Modular electrical cabinet system with multiple protections and high energy efficiency

Abstract

The present invention provides a modular electrical cabinet system with multiple protections and high efficiency energy saving, which relates to the field of system control technology, including an electrical module, a protection module, an energy management module, a diagnosis and prediction module, and an adaptive scheduling module. The fault prediction module based on deep learning analyzes these data to accurately predict potential faults and generate maintenance alarms to prevent faults from occurring in advance. The AI ​​fault self-diagnosis module further automatically diagnoses the fault type and provides specific repair suggestions, thereby improving the accuracy and timeliness of fault handling. The predictive maintenance module combines historical data and prediction algorithms to formulate maintenance plans in advance, reducing the incidence of sudden failures and maintenance costs. Through these intelligent means, the system can not only achieve self-monitoring and self-repair, improve maintenance efficiency, but also extend the service life of the electrical cabinet.

Description

Technical Field

[0001] The present invention relates to the technical field of system control, and in particular to a modular electrical cabinet system with multiple protections and high efficiency energy saving. Background Art

[0002] According to the electrical cabinet fault monitoring system disclosed in Chinese Patent Publication No. "CN118795249A", it includes an environmental detection component, a controller and an environmental adjustment component arranged in the electrical cabinet; the environmental detection component is electrically connected to the controller and is used to collect target environmental parameters in the electrical cabinet; the target environmental parameters are used to compare with corresponding threshold parameters in a database to determine the current environmental state in the electrical cabinet; if the current environmental state is an abnormal state, the controller executes a corresponding abnormal maintenance strategy; the abnormal maintenance strategy includes: controlling the environmental adjustment component to execute target adjustment control, and / or issuing an alarm prompt for maintenance of the environmental adjustment component.

[0003] The existing electrical cabinet system was not adequate for energy management and therefore required technical improvements. Summary of the invention

[0004] Technical issues solved In view of the deficiencies of the prior art, the present invention provides a modular electrical cabinet system with multiple protections and high efficiency and energy saving.

[0005] Technical Solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a modular electrical cabinet system with multiple protections and high efficiency energy saving, comprising the following parts: Electrical module, used to complete the basic operation of the electrical cabinet; Protection module, used to provide short circuit protection, overload protection, and lightning protection for electrical components inside the electrical cabinet; Energy management module, which is used to intelligently schedule energy distribution in electrical cabinets and improve energy efficiency by dynamically adjusting loads, enabling backup power or cooling systems; Diagnostic prediction module, used to monitor the operating status of each module in the electrical cabinet in real time and predict potential faults; The adaptive scheduling module is used to dynamically adjust the working mode of each electrical module according to the real-time load and operating status.

[0007] Preferably, the energy management module further comprises: Load regulation module, used to automatically adjust the power distribution of each module in the electrical cabinet according to real-time monitored load information, environmental factors and power demand; The energy-saving adjustment module is used to dynamically adjust the working mode of the electrical cabinet according to real-time data.

[0008] Preferably, the diagnosis prediction module further comprises: A multi-dimensional sensor network for real-time monitoring of the operating status of each module in the electrical cabinet, including temperature, humidity, current, voltage and vibration data; A deep learning-based fault prediction module that processes data from a multi-dimensional sensor network to predict potential faults and generate maintenance alerts; The predictive maintenance module is used to predict possible failures based on historical data and prediction algorithms, and automatically adjust the operating parameters of the electrical cabinet to reduce the occurrence of failures.

[0009] Preferably, the diagnosis prediction module further comprises: An adaptive repair module configured to automatically adjust load distribution, power regulation or enable standby modules in the electrical cabinet according to the fault prediction results, so as to proactively perform repairs and ensure continuous operation of the system; The self-healing feedback module is used to reduce the possibility of failure by automatically adjusting the current, temperature or enabling the backup module to adjust the load when an abnormal operation of a module in the electrical cabinet is detected, and continuously adjust the self-healing strategy through the reinforcement learning algorithm.

[0010] Preferably, the energy management module further includes: The blockchain module is used to record data such as energy usage, maintenance records, and load adjustment inside the electrical cabinet; the blockchain module is used to save energy usage data and maintenance records, and cannot be tampered with.

[0011] Preferably, the energy management module further comprises: The power switching module is used to dynamically select grid power, local energy storage or renewable energy for power supply according to the load demand of the electrical cabinet and the external power market price; the power switching module makes the best selection of power source through a neural algorithm.

[0012] Preferably, the diagnosis prediction module further comprises: The artificial intelligence-based fault self-diagnosis module is used to automatically diagnose faults according to the operating status of each module in the electrical cabinet, and dynamically adjust the load distribution in the electrical cabinet according to the real-time data of equipment operation.

[0013] Preferably, the adaptive scheduling module further comprises: The module virtualization module is configured to virtualize the resources of each electrical module and reconfigure it in real time according to demand, so that the module can perform different functions at different time periods.

[0014] Preferably, the protection module further comprises: The multi-level protection module is used for overload protection, short circuit protection, overvoltage protection, and overheat protection of the internal components of the electrical cabinet; the multi-level protection module monitors the working status of each module through an intelligent algorithm, and when an abnormality occurs, the multi-level protection module is automatically enabled and an alarm is issued; The automatic recovery module automatically switches to the backup module or performs load adjustment when a short circuit, overload or other fault occurs inside the electrical cabinet. The intelligent control system adjusts the working state inside the electrical cabinet after detecting the fault.

