intelligent agent of this solution can autonomously learn and execute a set of complex, dynamic optimal control instructions under variable operating conditions to maximize long-term cumulative rewards, thereby achieving the Pareto optimality of power generation revenue and equipment health in practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further explained below in conjunction with the accompanying drawings and Examples: Figure 1 This is a flowchart of an intelligent performance evaluation and management system for electrical equipment in photovoltaic power stations according to the present invention; Figure 2 This is a diagram showing the steps for determining the functional steady-state deviation in Example 2. DETAILED DESCRIPTION

[0014] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0015] Example 1: See also Figure 1 The present invention provides an intelligent performance evaluation and management system for electrical equipment in photovoltaic power stations, comprising: Data acquisition module, used to obtain environmental data, electrical data and operating status data of target electrical equipment in real time; a state assessment module for determining a functional steady-state deviation of the target electrical equipment based on the data acquired by the data acquisition module and in combination with a preset functional steady-state interval; A decision optimization module is used to generate optimal control instructions based on the functional steady-state deviation and a preset reward function; A control execution module is used to execute the optimal control instructions to regulate the operating state of the target electrical equipment; The present invention provides an intelligent electrical equipment performance evaluation and management system for photovoltaic power plants. This system aims to address the problem of traditional control strategies pursuing instantaneous maximum power generation at the expense of long-term equipment health through proactive health management. This system minimizes performance degradation of key electrical equipment while ensuring reasonable power generation revenue, thereby reducing long-term operation and maintenance costs. In this implementation, the system is deployed to manage inverters in a photovoltaic power plant. The system is constructed as a closed-loop control system, and its composition and workflow are explained. The data acquisition module is designed to provide comprehensive, real-time basic data for subsequent evaluation and decision-making. In this embodiment, the module is configured to acquire real-time environmental data, electrical data, and operating status data of the target electrical equipment. Environmental data refers to physical quantities reflecting the operating conditions of the equipment, such as light intensity and ambient temperature acquired by temperature sensors. Electrical data refers to parameters characterizing the internal electrical state of the equipment, such as the DC voltage and current of the inverter, and the AC output voltage and frequency acquired by built-in sensors. Operating status data refers to accumulated information reflecting the historical operating conditions of the equipment, such as accumulated operating hours or accumulated power generation. Data acquisition is multi-time scale, including both high-frequency data at the millisecond level to capture transient stresses and low-frequency data at the minute or hour level to track long-term trends. The state assessment module is designed to quantitatively assess the current health status of the target electrical equipment. This module is configured to determine the functional steady-state deviation of the target electrical equipment based on the data acquired by the data acquisition module and a preset functional steady-state interval. The functional steady-state interval refers to the optimal operating range of a set of key electrical and thermodynamic indicators. When operating within this range, the aging rate of the equipment due to stress accumulation is minimized. The determination of this range is not arbitrary; its internal logic is based on the specifications provided by the equipment manufacturer, a large amount of laboratory accelerated aging test data, and simulation analysis of the equipment aging mechanism model, resulting in a pre-determined optimal healthy operating range. The decision optimization module aims to generate optimal intervention instructions based on the current equipment health status to guide the equipment back to or maintain a healthy state. This module is configured to generate optimal control instructions based on the functional steady-state deviation calculated by the state assessment module and a preset reward function. The reward function is a mathematical construct used to quantify objectives. Its working principle is to unify the two conflicting objectives of power generation revenue and equipment health loss into a single scalar evaluation signal, thereby providing a clear optimization direction for the optimization algorithm. A control execution module, whose purpose is to convert decision instructions into actual control of physical devices. This module is configured to execute the optimal control instructions generated by the decision optimization module to regulate the operating state of the target electrical device. For example, this module issues instructions to the central processing module of the inverter to fine-tune the perturbation step size of its maximum power point tracking algorithm or limit the slope of change of its power output. Through the collaborative work of the above modules, a complete technical chain from data perception, state quantification, intelligent decision-making to closed-loop control is formed; By building a closed-loop health management system encompassing data collection, status assessment, decision optimization, and control execution, a paradigm shift has been achieved, shifting from traditional passive maintenance to proactive health management. While ensuring reasonable power generation returns, the system proactively intervenes and regulates the operating status of electrical equipment, keeping it within the functional steady-state range with the lowest aging rate possible. This effectively slows equipment performance degradation, extends its effective service life, and reduces the total operation and maintenance costs throughout the photovoltaic power station's lifecycle. The beneficial effects of the embodiments of the present invention are rooted in the new technical paradigm it establishes, moving from passive response assessment to proactive health management. Compared to existing technologies that focus solely on maximizing instantaneous power generation efficiency, this solution represents a significant advancement in technical concept, implementation path, and ultimate results. The fundamental limitation of existing technologies is that their aggressive control strategies inevitably subject critical electrical equipment, such as inverters, to severe cycles of electrical and thermal stress, accelerating their aging process. Reactive maintenance is only performed after significant performance degradation occurs. This solution, by introducing closed-loop control, enables proactive and forward-looking management of equipment health.

