Converter intelligent voltage management system based on AC-DC conversion

Abstract

The invention provides a converter intelligent voltage management system based on alternating current and direct current conversion, relates to the technical field of alternating current distribution networks, and realizes accurate identification of different load types and adaptive optimization of voltage regulation parameters by integrating a load identification module, an operation health prediction module, a voltage regulation module and the like. Meanwhile, the system constructs a component wear prediction model, monitors the operation health index of a key component in real time, and dynamically adjusts the voltage parameter according to the health state, thereby remarkably improving the operation efficiency of the power converter and the system reliability, prolonging the service life of equipment, and improving the reliability of the power converter. And the requirements of a modern complex power system on intelligent and high-efficiency voltage management are met.

Description

Technical Field

[0001] The present invention relates to the technical field of AC power distribution networks, and in particular to an intelligent voltage management system for converters based on AC / DC conversion. Background Art

[0002] Power converters are primarily used for efficient conversion between AC and DC power and are widely used in power transmission and distribution systems, as well as various industrial equipment. In recent years, the development of intelligent voltage management systems has seen significant progress, aiming to improve the energy efficiency, stability, and reliability of power converters. Traditional voltage management systems rely on fixed PID control algorithms, which can adjust the output voltage to a certain extent to adapt to load changes. However, with the expansion of system scale and the diversification of load types, relying solely on traditional PID control is unable to meet the dynamic regulation and high-precision control requirements of complex power systems.

[0003] While existing intelligent voltage management systems have improved the performance of power converters to a certain extent, they still have many shortcomings. First, traditional systems have relatively static voltage regulation parameter settings when handling various load types. They lack the ability to deeply identify and dynamically adapt to different load characteristics, resulting in suboptimal voltage regulation in complex load environments. Second, existing systems generally lack real-time monitoring and prediction of the health status of key components, making it impossible to promptly detect and respond to early component wear or failure, which in turn affects the stability and service life of the entire system.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The object of the present invention is to provide an intelligent voltage management system for a converter based on AC / DC conversion, so as to solve the problems raised in the above background technology.

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

[0007] The intelligent voltage management system for AC / DC converters specifically includes a power input protection module, a bidirectional rectification and power compensation module, a high-frequency isolation and voltage reduction module, a bidirectional inverter and rectification efficiency improvement module, and a voltage superposition and output module, which are connected in sequence. In addition, it also includes an initial voltage regulation module, wherein:

[0008] Initial voltage regulation module: This module collects and analyzes the AC signal from the bidirectional rectifier input and the DC signal from the bidirectional inverter input to build a load identification model. The load identification model is used to identify the load type of the power supply device and apply the corresponding initial voltage regulation parameters to each load type.

[0009] Wear prediction model building module: This module identifies multiple key components of the power supply load equipment and, based on the initial voltage regulation parameters corresponding to different load types, analyzes the vibration and wear data collected from each key component to generate a component health index.

[0010] The initial voltage regulation parameters and vibration data corresponding to the identified load type are used as input features, and the component health index is used as the output to build a wear prediction model for each key component based on a machine learning prediction model.

[0011] Adjustment parameter optimization module: used to obtain the initial voltage adjustment parameters and vibration data of each key component at the current moment, and input these data into the wear degree prediction model to obtain the component operation health index prediction results of each key component; compare and analyze the component operation health index prediction results with the preset warning thresholds, and dynamically adjust the initial voltage adjustment parameters of each load type based on the analysis results.

[0012] Compared with the prior art, the present invention has the following beneficial effects:

[0013] By integrating modules such as load identification, operational health prediction, and voltage regulation, accurate identification of different load types and adaptive optimization of voltage regulation parameters are achieved. At the same time, the system builds a component wear prediction model to monitor the operational health index of key components in real time and dynamically adjusts voltage parameters according to the health status, thereby significantly improving the operating efficiency and system reliability of the power converter, extending the service life of the equipment, and meeting the needs of modern complex power systems for intelligent and high-efficiency voltage management. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the overall system module of the present invention. DETAILED DESCRIPTION

[0015] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0016] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0017] Example 1:

[0018] See also Figure 1 , the present invention provides a technical solution:

[0019] The intelligent voltage management system for converters based on AC / DC conversion includes:

[0020] Power input protection module: used to introduce AC power from the low-voltage end of the distribution transformer;

[0021] Further explanation: The power input protection module is connected to the converter intelligent voltage management system via a standard cable;

[0022] The power input protection module includes a high-performance standard cable connection unit and an intelligent circuit breaker protection unit;

[0023] High-performance standard cable connection units achieve efficient and safe transmission through high-conductivity cables and high-temperature resistant insulation materials;

[0024] High-performance standard cable connection units utilize high-conductivity copper or aluminum core cables and utilize heat-resistant and corrosion-resistant insulation materials to connect to the converter, adapting to current and voltage requirements. Optimized wiring paths and mechanical reinforcement ensure efficient power transmission and prevent cable damage.

[0025] The high-performance standard cable connection unit plans the shortest path through computer-aided design (CAD), and lays out sheath tubes and fixed bridges in areas susceptible to mechanical damage to protect the cables from external physical damage.

[0026] The intelligent circuit breaker protection unit is installed at the power input end and has overload protection, short circuit protection, undervoltage protection, overvoltage protection and leakage protection functions; and triggers circuit breaker protection when a fault occurs;

[0027] It should be noted that the power input end is the interface for introducing AC power from the low-voltage end of the distribution transformer to the power input protection module. It is used to obtain AC power from the low-voltage end of the distribution transformer and serves as the power input starting point for the entire converter intelligent voltage management system.

[0028] The intelligent circuit breaker protection unit includes an automatic reset function, which can automatically restore system power supply after the fault is eliminated, reducing manual intervention and improving operation efficiency.

[0029] Bidirectional rectification and power compensation module: used to convert the AC power introduced from the low-voltage end into a high DC voltage using a bidirectional rectifier, wherein the bidirectional rectifier is configured to allow energy to flow in both directions;

[0030] Further explanation: The bidirectional rectifier is a TI VOR0532 model; the low-voltage side of the distribution transformer is 0.4 kV; the bidirectional rectification and power compensation module integrates a limited-capacity reactive power compensation unit in the rectifier circuit, achieving reactive power compensation through capacitors and inductors;

[0031] The operation logic of the bidirectional rectification and power compensation module includes:

[0032] 1.1) AC power access and pre-processing:

[0033] The low voltage end of the distribution transformer is introduced into the bidirectional rectification and power compensation module through the input end;

[0034] Add an EMI filter at the input end to suppress electromagnetic interference from the input power grid and improve the purity of the AC signal;

[0035] The pre-processed AC signal is passed through the current monitoring module inside the bidirectional rectifier to verify whether the frequency of the AC voltage is stable at a preset rated value; in this embodiment, the frequency of the AC voltage is set to 50Hz or 60Hz;

[0036] In this embodiment, adding an EMI filter can improve the quality of the input current and reduce the operating loss of the power module;

[0037] 1.2) Rectification function realization:

[0038] The bidirectional rectifier performs rectification, converting the AC signal into a DC400V high DC voltage;

[0039] Synchronous rectification technology is introduced into the bidirectional rectifier bridge circuit, replacing traditional diodes with MOSFETs to reduce losses and improve the voltage quality of the rectifier output;

[0040] Output the rectified high DC voltage to the subsequent high-frequency isolation step-down module;

[0041] An active voltage controller is added to the DC voltage on the rectifier side to adjust and stabilize the output voltage waveform in real time and compensate for fluctuations;

[0042] Furthermore, the limited reactive power compensation unit is composed of a capacitor and an inductor forming an LC circuit, which automatically adjusts the current phase angle to reduce reactive power;

[0043] Detect real-time power factor and control the capacitor and inductor combination value to keep the power factor close to 1;

[0044] If the power factor deviates from the reasonable range, the compensation unit is triggered to adjust the parameters of the LC circuit dynamically to ensure operating efficiency.

