Inverter control system

Abstract

The invention relates to an inverter control system, and the system comprises distributed intelligent nodes which are used for collecting sensor data of a target part, obtaining a fault signal, and simply controlling an inverter according to the sensor data; the intelligent control module is used for generating an optimal power control instruction to control the inverter and communicating with external equipment; the intelligent feedback regulation module is used for fusing the sensor data and obtaining an optimal control strategy to control the inverter; the intelligent energy interconnection and scheduling module is used for collecting information of distributed energy, obtaining a global optimal energy scheduling strategy according to the information of the distributed energy, and controlling the inverter according to the global optimal energy scheduling strategy; and the intelligent energy efficiency evaluation and optimization module is used for monitoring the inverter, obtaining and evaluating the energy efficiency level of the inverter, and optimizing the control parameters and the operation mode of the inverter according to the evaluation result. According to the invention, the performance and efficiency of the inverter can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power electronic equipment control, and particularly to an inverter control system. Background Art

[0002] As a crucial component in modern power electronic equipment, inverters are widely used in renewable energy systems, energy storage systems, smart grids and other fields. Its main function is to convert direct current into alternating current and dynamically adjust according to grid conditions to ensure the quality and stability of power output. With the rapid development of renewable energy, the role of inverters in the power system is becoming increasingly important, especially in the fields of solar photovoltaic and wind power generation. In order to improve the operating efficiency of inverters, reduce losses, and ensure the safety and stability of the power system, the control and management technologies of inverters have been continuously developed. In recent years, with the progress of intelligent and digital technologies, the control methods of inverters have gradually developed towards integration and intelligence, especially by combining technologies such as deep learning, Internet of Things, and blockchain, which have promoted the upgrade of energy management and dispatching systems.

[0003] Most traditional inverter control technologies are based on hardware control and simple algorithms. Most inverters rely on pulse width modulation (PWM) technology for control, and adjust the voltage, frequency and phase of the inverter output to meet grid requirements. Although these traditional control methods can ensure the basic functions of inverters to a certain extent, they are often insufficient when dealing with grid dynamic fluctuations, load changes and power quality requirements. First of all, traditional inverters are difficult to achieve precise power management in complex grid environments, especially in the case of voltage fluctuations, load changes or grid anomalies, and power losses or power quality problems are likely to occur. Secondly, traditional protection mechanisms are limited to electrical protection and do not consider electromagnetic compatibility and network security issues, resulting in poor security of inverters when facing external interference or network attacks. Finally, the optimization scheduling mechanism of traditional inverters usually lacks intelligence and cannot adjust the output power dynamically according to real-time electricity prices or energy supply and demand, thus limiting the improvement of energy utilization efficiency and economic benefits.

[0004] In the prior art, the main problem faced by traditional inverters is that they cannot operate efficiently and stably under grid fluctuations and load changes. Summary of the Invention

[0005] The purpose of the present invention is to provide an inverter control system, which not only significantly improves the performance and efficiency of the inverter through intelligent control, optimization, scheduling and safety protection mechanisms, but also provides guarantees for the efficient utilization of renewable energy, energy conservation and emission reduction, and the reliability of the power system.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] An inverter control system includes: distributed intelligent nodes, intelligent control modules, intelligent feedback regulation modules, intelligent energy interconnection and scheduling modules, and intelligent energy efficiency evaluation and optimization modules;

[0008] The distributed intelligent nodes are used to collect sensor data of target components and obtain fault signals, start or stop the inverter according to the sensor data, adjust the operating frequency, and transmit the fault signals to the master controller;

[0009] The intelligent control module is used to receive the sensor data collected by the distributed intelligent nodes, generate an optimal power control instruction according to the sensor data to control the inverter, and manage communication with external devices;

[0010] The intelligent feedback regulation module is used to fuse the sensor data, obtain the operating information of the inverter, and obtain an optimal control strategy according to the operating information of the inverter to control the inverter;

[0011] The intelligent energy interconnection and scheduling module is used to collect information of distributed energy, obtain a globally optimal energy scheduling strategy according to the information of distributed energy, and control the inverter according to the globally optimal energy scheduling strategy;

[0012] The intelligent energy efficiency evaluation and optimization module is used to monitor the inverter, evaluate the energy efficiency level of the inverter, and optimize the control parameters and operating mode of the inverter according to the evaluation results.

[0013] Optionally, the intelligent control module includes a microprocessor and an FPGA;

[0014] The microprocessor includes a data receiving unit, a calculation unit, and a communication management unit. The data receiving unit is used to receive the sensor data collected by the distributed intelligent nodes. The calculation unit is used to obtain the voltage, current, and frequency data of the power grid, calculate the optimal power control instruction, and control the inverter. The communication management unit is used to perform data encryption and decryption and control the communication interface of external devices by using the FPGA;

[0015] The FPGA is used to generate a pulse width modulation signal to control the output voltage of the inverter, encrypt and decrypt the data exchanged and stored between modules, and control the communication interface with external devices.

[0016] Optionally, calculating the optimal power control instruction and generating an optimal power control instruction to control the inverter includes:

[0017] Based on the instantaneous reactive power theory and space vector pulse width modulation technology, calculate the active power and reactive power of the inverter, where the space vector pulse width modulation technology adopts a sector division method and a vector selection strategy;

[0018] According to the active power and reactive power of the inverter, combined with the voltage fluctuation, frequency change of the power grid and the dynamic characteristics of the load, obtain the optimal power control instruction;

[0019] At the same time, adopt a power factor dynamic correction algorithm to adjust the output power factor of the inverter.

[0020] Optionally, adopting a power factor dynamic correction algorithm to adjust the output power factor of the inverter includes:

[0021] The power factor dynamic correction algorithm is based on fuzzy control theory, and adjusts the phase of the output current of the inverter according to the phase difference between the grid voltage and current and the magnitude of the reactive power, so as to adjust the output power factor of the inverter.