[0016] Example 2 See also Figure 2 , the state assessment module determines the functional steady-state deviation, including: Extracting the current value of the stress index from the data acquired by the data acquisition module; calling a preset functional steady-state interval, which is defined by a preset optimal center value of the stress index and a preset safety range of the stress index; calling a preset weight coefficient; and calculating and generating a functional steady-state deviation based on the current value of the stress index, the functional steady-state interval, and the weight coefficient; This embodiment defines the process by which the state assessment module determines the deviation from functional homeostasis; this process aims to integrate multi-dimensional stress states with different physical properties into a unified, quantifiable, dimensionless health state metric. The process of determining the deviation from the functional steady state by the state assessment module includes the following steps: Extracting the current value of the stress index from the real-time data stream acquired by the data acquisition module; Stress Index Refers to a physical quantity that directly or indirectly reflects the stress on key components of a device, such as power semiconductor IGBTs and capacitors. In this embodiment, it can specifically be the junction temperature of the IGBT, the ripple current of the DC bus capacitor, etc. The systematic selection of stress indicators should be based on a failure mode and effects analysis of the target electrical equipment. FMEA should be used to identify the most critical failure modes that have the greatest impact on equipment reliability. The physical stress sources that cause these failure modes, such as temperature, current, and voltage, should then be identified as stress indicators that must be included in the assessment to ensure a comprehensive and targeted assessment. The current values ​​of stress indicators are the measured values ​​of these physical quantities at the current moment; Call the preset functional steady-state interval; as mentioned above, the functional steady-state interval is defined by the preset optimal center value of the stress index and the preset safety range of the stress index. The optimal center value of the stress index refers to the ideal operating point at which the equipment aging rate is theoretically lowest; the safety range of the stress index refers to the allowable fluctuation range around the center value. Both parameters are pre-set based on the equipment aging mechanism model and experimental data. An example of the quantitative determination steps is: for a specific stress indicator, such as IGBT junction temperature, multiple sets of accelerated aging experiments are conducted in the laboratory at different constant temperatures; based on the experimental data, a curve is fitted to show the relationship between the stress and the predicted life of the device; the point on the curve corresponding to the longest life is the optimal center value of the stress The stress range corresponding to when the lifespan drops to 95% of the maximum lifespan is defined as the safety range of the stress. ; Call the preset weight coefficient; the weight coefficient refers to a set of numerical values, which is used to characterize the relative importance of different types of stress on the long-term health of the equipment; Based on the current value of the stress index, the functional steady-state interval and the weight coefficient, the functional steady-state deviation is calculated and generated; in this embodiment, the calculation is completed by a specific mathematical formula; for further explanation, the functional steady-state deviation is introduced The calculation formula is:

[0017] in, is the deviation of functional steady state; is the index of the summation term, representing the i-th stress index; n is the total number of stress indices involved in the calculation; For the The weight coefficients of the stresses are derived from the digital twin simulation described in the subsequent embodiments; is the current value of the stress index obtained in real time by the data acquisition module; It is the optimal center value of stress index pre-set based on equipment mechanism and experimental data; is the same pre-set safety range of stress indicators; By introducing a comprehensive formula for calculating functional steady-state deviation, the complex, multi-dimensional equipment health status is accurately quantified into a single, dimensionless scalar index. This quantification not only makes the health status of the equipment intuitive and comparable, but more importantly, it provides a clear and specific optimization goal for the subsequent decision-making optimization module, namely, minimizing , thereby greatly improving the accuracy and effectiveness of the closed-loop health management system; This solution establishes a quantifiable equipment health status assessment system. Through the status assessment module, the concept of functional steady-state deviation is introduced. To concretize this concept, a comprehensive mathematical construction is proposed: ,in, : Steady-state deviation, : weight coefficient, : current value of stress, : optimal stress value, : Stress safety range, : Total stress; This formula is not a simple empirical fit. Its physical meaning is that it represents a weighted Euclidean distance between the current equipment state point and the theoretical optimal health center point in the multidimensional stress state space; Among them, A method for dimensionlessly transforming stress indicators of different dimensions into additive ones; a design of the square term causes the deviation to grow quadratically, thereby imposing a stronger penalty on larger health deviations; the current value of the stress indicator provided by the data acquisition module, combined with the functional steady-state deviation calculated based on the preset functional steady-state interval, enables the abstract equipment health to be quantified as a precise, dimensionless scalar for the first time, providing a solid mathematical foundation for subsequent closed-loop control.

[0018] Example 3 The determination of weight coefficients includes: In the pre-set digital twin model, systematic perturbations are performed on each stress indicator. Through accelerated simulation, the negative impact of each stress indicator on the predicted remaining service life of the equipment is quantified. Normalization is performed based on the degree of negative impact to determine the corresponding weight coefficient for each stress indicator. In this embodiment, the weight coefficient The method for determining the weight coefficient is further limited; this method is intended to ensure that the allocation of weight coefficients has clear physical meaning and engineering basis, rather than subjective settings; The weight coefficient determination process is usually performed offline. The working principle is to quantify the contribution of various stresses to equipment life loss through digital twin simulation. It includes the following steps: Systematic perturbations are applied to various stress indicators within a pre-defined digital twin model. This model is a highly faithful digital counterpart to the physical device, incorporating the device's electrical and thermodynamic models, as well as a critical, mechanism-based, and data-driven multi-scale aging model. This aging model can predict the performance degradation trajectory and remaining useful life of key components of the device based on input stress profiles. To enable those skilled in the art to implement, the digital twin model construction method here is as follows: Thermodynamic model: A fourth-order Cauer thermal network model is used to describe the transient thermal impedance of the IGBT module. The model parameters are obtained by consulting the manufacturer's data sheet or through experimental calibration. Aging model: For IGBT power cycle aging, the Norris-Landzberg model, which combines the effects of temperature cycle amplitude and average junction temperature, is used to predict its lifespan. For capacitor aging, a model based on the Arrhenius equation is used to correlate ripple current, operating temperature, and lifespan degradation. Model calibration: Parameterize the aforementioned mechanistic model and use optimization algorithms such as particle swarm optimization or genetic algorithms to fit the model simulation output to real data collected from laboratory accelerated aging experiments. Accurately calibrate the model parameters to ensure high fidelity. In the digital twin environment, through accelerated simulation, the negative impact of each stress indicator on the predicted remaining service life of the equipment is quantified; the specific operation is: select the stress index, causing a unit disturbance while keeping other stress indexes stable at the optimal central value; running the aging model for accelerated simulation to obtain a predicted RUL reduction caused by this stress disturbance; Repeat this process for each stress indicator; Normalize the process according to the degree of negative impact and determine the weight coefficient corresponding to each stress index ; Sort and normalize the RUL reduction caused by each stress indicator so that the stress with the greatest impact on RUL has the highest weight coefficient; Provides an objective and reproducible method for determining weight coefficients; by performing sensitivity analysis in the digital twin model, the weight coefficients Directly linked to its actual impact on the predicted lifespan of the equipment; this ensures that the control system can suppress the most critical damage factors with higher priority, making health management strategies more targeted and resource allocation more reasonable, thereby more effectively delaying the overall aging process of the equipment; The control priority of this scheme has a clear physical basis; the weight coefficient in the above formula , and its determination process relies deeply on a preset digital twin model; by systematically perturbing each stress indicator in the model and simulating its negative impact on the predicted remaining service life of the equipment, the contribution of different stresses to equipment aging can be quantified; this ensures that the distribution of weight coefficients is directly related to the real physical degradation mechanism, allowing the decision-making optimization module to prioritize the suppression of the most critical damage factors, greatly improving the pertinence and efficiency of health management, which is unmatched by the experience-based, indiscriminate control methods in existing technologies.