[0015] Preferably, the energy management module further comprises: Distributed energy coordination module, which is used to realize energy sharing or trading with other devices in the electrical cabinet and exchange energy through the blockchain platform; Adaptive demand response module, which adjusts the load demand in the electrical cabinet according to the real-time price of the external power market and the grid load condition; Microgrid control module for coordination of electrical cabinets with external renewable energy sources.

[0016] Beneficial Effects

[0017] The present invention provides a modular electrical cabinet system with multiple protections and high energy efficiency. It has the following beneficial effects: 1. The present invention adopts a diagnostic prediction module through a multidimensional sensor network, a fault prediction module based on deep learning, an AI fault self-diagnosis module and a predictive maintenance module to realize comprehensive intelligent monitoring and maintenance management of the electrical cabinet system. The multidimensional sensor network collects multidimensional data such as temperature, humidity, current, voltage and vibration in real time to provide the system with comprehensive operating status information. The fault prediction module based on deep learning accurately predicts potential faults and generates maintenance alarms by analyzing these data to prevent faults from occurring in advance. The AI ​​fault self-diagnosis module further automatically diagnoses the fault type and provides specific repair suggestions, thereby improving the accuracy and timeliness of fault handling. The predictive maintenance module combines historical data and prediction algorithms to formulate maintenance plans in advance, reducing the incidence of sudden faults and maintenance costs. Through these intelligent means, the system can not only achieve self-monitoring and self-repair, improve maintenance efficiency, but also extend the service life of the electrical cabinet, reduce human intervention and investment in maintenance resources, and significantly improve overall operational efficiency.

[0018] 2. The present invention realizes intelligent management and optimized distribution of energy inside the electrical cabinet by integrating load adjustment module, energy-saving adjustment module, power switching module, distributed energy coordination module and adaptive demand response module. Specifically, the load adjustment module automatically adjusts the power distribution of each module according to the real-time monitored load information and environmental factors to avoid energy waste; the energy-saving adjustment module effectively reduces the overall power consumption by dynamically adjusting the working mode, such as reducing the operating frequency of the equipment or shutting down unnecessary loads. The power switching module uses a neural network algorithm to intelligently select the optimal power source (grid power, local energy storage or renewable energy) according to the power market price and system load requirements, further reducing energy costs and improving system efficiency. In addition, the distributed energy coordination module realizes energy sharing and trading with other electrical cabinets or energy equipment through the blockchain platform, which improves the overall energy utilization efficiency. Combining these technical means, the system can significantly optimize energy use, reduce operating costs, achieve high efficiency and energy saving, and conform to the development trend of green environmental protection.

[0019] 3. The present invention realizes comprehensive protection of the internal components of the electrical cabinet through a multi-level protection module and an automatic recovery module, including multiple protection measures such as overload protection, short circuit protection, overvoltage protection and overheat protection. Specifically, the multi-level protection module uses high-sensitivity sensors and intelligent algorithms to monitor the working status of each electrical module in real time, and can quickly take corresponding protection measures when an abnormal situation occurs, such as disconnecting the faulty circuit or adjusting the load distribution to prevent the fault from expanding and equipment damage. At the same time, after detecting a fault, the automatic recovery module can switch to a backup module or dynamically adjust the load to achieve rapid recovery of the system, greatly reducing the system's downtime and maintenance costs. This multi-level protection mechanism not only improves the overall safety of the electrical cabinet, but also enhances the reliability of the system in the face of various electrical faults, ensuring the continuity of key equipment and operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a system composition diagram of the present invention; Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment 1