[0045] 1.3) Energy bidirectional flow is realized:

[0046] When the converter intelligent voltage management system needs to feed DC400V back to the AC grid, the DC signal is converted into an AC signal through the reverse operation of the bidirectional rectifier.

[0047] During the feedback process, the bidirectional rectifier activates the built-in phase matching and power synchronization module to ensure that the frequency and phase of the feedback AC power are consistent with the grid voltage, thus avoiding grid-side disturbances.

[0048] The feedback AC power is purified again through the EMI filter and then returned to the distribution network. At the same time, the rectifier monitors the direction of energy flow in real time and adjusts the feedback power level.

[0049] High-frequency isolation step-down module: used to step down the obtained high DC voltage to a low DC voltage through a high-frequency isolation transformer;

[0050] Further explanation: The high-frequency isolation buck module includes:

[0051] Preliminary filtering unit: Set at the high DC voltage input end, it suppresses high-frequency electromagnetic interference of the input power supply through a high-frequency EMI filter and improves the purity of the power supply signal;

[0052] Energy isolation and step-down unit: High DC voltage is input to the primary side of the transformer through a high-frequency isolation transformer, and a low DC voltage of DC80V is directly obtained through electromagnetic energy conversion. Multi-layer winding technology and turns ratio design are used to achieve efficient energy transfer and voltage reduction.

[0053] Filtering and voltage stabilization unit: At the low DC voltage 80V output, a multi-stage LC filter removes residual voltage ripple. A low-voltage voltage stabilization module regulates the low DC voltage 80V to ensure the stability and high quality of the final output voltage.

[0054] The energy isolation and step-down unit directly steps down the primary-side high DC voltage (DC400V) to the secondary-side low DC voltage (DC80V) via a T5-80 high-frequency isolation transformer, eliminating the traditional AC conversion step. It utilizes a highly efficient turns ratio design and optimized electromagnetic coupling structure to ensure energy transfer efficiency and isolation performance. The turns ratio is optimized to a 5:1 ratio between the primary and secondary turns, ensuring the voltage step-down ratio meets system parameter requirements.

[0055] Bidirectional inverter and rectifier efficiency improvement module: used to convert low DC voltage into low voltage AC power using a bidirectional inverter;

[0056] Further explanation: The bidirectional inverter uses IRF540N MOSFETs and IRG4PH50U IGBTs to achieve synchronous rectification to improve conversion efficiency;

[0057] Use a bidirectional inverter to invert the low DC voltage DC80V generated by the high-frequency isolation step-down module into low-voltage AC power;

[0058] The peak value of the low-voltage AC power is set to 40V, and the instantaneous voltage range during operation is -40V to 40V. The specific implementation steps are as follows:

[0059] 2.1) The low DC voltage DC80V generated by the high-frequency isolation step-down module is connected to the input end of the bidirectional inverter through the input connection unit, and the purity and stability of the input voltage are improved through preprocessing.

[0060] A high-frequency EMI filter is set at the input end of the bidirectional inverter to effectively suppress high-frequency electromagnetic interference, ensure the purity of the input voltage signal, and avoid the impact of interference on the inverter process;

[0061] An integrated high-precision DC voltage sensor monitors the input voltage in real time to ensure it remains stable at DC80V. When an anomaly is detected, the protection mechanism is triggered immediately to prevent voltage fluctuations from affecting inverter performance.

[0062] 2.2) Convert the low DC voltage of 80V to low-voltage AC power that matches the power supply load equipment through a bidirectional inverter;

[0063] The bidirectional inverter adopts a synchronous full-bridge converter topology, using IRF540N MOSFETs and IRG4PH50U IGBTs as switching elements to improve the response speed and efficiency of switching actions.

[0064] A fast diode branch is set in the full-bridge circuit to handle extreme voltage shocks and ensure circuit safety.

[0065] The switching frequency of the bidirectional inverter is set to 50kHz, which not only ensures efficient energy conversion but also reduces the impact of electromagnetic interference on the operation of load equipment.

[0066] The circuit controller realizes synchronous rectification by controlling the on and off timing of MOSFET and IGBT, replacing traditional diode rectification and avoiding voltage drop loss.

[0067] The synchronous rectification in this embodiment optimizes the conversion performance of the inversion process and improves the overall inversion efficiency.

[0068] Invert low DC voltage DC80V into low voltage AC power that matches the power supply load equipment, and adjust the frequency and voltage parameters according to functional requirements;

[0069] Furthermore, a new energy access interface is reserved on the load side of the power supply load device. The DC power generated by the connected new energy is inverted into AC power through a bidirectional inverter and fed back to the power grid to achieve bidirectional energy flow. The specific implementation steps are as follows:

[0070] A new energy access interface is reserved on the power supply load side. The DC power generated by the connected new energy is inverted through a bidirectional inverter, and the generated AC power is fed back to the power grid, realizing a two-way flow of energy.

[0071] 2.3) A standardized new energy access interface is reserved on the power supply load side for grid connection of new energy sources such as photovoltaic and wind power, supporting an input parameter range of DC60V to DC120V;

[0072] When new energy equipment is connected, the connected DC power is converted into AC power through a bidirectional inverter and synchronized with the grid voltage and frequency parameters.

[0073] Use bidirectional inverters to integrate secondary control algorithms, coordinate the converted AC power and feed it back to the grid, achieving dynamic grid energy balance and maximizing the utilization of new energy.

[0074] Voltage superposition and output module: used to connect low-voltage AC power in series with the low-voltage output end of the distribution transformer through the voltage superposition module to generate the target total output voltage range for powering load equipment;

[0075] Further explanation: the voltage superposition and output module includes an input configuration unit, a voltage superposition module and a total output voltage adjustment unit;

[0076] The low-voltage AC power is connected to the low-voltage output terminal of the distribution transformer through the input configuration unit; specifically, it includes:

[0077] Connect the low-voltage AC power generated by the bidirectional inverter to the low-voltage AC input terminal of the voltage superposition and output module through a high-conductivity copper wire;

[0078] Connect the low-voltage output terminal of the distribution transformer to the distribution transformer input terminal of the voltage superposition and output module through a high-conductivity copper wire;

[0079] A high-precision AC voltage sensor is integrated into the input configuration unit to continuously monitor the voltage output of the low-voltage AC power and the distribution transformer to ensure stable voltage input.

[0080] The voltage superposition module superimposes the low-voltage AC power and the low-voltage output voltage of the distribution transformer to generate the target total output voltage range;

[0081] The low-voltage output terminal of the distribution transformer is set to 220V. The target total output voltage range is set to 180V to 260V. The voltage superposition principle specifically includes:

[0082] The voltage superposition module is designed based on a direct-connected series superposition circuit. It achieves dynamic series connection of the two power sources by performing real-time phase synchronization and voltage amplitude matching between the low-voltage AC power and the AC power of the distribution transformer.

[0083] It should be noted that the direct-connected series superposition circuit uses the transformer coupling principle, specifically using a transformer with multiple secondary windings, and superimposing voltages by properly connecting these windings;

[0084] A high-precision synchronous phase adjustment circuit is used to ensure the phase consistency of the two AC power supplies and prevent voltage interference caused by phase deviation.