[0019] Example 4 The decision optimization module generates optimal control instructions, including: The functional steady-state deviation is used as a negative penalty term in a preset reward function. Based on the preset reward function, a deep reinforcement learning task is used to search for the optimal control instructions for intervening in the target electrical equipment. In this embodiment, a soft actor-critic algorithm suitable for continuous action space control is specifically adopted, wherein: Agent network structure: Both the actor network and the critic network use a multilayer perceptron with three hidden layers. The input layer receives state data, and the output layer outputs control instructions, such as the MPPT perturbation step size. The hidden layer uses ReLU as the activation function. State space: The state is composed of environmental data and electrical data obtained by the data acquisition module and the functional steady-state deviation calculated by the state evaluation module. together constitute; Action space: Actions are defined as adjustments to inverter control parameters, such as fine-tuning the perturbation step size of the maximum power point tracking algorithm, which are normalized to within the interval; This embodiment defines how the decision optimization module generates optimal control instructions; this approach is intended to enable the system to autonomously learn complex control strategies that balance power generation efficiency and equipment health. The process of generating optimal control instructions by the decision optimization module is modeled as a deep reinforcement learning task. Its internal logic is as follows: The functional steady-state deviation calculated by the state assessment module As a negative penalty term in the preset reward function; this means that any behavior that causes the device to deviate from its healthiest working state will be punished by an increasing The value is immediately converted into a negative reward signal; Based on this preset reward function, a deep reinforcement learning task is used to search for optimal control instructions for intervening in the target electrical equipment. In this task, the central processing module acts as an intelligent agent, continuously interacting with the physical device or its digital twin model. The intelligent agent outputs an action at each time step, namely the optimal control instruction, such as adjusting the MPPT perturbation step size. After the device executes, the state changes, and the environment, including the state evaluation module, returns a new state and a reward value calculated according to the reward function. The goal of the intelligent agent is to learn an optimal policy through training, which can output an action that maximizes the long-term cumulative reward based on the input device state. By introducing a deep reinforcement learning framework, complex control problems are transformed into a well-defined optimization task. This approach frees the system from dependence on preset, rigid control rules. The intelligent agent can autonomously learn and discover sophisticated control strategies that are difficult for human experts to design through dynamic interaction with the environment, thereby achieving the optimal balance between power generation benefits and equipment health in a more intelligent and adaptive manner under changing operating conditions.

[0020] Preset reward functions, including: The instantaneous power generation efficiency term that represents the power generation revenue; The deviation from the functional steady state that characterizes the health status of the equipment; Penalties for grid violations to ensure grid friendliness; Determine the instantaneous power generation efficiency items, including: Obtain the actual output power provided by the data acquisition module; call the preset digital twin model to calculate the theoretical maximum power under current environmental conditions; determine the instantaneous power generation efficiency item by calculating the ratio of the actual output power to the theoretical maximum power; Determination of penalties for grid violations, including: Comparing the output indicators of the target electrical equipment with the preset grid specifications; When the output index exceeds the limit, the grid violation penalty item is assigned a preset negative value; When the output index does not exceed the limit, the grid violation penalty item is assigned a value of zero; This embodiment uses the preset reward function The specific composition of is limited; the design of this reward function is the basis for guiding the deep reinforcement learning agent to learn the desired behavior; The default reward function works by combining multiple objectives into a single, dimensionless scalar reward signal using a linear weighted summation approach. In this example, the function consists of three core components: The instantaneous power generation efficiency term that represents the power generation revenue; The deviation from the functional steady state that characterizes the health status of the equipment; Penalties for grid violations to ensure grid friendliness; The three together constitute the moment Instant rewards: :