[0023] As shown in the figure, the modular electrical cabinet system with multiple protections and high energy efficiency includes the following parts: Electrical module, used to complete the basic operation of the electrical cabinet; The protection module is used to provide short-circuit protection, overload protection, and lightning protection for the electrical components inside the electrical cabinet; the protection module further includes: a multi-level protection module for overload protection, short-circuit protection, overvoltage protection, and overheat protection of the components inside the electrical cabinet; the multi-level protection module monitors the working status of each module through an intelligent algorithm, and when an abnormality occurs, the multi-level protection module is automatically enabled and an alarm is issued; the automatic recovery module automatically switches to a backup module or performs load adjustment when a short circuit, overload, or other fault occurs inside the electrical cabinet, and adjusts the working status inside the electrical cabinet through an intelligent control system after detecting the fault The energy management module is used to intelligently dispatch the energy distribution in the electrical cabinet and improve the energy-saving efficiency by dynamically adjusting the load, enabling the backup power supply or the cooling system. The energy management module further includes: a load adjustment module, which is used to automatically adjust the power distribution of each module in the electrical cabinet according to the real-time monitored load information, environmental factors and power demand; an energy-saving adjustment module, which is used to dynamically adjust the working mode of the electrical cabinet according to real-time data; a power switching module, which is used to dynamically select grid power, local energy storage or renewable energy for power supply according to the load demand of the electrical cabinet and the external power market price; the power switching module makes the best selection of the power source through a neural algorithm; the energy management module also includes: a blockchain module, which is used to record the energy usage, maintenance records and load adjustment data inside the electrical cabinet; the blockchain module is used to save energy usage data and maintenance records, and cannot be tampered with; a distributed energy coordination module, which is used to realize energy sharing or trading with other equipment in the electrical cabinet and exchange energy through the blockchain platform; an adaptive demand response module, which adjusts the load demand in the electrical cabinet according to the real-time price of the external power market and the grid load status; a microgrid control module, which is used to coordinate the electrical cabinet with external renewable energy; The diagnostic prediction module is used to monitor the operating status of each module in the electrical cabinet in real time and predict potential faults; the diagnostic prediction module further includes an artificial intelligence-based fault self-diagnosis module, which is used to automatically diagnose faults according to the operating status of each module in the electrical cabinet, and dynamically adjust the load distribution in the electrical cabinet according to the real-time data of equipment operation; a multi-dimensional sensor network is used to monitor the operating status of each module in the electrical cabinet in real time, including temperature, humidity, current, voltage and vibration data; a deep learning-based fault prediction module is used to process data from the multi-dimensional sensor network, predict potential faults and generate maintenance alerts; a predictive maintenance module is used to prejudge possible faults based on historical data and prediction algorithms, and automatically adjust the operating parameters of the electrical cabinet to reduce the occurrence of faults. An adaptive repair module is configured to automatically adjust the load distribution, power regulation or enable the backup module in the electrical cabinet according to the fault prediction results, so as to actively perform repairs and ensure the continuous operation of the system; a self-healing feedback module is used to reduce the possibility of faults by automatically adjusting the current, temperature or enabling the backup module when an abnormal operation of a module in the electrical cabinet is detected, and continuously adjust the self-healing strategy through the reinforcement learning algorithm; The adaptive scheduling module is used to dynamically adjust the working mode of each electrical module according to the real-time load and operating status. The adaptive scheduling module further includes a module virtualization module, which is configured to virtualize the resources of each electrical module and reconfigure them in real time according to demand, so that the modules can perform different functions at different time periods.

[0024] Power management unit: including high-efficiency transformer, power distributor, power filter, used to stabilize power supply and distribute power to each load; load distribution unit: using intelligent circuit breaker and intelligent relay to achieve dynamic load distribution and control; communication interface: equipped with industrial Ethernet port (including Ethernet / IP, Profinet), supporting high-speed data transmission and communication between modules. As the core of the system, the electrical module is responsible for the distribution and management of power. Each electrical module exchanges data and transmits instructions with the protection module, energy management module and diagnosis and prediction module through a standardized communication bus (including CAN bus or Ethernet) to ensure the coordination and linkage of each module.

[0025] Monitor the power status in real time, adjust the power output, and ensure stable power supply; Load management software: dynamically adjust the power distribution of each load according to real-time load information to optimize energy efficiency; Communication protocol ensures the reliability and real-time performance of data exchange and command transmission between different modules.

[0026] The electrical module receives instructions from the energy management module and the diagnostic prediction module through the communication interface, and adjusts the power distribution in real time to meet the system requirements. The power management unit ensures that each load has a stable power supply, and the load distribution unit intelligently adjusts the power distribution of each load according to the demand to achieve efficient operation of the system.

[0027] Multi-level protection devices: including overload protectors, short-circuit breakers, overvoltage protectors, and overheating protection sensors; intelligent algorithm processors: embedded processors for running protection algorithms and processing sensor data; alarm systems: integrated sound and light alarms and remote alarm interfaces to notify abnormal conditions in real time. The protection module monitors the status of electrical components inside the electrical cabinet in real time through sensors. When an abnormality is detected (including overload, short circuit, overvoltage, overheating), the intelligent algorithm processor analyzes the data and triggers the corresponding protection measures.

[0028] The protection algorithms include overload detection algorithm, short circuit detection algorithm, overvoltage detection algorithm and overheat detection algorithm. They analyze sensor data in real time, determine the fault type and decide on the protection measures to be taken, control the triggering of the alarm system, and send fault notifications to maintenance personnel and system management software.

[0029] When the multi-dimensional sensors of the protection module detect abnormal electrical conditions, the protection algorithm software will immediately analyze the data, determine the fault type and initiate corresponding protection measures, including disconnecting the faulty circuit, adjusting the load distribution or activating the backup module. At the same time, the alarm system will sound an audible and visual alarm and send fault information to the central control system through the communication interface to ensure that maintenance personnel respond in a timely manner.

[0030] The multi-level protection algorithm is used to detect and respond to various abnormal situations in the electrical cabinet. Its core is threshold-based detection and intelligent decision-making.

[0031] Overload detection:

[0032] Current, : Overload threshold; Short circuit detection: Detection is performed using the mutation characteristics of voltage and current.

[0033]

[0034] and , Voltage change, Current change, , : short circuit detection threshold; Overvoltage detection:

[0035] Current voltage, : Overvoltage threshold; Overheat detection:

[0036] Current temperature, : Overheat threshold; Intelligent decision logic: When any of the above anomalies is detected, the intelligent algorithm processor selects the corresponding protection measures according to the fault type. For example, disconnect the relevant circuit in case of overload and short circuit, start the voltage stabilization device in case of overvoltage, adjust the load or enable the cooling system in case of overheating.