[0085] The integrated intelligent controller (MCU) monitors and controls the superimposed amplitude of low-voltage AC power and distribution transformer voltage in real time, ensuring that the total output voltage after superposition is smooth and stable.

[0086] The dynamic regulation range is set so that the generated total output voltage is between 180V and 260V, and adaptively adjusted according to load changes.

[0087] A multi-stage LC filter is installed at the output end of the voltage superposition module to filter out noise and ripple during the superposition process, ensuring high purity and stability of the output voltage.

[0088] The total output voltage regulation unit dynamically optimizes the superimposed voltage to ensure that the voltage range is between 180V and 260V and meets the specific needs of the power supply load equipment. The specific implementation of the total output voltage regulation unit includes:

[0089] A digitally adjustable resistor and capacitor combination is integrated into the total output voltage regulation unit, and its operation is controlled by an intelligent controller;

[0090] The total output voltage regulation unit dynamically adjusts the voltage amplitude based on the input voltage and load demand to ensure that the total output voltage remains between 180V and 260V.

[0091] It should be noted that the load requirements of the load device include the requirements for load power, voltage range, and current range parameters;

[0092] This embodiment calculates the required output voltage target value in real time based on the voltage range requirements of the load device and the input voltage. The target value is dynamically adjusted within a range of 180V to 260V and is optimized based on the real-time requirements of the load.

[0093] In this embodiment, if the instantaneous voltage range of the low-voltage AC power is -38V to 38V and the distribution transformer voltage is 220V, the superimposed instantaneous input voltage range is 182V to 258V.

[0094] The digital microcontroller MCU calculates the target output voltage as 240V, and the regulation module automatically adjusts the input amplitude to ensure that the output reaches the target range;

[0095] The current load voltage range is 192V to 240V, and the real-time operating power is 80kW. The regulation module dynamically adjusts the output voltage to the target value of 230V to meet the load demand.

[0096] Further explanation: The converter is defined as including a bidirectional rectifier, a high-frequency isolation transformer, a bidirectional inverter, and a voltage superposition module. The voltage regulator based on the converter requires the same power as the transformer output power. For example, a 200kW power transformer requires a 200kW power electronic converter. However, the converter power of this embodiment is 1 / 5 of the power of the power transformer, reducing converter cost. The reasons for reducing converter cost are as follows:

[0097] The converter for a 200kW transformer in this embodiment only requires 40kW of power;

[0098] Distribution transformers usually provide a stable basic voltage of 220V, and the superimposed low-voltage AC power only needs to be slightly adjusted in voltage, within a small range of 195V to 260V.

[0099] Since the voltage regulation range is small, the converter only works within a part of the total power range, so there is no need to fully match the total power;

[0100] Furthermore, the voltage superposition module directly utilizes the stable output voltage of the distribution transformer to compensate the total output voltage range by superimposing or correcting the low-voltage AC power in series;

[0101] In this process, the converter is only responsible for generating and regulating low-voltage AC power for superimposed correction, rather than directly generating the entire output voltage range;

[0102] The output voltage of the distribution transformer bears most of the total power, while the converter only processes the smaller power required for voltage correction;

[0103] By optimizing the design of the voltage regulation function, the converter power can be effectively saved, thereby reducing the overall cost of power electronic devices and systems;

[0104] Low-power converters avoid the additional burden of high-power operation, thereby reducing power consumption and the use of power electronic components.

[0105] The converter has lower design specifications, which further reduces device costs and daily operation and maintenance expenses.

[0106] Initial voltage regulation module: This module collects and analyzes the AC signal from the bidirectional rectifier input and the DC signal from the bidirectional inverter input to build a load identification model. The load identification model is used to identify the load type of the power supply device and apply the corresponding initial voltage regulation parameters to each load type.

[0107] To further explain, the steps for building the load identification model include:

[0108] The AC signal at the input of the bidirectional rectifier and the DC signal at the input of the bidirectional inverter are monitored in real time, the acquired AC and DC signals are converted into digital signals through an ADC, and the converted digital signals are transmitted to an embedded microcontroller through a data acquisition card;

[0109] Both AC and DC signals include voltage, current, and phase information;

[0110] In this embodiment, the voltage, current and phase information are measured and obtained by installing a current sensor and a voltage sensor at the input end of the bidirectional rectifier and the input end of the bidirectional inverter respectively;

[0111] The data acquisition card uses standardized transmission protocols UART, SPI or I2C to ensure signal transmission stability and low latency;

[0112] The fast Fourier transform (FFT) algorithm of the embedded microcontroller is used to perform frequency domain analysis on the acquired digital signal to extract the main frequency components, harmonic content and phase difference characteristic parameters;

[0113] It should be noted that the Fast Fourier Transform (FFT) algorithm deployment:

[0114] Pre-deploy FFT algorithm in embedded microcontroller to convert time domain signal into frequency domain signal;

[0115] Set the FFT window length to match the sampling rate; the window length is 256 points and the sampling rate is 100kHz.

[0116] Frequency component and harmonic analysis: Extract the fundamental frequency component and harmonic content of the signal, and normalize the amplitude of the harmonics.

[0117] Analyze the non-integer frequency harmonic components in the signal to distinguish the characteristics of single loads and complex loads.

[0118] Phase difference feature calculation: Based on the phase information of the frequency domain signal, the phase difference between the AC signal and the DC signal is calculated, providing auxiliary parameters for load type determination.

[0119] The frequency domain features are saved to the embedded microcontroller memory for subsequent load identification.

[0120] A pre-trained convolutional neural network (CNN) model is deployed on an embedded microcontroller to perform real-time classification and identification of the load type of the powered load device based on the extracted feature parameters. The load classification results include resistive load, inductive load, and capacitive load.

[0121] It should be noted that the convolutional neural network (CNN) model has been pre-trained and can classify load types in real time and automatically select the corresponding voltage regulation strategy based on the classification results;

[0122] Convolutional neural network (CNN) model deployment: A pre-trained CNN model consisting of convolutional layers, pooling layers, and fully connected layers is loaded into the embedded microcontroller for workload classification.

[0123] Ensure that the CNN model has been trained with a large-scale workload dataset and has the ability to generalize to handle complex real-time workload characteristics.

[0124] Real-time load classification operation: Use convolutional layers to extract and pattern match frequency components, harmonic content, and phase difference features layer by layer.

[0125] The load classification results are output through the fully connected layer, including resistive load, inductive load and capacitive load.

[0126] Classification model optimization strategy: Integrate a model optimization unit in the embedded microcontroller to update the model weights based on real-time operation feedback data to improve classification accuracy.

[0127] Ensure that the classification results are output stably and saved to the microcontroller memory for subsequent adjustment decisions.