[0021] in, For the moment The immediate reward; t is the time; is the instantaneous power generation efficiency calculated by the subsequent steps; subscript g: represents the power grid; subscript t: represents time t; is the steady-state deviation calculated in real time by the state assessment module; Penalties for grid violation; is the dimensionless equilibrium coefficient; Balance coefficient The method for determining is to conduct multiple rounds of offline training and evaluation in the digital twin environment to screen out the strategy set that constitutes the Pareto optimal frontier between extending equipment life and sacrificing power generation efficiency. The system operator selects the most appropriate strategy point on this frontier based on its economic model and asset management objectives to determine its final value. The operation method of generating Pareto optimal frontier is: To ensure the safety of power grid, Set to a sufficiently large constant by Systematically change within the scope of and For example, take For each ratio, a deep reinforcement learning agent is trained independently until convergence, and the long-term benefits corresponding to each converged strategy, such as the decay inhibition factor and short-term costs, such as regulatory efficiency loss As a point plotted in a two-dimensional coordinate system, the set of points constitutes the discretized Pareto optimal frontier for operators to choose; Instantaneous power generation efficiency The determination process is as follows: Get the actual output power provided by the data acquisition module ; Call the preset digital twin model to calculate the theoretical maximum power under current environmental conditions, such as light and temperature The theoretical maximum power is the instantaneous power reference value that can be achieved using the standard MPPT algorithm under current environmental conditions. The instantaneous power generation efficiency term is determined by calculating the ratio of actual output power to theoretical maximum power:

[0022] in, It is the instantaneous power generation efficiency; is the actual output power obtained in real time by the data acquisition module; is the theoretical maximum power calculated in real time by the digital twin model; this normalization process makes Becomes a dimensionless value ranging from 0 to 1, ensuring the dimensional consistency of the reward function; subscript m: represents the maximum; Penalties for grid violations The determination process is as follows: compare the output indicators of the target electrical equipment, such as voltage, frequency, and harmonic content, with the preset grid specifications; Preset grid specifications Derived from the grid connection technical standards issued by the power sector, the set logic is to serve as a hard constraint to ensure grid security. When any output indicator exceeds the limit, the grid violation penalty item is assigned a preset large negative value. To ensure the absolute effectiveness of the penalty, the large negative value should be set to be at least greater than the benefit term in the reward function. The maximum positive value that can be achieved in one time step is an order of magnitude larger; this ensures that any exploration behavior that violates the grid code will immediately receive strong negative feedback, thereby guiding the agent to learn to avoid such dangerous actions in the early stages of policy learning; When all output indicators are within the limit, the grid violation penalty item is assigned a value of zero; The gain technical effect of this embodiment is: Comprehensiveness of objectives: Building a comprehensive consideration of power generation benefits , equipment health and grid security The reward function of three core dimensions ensures the comprehensiveness and practicality of the control strategy; Quantification and closed loop: The output of the state assessment module Directly serving as the core negative penalty term in the reward function, it establishes a critical closed-loop feedback path; any behavior that harms health will be immediately punished, guiding the agent to learn to avoid such behavior; Constraints and practicality: By incorporating grid-connection regulations into the learning process as hard constraints through grid violation penalties, the generated control strategy is guaranteed to be safe and feasible in engineering. This solution achieves a dynamic optimal balance between power generation revenue and equipment health; the decision optimization module uses the functional steady-state deviation as a core negative penalty term in the preset reward function and uses deep reinforcement learning tasks for optimization; the reward function is designed to be ,in, : Instant rewards, : Instantaneous power generation efficiency, : Steady-state deviation, : Penalty items for power grid violations, : Balance coefficient; the construction of this function is logically self-consistent and complete; The term is the instantaneous power generation efficiency term, which is normalized by the ratio of actual output power to theoretical maximum power, ensuring the pursuit of power generation benefits; The term represents the health cost paid to obtain the benefit; That is, the grid violation penalty item ensures that all optimization behaviors are carried out within the boundaries of grid safety regulations; compared with the single, static control objectives of existing technologies, the intelligent agent of this scheme can autonomously learn and execute a set of complex, dynamic optimal control instructions under variable working conditions to maximize long-term cumulative rewards, thereby achieving the Pareto optimality of power generation revenue and equipment health in practice.