[0022] Optionally, fusing the sensor data to obtain the inverter operation information includes:

[0023] Based on the Kalman filter-based fusion algorithm, weight-fuse the sensor data to obtain fusion data;

[0024] Input the fusion data into a pre-trained deep neural network to obtain the inverter operation information, where the pre-trained deep neural network is constructed by combining a convolutional neural network and a recurrent neural network and is obtained by training with a training set, and the training set includes historical fusion data and corresponding operation conditions and load types.

[0025] Optionally, the intelligent energy interconnection and scheduling module includes a local energy management unit and a central coordination unit;

[0026] The local energy management unit is used to monitor and control local distributed energy resources, energy storage systems and inverters, collect energy production, storage and consumption information and upload it to the central coordination unit;

[0027] The central coordination unit is used to adopt a mixed integer linear programming algorithm to obtain a globally optimal energy scheduling strategy according to energy production, storage, consumption information and electricity price information, and issue it to each local energy management unit to control the inverter power.

[0028] Optionally, the intelligent energy efficiency evaluation and optimization module includes: an energy efficiency level evaluation unit and an optimization unit;

[0029] The energy efficiency level evaluation unit is used to evaluate the energy efficiency level according to the ratio of the input power and the output power of the inverter;

[0030] The optimization unit is used to optimize the combination of control parameters of the inverter by combining the genetic algorithm and the particle swarm optimization algorithm, and combine with the energy efficiency level evaluation unit to determine whether the inverter reaches the best operating efficiency under different operating conditions. Among them, the genetic algorithm is used for global optimization to search for the optimal solution of the inverter control parameters, and the particle swarm optimization algorithm is used for local optimization to adjust the control parameters.

[0031] Optionally, the objective function for optimizing the combination of control parameters of the inverter by combining the genetic algorithm and the particle swarm optimization algorithm is:

[0032] f(x) = α·E(x) + β·H(x)

[0033] Where, f(x) is the objective function, x is the optimized solution of the control parameters, E(x) is the energy efficiency, H(x) is the harmonic distortion, and α and β are the weight coefficients of the energy efficiency and the harmonic distortion on the optimization result respectively.

[0034] Optionally, the system further includes a safety protection module, and the safety protection module includes: an electrical safety protection unit, an overvoltage and overcurrent protection unit, an electromagnetic compatibility protection unit, and a network security protection unit;

[0035] The electrical safety protection unit is used to monitor the leakage current in real time through a zero-sequence current transformer, and cut off the circuit when the current exceeds a predetermined threshold;

[0036] The overvoltage and overcurrent protection unit is used to monitor the voltage and current in the circuit in real time through a sampling resistor and a fast comparator, and trigger a protection action when overvoltage or overcurrent occurs;

[0037] The electromagnetic compatibility protection unit is used to block external electromagnetic interference by using a multi-layer metal shielding material, and filter out interference signals by using a filter circuit combined with a common-mode inductor and a differential-mode capacitor in the internal circuit;

[0038] The network security protection unit is used to encrypt the control instructions and monitoring data transmitted between modules during the operation of the system by using an encryption communication protocol combining AES and ECC.

[0039] The beneficial effects of the present invention are as follows: The integrated intelligent control architecture of the present invention combines multi-core processors and FPGA technology, enabling precise monitoring and high-speed data processing of the inverter. Through the collaboration of distributed intelligent nodes, the system features fast response and high reliability, especially under complex grid conditions, ensuring that the inverter always operates in the optimal state. This architecture improves the working stability and adaptability of the inverter, avoiding system failures or energy losses caused by data processing lags or untimely fault responses.

[0040] The dynamic and precise power management system combines the instantaneous reactive power theory and SVPWM technology, enabling precise control of the inverter's output power under grid voltage fluctuations and load changes, reducing reactive power transmission losses, and optimizing power quality. In addition, the intelligent feedback regulation network uses multi-sensor fusion and deep learning technologies to adaptively adjust the operating conditions of the inverter, ensuring its efficient and stable operation under various load conditions.

[0041] The intelligent energy efficiency evaluation and optimization module continuously monitors the input and output power and conversion efficiency of the inverter in real time. Through the combined optimization of genetic algorithms and particle swarm optimization algorithms, the inverter is always maintained near the optimal efficiency point under different load conditions, minimizing energy losses. The optimized control parameters not only improve the energy conversion efficiency but also reduce harmonic distortion, enhance power quality, reduce pollution to the grid, and contribute to energy conservation, emission reduction, and environmental protection.

[0042] The all-round safety protection architecture provides guarantees from multiple aspects such as electrical safety, electromagnetic compatibility, and network security. Leakage protection, overvoltage and overcurrent protection, electromagnetic interference resistance design, and network security measures ensure the safe operation of the inverter in various extreme environments, enable it to quickly respond to fault situations, prevent equipment damage or system failures, and enhance the reliability and security of the system.

[0043] The intelligent energy interconnection and scheduling module interconnects the inverter with distributed energy resources, energy storage systems, and the power grid through Internet of Things technology. Combining real-time electricity prices and energy supply and demand situations, it automatically schedules and optimizes energy distribution. This module not only improves the energy utilization efficiency but also reasonably schedules the energy storage system or adjusts the output power of the inverter during peak power system loads, helping to balance the grid load, reduce energy waste, and improve the economic benefits of energy.

[0044] Through the feedback control of distributed intelligent nodes and deep learning, the system can identify faults in real time and give early warnings. By adaptively adjusting the control strategy, it ensures that the inverter can quickly return to the normal operating state even in the event of faults or abnormal operating conditions. This intelligent fault diagnosis and self-healing ability greatly improves the fault tolerance and reliability of the system, reduces the need for manual intervention, and improves the operation and maintenance efficiency.

[0045] The modular design adopted by this system and the intelligent control platform based on a distributed architecture enable the system to have good scalability. With the development of technology and the change of requirements, new intelligent control algorithms, optimization models or devices can be seamlessly integrated into the system to ensure that the solution can adapt to the changes in future energy management technologies and has strong flexibility and adaptability.