[0037] Load regulation unit: including intelligent current sensor, load regulator and power controller; Energy-saving regulation unit: equipped with high-efficiency energy consumption controller and dynamic power regulator; Power switching unit: including multiple power input interfaces (grid, local energy storage, renewable energy) and automatic switching device; Blockchain processor: blockchain storage for energy usage data and maintenance records; Distributed energy coordination unit: equipped with wireless communication module to realize energy sharing with other electrical cabinets; Adaptive demand response unit: integrated intelligent load response controller; Microgrid control unit: used to manage coordination with external renewable energy.

[0038] The energy management module realizes intelligent dispatch and optimal utilization of electricity through the collaborative work of various submodules. The load adjustment unit and energy-saving adjustment unit are responsible for real-time adjustment of load and working mode, the power switching unit selects the optimal power source according to system requirements and market conditions, the blockchain module records all energy use and maintenance data, the distributed energy coordination unit shares or trades energy with other electrical cabinets, the adaptive demand response unit adjusts load demand according to external conditions, and the microgrid control unit coordinates the use of local renewable energy.

[0039] Intelligent dispatching algorithm: real-time analysis of load demand, environmental factors and electricity market data, optimize power distribution and select the best power source; energy-saving optimization algorithm: dynamically adjust the working mode, reduce energy consumption and improve system efficiency; blockchain management software: responsible for data recording, storage and verification, ensuring the transparency and non-tamperability of energy use and maintenance records; distributed energy trading software: supports energy sharing and trading with other electrical cabinets to achieve efficient use of energy; demand response management software intelligently adjusts load demand according to the real-time price of the external electricity market and the load status of the power grid; microgrid control software coordinates the connection and interaction with external renewable energy to optimize energy supply.

[0040] The energy management module monitors power demand and supply in real time, and uses intelligent scheduling algorithms and energy-saving optimization algorithms to dynamically adjust power distribution and working modes. When power demand changes or market conditions fluctuate, the power switching unit automatically selects the optimal power supply to ensure the lowest energy cost and stable supply. The blockchain module records all energy use and maintenance data, the distributed energy coordination unit shares or trades energy with other electrical cabinets through the wireless communication module, the adaptive demand response unit adjusts load demand according to the real-time price of the power market and the load status of the power grid, and the microgrid control unit coordinates the use of local renewable energy to improve the energy independence and responsiveness of the system.

[0041] Intelligent dispatch algorithm: optimizes power distribution in real time to ensure maximum energy efficiency. It uses a multi-objective optimization method to consider load demand, energy cost and renewable energy utilization. The calculation formula used by the intelligent dispatch algorithm is:

[0042]

[0043] Represents the output value of the intelligent scheduling algorithm, The weight coefficients represent the importance of energy cost, power consumption and renewable energy utilization, respectively. : Energy cost function, which represents the cost of using different energy sources (grid, local energy storage, renewable energy), The power consumption function represents the total power consumption of the system. : Renewable energy utilization rate function, which indicates the proportion of renewable energy used.

[0044] Energy-saving optimization algorithm: Reduce the overall power consumption of the system by dynamically adjusting the working mode. The calculation formula used by the energy-saving optimization algorithm is:

[0045] Total system power consumption; No. The power consumption of each module; :No. Modules at time The operating frequency or duty cycle; Power switching algorithm (neural network): uses a feedforward neural network to predict the optimal power source selection. The input includes load demand, energy cost, renewable energy availability, etc., and the output is the power source selection decision. The calculation formula used by the power switching algorithm is:

[0046]

[0047] is the power source selection decision matrix. A positive value means it is biased towards traditional energy, while a negative value means it is biased towards new energy. Input feature vector (load demand, energy cost, renewable energy availability, etc.) Weight matrix; Bias vector; Activation function (ReLU); Blockchain management algorithm: Using Ethereum-based smart contracts to ensure the transparency and immutability of energy usage data and maintenance records. Each energy transaction and maintenance operation generates a block to record detailed information, which is verified and stored through a consensus mechanism.

[0048] Multidimensional sensor network: including temperature sensors, humidity sensors, current sensors, voltage sensors and vibration sensors; artificial intelligence processor: used to run AI fault diagnosis and prediction algorithms; storage module: used to store historical operation data and prediction models; communication interface: used to exchange data with other modules and central control system.

[0049] The diagnostic prediction module collects the operating data of each module of the electrical cabinet through a multi-dimensional sensor network and transmits it to the artificial intelligence processor for analysis. The fault prediction module based on deep learning and the AI ​​fault self-diagnosis module process the data, predict potential faults and generate maintenance alerts. The AI ​​load balancing module optimizes load distribution based on real-time data to ensure the stability of system operation.

[0050] Deep learning model: training neural network models for fault prediction and diagnosis; fault prediction algorithm: analyzing sensor data and identifying potential fault trends; fault self-diagnosis algorithm: automatically diagnosing specific fault types and providing repair suggestions; load balancing algorithm: dynamically optimizing load distribution based on real-time data to ensure system stability; predictive maintenance algorithm: combining historical data and predictive models to predict possible faults and automatically adjust operating parameters.