[0023] Also includes: The performance evaluation module is used to determine the predicted life under the steady-state control strategy composed of optimal control instructions and the predicted life under the standard control strategy based on the preset digital twin model. By calculating the ratio of the two, the decline inhibition factor that characterizes the long-term effectiveness of the steady-state control strategy is obtained; The performance evaluation module is also used to: Determine the actual output power guided by the optimal control command under this method; Determine the theoretical maximum power under current environmental conditions; Calculate the integral of the difference between the actual output power and the theoretical maximum power within the preset time; Calculate the integral of the theoretical maximum power within the preset time; By dividing the integral of the difference by the integral of the theoretical maximum power, the control efficiency loss rate representing the short-term cost of the steady-state control strategy is determined; The system also includes a performance evaluation module. This module is not intended to participate in real-time closed-loop control, but rather serves as an offline evaluation tool for verifying the performance of a trained control strategy and conducting a macro-evaluation of its effectiveness from the perspectives of long-term benefits and short-term costs. To further illustrate, the performance evaluation module is configured to determine the decay suppression factor ; recession inhibitors son The definition of is used to intuitively measure the effectiveness of this method in extending the life of the equipment; the determination process is: based on the aging module in the preset digital twin model, determine the predicted life under the steady-state control strategy composed of the optimal control instructions , and determine the predicted life under the standard control strategy under the same external conditions ; The standard control strategy here specifically refers to the control strategy that is installed by default by the inverter manufacturer when it leaves the factory, with the sole goal of maximizing instantaneous power generation. This strategy is usually the classic perturbation-and-observe method or the incremental conductance maximum power point tracking algorithm. This strategy does not consider or intervene in the health status of the device during operation. By calculating the ratio of the two, the decay suppression factor that characterizes the long-term benefits of the steady-state control strategy is obtained:

[0024] in, It is a recession inhibitor; To predict life under steady-state control; To predict the life under standard control, both are obtained through long-term simulation prediction in the digital twin model; To evaluate short-term costs, the performance evaluation module is also configured to determine the control efficiency loss rate The definition of the control efficiency loss rate is used to quantify the short-term cost of power generation to maintain the long-term health of the equipment; its determination process is: Determine the actual output power guided by the optimal control command under this method , and the theoretical maximum power under current environmental conditions ; Calculate at preset time The difference between the actual output power and the theoretical maximum power is integrated, as well as the theoretical maximum power. The efficiency loss rate representing the short-term cost of the steady-state control strategy is determined by dividing the difference integral by the theoretical maximum power integral:

[0025] in, is the efficiency loss rate; is the theoretical maximum power calculated by the digital twin model; It is the actual output power measured during the actual operation of the system; is time; T: preset integration time period; subscript a: represents actual; : integral symbol; d: differential symbol; The gain technology of this embodiment has the following effects: providing a complete and objective offline strategy evaluation system; and control efficiency loss rate These two complementary metrics allow system operators to clearly quantify the long-term benefits of any health management strategy (how many times the lifespan is extended) and the short-term costs (how much power generation efficiency is lost). This quantitative assessment provides a direct and reliable basis for operators to choose between different control strategies or make informed trade-offs between benefits and costs that are consistent with their business models. This solution provides a complete macro-evaluation system for quantitatively evaluating the benefits and costs of strategies; by introducing the recession suppression factor in, : Decline inhibition factor, : Predicted life under steady-state control, :Predicted lifespan and control efficiency loss rate under standard control ,in, : efficiency loss rate, is the theoretical maximum power calculated by the digital twin model; is the actual output power measured during the actual operation of the system, : Time, the long-term benefits of the program, life extension and short-term costs, efficiency loss are clearly presented; for example, a specific strategy may achieve , which means that the predicted life of the equipment is extended by 40%, and the cost is only This quantitative cost-benefit analysis capability enables power plant operators to make data-driven, informed asset management decisions based on their economic models, which is unprecedented in the existing technology. In summary, this solution fundamentally resolves the inherent contradiction of existing technologies, which sacrifice long-term equipment health for short-term power generation, by building a complete technical system that includes data collection, quantitative evaluation, intelligent decision-making, and closed-loop control. It achieves coordinated management and optimization of the efficiency and health of electrical equipment in photovoltaic power stations, and has significant technological progress and huge application value.