[0046] In summary, through the intelligent control, optimization, scheduling and safety protection mechanisms, the present invention not only significantly improves the performance and efficiency of the inverter, but also provides guarantees for the efficient utilization of renewable energy, energy conservation and emission reduction, and the reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is the integrated intelligent control architecture diagram of the embodiment of the present invention;

[0049] Figure 2 It is the flow chart of the dynamic precise power management system of the embodiment of the present invention;

[0050] Figure 3 It is the intelligent feedback regulation network architecture diagram of the embodiment of the present invention;

[0051] Figure 4 It is the intelligent energy interconnection and scheduling module architecture diagram of the embodiment of the present invention;

[0052] Figure 5 It is the structure diagram of an inverter control system of the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0054] To make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0055] This embodiment solves this problem through an integrated intelligent control architecture and a dynamic and precise power management system. Through the collaborative work of a multi-core processor architecture, FPGA technology, and distributed intelligent nodes, the inverter can monitor key signals such as voltage and current in real time and respond quickly, ensuring that under the conditions of grid voltage fluctuations and load changes, it can accurately adjust the output power, reduce reactive power loss, and improve power quality. In addition, by introducing an intelligent feedback regulation network and deep learning technology, the system can adaptively adjust the operating conditions of the inverter and always maintain the best operating efficiency point under different load conditions, reducing energy loss. This intelligent control method effectively overcomes the problems of manual regulation and inefficient optimization in traditional technologies, can improve the working stability and adaptability of the inverter, and reduce the frequency of faults. Further, the innovative all-round safety protection architecture, covering multiple aspects such as electrical, electromagnetic compatibility, and network security, solves the deficiencies of traditional inverters in electrical protection and network security, ensuring the safety and reliability of the inverter in harsh environments. Through these innovations, the solution realizes a comprehensive improvement in the performance of the inverter, meets the requirements of high-efficiency, stable, and safe operation, and promotes the sustainable development of energy utilization.

[0056] As Figure 5 shown, an inverter control system provided in this embodiment includes: a distributed intelligent node, an intelligent control module, an intelligent feedback regulation module, an intelligent energy interconnection and scheduling module, and an intelligent energy efficiency evaluation and optimization module;

[0057] The distributed intelligent node is used to collect sensor data of the target component and obtain a fault signal, start or stop the inverter according to the sensor data, adjust the operating frequency, and transmit the fault signal to the main controller;

[0058] The intelligent control module is used to receive the sensor data collected by the distributed intelligent node, generate an optimal power control instruction according to the sensor data to control the inverter, and manage communication with external devices;

[0059] The intelligent feedback regulation module is used to fuse the sensor data, obtain the operating information of the inverter, and obtain an optimal control strategy according to the operating information of the inverter to control the inverter;

[0060] The intelligent energy interconnection and scheduling module is used to collect information of distributed energy, obtain a globally optimal energy scheduling strategy according to the information of the distributed energy, and control the inverter according to the globally optimal energy scheduling strategy;

[0061] The intelligent energy efficiency evaluation and optimization module is used to monitor the inverter, obtain the evaluation of the energy efficiency level of the inverter, and optimize the control parameters and operating mode of the inverter according to the evaluation results.

[0062] Furthermore, the intelligent control module includes a microprocessor and an FPGA;

[0063] The microprocessor includes a data receiving unit, a calculation unit, and a communication management unit. The data receiving unit is used to receive the sensor data collected by the distributed intelligent node. The calculation unit is used to obtain the voltage, current, and frequency data of the power grid, calculate the optimal power control instruction, and control the inverter. The communication management unit is used to perform data encryption and decryption and control the communication interface of external devices by using the FPGA;

[0064] The FPGA is used to generate a pulse width modulation signal to control the output voltage of the inverter, encrypt and decrypt the data exchanged between modules and stored, and control the communication interface with external devices.

[0065] Specifically, the microprocessor adopts a multi-core architecture, and each core is responsible for different tasks. These tasks are efficiently allocated and coordinated through a task scheduler. One core is responsible for data acquisition, another core focuses on the real-time calculation of control algorithms, and another core is used for processing communication management. This design can improve the system's parallel processing ability, reduce the waiting time between tasks, and ensure the efficient operation of the inverter under complex power grid conditions. The FPGA plays a crucial role in the architecture, especially in the high speed and accuracy of data processing.

[0066] Furthermore, calculating the optimal power control instruction and controlling the inverter includes:

[0067] Based on the instantaneous reactive power theory and space vector pulse width modulation technology, calculate the active power and reactive power of the inverter. Among them, the space vector pulse width modulation technology adopts a sector division method and a vector selection strategy;

[0068] According to the active power and reactive power of the inverter, combined with the voltage fluctuation, frequency change of the power grid, and the dynamic characteristics of the load, obtain the optimal power control instruction;

[0069] At the same time, adopt a power factor dynamic correction algorithm to adjust the output power factor of the inverter.

[0070] Furthermore, adjusting the output power factor of the inverter includes:

[0071] The power factor dynamic correction algorithm is based on the fuzzy control theory. According to the phase difference between the grid voltage and current and the magnitude of the reactive power, it adjusts the phase of the output current of the inverter to achieve the adjustment of the output power factor of the inverter.

[0072] Specifically, the power factor dynamic correction algorithm is based on the fuzzy control theory. According to the phase difference between the grid voltage and current and the magnitude of the reactive power, it dynamically adjusts the phase of the output current of the inverter to achieve fast and accurate correction of the power factor and effectively improve the power quality of the grid.

[0073] Furthermore, the sensor data is fused to obtain the inverter operation information, including:

[0074] The fusion algorithm based on Kalman filtering weights and fuses the sensor data to obtain the fused data;

[0075] The fused data is input into a pre-trained deep neural network to obtain the inverter operation information. The pre-trained deep neural network is constructed by combining a convolutional neural network and a recurrent neural network and is obtained by training with a training set. The training set includes historical fused data and the corresponding operating conditions and load types.