[0051] The multi-dimensional sensor network monitors the operating status of each module in the electrical cabinet in real time, and transmits data such as temperature, humidity, current, voltage and vibration to the artificial intelligence processor. The fault prediction module based on deep learning analyzes the data, identifies potential fault trends and generates maintenance alerts. The fault self-diagnosis module based on artificial intelligence further processes the alerts, automatically diagnoses the specific fault type and provides repair suggestions. The AI ​​load balancing module dynamically adjusts the load distribution according to real-time data to ensure the stability of system operation. The predictive maintenance module combines historical operating data and prediction models to predict possible faults in advance and automatically adjust the operating parameters of the electrical cabinet to reduce the occurrence of faults and maintenance costs.

[0052] Fault prediction algorithm based on deep learning: The long short-term memory network (LSTM) model is used to predict faults in time series data. The LSTM model can capture long-term dependencies in the data and is suitable for predicting future fault trends.

[0053]

[0054] Time step Input characteristics (temperature, humidity, current, voltage, vibration, etc.); : The hidden state of the LSTM unit Memory state of LSTM unit Prediction output (failure probability) Training process: Train the LSTM model through historical running data to minimize the prediction error:

[0055] The number of training samples; Actual fault label; The model predicts the probability of failure; AI fault self-diagnosis algorithm: Convolutional neural network (CNN) combined with support vector machine (SVM) is used to classify multi-dimensional data faults. First, CNN is used to extract features, and then SVM is used for classification and discrimination. Classification process:

[0056] : Input features; Fault type classification results; Load balancing algorithm: Use optimization algorithms (such as genetic algorithms or particle swarm optimization algorithms) for real-time load distribution to achieve dynamic balance and optimal configuration of system load.

[0057] Optimization goal:

[0058] Current load; Optimized target load; Load quantity; Predictive maintenance algorithm: Use regression models to predict the remaining useful life (RUL) of equipment and make maintenance plans in advance.

[0059]

[0060] No. The remaining useful life of the equipment; : No. Device Features Regression coefficients; Module virtualization unit: includes embedded virtualization processor and resource manager; intelligent resource scheduler: high-performance processor for running resource scheduling algorithm; communication interface: connects with other modules and central control system.

[0061] The adaptive scheduling module virtualizes the physical resources of each electrical module through the module virtualization unit to form a unified resource pool. The intelligent resource scheduler runs advanced scheduling algorithms, analyzes system load and operating status in real time, dynamically allocates resources and adjusts module functions to achieve optimal resource configuration.

[0062] Virtualization management software: responsible for managing and allocating virtual resources to ensure efficient use of resources in each module; intelligent resource scheduling algorithm: based on real-time load, operating status and environmental changes, intelligently schedule the work tasks of each electrical module to achieve optimal resource configuration; the module virtualization unit virtualizes the resources of each electrical module through an embedded virtualization processor to form a unified resource pool. The intelligent resource scheduling algorithm analyzes the system load and operating status in real time, dynamically allocates resources and adjusts module functions. For example, under high load, a module can work as a power management module, and switch to a standby cooling module under low load. Through virtualization and intelligent scheduling, efficient resource utilization and flexible adaptability of the system are achieved.

[0063] Module virtualization and resource scheduling algorithm: A hybrid optimization algorithm (combining particle swarm optimization PSO and genetic algorithm GA) is used for resource scheduling to ensure the optimality and dynamic adaptability of resource allocation.

[0064] Objective function:

[0065] : The power of the module; :No. Maximum power of each module; :No. Modules at time The operating frequency or duty cycle; No. Optimized operating frequency or duty cycle of each module; Weight parameters, balancing power utilization and frequency optimization; Particle Swarm Optimization (PSO) steps: 1. Initialization: Randomly initialize the position and speed of the particle. The particle position represents the power distribution and operating frequency of each module. 2. Evaluation: Calculate the fitness value of each particle and evaluate it according to the objective function. 3. Update individual and global optimal: Update the optimal position of each particle and the global optimal position according to the fitness value. 4. Speed ​​and position update:

[0066] Inertia weight; Learning factor; Random numbers; :particle The individual best position of : Global optimal position; 5. Iteration: Repeat the evaluation and update steps until the maximum number of iterations or convergence condition is reached.

[0067] Genetic Algorithm (GA) steps: Encoding: Encode the resource scheduling problem into chromosomes, which represent the power allocation and operating frequency of each module.

[0068] Selection: Select excellent individuals for reproduction based on fitness values.

[0069] Crossover and mutation: Generate new individuals through crossover and mutation operations to increase population diversity.

[0070] Evaluation: Calculate the fitness value of the new individual.

[0071] Replacement: Replace part or all of the original population with new individuals to maintain the population size.

[0072] Iteration: Repeat the selection, crossover, mutation, and evaluation steps until a maximum number of iterations or a convergence criterion is reached.

[0073] Hybrid optimization strategy: Combining the advantages of PSO and GA, using PSO for global search and GA for local optimization to improve the efficiency and accuracy of resource scheduling.

[0074] Multi-dimensional sensor network for diagnosis and prediction modules: Temperature sensor: monitors the temperature of each electrical module in real time to prevent overheating.

[0075] Humidity sensor: monitors ambient humidity to prevent electrical failures caused by excessive humidity.

[0076] Current sensor: measures the current of each electrical module to prevent overload.