[0128] Further, it is explained that the corresponding initial voltage regulation parameters are selected based on the load classification result, and a control instruction is sent to the bidirectional inverter;

[0129] For resistive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "maintain output voltage stability", quantified as the target range of voltage amplitude;

[0130] The target range of voltage amplitude is recorded as E target,resistive =[VU min ,VU max ];

[0131] E target,resistive is the target range of voltage amplitude used to characterize resistive loads;

[0132] VU min It is the minimum voltage amplitude; it is set to prevent the output voltage from being too low, which may cause the powered load equipment to not operate normally;

[0133] VU max It is the maximum voltage amplitude; it is set to prevent the output voltage from being too high, which may cause overload or damage to the power supply load equipment;

[0134] By ensuring that the voltage operates within the specified amplitude range, equipment performance fluctuations or damage caused by excessive voltage changes can be avoided, and the stability of the electrical system can be optimized;

[0135] Sending instructions to the bidirectional inverter to continuously monitor and adjust the output voltage within the set voltage amplitude target range;

[0136] For inductive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "power factor correction" and quantify it as the target value of the phase angle;

[0137] The target value of the phase angle is denoted as φ target,inductive =arccos(PF desired );

[0138] Among them, φ target,inductive It is the target phase angle value used to characterize the inductive load to achieve power factor correction;

[0139] PF desired is the desired power factor; in this embodiment, the selection range approaches the ideal power factor of 0.95 or 1.0; arccos represents the inverse cosine function;

[0140] Improving the power factor means reducing energy loss and improving transmission efficiency per unit of power transmission. When the inductive load operates close to this ideal state, the system energy efficiency improves.

[0141] Send control instructions to the bidirectional inverter to adjust the load angle so that the actual power factor reaches the target value, thereby optimizing power transmission;

[0142] For capacitive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "reduce output voltage amplitude", which is quantified as reducing the voltage amplitude range;

[0143] Capacitive loads can cause voltage increases or resonance, making the powered load susceptible to overvoltage risks. Output voltage must be reduced to mitigate these effects.

[0144] The reduced voltage amplitude range is recorded as E target,capacitive =[VU reduce,min ,VU reduce,max ];

[0145] Among them, E target,capacitive It is a reduced voltage amplitude range used to characterize capacitive loads;

[0146] VU reduce,min This is the minimum value to reduce the voltage amplitude; ensuring that the voltage reduction does not affect the system efficiency.

[0147] VU reduce,max It is the maximum value to which the voltage amplitude can be reduced; it prevents excessive voltage reduction from limiting device performance.

[0148] Send control instructions to the bidirectional inverter to adjust the output voltage amplitude down to the set reduced voltage amplitude range to achieve optimal stability;

[0149] The resistive load, inductive load and capacitive load are denoted as k1, and k1∈{1,2,3}, {1,2,3} represent the resistive load, inductive load and capacitive load respectively;

[0150] The initial voltage regulation parameter of load type k1 is recorded as E1 k1 ,

[0151] Wear prediction model building module: This module identifies multiple key components of the power supply load equipment and, based on the initial voltage regulation parameters corresponding to different load types, analyzes the vibration and wear data collected from each key component to generate a component health index.

[0152] The initial voltage regulation parameters and vibration data corresponding to the identified load type are used as input features, and the component health index is used as the output to build a wear prediction model for each key component based on a machine learning prediction model.

[0153] Further explanation: Assume that a set of multiple key components is {1, 2, ..., i, ..., n}, where i represents the i-th key component and n is the total number of key components; by identifying multiple key components of the power supply load device, a component database of the converter intelligent voltage management system is established; specifically, the database includes:

[0154] Prepare a list of key components based on the functional structure of the power supply load equipment, including but not limited to transformers, rectifiers, inverters, capacitors, and inductors;

[0155] Conduct a detailed analysis of the wear pattern of each key component to identify the main wear factors of each key component; the specific steps are as follows:

[0156] Data extraction: Extracts specific fault information from the fault logs of the powered load equipment, including entries on the vibration amplitude and wear of key components; ensuring a direct correlation between the collected data and the health status of the equipment.

[0157] Data formatting: Format the fault log to ensure a uniform data structure. This facilitates subsequent data processing and analysis, allowing the data to be input into the analysis model in a standardized manner.

[0158] Data Sorting: Fault log data is sorted by time to ensure the rationality of the historical data being analyzed. This sorted data helps analyze wear trends of power supply load equipment, providing a time reference for preventive maintenance.

[0159] Establish key component information tables in the database system, including component names, models, functional descriptions, and wear characteristics;

[0160] Generation of component health index, including:

[0161] Accurately collect and store data through sensors and data recording equipment; specifically including:

[0162] Install vibration sensors and wear sensors on each key component to ensure that the sensors can monitor the vibration characteristics and wear conditions of key components in real time;

[0163] Pre-process the collected vibration data and wear index data, including noise removal, outlier detection and processing, to ensure data quality and consistency;

[0164] Use filtering algorithms to remove unnecessary high-frequency noise and improve the signal-to-noise ratio of the data;

[0165] Further explanation: The vibration data is characterized as the vibration amplitude fluctuation coefficient, and the initial voltage adjustment parameter E1 of load type k1 is k1 Under the condition of , calculate the vibration amplitude fluctuation coefficient of the i-th key component in the current monitoring time period

[0166]

[0167] Among them, v current,i is the vibration amplitude of the i-th key component collected during the current working condition monitoring period; v min,i is the minimum vibration amplitude of the i-th key component under all test conditions; v max,iis the maximum vibration amplitude of the i-th key component under all test conditions;

[0168] set up The valid value range of is the interval (0,1); The larger the value, the greater the vibration amplitude of the i-th key component, and the greater the impact on the wear degree;

[0169] when The closer it is to 0, the closer the i-th key component is to the minimum vibration amplitude, and the smaller the impact on the wear degree;

[0170] when The closer it is to 1, the closer the i-th key component is to the maximum vibration amplitude, and the greater the impact on the wear degree;

[0171] It should be noted that a larger vibration amplitude fluctuation coefficient indicates greater mechanical load and wear on key components. Standardization maps the vibration amplitudes of different components to a uniform range, facilitating comparison and comprehensive analysis.

[0172] Initial voltage regulation parameter E1 at load type k1 k1 Calculate the wear of the i-th key component in the current working condition monitoring period

[0173]

[0174] Among them, m current,i is the wear amount of the i-th key component collected during the current working condition monitoring period; m min,i is the minimum wear of the i-th key component under all test conditions; m max,i is the maximum wear of the i-th key component under all test conditions;

[0175] set up The valid value range of is the interval (0,1); The larger the value, the greater the wear of the i-th key component, which means the worse the health status of the i-th key component;

[0176] when The closer it is to 0, the closer the wear of the i-th key component is to the minimum wear, which means the health status of the i-th key component is better;

[0177] when The closer it is to 1, the closer the wear of the i-th key component is to the maximum wear, which means the health status of the i-th key component is worse;

[0178] It should be noted that: based on historical data or preset test conditions, the minimum vibration amplitude v of each key component is determined min,iand the maximum vibration amplitude v max,i .

[0179] Determine the minimum wear amount m min,i and maximum wear volume m max,i .

[0180] The vibration amplitude fluctuation coefficient of the i-th key component and wear Perform combined analysis to obtain the following component health indexes:

[0181]

[0182] Among them, α is the weight coefficient of the vibration amplitude fluctuation coefficient, β is the weight coefficient of the wear amount, α+β=1, and the values of α and β are both in the interval (0,1);

[0183] set up The valid value range of is the interval (0,1);

[0184] when The closer it is to 0, the lower the vibration and / or wear of the i-th key component is, which means the health status of the i-th key component is better;

[0185] when The closer it is to 1, the higher the vibration and / or wear level of the i-th key component is, which means the health status of the i-th key component is worse;

[0186] Further explanation: When When it increases, it means that the vibration amplitude is larger, which means that the i-th key component is subjected to higher mechanical stress, which will lead to accelerated wear;

[0187] will eventually lead to increases, there is a situation that causes the status of the i-th key component to change from "good" to "warning" or "critical";

[0188] when When it increases: the greater the wear amount, the higher the physical degradation of the i-th key component, and the greater the risk of performance degradation;

[0189] will eventually lead to Increases, causing the status of the i-th key component to change from "good" to "warning" or "critical".