[0076] Specifically, the CNN is used to extract the spatial features of the sensor data, and the RNN is used to capture the time series features of the data. Through a large number of sample trainings, the adaptive feedback controller, i.e., the deep neural network, can automatically adapt to different operating conditions and load changes.

[0077] Furthermore, the intelligent energy interconnection and scheduling module includes a local energy management unit and a central coordination unit;

[0078] The local energy management unit is used to monitor and control the local distributed energy resources, energy storage systems, and inverters, collect energy production, storage, and consumption information, and upload it to the central coordination unit;

[0079] The central coordination unit is used to obtain the globally optimal energy scheduling strategy by using the mixed-integer linear programming algorithm according to the energy production, storage, consumption information, and electricity price information, and send it to each local energy management unit.

[0080] Specifically, in the energy scheduling process, the intermittent and volatile characteristics of distributed energy are fully considered. Through the charge and discharge regulation of the energy storage system and the power control of the inverter, the smooth output and efficient utilization of energy are achieved, the stability and reliability of the power system are improved, and the energy cost is reduced.

[0081] Furthermore, the intelligent energy efficiency evaluation and optimization module includes: an energy efficiency level evaluation unit and an optimization unit;

[0082] An energy efficiency level evaluation unit, which is used to evaluate the energy efficiency level according to the ratio of the input power and the output power of the inverter;

[0083] An optimization unit, which is used to optimize the combination of control parameters of the inverter by combining the genetic algorithm and the particle swarm optimization algorithm, and obtain whether the inverter reaches the best operating efficiency under different operating conditions in combination with the energy efficiency level evaluation unit, where the genetic algorithm is used for global optimization to search for the optimal solution of the inverter control parameters, and the particle swarm optimization algorithm is used for local optimization to adjust the control parameters.

[0084] Furthermore, the objective function for optimizing the combination of control parameters of the inverter by combining the genetic algorithm and the particle swarm optimization algorithm is:

[0085] f(x) = α·E(x) + β·H(x)

[0086] Where, f(x) is the objective function, x is the optimized solution of the control parameters, E(x) is the energy efficiency, H(x) is the harmonic distortion, and α and β are the weight coefficients of the energy efficiency and the harmonic distortion on the optimization result respectively.

[0087] Specifically, the purpose of the optimization function is to reduce the harmonic distortion while ensuring the maximum energy efficiency, thereby improving the power quality. The genetic algorithm and the particle swarm optimization algorithm finally find a solution that can minimize the energy loss and the harmonic distortion through continuous iterative calculations, so that the energy efficiency and the power quality of the inverter reach the optimal.

[0088] Further, the system further includes a safety protection module, and the safety protection module includes: an electrical safety protection unit, an overvoltage overcurrent protection unit, an electromagnetic compatibility protection unit, and a network security protection unit;

[0089] The electrical safety protection unit is used to monitor the leakage current in real time through a zero-sequence current transformer, and cut off the circuit when the current exceeds a predetermined threshold;

[0090] The overvoltage overcurrent protection unit is used to monitor the voltage and current in the circuit in real time through a sampling resistor and a fast comparator, and trigger a protection action when overvoltage or overcurrent occurs;

[0091] The electromagnetic compatibility protection unit is used to block external electromagnetic interference by using a multi-layer metal shielding material, and filter out interference signals by using a filter circuit combining a common-mode inductor and a differential-mode capacitor in the internal circuit;

[0092] The network security protection unit is used to encrypt data by using an encryption communication protocol combining AES and ECC

[0093] Specifically, the effective cooperation of the electrical safety protection circuit, electromagnetic compatibility design, and network security protection measures ensures that the inverter can operate safely and stably when facing potential threats in multiple aspects. These designs not only enhance the fault tolerance and stability of the system but also optimize the system's security and anti-interference capabilities, effectively protecting the long-term stable operation of the inverter and the power grid.

[0094] The following further describes the system of this embodiment with reference to the attached Figures 1-4 drawings:

[0095] This embodiment proposes an inverter control system. Its core lies in the coordinated operation of an integrated intelligent control architecture, a dynamic and precise power management system, an intelligent feedback regulation network, an all-round security protection architecture, and an intelligent energy interconnection and scheduling module, so as to achieve the efficient and stable operation of the inverter under complex grid conditions and the optimal utilization of energy. The specific operation steps are as follows:

[0096] The integrated intelligent control architecture integrates advanced microprocessors and programmable logic devices (FPGAs) to centrally monitor and manage the operating state of the inverter. By constructing a high-speed data bus and a distributed storage system, rapid acquisition, storage, and processing of parameters such as voltage, current, frequency, and phase are achieved. At the same time, distributed intelligent nodes are used to locally monitor and perform preliminary data processing on key components, reducing the burden on the main controller and improving the response speed and reliability of the system. The key components refer to the components in the inverter that are locally monitored and have preliminary data processed by distributed intelligent nodes, including but not limited to the components related to the detection by voltage sensors, current sensors, and temperature sensors, such as circuit elements and power devices involved in voltage and current transmission and heat generation. The dynamic and precise power management system is based on the instantaneous reactive power theory and space vector pulse width modulation (SVPWM) technology to accurately calculate the active power and reactive power requirements of the inverter and generate optimal power control commands in real time according to the voltage fluctuations, frequency changes of the power grid, and the dynamic characteristics of the load. During the control process, a power factor dynamic correction algorithm is introduced to automatically adjust the output power factor of the inverter to meet the requirements of the power grid for power quality, reduce the transmission loss of reactive power, and improve the efficiency of the power system. As Figure 2 shown, it is the flowchart of the dynamic and precise power management system.

[0097] The intelligent feedback regulation network uses multi-sensor fusion technology to fuse the data of voltage sensors, current sensors, temperature sensors, and power sensors, obtaining more comprehensive and accurate inverter operation information. By constructing an adaptive feedback controller based on deep learning, using a deep neural network to learn and train a large amount of operation data, automatically identifying different operation conditions and load types, and dynamically adjusting the feedback control strategy to ensure that the output voltage and current of the inverter are stable and meet the preset standards, effectively improving the adaptability and control accuracy of the system. As Figure 3 shown, it is the architecture diagram of the intelligent feedback regulation network.