[0077] Voltage Sensor: Monitors voltage levels to prevent overvoltage and undervoltage.

[0078] Vibration Sensors: Detect mechanical vibrations to prevent equipment wear and failure.

[0079] Fault prediction module based on deep learning: Data preprocessing: Cleaning, normalizing, and feature extraction of multi-dimensional sensor data in preparation for input into deep learning models.

[0080] Neural network models: Deep neural networks (such as LSTM, CNN) trained to identify failure patterns can predict future failure trends.

[0081] Maintenance alert generation: Based on the model prediction results, maintenance alerts are generated and notified to relevant modules and maintenance personnel.

[0082] Predictive Maintenance Module: Historical data analysis: Collect and store historical operating data of electrical cabinets to analyze the frequency and pattern of faults.

[0083] Predictive algorithms: Use statistical analysis and machine learning algorithms to predict possible failures and develop preventive maintenance plans.

[0084] Automatic operation parameter adjustment: Based on the prediction results, the operation parameters of the electrical cabinet (such as power distribution, equipment start and stop) are automatically adjusted to reduce the probability of failure.

[0085] Adaptive repair module: Load distribution adjustment: Automatically adjust power distribution based on fault prediction results to reduce reliance on faulty modules.

[0086] Power regulation: Dynamically adjust power output to prevent system instability due to power overload.

[0087] Backup module enabled: When the main module fails, it automatically switches to the backup module to ensure continuous operation of the system.

[0088] Self-healing feedback module: Abnormality detection: monitor the working status of each module in the electrical cabinet in real time and identify abnormal situations.

[0089] Automatic adjustment: When an abnormality is detected, the current, temperature or load is automatically adjusted to restore normal system operation.

[0090] Reinforcement learning algorithm: Through continuous learning and optimization, improve self-healing strategies and enhance the system's ability to respond to abnormal situations.

[0091] Fault self-diagnosis module based on artificial intelligence: Convolutional neural network (CNN) combined with support vector machine (SVM) is used to classify multi-dimensional data faults. First, CNN is used to extract features, and then SVM is used for classification and discrimination.

[0092] Classification process:

[0093] Input characteristics (temperature, humidity, current, voltage, vibration, etc.); Fault type classification results; Multidimensional sensor data fusion algorithm: The weighted average method combined with principal component analysis (PCA) is used to reduce the dimension and fuse the multidimensional sensor data to improve the accuracy of fault prediction.

[0094] Fusion process:

[0095] Raw sensor data matrix; Weight matrix; The weighted data matrix; The data matrix after dimensionality reduction; Reinforcement learning self-healing strategy: Use Q learning algorithm to optimize the self-healing feedback strategy to improve the system's response speed and effectiveness to abnormalities.

[0096] Q-learning formula:

[0097] state Next action Q value; Learning rate; Discount factor; Instant rewards; Next state; Next action.

[0098] The diagnostic prediction module collects the operating data of each module of the electrical cabinet through a multi-dimensional sensor network. After preprocessing and feature extraction, the data is input into the deep learning model for fault prediction. The prediction results are further analyzed by the AI ​​fault self-diagnosis module to provide specific fault types and repair suggestions. The AI ​​load balancing module dynamically optimizes load distribution based on real-time data to ensure stable operation of the system. The predictive maintenance module combines historical data and prediction models to predict possible failures in advance and automatically adjust operating parameters to reduce the failure rate and maintenance costs. The adaptive repair module and the self-healing feedback module automatically adjust the load distribution, power regulation or enable the standby module to actively repair and adjust to ensure the continuous and stable operation of the system, and continuously optimize the self-healing strategy through reinforcement learning algorithms.

[0099] Module virtualization module: Embedded virtualization processor: supports hardware-level virtualization, allowing multiple virtual instances to run on the same physical module; resource manager: responsible for allocating and scheduling virtual resources to ensure efficient utilization and isolation of resources; intelligent resource scheduling algorithm: uses a hybrid optimization algorithm (combining particle swarm optimization PSO and genetic algorithm GA) for resource scheduling to ensure optimality and dynamic adaptability of resource allocation.

[0100] Module virtualization and resource scheduling algorithm: A hybrid optimization algorithm (combining particle swarm optimization PSO and genetic algorithm GA) is used for resource scheduling to ensure the optimality and dynamic adaptability of resource allocation. Specific embodiment 2: Based on the technical solution of the specific embodiment 1, the following contents are further disclosed: Real-time monitoring and data collection: The multi-dimensional sensor network continuously monitors the operating parameters of each module in the electrical cabinet, such as temperature, humidity, current, voltage and vibration. The data is transmitted to the diagnosis and prediction module and the energy management module through the communication interface.

[0102] Fault prediction and diagnosis: The deep learning-based fault prediction module analyzes sensor data, identifies potential fault trends and generates maintenance alerts. The artificial intelligence-based fault self-diagnosis module further processes the alerts, automatically diagnoses the specific fault type and provides repair suggestions.

[0103] Load regulation and energy optimization: The load regulation module and energy-saving regulation module in the energy management module automatically adjust power distribution and working mode according to real-time monitored load information and environmental factors to optimize energy efficiency. The power switching module selects the optimal power source through a neural algorithm to ensure the lowest energy cost and stable supply.