[0190] when and When they decrease at the same time: the stress on the i-th key component decreases and the degree of wear decreases.

[0191] will eventually lead to Reduce, maintain or restore to a "good" state.

[0192] Using the initial voltage regulation parameters and vibration data corresponding to the identified load type as input features and the component health index as output, data preprocessing and feature engineering are performed to construct a training dataset for machine learning. This includes:

[0193] Based on the vibration data, the fast Fourier transform (FFT) algorithm is applied to convert the time domain signal into the frequency domain signal, and the main frequency components, harmonic content and phase difference characteristic parameters are extracted;

[0194] Combined with the initial voltage regulation parameters, a comprehensive feature vector is constructed to ensure that the input features can fully reflect the load operating status and component wear conditions;

[0195] The pre-processed data is labeled according to different load types, including resistive load, inductive load and capacitive load categories;

[0196] The dataset is divided into training set and test set to ensure the effectiveness of model training and the reliability of evaluation.

[0197] Based on machine learning methods, a wear prediction model for each key component is constructed, and pre-trained algorithm models are used for training and optimization to predict the component's operational health index. Specifically, it includes:

[0198] The pre-trained algorithm model selects the convolutional neural network (CNN) model as the basic algorithm for wear degree prediction;

[0199] Use the training data set to train the CNN model and optimize the learning effect of the model by adjusting the network structure and hyperparameters;

[0200] Cross-validation technology is applied to prevent model overfitting and improve the generalization ability of the model.

[0201] The trained CNN model was validated using the test set data to evaluate its accuracy and stability in wear degree prediction.

[0202] Evaluation indicators such as mean square error (MSE), determination coefficient (R 2 ) etc., to quantify the prediction performance of the model and further optimize the model parameters based on the evaluation results.

[0203] Deploy the trained and optimized CNN model to the embedded system or server to ensure that it can receive input features and output component health index prediction results in real time.

[0204] Integrate the wear degree prediction model into the converter intelligent voltage management system to achieve real-time monitoring and prediction of the wear status of key components of the power supply load equipment.

[0205] Adjustment parameter optimization module: used to obtain the initial voltage adjustment parameters and vibration data of each key component at the current moment, and input these data into the wear degree prediction model to obtain the component operation health index prediction results of each key component; compare and analyze the component operation health index prediction results with the preset warning thresholds, and dynamically adjust the initial voltage adjustment parameters of each load type based on the analysis results.

[0206] Further explanation: the predicted operating health index of the i-th key component is output by the wear degree prediction model, and the predicted operating health index value is recorded as

[0207] Set the predicted value of the operational health index The warning threshold interval is [q1 i ,q2 i ], q1 i and q2 i are the lower and upper limits of the warning threshold interval, and 0.3≤q1 i <q2 i ≤0.7;q1 i and q2 i Determined by an expert panel using a ranking-based quantile calculation method; this method ranks and analyzes the component health index of the power supply load equipment's historical fault logs, selectively using the 25th and 75th percentile positions to set warning intervals;

[0208] Will run the health index prediction value The following status divisions are made:

[0209] when When , it means that the health status corresponding to the i-th key component is in a high-normal working state and no maintenance is required;

[0210] when When , it means that the health status of the i-th key component is medium, and it is recommended to perform inspection and maintenance;

[0211] when When , it means that the health status of the i-th key component is low and needs to be maintained or replaced immediately;

[0212] The lower the health status of key components, the higher the corresponding vibration and / or wear level;

[0213] Multiple key component sets {1,2,...,i,...,n} are matched and The key components are screened out to form a first screening set and a second screening set respectively;

[0214] The first screening set is denoted as i1∈{1, 2, ..., m1}, and {1, 2, ..., m1} is included in {1, 2, ..., i, ..., n}; i1 represents the index of the key component in the first screening set, and m1 is the index of the key component in the first screening set. The total number of key components;

[0215] The second screening set is denoted as i2∈{1, 2, ..., m2}, and {1, 2, ..., m2} is included in {1, 2, ..., i, ..., n}; i2 represents the index of the key component in the second screening set, and m2 is the index of the key component in the second screening set. The total number of key components; set m1+m2≤n;

[0216] Calculate the average predicted values of the operation health index of the first screening set and the second screening set respectively; get and

[0217] in, and are the average values of the predicted operating health index of the first and second screening sets, respectively;

[0218] Combine and By performing weight analysis, we obtain the following comprehensive judgment coefficient:

[0219]

[0220] Among them, Pd is the comprehensive judgment coefficient, a1 and a2 are the weight coefficients of the corresponding parameters, and a1+a2=1; the values of a1 and a2 are both within the interval (0,1); the valid value range of Pd is set within the interval (0,1); and the judgment threshold of Pd is set to Pd th , Pd th The value of is determined within the range of (0.2, 0.8);

[0221] When m1>m2, it means that The number of key components dominates, and a1>a2 is set at this time;

[0222] When m1=m2, it means that and The number of key components is the same, in this case, set a1 = a2;

[0223] When m1<m2, it means that The number of key components dominates, and a1 is set to be less than a2. The expert group uses the entropy weight method to determine the corresponding weights of a1 and a2.

[0224] If Pd>Pd thWhen E1 is the initial voltage regulation parameter for each load type k1 Execute the first-level adjustment strategy;

[0225] If Pd≤Pd th When E1 is the initial voltage regulation parameter for each load type k1 Execute secondary adjustment strategies;

[0226] The adjustment range of the first-level adjustment strategy is greater than the adjustment range of the second-level adjustment strategy.

[0227] Further explanation: Explanation of the first-level adjustment strategy:

[0228] When Pd>Pd th When the number of critical components with low health status is dominant, the initial voltage adjustment parameter E1 of each load type needs to be adjusted through the first-level adjustment strategy. k1 Make adjustments to improve the health of key components; the first-level adjustment strategy is characterized as follows:

[0229]

[0230] in,

[0231] ΔE1 k1 is the adjustment amplitude of the initial voltage regulation parameter in the first-level adjustment strategy,

[0232] η1 is the adjustment coefficient of the first-level adjustment strategy, and the value range of η1 is [0.1, 0.5];

[0233] When m1>m2, due to The number of key components dominates, so the value range of η1 is limited to [0.1, 0.25];

[0234] When m1≤m2, due to The number of key components dominates, so the value range of η1 is limited to (0.25,0.5];

[0235] The above η1 value setting is used to increase the η1 value as the health status level of the key component decreases, thereby increasing ΔE1. k1 The output value of , thereby increasing the adjustment range of the first-level adjustment strategy;

[0236] μ1 is a correction factor used to avoid |m2-m1|+μ1 being 0, and 0.1≤μ1≤0.2;

[0237] The reasons for adjusting the first-level adjustment strategy are as follows:

[0238] When the health status of multiple key components is low Pd>Pd th, by reducing the initial voltage regulation parameter E1 for each load type k1 , which can reduce the overall system load and reduce the pressure on key components with low health status, thereby delaying their further wear;

[0239] Extend equipment life: By reducing system load, reducing the working pressure of high-wear components, delaying the wear rate of equipment, and extending the overall service life of the equipment;

[0240] Reduce sudden failures: Reduce the wear rate of key components, reduce sudden failures caused by overload, and improve system stability and reliability.