[0098] The all-round safety protection architecture covers multiple aspects such as electrical safety protection, electromagnetic compatibility protection, and network security protection. In terms of electrical safety, multiple protection mechanisms such as leakage protection, ground fault protection, and overvoltage and overcurrent protection are adopted. Through the coordinated work of the hardware protection circuit and the intelligent monitoring software, electrical faults are detected and processed in real time. In terms of electromagnetic compatibility protection, a special shielding structure and filtering circuit are designed to reduce the electromagnetic interference of the inverter to the outside world and improve its own anti-interference ability at the same time. In terms of network security, encrypted communication protocols, firewall technology, and intrusion detection systems are adopted to prevent network attacks and malicious tampering of control instructions, ensuring the safe and stable operation of the inverter.

[0099] The intelligent energy interconnection and scheduling module uses Internet of Things technology to achieve interconnection between the inverter and distributed energy resources (solar energy, wind energy, etc.), energy storage systems, and the power grid. By establishing an energy management system (EMS), based on real-time energy supply and demand information and electricity price fluctuations, using optimization algorithms to formulate the optimal energy scheduling strategy, realizing the efficient allocation and utilization of energy. For example, when renewable energy is sufficient and the electricity price is low, the excess electric energy is preferentially stored in the energy storage system; when the power grid load is at a peak or renewable energy is insufficient, the energy storage system is reasonably scheduled to discharge or the output power of the inverter is adjusted to maintain the supply and demand balance of the power system and improve energy utilization efficiency and economic benefits. As Figure 4 shown, it is the architecture diagram of the intelligent energy interconnection and scheduling module.

[0100] In the integrated intelligent control architecture, the microprocessor adopts a multi-core architecture, where each core is responsible for different tasks, and these tasks are efficiently allocated and coordinated through a task scheduler. Specifically, one core is responsible for data acquisition, which refers to receiving data from various sensors such as voltage, current, temperature, power, etc. Another core focuses on the real-time calculation of control algorithms, which refer to the relevant algorithms based on the instantaneous reactive power theory and space vector pulse width modulation (SVPWM) technology. Through this algorithm, the active power and reactive power of the inverter are calculated, and the optimal power control command is obtained by combining the voltage fluctuation, frequency change of the power grid and the dynamic characteristics of the load. At the same time, the power factor dynamic correction algorithm is used to adjust the output power factor. Another core is used to handle communication management, which is the responsibility of a core of the microprocessor. It uses FPGA for data encryption and decryption and communication interface control with external devices to achieve data interaction with distributed intelligent nodes and other modules (intelligent feedback regulation module, intelligent energy interconnection and scheduling module, and intelligent energy efficiency evaluation and optimization module), ensuring the stable operation of the system. And the task scheduler allocates computing resources for these operations according to the task priority, improving the system response speed and stability. This design can improve the system's parallel processing ability, reduce the waiting time between tasks, and ensure the efficient operation of the inverter under complex grid conditions. After receiving the sensor data, the microprocessor first performs preprocessing, screening, and data formatting, and transmits the collected data to the high-speed bus for further processing. During this process, the task scheduler allocates corresponding computing resources according to the priority of each task, thus maximizing the system response speed and stability. For example, in the power control part of the inverter, the algorithm needs to obtain the voltage, current, and frequency data of the power grid in real time, calculate the optimal control command, and then send it to the execution module through the control core of the microprocessor. FPGA plays a crucial role in the architecture, especially in the high speed and accuracy of data processing. FPGA is used for the generation of pulse width modulation (PWM) signals, data encryption and decryption, and communication interface control with external devices. Among them, the optimal power control command obtained by the microprocessor is used to control the inverter, while the pulse width modulation (PWM) signal generated by FPGA controls the output voltage quality of the inverter, thereby affecting the power regulation effect. The two work together on the power control of the inverter; the data in data encryption and decryption refers to various information exchanged and stored among modules during system operation; the communication function of the microprocessor focuses on overall communication management and coordination, and the external device communication interface control of FPGA here is more focused on high-speed and accurate data interaction with external devices.

[0101] PWM signal generation is a crucial part of inverter control. By leveraging the parallel processing capabilities of the hardware circuit, the FPGA can generate high-frequency PWM signals in real time and interact with other modules (such as distributed intelligent nodes, microprocessors in intelligent control modules, intelligent feedback regulation modules, intelligent energy interconnection and scheduling modules, intelligent energy efficiency evaluation and optimization modules, and safety protection modules in the inverter control system) through high-speed interfaces, controlling the output voltage quality of the inverter and thus affecting the power regulation effect. Specifically, the generation of PWM signals follows the following formula:

[0102]

[0103] where, V out (t) is the output voltage of the inverter, V dc is the DC voltage, ω is the angular frequency, t is the time, and θ is the phase. This formula reflects the law of the inverter output voltage changing with time. By adjusting the frequency and duty cycle of the PWM, the FPGA can control the quality of the output voltage and thus affect the power regulation effect. The hardware circuit of the FPGA can complete this calculation at a very high speed and accurately output the corresponding signal, avoiding system instability caused by processing delays.

[0104] In the distributed intelligent node part, the low-power microcontroller and sensor integration module undertakes the tasks of local data processing and fault diagnosis. These intelligent nodes can promptly feedback to the main controller when receiving abnormal signals, ensuring that faults can be quickly located and processed. Each distributed node is equipped with a set of basic sensors (such as voltage, current, temperature, etc.) and conducts preliminary diagnosis in combination with local simple algorithms (such as threshold-based algorithms). If the node detects an abnormality, it will transmit the fault signal to the main controller through a preset communication protocol. At the same time, the node can also perform simple local control operations, such as starting or stopping the operation of the inverter and adjusting the operating frequency. This design can effectively reduce the burden on the main controller and make the system have higher fault tolerance and robustness.