[0104] Intelligent scheduling and resource allocation: The adaptive scheduling module uses the module virtualization module and intelligent resource scheduling algorithm to dynamically adjust the working mode of each electrical module to achieve optimal resource configuration and load balancing, ensuring efficient operation of the system.

[0105] Fault response and self-healing: When the diagnostic prediction module detects a potential fault, the adaptive repair module automatically adjusts the load distribution, power regulation or enables the backup module to proactively repair and ensure the continuous operation of the system. When the self-healing feedback module detects an abnormality, it adjusts the current, temperature or load to reduce the probability of faults and optimizes the self-healing strategy through the reinforcement learning algorithm.

[0106] Energy recording and management: The blockchain module records the energy usage, maintenance records, load adjustment and other data inside the electrical cabinet to ensure the data is tamper-proof and transparent. The distributed energy coordination module shares or trades energy with other electrical cabinets through the wireless communication module to improve the overall energy utilization efficiency.

[0107] Demand response and energy trading: The adaptive demand response module adjusts the load demand in the electrical cabinet according to the real-time price of the external power market and the load status of the power grid to achieve intelligent demand response. The distributed energy coordination module conducts energy transactions with other electrical cabinets or energy equipment through the blockchain platform to optimize energy distribution and utilization efficiency.

[0108] Coordination of microgrid and renewable energy: The microgrid control module coordinates the connection between the electrical cabinet and external renewable energy (such as solar or wind energy), ensuring that the electrical cabinet can be powered by local renewable energy during peak grid load, improving the energy independence and responsiveness of the system.

[0109] System protection and recovery: The multi-level protection module monitors the working status of the components inside the electrical cabinet in real time and provides a multi-level protection mechanism. When abnormal conditions such as overload, short circuit, overvoltage or overheating are detected, the corresponding protection measures are automatically enabled and an alarm is issued. When a fault occurs, the automatic recovery module can quickly restore the system by switching to a backup module or adjusting the load to reduce downtime.

[0110] Data management and transparency: The blockchain module ensures the immutability and transparency of all energy usage data, maintenance records, load adjustment and other information, provides a trusted data management platform, facilitates user queries and audits, and improves the security and reliability of the system.

[0111] The workflow is as follows: Data collection and monitoring: The sensor network continuously collects the operating data of each module and transmits it to the diagnosis and prediction module and the energy management module through the communication interface.

[0112] Fault prediction and early warning: The deep learning model analyzes sensor data, identifies potential fault trends, and generates maintenance alerts; the AI ​​self-diagnosis module further diagnoses specific fault types and provides repair suggestions.

[0113] Energy optimization and load regulation: The energy management module automatically adjusts power distribution and working mode according to real-time data, uses the energy-saving regulation module to reduce power consumption, and selects the optimal power supply through the power switching module.

[0114] Intelligent scheduling and resource allocation: The adaptive scheduling module dynamically allocates resources and optimizes load balancing to ensure efficient system operation through module virtualization and intelligent resource scheduling algorithms.

[0115] Fault response and self-healing: When the fault prediction module detects a potential fault, the adaptive repair module automatically adjusts the load distribution or enables the backup module to ensure continuous operation of the system. The self-healing feedback module reduces the probability of faults by adjusting the current, temperature or load, and optimizes the self-healing strategy through the reinforcement learning algorithm.

[0116] Energy recording and management: The blockchain module records all energy usage and maintenance data to ensure data transparency and immutability. The distributed energy coordination module shares or trades energy with other electrical cabinets through the wireless communication module to improve overall energy efficiency.

[0117] Demand response and energy trading: The adaptive demand response module intelligently adjusts load demand according to electricity market prices and grid load conditions; the distributed energy coordination module conducts energy transactions with other electrical cabinets or energy equipment through the blockchain platform to optimize energy distribution and utilization efficiency.

[0118] Coordination of microgrid and renewable energy: The microgrid control module coordinates the connection between the electrical cabinet and external renewable energy to ensure that power is supplied by local renewable energy during peak grid load periods, thereby improving the energy independence and responsiveness of the system.

[0119] System protection and recovery: The multi-level protection module monitors the working status of each module through intelligent algorithms. When an abnormality occurs, it automatically enables protection measures and issues an alarm. When a fault occurs, the automatic recovery module switches to a backup module or adjusts the load to achieve rapid system recovery and reduce downtime.

[0120] Data management and transparency: The blockchain module ensures the immutability and transparency of all energy usage and maintenance data, provides a trusted data management platform, facilitates user queries and audits, and improves the security and reliability of the system.