[0241] Optimize operation strategy: adjust initial voltage parameters to make system operation more balanced and optimize overall operation efficiency.

[0242] Explanation of the secondary adjustment strategy:

[0243] When Pd≤Pd th When the health status is low, the number of key components is relatively small, and the initial voltage adjustment parameter E1 of each load type needs to be adjusted through the secondary adjustment strategy. k1 Adjustments are made to maintain stable operation of the system and further delay component wear. The secondary adjustment strategy is characterized as follows:

[0244]

[0245] in,

[0246] ΔE2 k1 is the adjustment amplitude of the initial voltage regulation parameter in the secondary adjustment strategy,

[0247] η2 is the adjustment coefficient of the secondary adjustment strategy, and the value range of η2 is [0.1, 0.3];

[0248] When m1>m2, due to The number of key components dominates, so the value range of η2 is limited to [0.1, 0.15];

[0249] When m1≤m2, due to The number of key components dominates, so the range of η2 is limited to (0.15, 0.3];

[0250] Set η2<η1; this setting is used to make ΔE2 k1 The adjustment range is less than ΔE1 k1 The adjustment is in line with;

[0251] The above η2 value setting is used to increase the η2 value as the health status of the key components decreases, thereby increasing ΔE2. k1The output value of , thereby increasing the adjustment range of the secondary adjustment strategy;

[0252] μ2 is a correction factor used to avoid |m2-m1|+μ2 being 0, and 0.1≤μ2≤0.2;

[0253] The reasons for adjusting the secondary adjustment strategy are as follows:

[0254] When the comprehensive judgment coefficient Pd≤Pd th , the number of high-wear components in the system is relatively small, and they are mainly concentrated in the medium wear state. By slightly adjusting the initial voltage regulation parameter E1 for each load type k1 , which can optimize system load, further delay component wear, and prevent moderate wear components from turning into severe wear.

[0255] Maintain system stability: By fine-tuning initial voltage parameters, the system can ensure stable operation under low load and reduce system instability caused by voltage fluctuations.

[0256] Delaying component wear: Small adjustments to voltage parameters help balance the pressure distribution of various load types, further delaying the wear rate of key components.

[0257] Reduce maintenance frequency: Through timely and subtle adjustments, medium-wear components can be prevented from deteriorating into high-wear conditions, reducing system maintenance frequency and costs.

[0258] Through the comprehensive judgment coefficient Pd, the system can evaluate the health status of key components in real time and dynamically select the first or second level adjustment strategy to flexibly respond to the needs of different system load states.

[0259] When the number of critical components with poor health status dominates, the first-level adjustment strategy makes large adjustments to high-wear components to quickly reduce system load and protect critical components.

[0260] When the number of critical components with low health status is relatively small, the secondary adjustment strategy makes subtle adjustments to the components with medium wear to further delay wear and optimize resource allocation.

[0261] By reasonably adjusting the initial voltage parameters, the system can be ensured to operate stably under different load types, reducing system instability and failures caused by uneven loads.

[0262] The combination of the primary and secondary adjustment strategies makes the system more adaptable and robust, able to cope with different operating environments and load changes, and ensure long-term stable operation.

[0263] Example 2:

[0264] In order to verify the effectiveness of the "first-level adjustment strategy and second-level adjustment strategy" of the present invention in practical applications, a set of experimental schemes was designed to optimize the initial voltage adjustment parameter E1 by comparing the experimental methods. k1 The experiment selected three types of loads: resistive, inductive, and capacitive, labeled k1=1, k1=2, and k1=3, respectively. The experimental equipment included a bidirectional inverter, various load devices, a sensor module (including a voltage sensor and a frequency sensor), a data processing module, and a control signal generation module.

[0265] First, an experimental platform was built to ensure that the bidirectional inverter could stably output voltage and frequency within the 180V to 260V range. Sensors were installed on key components to monitor the output voltage and frequency in real time and transmit the data to a data processing module. This module uses digital signal processing (DSP) technology to filter the collected feedback signals, removing noise and interference to ensure signal accuracy.

[0266] Set the judgment threshold Pd of the comprehensive judgment coefficient Pd th The value is 0.5, and the first-level adjustment strategy or the second-level adjustment strategy is selected according to different Pd values.

[0267] During the experiment, the effects of load parameter adjustment using a traditional PID control algorithm were compared with those using the proposed method. Two groups were used: a control group employed traditional PID control, while the experimental groups employed both a primary and a secondary adjustment strategy. Each experiment ran for 1000 hours, recording various metrics, including system failure rate, average equipment lifespan, maintenance costs, system response time, voltage fluctuation range, and energy consumption.

[0268] In the control group, the traditional PID control algorithm performs initial voltage regulation parameter E1 according to fixed proportional, integral and differential parameters. k1 Due to the lack of a dynamic adjustment mechanism, the system is unable to optimize and adjust parameters in a timely manner when the load changes or key components wear out. This leads to overload and wear of some key components, increasing system failure rates and maintenance costs. Furthermore, the system suffers from long response times, wide voltage fluctuations, and high energy consumption, which impacts overall operational efficiency.

[0269] In the experimental group, the first-level and second-level adjustment strategies dynamically adjust E1 based on the real-time feedback loop. k1 When the comprehensive judgment coefficient Pd>Pd th When Pd≤Pd th When E1 k1Make small adjustments to further optimize system operation and slow the wear of critical components with medium wear.

[0270] Comparative analysis revealed significant advantages in system failure rate, equipment lifespan, maintenance costs, system response time, voltage fluctuation range, and energy consumption. Specific data is shown in the table below. The experimental results show that the system using both the primary and secondary adjustment strategies effectively reduced system failure rate by 30%, extended average equipment lifespan by 25%, and reduced maintenance costs by 20%. Furthermore, system response time was shortened by 33.3%, voltage fluctuation range was reduced by 37.5%, and energy consumption was reduced by 20%.

[0271] Experimental data comparison table:

[0272]

[0273]

[0274] As can be seen from the table, the experimental group outperformed the control group in many key indicators:

[0275] 1. The system failure rate decreased from 10% to 7%, a 30% reduction. This demonstrates that the "primary and secondary adjustment strategies" effectively reduced system overload and the frequency of failures.

[0276] 2. The average equipment lifespan increased by 25%, from 5 years to 6.25 years. Dynamic adjustment of control parameters slowed component wear and extended equipment lifespan.

[0277] 3. Maintenance costs were reduced by 20% from 500,000 yuan to 400,000 yuan. The reduction in failure rate and the extension of equipment life directly reduced maintenance frequency and related costs.

[0278] 4. The system response time is shortened from 150 milliseconds to 100 milliseconds, which improves the response speed and enhances the dynamic performance of the system.

[0279] 5. The voltage fluctuation range is reduced from 8% to 5%, showing that the system output is more stable and reducing the potential impact of voltage fluctuations on equipment.

[0280] 6. Energy consumption is reduced from 500 kWh to 400 kWh, saving 20% of energy and improving the overall energy efficiency of the system.

[0281] 7. The reduction in the adjustment amplitude indicates that the system has reduced the demand for fluctuations in the adjustment parameters while optimizing the operating state.

[0282] 8. The system stability score increased from 6.5 to 8.5, reflecting a significant improvement in the system's operational stability.

[0283] 9. The wear rate of key components was reduced from 20% to 14%, further verifying the effectiveness of the control algorithm in reducing component wear.

[0284] 10. The comprehensive judgment coefficient dropped from 0.7 to 0.4, indicating that the overall health of the system has been significantly improved.