[0105] The above-mentioned modules work together, utilizing the parallel computing capabilities of the microprocessor, the high-speed data processing function of the FPGA, and the local intelligent decision-making of the distributed nodes to form an integrated intelligent architecture of the inverter control system. Through these means, not only can the stability of the system under complex grid conditions be ensured, but also the energy efficiency can be improved and the risk of system failures can be reduced. As Figure 1 shown, it is the diagram of the integrated intelligent control architecture.

[0106] The instantaneous reactive power theory algorithm in the dynamic and precise power management system combines the adaptive filter and wavelet transform technologies, which can extract the reactive components in the grid voltage and current more accurately, improve the accuracy of reactive power calculation. Specifically, first, the wavelet transform is used to decompose the grid voltage / current signal in the time-frequency domain to separate the reactive components of different frequency components; then, the adaptive filter is used to track the grid frequency fluctuation in real time and dynamically adjust the filter parameters to filter out the noise interference; finally, based on the instantaneous reactive power theory framework, combined with the high-frequency reactive components after wavelet decomposition and the fundamental wave signal after adaptive filtering, the accurate extraction of reactive power under complex working conditions is realized. In terms of space vector pulse width modulation technology, a new sector division method and vector selection strategy are adopted, which reduces the switching times of power devices, reduces the switching loss, and improves the waveform quality of the inverter output voltage at the same time. The power factor dynamic correction algorithm is based on the fuzzy control theory. According to the phase difference between the grid voltage and current and the magnitude of the reactive power, it dynamically adjusts the phase of the inverter output current to achieve fast and accurate correction of the power factor and effectively improve the power quality of the grid.

[0107] Specifically, based on the fuzzy control theory, dynamically adjusting the phase of the inverter output current according to the phase difference between the grid voltage and current and the magnitude of the reactive power includes:

[0108] Define the input variables: voltage phase difference (ΔV): the phase difference between grid voltages, current phase difference (ΔI): the phase difference between currents, reactive power (Q).

[0109] Define the output variable: current phase adjustment (Δθ): the amount by which the phase of the inverter output current needs to be adjusted.

[0110] Based on experience or expert knowledge, design fuzzy rules;

[0111] For each input variable, define fuzzy sets;

[0112] Use the fuzzy rules for reasoning to determine the fuzzy set of the output variable according to the fuzzy sets of the input variables;

[0113] Convert the result of the fuzzy reasoning into an exact value. This is usually achieved through a defuzzification method;

[0114] Apply the defuzzified phase adjustment value to the inverter to adjust the phase of its output current.

[0115] The multi-sensor fusion technology in the intelligent feedback regulation network adopts a fusion algorithm based on Kalman filtering to perform weighted fusion on the data of different sensors, making full use of the advantages of each sensor to improve the accuracy and reliability of the data. The fusion algorithm based on Kalman filtering is an algorithm for weighted fusion of data from different sensors. Through the prediction and update processes, it uses the estimated value at the previous moment and the measured value at the current moment to continuously optimize the fused data, so as to make full use of the advantages of each sensor and improve the accuracy and reliability of the data, which is used for multi-sensor data processing in the intelligent feedback regulation network. The adaptive feedback controller of deep learning adopts an architecture that combines a convolutional neural network (CNN) and a recurrent neural network (RNN). The CNN is used to extract the spatial features of the sensor data, and the RNN is used to capture the time series features of the data. Through a large number of sample trainings, the controller can automatically adapt to different operating conditions and load changes. During the control strategy adjustment process, a reinforcement learning algorithm is used to evaluate and optimize different control strategies, and the optimal control strategy is selected and applied to the inverter control, effectively improving the control performance and stability of the system.

[0116] In the all-round safety protection architecture, the design of the electrical safety protection circuit uses an intelligent leakage protection relay and a high-precision overvoltage and overcurrent protection chip to further improve the reliability and safety of the system. The working principle of the leakage protection relay is to continuously monitor the leakage current through a zero-sequence current transformer. When the current exceeds a predetermined threshold, the circuit is quickly cut off. The detection of the leakage current can be calculated by the following formula:

[0117]

[0118] where, I leak is the leakage current, I line is the line current, I neutral is the neutral line current, and θ is the phase difference between the currents. This formula calculates the difference between the line current and the neutral line current through a zero-sequence current transformer, and then estimates the leakage current. When the leakage current exceeds the preset safety threshold, the protection relay will immediately trigger the circuit cut-off action to avoid electrical fires or electric shock accidents, and at the same time send an alarm message to the monitoring center through a wireless communication module to ensure timely response.

[0119] The function of the overvoltage and overcurrent protection chip is to continuously monitor the voltage and current in the circuit through a high-precision sampling resistor and a fast comparator. When overvoltage or overcurrent occurs, it can trigger a protection action within microseconds. When the chip quickly detects the voltage and current values and performs overvoltage and overcurrent protection, the basic formula used is:

[0120] P max =V max I max

[0121] Among them, P max is the maximum power of the system, V max is the maximum voltage, and I max is the maximum current. When the current or voltage exceeds the predetermined safety value, the protection chip will trigger power-off protection in real time to avoid damage to the device due to overvoltage and overcurrent.

[0122] In terms of electromagnetic compatibility protection, the system uses multi-layer metal shielding materials to block external electromagnetic interference, and a filtering circuit combining common-mode inductors and differential-mode capacitors is used in the internal circuit to effectively filter out interference signals. This design can not only improve the system's resistance to external electromagnetic interference but also reduce the pollution of the inverter itself to the external electromagnetic environment. In the electromagnetic shielding layer, the electromagnetic blocking ability of each layer of shielding material can be estimated by the following formula:

[0123]

[0124] Among them, Z shield is the impedance of the shielding material, μ is the magnetic permeability of the material, σ is the conductivity of the material, d outer and d inner are the distances outside and inside the shielding layer respectively. By reasonably selecting the shielding material and designing the number of layers, electromagnetic interference can be effectively reduced, and the operating stability of the inverter in a complex electromagnetic environment can be improved.