[0121] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprising a reference structure" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0122] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A modular electrical cabinet system with multiple protections and high energy efficiency, characterized by: Includes the following parts: Electrical module, used to complete the basic operation of the electrical cabinet; Protection module, used to provide short circuit protection, overload protection, and lightning protection for electrical components inside the electrical cabinet; Energy management module, which is used to intelligently schedule energy distribution in electrical cabinets and improve energy efficiency by dynamically adjusting loads, enabling backup power or cooling systems; The energy management module monitors power demand and supply in real time, and uses intelligent scheduling algorithms and energy-saving optimization algorithms to dynamically adjust power distribution and working modes. When power demand changes or market conditions fluctuate, the power switching unit automatically selects the optimal power supply. The blockchain module records all energy usage and maintenance data. The distributed energy coordination unit shares or trades energy with other electrical cabinets through the wireless communication module. The adaptive demand response unit adjusts load demand according to the real-time price of the power market and the load status of the power grid. The microgrid control unit coordinates the use of local renewable energy to improve the energy independence and responsiveness of the system. Intelligent dispatch algorithm: optimizes power distribution in real time to ensure maximum energy efficiency; adopts a multi-objective optimization method that takes into account load demand, energy cost, and renewable energy utilization; the calculation formula used by the intelligent dispatch algorithm is: ， Represents the output value of the intelligent scheduling algorithm, weight coefficients, representing the importance of energy cost, power consumption, and renewable energy utilization, respectively; : Energy cost function, which represents the cost of using different energy sources. The power consumption function represents the total power consumption of the system; : Renewable energy utilization rate function, which indicates the proportion of renewable energy used; Energy-saving optimization algorithm: By dynamically adjusting the working mode, the overall power consumption of the system is reduced; the calculation formula of the energy-saving optimization algorithm is: ， Total system power consumption; No. The power consumption of each module; :No. Modules at time The operating frequency or duty cycle; Power switching algorithm: The power switching algorithm uses a feedforward neural network to predict the optimal power source selection; the input includes load demand, energy cost, and renewable energy availability, and the output is the power source selection decision; the calculation formula of the power switching algorithm is: ， is the power source selection decision matrix. A positive value means it is biased towards traditional energy, while a negative value means it is biased towards new energy. Input feature vector, Weight matrix; Bias vector; Activation function; Blockchain management algorithm: Using Ethereum-based smart contracts to ensure the transparency and immutability of energy usage data and maintenance records; each energy transaction and maintenance operation generates a block to record detailed information, which is verified and stored through a consensus mechanism; Diagnostic prediction module, used to monitor the operating status of each module in the electrical cabinet in real time and predict potential faults; The adaptive scheduling module is used to dynamically adjust the working mode of each electrical module according to the real-time load and operating status.

2. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The energy management module further comprises: Load regulation module, used to automatically adjust the power distribution of each module in the electrical cabinet according to real-time monitored load information, environmental factors and power demand; The energy-saving adjustment module is used to dynamically adjust the working mode of the electrical cabinet according to real-time data.

3. The modular electrical cabinet system with multiple protections and high energy efficiency according to claim 1 is characterized in that: The diagnosis prediction module further comprises: A multi-dimensional sensor network for real-time monitoring of the operating status of each module in the electrical cabinet, including temperature, humidity, current, voltage and vibration data; A deep learning-based fault prediction module that processes data from a multi-dimensional sensor network to predict potential faults and generate maintenance alerts; The predictive maintenance module is used to predict possible failures based on historical data and prediction algorithms, and automatically adjust the operating parameters of the electrical cabinet to reduce the occurrence of failures.

4. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The diagnosis prediction module further comprises: An adaptive repair module configured to automatically adjust load distribution, power regulation or enable standby modules in the electrical cabinet according to the fault prediction results, so as to proactively perform repairs and ensure continuous operation of the system; The self-healing feedback module is used to reduce the possibility of failure by automatically adjusting the current, temperature or enabling the backup module to adjust the load when an abnormal operation of a module in the electrical cabinet is detected, and continuously adjust the self-healing strategy through the reinforcement learning algorithm.

5. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The energy management module also includes: The blockchain module is used to record energy usage, maintenance records and load adjustment data inside the electrical cabinet; the blockchain module is used to save energy usage data and maintenance records, and cannot be tampered with.

6. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The energy management module further comprises: The power switching module is used to dynamically select grid power, local energy storage or renewable energy for power supply according to the load demand of the electrical cabinet and the external power market price; the power switching module makes the best selection of power source through a neural algorithm.

7. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The diagnosis prediction module further comprises: The artificial intelligence-based fault self-diagnosis module is used to automatically diagnose faults according to the operating status of each module in the electrical cabinet, and dynamically adjust the load distribution in the electrical cabinet according to the real-time data of equipment operation.

8. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The adaptive scheduling module further comprises: The module virtualization module is configured to virtualize the resources of each electrical module and reconfigure it in real time according to demand, so that the module can perform different functions at different time periods.

9. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1 is characterized in that: The protection module further comprises: The multi-level protection module is used for overload protection, short circuit protection, overvoltage protection, and overheat protection of the internal components of the electrical cabinet; the multi-level protection module monitors the working status of each module through an intelligent algorithm, and when an abnormality occurs, the multi-level protection module is automatically enabled and an alarm is issued; The automatic recovery module automatically switches to the backup module or performs load adjustment when a short circuit or overload fault occurs inside the electrical cabinet. The intelligent control system adjusts the working state inside the electrical cabinet after detecting the fault.

10. The modular electrical cabinet system with multiple protections and high efficiency energy saving according to claim 1, characterized in that: The energy management module further comprises: Distributed energy coordination module, which is used to realize energy sharing or trading with other devices in the electrical cabinet and exchange energy through the blockchain platform; Adaptive demand response module, which adjusts the load demand in the electrical cabinet according to the real-time price of the external power market and the grid load condition; Microgrid control module for coordination of electrical cabinets with external renewable energy sources.

Images