[0285] The beneficial effects of the table analysis are as follows:

[0286] 1. Reduce system failure rate: By dynamically optimizing the initial voltage regulation parameters, the overload of key components is reduced, significantly reducing the probability of system failure.

[0287] 2. Extend equipment life: The optimized adjustment strategy slows down the wear rate of key components and extends the overall service life of the equipment.

[0288] 3. Reduce maintenance costs: The reduction in failure rate and the extension of equipment life directly reduce maintenance frequency and maintenance costs, and improve the economic benefits of the system.

[0289] 4. Improve system response speed: The shortened response time enables the system to respond to load changes more quickly, improving dynamic performance.

[0290] 5. Enhanced system stability: Reduced voltage fluctuation range and higher stability scores ensure smooth operation of the system under different load conditions, reducing potential damage caused by voltage deviations.

[0291] 6. Energy saving: Reduced energy consumption not only reduces operating costs, but also improves the environmental performance of the system.

[0292] 7. Optimize resource allocation: Through scientific parameter adjustment strategies, system resources are effectively allocated, improving overall operating efficiency and reliability.

[0293] It should be noted that all calculation formulas in this application document utilize, including but not limited to, regression analysis within machine learning algorithms to deeply analyze the collected parameters and identify their natural trends and interrelationships. Professional software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Model performance is then objectively evaluated through methods such as cross-validation, combined with continuous feedback and optimization to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their validity and accuracy, and ensuring that the calculation process complies with the constraints of natural laws rather than being based on artificially set rules.

[0294] The technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0295] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0296] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0297] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent voltage management system for converters based on AC / DC conversion, characterized in that: Specifically, it includes a power input protection module, a bidirectional rectification and power compensation module, a high-frequency isolation and voltage reduction module, a bidirectional inverter and rectification efficiency improvement module, and a voltage superposition and output module, which are connected in sequence. In addition, it also includes an initial voltage regulation module, among which: Initial voltage regulation module: This module collects and analyzes the AC signal from the bidirectional rectifier input and the DC signal from the bidirectional inverter input to build a load identification model. The load identification model is used to identify the load type of the power supply device and apply the corresponding initial voltage regulation parameters to each load type. Wear prediction model building module: This module identifies multiple key components of the power supply load equipment and, based on the initial voltage regulation parameters corresponding to different load types, analyzes the vibration and wear data collected from each key component to generate a component health index. The initial voltage regulation parameters and vibration data corresponding to the identified load type are used as input features, and the component health index is used as the output to build a wear prediction model for each key component based on a machine learning prediction model. Adjustment parameter optimization module: used to obtain the initial voltage adjustment parameters and vibration data of each key component at the current moment, and input these data into the wear degree prediction model to obtain the component operation health index prediction results of each key component; compare and analyze the component operation health index prediction results with the preset warning thresholds, and dynamically adjust the initial voltage adjustment parameters of each load type based on the analysis results.

2. The intelligent voltage management system for converters based on AC / DC conversion according to claim 1, characterized in that: Power input protection module: used to introduce AC power from the low-voltage end of the distribution transformer; Bidirectional rectification and power compensation module: used to convert the AC power introduced from the low-voltage end into a high DC voltage using a bidirectional rectifier, wherein the bidirectional rectifier is configured to allow energy to flow in both directions; High-frequency isolation step-down module: used to step down the obtained high DC voltage to a low DC voltage through a high-frequency isolation transformer; Bidirectional inverter and rectifier efficiency improvement module: used to convert low DC voltage into low voltage AC power using a bidirectional inverter; Voltage superposition and output module: used to connect low-voltage AC power in series with the low-voltage output end of the distribution transformer through the voltage superposition module to generate the target total output voltage range for powering load equipment; The power input protection module is connected to the converter intelligent voltage management system via a standard cable; The power input protection module includes a high-performance standard cable connection unit and an intelligent circuit breaker protection unit; The intelligent circuit breaker protection unit is installed at the power input end and has overload protection, short circuit protection, undervoltage protection, overvoltage protection and leakage protection functions; The bidirectional rectifier performs rectification, converting the AC signal into a DC400V high DC voltage; Output the rectified high DC voltage to the subsequent high-frequency isolation step-down module; When the converter intelligent voltage management system needs to feed DC400V DC power back to the AC grid, the DC signal is converted into an AC signal through the reverse operation of the bidirectional rectifier.

3. The intelligent voltage management system for converters based on AC / DC conversion according to claim 2, characterized in that: The high-frequency isolation buck module includes: Preliminary filtering unit: set at the high DC voltage input end, suppressing high-frequency electromagnetic interference of the input power supply through high-frequency EMI filter; Energy isolation and step-down unit: High DC voltage is input to the primary side of the transformer through a high-frequency isolation transformer, and a low DC voltage of DC80V is directly obtained through electromagnetic energy conversion; Filtering and voltage stabilization unit: At the low DC voltage DC80V output end, the residual voltage ripple is filtered out through a multi-stage LC filter; Use a bidirectional inverter to invert the low DC voltage DC80V generated by the high-frequency isolation step-down module into low-voltage AC power; The peak value range of the low voltage AC is set to 40V, and the instantaneous voltage range during operation is -40V to 40V.

4. The intelligent voltage management system for converters based on AC / DC conversion according to claim 3, characterized in that: The voltage superposition and output module includes an input configuration unit, a voltage superposition module and a total output voltage adjustment unit; The low voltage AC power is connected to the low voltage output terminal of the distribution transformer through the input configuration unit; The voltage superposition module superimposes the low-voltage AC power and the low-voltage output voltage of the distribution transformer to generate the target total output voltage range; Set the low-voltage output terminal of the distribution transformer to 220V; set the generated target total output voltage range to 180V to 260V; The total output voltage regulation unit dynamically optimizes the superimposed voltage to ensure that the voltage range is between 180V and 260V; The converter is defined to include a bidirectional rectifier, a high-frequency isolation transformer, a bidirectional inverter, and a voltage superposition module.

5. The intelligent voltage management system for converters based on AC / DC conversion according to claim 4, characterized in that: The steps to build a load identification model include: Monitor the AC signal at the input of the bidirectional rectifier and the DC signal at the input of the bidirectional inverter in real time, convert the acquired AC and DC signals into digital signals through a digital converter, and transmit the converted digital signals to the embedded microcontroller through a data acquisition card; Both AC and DC signals include voltage, current, and phase information; The obtained digital signal is analyzed in the frequency domain by the fast Fourier transform algorithm of the embedded microcontroller to extract the main frequency components, harmonic content and phase difference characteristic parameters; A pre-trained convolutional neural network model is deployed on an embedded microcontroller to perform real-time classification and identification of the load type of the powered load device based on the extracted feature parameters. The load classification results include resistive load, inductive load, and capacitive load. The corresponding initial voltage regulation parameters are selected based on the load classification result, and a control instruction is sent to the bidirectional inverter.