[0125] In terms of network security, the system adopts an encryption communication protocol combining AES and ECC to ensure the security and integrity of data transmission. AES encryption is used to encrypt the data content, while ECC is used to encrypt the communication key exchange process. Through this combination method, not only the confidentiality of data transmission is enhanced, but also the security of the key exchange process is ensured. The firewall technology in network security protection uses a stateful inspection-based firewall to effectively prevent external malicious attacks by monitoring and analyzing network traffic in real time. The network intrusion detection system analyzes network traffic in real time through deep learning algorithms to identify potential attack patterns. When the system detects abnormal data streams, it will automatically trigger an alarm and block malicious connections to ensure that the inverter is not attacked or tampered with externally.

[0126] Overall, the effective cooperation of the electrical safety protection circuit, electromagnetic compatibility design, and network security protection measures ensures that the inverter can still operate safely and stably when facing potential threats in multiple aspects. These designs not only enhance the system's fault tolerance and stability but also optimize the system's security and anti-interference capabilities, effectively protecting the long-term stable operation of the inverter and the power grid.

[0127] The Energy Management System (EMS) in the intelligent energy interconnection and scheduling module adopts a distributed architecture, consisting of multiple local energy management units and a central coordination unit. The local energy management units are responsible for monitoring and controlling the local distributed energy resources, energy storage systems, and inverters, collecting information on energy production, storage, and consumption, and uploading this information to the central coordination unit. The central coordination unit formulates a globally optimal energy scheduling strategy using the Mixed-Integer Linear Programming (MILP) algorithm based on the energy production, storage, consumption information, and electricity price information, and issues control instructions to each local energy management unit for execution to control the inverter power, achieve efficient energy utilization, and stabilize the power system. During the energy scheduling process, the intermittent and fluctuating characteristics of distributed energy are fully considered, and through the charge and discharge regulation of the energy storage system and the power control of the inverter, smooth output and efficient utilization of energy are achieved, the stability and reliability of the power system are improved, and the energy cost is reduced.

[0128] This system also includes an intelligent energy efficiency evaluation and optimization module. By real-time monitoring and analyzing parameters such as the input and output power, energy conversion efficiency, and harmonic distortion of the inverter, it calculates the energy efficiency level of the inverter using an energy efficiency evaluation model. At the same time, an optimization method combining genetic algorithms and particle swarm optimization algorithms is adopted to optimize and adjust the control parameters and operating modes of the inverter to improve the energy conversion efficiency and power quality of the inverter. For example, under different load conditions, it automatically adjusts the switching frequency and modulation ratio of the inverter to make the inverter operate near the optimal efficiency point, reduce energy losses, and achieve the goals of sustainable energy utilization and energy conservation and emission reduction. The optimal control instructions calculated by the microprocessor are based on grid data and theoretical technologies, focusing on power control; the optimal control strategy of intelligent feedback regulation is adaptively adjusted through multi-sensor fusion and deep learning; the optimized inverter control parameters obtained here use genetic and particle swarm algorithms to optimize parameters such as switching frequency and modulation ratio from the perspective of energy efficiency, improving energy conversion efficiency and power quality.

[0129] The core function of the intelligent energy efficiency evaluation and optimization module is to evaluate the energy efficiency performance of the inverter through real-time monitoring and analysis, and perform dynamic optimization based on the evaluation results to achieve the goals of efficient energy conversion and energy conservation and emission reduction. This module first comprehensively evaluates the operating performance of the inverter by collecting key parameters such as the input and output power, energy conversion efficiency, and harmonic distortion of the inverter. The energy efficiency evaluation model calculates the energy efficiency level based on the ratio of input power to output power, and the calculation formula for the energy efficiency level is:

[0130]

[0131] Among them, η is the energy efficiency level, P out . is the output power of the inverter, P inis the input power of the inverter. Through this formula, the system can monitor the energy efficiency level of the inverter in real time. When the ratio of the output power to the input power reaches the maximum, the operating efficiency of the inverter is in the best state. This evaluation model can help the system determine whether the inverter reaches the best operating efficiency under different operating conditions and provide a basis for subsequent optimization and adjustment.

[0132] The optimization process combines the genetic algorithm (GA) and the particle swarm optimization algorithm (PSO). Each of them has its own advantages in global search and local search, and they can complement and cooperate with each other to effectively improve the operating efficiency of the inverter. In the optimization process, the genetic algorithm is mainly used for global optimization to search for the optimal solution of the inverter control parameters; the particle swarm optimization algorithm is used for local optimization to refine and adjust the control parameters to ensure the stable performance of the inverter under different load conditions. The optimization of the control parameters includes the adjustment of the switching frequency and the modulation ratio. These two parameters directly affect the efficiency and power quality of the inverter. Especially when the load fluctuates, precise adjustment can avoid excessive energy loss and ensure that the inverter operates at a state close to the best efficiency point. The combination of the fitness function in the genetic algorithm and the objective function in the particle swarm optimization algorithm, the optimization process can be expressed as:

[0133] f(x) = α·E(x) + β·H(x).

[0134] Among them, f(x) is the objective function, x is the optimal solution of the control parameters, E(x) is the energy efficiency, H(x) is the harmonic distortion, and α and β are the weight coefficients of the energy efficiency and the harmonic distortion on the optimization result respectively. The purpose of this optimization function is to reduce the harmonic distortion while ensuring the maximum energy efficiency, thereby improving the power quality. The genetic algorithm and the particle swarm optimization algorithm finally find an optimal solution that can minimize the energy loss and the harmonic distortion through continuous iterative calculations, so that the energy efficiency and the power quality of the inverter reach the best.

[0135] By combining the energy efficiency evaluation model with the genetic algorithm and the particle swarm optimization algorithm, the system can not only evaluate the operating state of the inverter in real time, but also dynamically adjust the control strategy of the inverter according to the real-time load changes, so that it can maintain a high operating efficiency and low energy loss under different load conditions. This optimization scheme effectively improves the overall performance of the inverter, helps to achieve the goals of sustainable energy utilization, energy conservation and emission reduction, and promotes the wide application of green energy.