Claims

1. An intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants, characterized by: include: Data acquisition module, used to obtain environmental data, electrical data and operating status data of target electrical equipment in real time; a state assessment module for determining a functional steady-state deviation of the target electrical equipment based on the data acquired by the data acquisition module and in combination with a preset functional steady-state interval; A decision optimization module is used to generate optimal control instructions based on the functional steady-state deviation and a preset reward function; The control execution module is used to execute the optimal control instructions to regulate the operating state of the target electrical equipment.

2. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 1, characterized in that: The state assessment module determines the degree of deviation from functional homeostasis, including: The current value of the stress index is extracted from the data obtained by the data acquisition module; the preset functional steady-state interval is called, and the functional steady-state interval is defined by the preset optimal center value of the stress index and the preset safety range of the stress index; the preset weight coefficient is called; based on the current value of the stress index, the functional steady-state interval and the weight coefficient, the functional steady-state deviation is calculated and generated.

3. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 2, characterized in that: Determination of the weight coefficient includes: In the preset digital twin model, systematic perturbations are performed on each stress indicator. Through accelerated simulation, the negative impact of each stress indicator on the predicted remaining service life of the equipment is quantified. Normalization is performed based on the degree of negative impact to determine the weight coefficient corresponding to each stress indicator.

4. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 1, characterized in that: The decision optimization module generates the optimal control instructions, including: The functional steady-state deviation is used as the negative penalty term in the preset reward function. Based on the preset reward function, deep reinforcement learning tasks are used to search for the optimal control instructions for intervening in the target electrical equipment.

5. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 4, characterized in that: Preset reward functions, including: The instantaneous power generation efficiency term that represents the power generation revenue; The deviation from the functional steady state that characterizes the health status of the equipment; Penalties for grid violations to ensure grid friendliness.

6. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 5, characterized in that: Determining the instantaneous power generation efficiency item includes: Obtain the actual output power provided by the data acquisition module; call the preset digital twin model to calculate the theoretical maximum power under the current environmental conditions; determine the instantaneous power generation efficiency item by calculating the ratio of the actual output power to the theoretical maximum power.

7. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 5, characterized in that: The determination of the penalty items for grid violation includes: Comparing the output indicators of the target electrical equipment with the preset grid specifications; When the output index exceeds the limit, the grid violation penalty item is assigned a preset negative value; When the output indicator does not exceed the limit, the grid violation penalty item is assigned a value of zero.

8. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 1, characterized in that: Also includes: The performance evaluation module is used to determine the predicted life under the steady-state control strategy composed of optimal control instructions based on the preset digital twin model, and to determine the predicted life under the standard control strategy. By calculating the ratio of the two, the decay inhibition factor that characterizes the long-term benefits of the steady-state control strategy is obtained.

9. The intelligent performance evaluation and management system for electrical equipment in photovoltaic power plants according to claim 8, characterized in that: The performance evaluation module is also used to: Determine the actual output power guided by the optimal control command under this method; Determine the theoretical maximum power under current environmental conditions; Calculate the integral of the difference between the actual output power and the theoretical maximum power within the preset time; Calculate the integral of the theoretical maximum power within the preset time; The control efficiency loss rate representing the short-term cost of the steady-state control strategy is determined by dividing the integral of the difference by the integral of the theoretical maximum power.

Images