6. The intelligent voltage management system for converters based on AC / DC conversion according to claim 5, characterized in that: For resistive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "maintain output voltage stability," quantified as the target range of voltage amplitude. The target range of voltage amplitude is recorded as E target,resistive =[VU min ,VU max ]; E target,resistive is the target range of voltage amplitude used to characterize resistive loads; VU min is the minimum voltage amplitude; VU max is the maximum voltage amplitude; Sending instructions to the bidirectional inverter to continuously monitor and adjust the output voltage within the set voltage amplitude target range; For inductive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "power factor correction" and quantify it as the target value of the phase angle. The target value of the phase angle is denoted as φ target,inductive =arccos(PF desired ); Among them, φ target,inductive is the target phase angle value used to characterize inductive loads; PF desired is the desired power factor; Send control instructions to the bidirectional inverter to adjust the load angle; For capacitive loads: Set the initial voltage regulation parameter of the bidirectional inverter to "reduce output voltage amplitude," which is quantified as reducing the voltage amplitude range. The reduced voltage amplitude range is recorded as E target,capacitive =[VU reduce,min ,VU reduce,max ]; Among them, E target,capacitive It is a reduced voltage amplitude range used to characterize capacitive loads; VU reduce,min It is the minimum value to reduce the voltage amplitude; VU reduce,max It is the maximum value of the reduced voltage amplitude; Sending control instructions to the bidirectional inverter to adjust the output voltage amplitude down to within the set reduced voltage amplitude range; The resistive load, inductive load and capacitive load are denoted as k1, and k1∈{1,2,3}, {1,2,3} represent the resistive load, inductive load and capacitive load respectively; The initial voltage regulation parameter of load type k1 is recorded as E1 k1 , 7. The intelligent voltage management system for converters based on AC / DC conversion according to claim 6, characterized in that: Set the set of multiple key components to be {1,2,...,i,...,n}, where i represents the i-th key component and n is the total number of key components; Generation of component health index, including: The vibration data is characterized as the vibration amplitude fluctuation coefficient, and the initial voltage adjustment parameter E1 of load type k1 is k1 Under the condition of , calculate the vibration amplitude fluctuation coefficient of the i-th key component in the current monitoring time period set up The valid value range of is the interval (0,1); The larger the value, the greater the vibration amplitude of the i-th key component, and the greater the impact on the wear degree; Initial voltage regulation parameter E1 at load type k1 k1 Calculate the wear of the i-th key component in the current working condition monitoring period set up The valid value range of is the interval (0,1); The larger the value, the greater the wear of the i-th key component, which means the worse the health status of the i-th key component; The vibration amplitude fluctuation coefficient of the i-th key component and wear Perform combined analysis to obtain the following component health indexes: Among them, α is the weight coefficient of the vibration amplitude fluctuation coefficient, β is the weight coefficient of the wear amount, α+β=1, and the values of α and β are both in the interval (0,1); set The valid value range of is the interval (0,1); when The closer it is to 0, the lower the vibration and / or wear of the i-th key component is, which means the health status of the i-th key component is better; when The closer it is to 1, the higher the vibration and / or wear level of the i-th key component is, which means the health status of the i-th key component is worse; Using the initial voltage regulation parameters and vibration data corresponding to the identified load type as input features and the component health index as output, data preprocessing and feature engineering are performed to construct a training dataset for machine learning. A wear degree prediction model for each key component is constructed based on machine learning methods, and pre-trained algorithm models are used for training and optimization to predict the component's operating health index.

8. The intelligent voltage management system for converters based on AC / DC conversion according to claim 7, characterized in that: The predicted operating health index of the i-th key component is output by the wear degree prediction model, and the predicted operating health index value is recorded as Set the predicted value of the operational health index The warning threshold interval is [q1 i ,q2 i ], q1 i and q2 i are the lower and upper limits of the warning threshold interval, and 0.3≤q1 i <q2 i ≤0.7; Will run the health index prediction value The following status divisions are made: when When , it means that the health status corresponding to the i-th key component is in a high-normal working state and no maintenance is required; when When , it means that the health status of the i-th key component is medium, and it is recommended to perform inspection and maintenance; when When , it means that the health status of the i-th key component is low and needs to be maintained or replaced immediately; The lower the critical component health level, the higher the corresponding vibration and / or wear level.

9. The intelligent voltage management system for converters based on AC / DC conversion according to claim 8, characterized in that: Multiple key component sets {1,2,...,i,...,n} are matched and The key components are screened out to form a first screening set and a second screening set respectively; The first screening set is denoted as i1∈{1, 2, ..., m1}, and {1, 2, ..., m1} is included in {1, 2, ..., i, ..., n}; i1 represents the index of the key component in the first screening set, and m1 is the index of the key component in the first screening set. The total number of key components; The second screening set is denoted as i2∈{1, 2, ..., m2}, and {1, 2, ..., m2} is included in {1, 2, ..., i, ..., n}; i2 represents the index of the key component in the second screening set, and m2 is the index of the key component in the second screening set. The total number of key components; Set m1+m2≤n; Calculate the average predicted values of the operation health index of the first screening set and the second screening set respectively; get and in, and are the average values of the predicted operating health index of the first and second screening sets, respectively; Combine and By performing weight analysis, we obtain the following comprehensive judgment coefficient: Among them, Pd is the comprehensive judgment coefficient, a1 and a2 are the weight coefficients of the corresponding parameters, and a1+a2=1; the values of a1 and a2 are both within the interval (0,1); the valid value range of Pd is set within the interval (0,1); and the judgment threshold of Pd is set to Pd th , Pd th The value of is determined within the range of (0.2, 0.8); When m1>m2, it means that The number of key components dominates, and a1>a2 is set at this time; When m1=m2, it means that and The number of key components is the same, in this case, set a1 = a2; When m1<m2, it means that The number of key components dominates, and a1<a2 is set at this time; If Pd>Pd th When E1 is the initial voltage regulation parameter for each load type k1 Execute the first-level adjustment strategy; If Pd≤Pd th When E1 is the initial voltage regulation parameter for each load type k1 Execute secondary adjustment strategies; The adjustment range of the first-level adjustment strategy is greater than that of the second-level adjustment strategy.

10. The intelligent voltage management system for converters based on AC / DC conversion according to claim 9, characterized in that: Explanation of the first-level adjustment strategy: When Pd>Pd th When the number of critical components with low health status is dominant, the initial voltage adjustment parameter E1 of each load type needs to be adjusted through the first-level adjustment strategy. k1 Make adjustments to improve the health of key components; The first-level adjustment strategy is characterized as follows: E1 k1,new =E1 k1 -ΔE1 k1 ; in, ΔE1 k1 is the adjustment amplitude of the initial voltage regulation parameter in the first-level adjustment strategy, η1 is the adjustment coefficient of the first-level adjustment strategy, and the value range of η1 is [0.1, 0.5]; When m1>m2, due to The number of key components dominates, so the value range of η1 is limited to [0.1, 0.25]; When m1≤m2, due to The number of key components dominates, so the value range of η1 is limited to (0.25,0.5]; μ1 is a correction factor used to avoid |m2-m1|+μ1 being 0, and 0.1≤μ1≤0.2; Explanation of the secondary adjustment strategy: When Pd≤Pd th When the health status is low, the number of key components is relatively small, and the initial voltage adjustment parameter E1 of each load type needs to be adjusted through the secondary adjustment strategy. k1 Make adjustments; The secondary adjustment strategy is characterized as follows: E1 k1,new =E1 k1 -ΔE2 k1 ; in, ΔE2 k1 is the adjustment amplitude of the initial voltage regulation parameter in the secondary adjustment strategy, η2 is the adjustment coefficient of the secondary adjustment strategy, and the value range of η2 is [0.1, 0.3]; When m1>m2, due to The number of key components dominates, so the value range of η2 is limited to [0.1, 0.15]; When m1≤m2, due to The number of key components dominates, so the value range of η2 is limited to (0.15,0.3]; μ2 is a correction coefficient used to prevent |m2-m1|+μ2 from being 0, and 0.1≤μ2≤0.2.

Images