[0136] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An inverter control system, characterized in that: include: Distributed intelligent nodes, intelligent control modules, intelligent feedback regulation modules, intelligent energy interconnection and scheduling modules, intelligent energy efficiency evaluation and optimization modules; The distributed intelligent node is used to collect sensor data of the target component and obtain a fault signal, start or stop the inverter and adjust the operating frequency according to the sensor data, and transmit the fault signal to the main controller; The intelligent control module is used to receive the sensor data collected by the distributed intelligent node, generate optimal power control instructions to control the inverter according to the sensor data, and manage the communication with external devices; The intelligent feedback adjustment module is used to fuse the sensor data, obtain the inverter operation information, and obtain the optimal control strategy according to the inverter operation information to control the inverter; The smart energy interconnection and scheduling module is used to collect information about distributed energy, obtain a global optimal energy scheduling strategy based on the information about the distributed energy, and control the inverter based on the global optimal energy scheduling strategy; The intelligent energy efficiency evaluation and optimization module is used to monitor the inverter, obtain an evaluation of the energy efficiency level of the inverter, and optimize the control parameters and operation mode of the inverter according to the evaluation result.

2. The inverter control system according to claim 1, characterized in that: The intelligent control module includes a microprocessor and an FPGA; The microprocessor includes a data receiving unit, a computing unit and a communication management unit, wherein the data receiving unit is used to receive the sensor data collected by the distributed intelligent node, the computing unit is used to obtain the voltage, current and frequency data of the power grid, calculate the optimal power control instruction, and control the inverter, and the communication management unit is used to use the FPGA to encrypt and decrypt data and control the communication interface of the external device; The FPGA is used to generate a pulse width modulation signal to control the inverter output voltage, encrypt and decrypt the data interacting and stored between the modules, and control the communication interface with the external device.

3. The inverter control system according to claim 2, characterized in that: Calculating the optimal power control instruction and generating the optimal power control instruction to control the inverter includes: Based on instantaneous reactive power theory and space vector pulse width modulation technology, active power and reactive power of the inverter are calculated, wherein the space vector pulse width modulation technology adopts a sector division method and a vector selection strategy; According to the active power and reactive power of the inverter, combined with the voltage fluctuation and frequency change of the power grid and the dynamic characteristics of the load, the optimal power control instruction is obtained; At the same time, a power factor dynamic correction algorithm is adopted to adjust the output power factor of the inverter.

4. The inverter control system according to claim 3, characterized in that: The output power factor of the inverter is adjusted by using a dynamic power factor correction algorithm, including: The power factor dynamic correction algorithm is based on fuzzy control theory, and adjusts the output current phase of the inverter according to the grid voltage, current phase difference and reactive power, so as to adjust the output power factor of the inverter.

5. The inverter control system according to claim 1, characterized in that: Fusing the sensor data to obtain the inverter operation information includes: The sensor data is weightedly fused based on a fusion algorithm of Kalman filtering to obtain fused data; The fused data is input into a pre-trained deep neural network to obtain the inverter operation information, wherein the pre-trained deep neural network is constructed based on a combination of a convolutional neural network and a recursive neural network and is obtained by training with a training set, and the training set includes historical fused data and corresponding operating conditions and load types.

6. The inverter control system according to claim 1, characterized in that: The intelligent energy interconnection and dispatching module includes a local energy management unit and a central coordination unit; The local energy management unit is used to monitor and control local distributed energy resources, energy storage systems and inverters, collect energy production, storage and consumption information and upload it to the central coordination unit; The central coordination unit is used to obtain the global optimal energy scheduling strategy based on energy production, storage, consumption information and electricity price information using a mixed integer linear programming algorithm, and send it to each of the local energy management units to control the inverter power.

7. The inverter control system according to claim 1, characterized in that: The intelligent energy efficiency evaluation and optimization module includes: an energy efficiency level evaluation unit and an optimization unit; The energy efficiency rating evaluation unit is used to evaluate the energy efficiency rating according to the ratio of the input power to the output power of the inverter; The optimization unit is used to optimize the control parameter combination of the inverter in combination with the genetic algorithm and the particle swarm optimization algorithm, and to determine whether the inverter has achieved the best operating efficiency under different operating conditions in combination with the energy efficiency rating evaluation unit, wherein the genetic algorithm is used for global optimization to search for the optimal solution of the inverter control parameters, and the particle swarm optimization algorithm is used for local optimization to adjust the control parameters.

8. The inverter control system according to claim 7, characterized in that: The objective function of optimizing the control parameter combination of the inverter by combining the genetic algorithm and the particle swarm optimization algorithm is: f(x)=α·E(x)+β·H(x) Among them, f(x) is the objective function, x is the optimized solution of the control parameters, E(x) is the energy efficiency, H(x) is the harmonic distortion, and α and β are the weight coefficients of energy efficiency and harmonic distortion on the optimization result, respectively.

9. The inverter control system according to claim 1, characterized in that: The system further comprises a safety protection module, which comprises: an electrical safety protection unit, an overvoltage and overcurrent protection unit, an electromagnetic compatibility protection unit and a network security protection unit; The electrical safety protection unit is used to monitor the leakage current in real time through the zero-sequence current transformer and cut off the circuit when the current exceeds a predetermined threshold; The overvoltage and overcurrent protection unit is used to monitor the voltage and current in the circuit in real time through a sampling resistor and a fast comparator, and trigger a protection action when overvoltage or overcurrent occurs; The electromagnetic compatibility protection unit is used to block external electromagnetic interference by using multi-layer metal shielding materials, and to filter out interference signals by using a filter circuit composed of a common-mode inductor and a differential-mode capacitor in an internal circuit; The network security protection unit is used to encrypt the control instructions and monitoring data transmitted between modules during system operation by using an encryption communication protocol combining AES and ECC.

Images