New energy automobile intelligent DCDC converter integrated charger

Abstract

The application provides a new energy automobile intelligent DCDC converter integrated charger, and relates to the field of power electronic technology of new energy automobiles.The charger comprises a main circuit module, a sensor module, a data processing module, a machine learning module, a control execution module and a communication module; the main circuit module integrates a vehicle-mounted charger, a DCDC conversion and a high-voltage power distribution unit, realizing miniaturization of the equipment; the sensor module collects multi-dimensional parameters, which are analyzed by the machine learning module after data processing; a built-in prediction model in the machine learning module can predict the service life and fault risk of components, and a dynamic adjustment model generates a power adjustment strategy in combination with road conditions and battery states; the control execution module realizes power adjustment, hierarchical protection and mode smooth switching according to the analysis results.The application improves the energy conversion efficiency, system safety and working condition adaptability through integrated design and intelligent algorithm, and meets the requirements of high efficiency, safety and intelligence of new energy automobiles.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electric power electronic technology for new energy vehicles, and particularly relates to a new energy vehicle intelligent DCDC converter integrated charger. BACKGROUND

[0002] Various power conversion devices such as motor drive inverters, chargers for charging high-voltage batteries from commercial power sources, and DCDC converters for powering auxiliary batteries are installed in electric vehicles, hybrid vehicles, and the like. Switching circuits that generate large high-frequency noise are used in chargers and power conversion devices.

[0003] With the rapid development of the new energy vehicle industry, higher requirements are placed on the performance, reliability, and integration of on-board charging equipment. Traditional on-board chargers and DCDC converters are independent of each other, and have problems such as large size, heavy weight, high cost, and low energy conversion efficiency. At the same time, under complex driving conditions and battery state changes, it is difficult to achieve precise power regulation and intelligent management, and it is difficult to fully meet the development needs of new energy vehicles for high efficiency, safety, and intelligence. For example, under different road conditions, the charging and discharging requirements of the vehicle for the battery differ greatly, and the traditional charger cannot quickly respond and optimize energy distribution; when the battery is aging or the temperature is abnormal, there is also a lack of effective protection and adaptive adjustment mechanism.

[0004] Therefore, it is necessary to provide a new energy vehicle intelligent DCDC converter integrated charger to solve the above technical problems. SUMMARY

[0005] The present application aims to provide a new energy vehicle intelligent DCDC converter integrated charger, which realizes the miniaturization, lightweight, high efficiency, and intelligence of the charging equipment through highly integrated design, intelligent control algorithm, and multi-mode collaborative working mechanism, and improves the overall performance and safety of new energy vehicles.

[0006] To solve the above technical problems, the new energy vehicle intelligent DCDC converter integrated charger provided by the present application comprises:

[0007] A main circuit module integrated with an on-board charger unit, a DCDC conversion unit, and a high-voltage power distribution unit;

[0008] A sensor module comprising a plurality of sensor groups, respectively arranged on each key component of the main circuit module, for collecting electrical parameters and physical state parameters of the corresponding components;

[0009] A data processing module connected to the sensor module for receiving and preprocessing the electrical parameters and physical state parameters; wherein preprocessing includes filtering, calibration, normalization, and feature extraction;

[0010] The machine learning module, connected to the data processing module, has a built-in trained prediction model and dynamic adjustment model, which are used to analyze and calculate the preprocessed electrical parameters and physical state parameters.

[0011] A control execution module is connected to both the machine learning module and the main circuit module, and is used to control the operating state of the main circuit module based on the output of the machine learning module.

[0012] The communication module is used to enable data interaction with the vehicle controller and battery management system, and to receive road condition information and battery status information.

[0013] As a preferred embodiment of the present invention, the sensor module includes:

[0014] Voltage sensor array, used to collect input voltage, output voltage and voltage of each key node;

[0015] A current sensor array is used to collect input current, output current, and current in each branch.

[0016] Temperature sensor array, used to collect temperature data of power devices, inductor temperature and ambient temperature;

[0017] Vibration sensors are used to collect vibration parameters of critical components;

[0018] Insulation monitoring sensors are used to monitor the insulation status of a system.

[0019] As a preferred embodiment of the present invention, the machine learning module includes:

[0020] The predictive maintenance unit, based on the preprocessed electrical and physical state parameters, predicts the remaining service life and potential failure risks of each component through the predictive model.

[0021] The dynamic energy distribution unit, combining the road condition information and battery status information, generates a DC-DC output power regulation strategy through the dynamic adjustment model;

[0022] The model update unit is used to optimize the prediction model and the dynamic adjustment model online based on actual operating data.

[0023] As a preferred embodiment of the present invention, the predictive maintenance unit includes:

[0024] The input feature processing subunit is used to standardize the preprocessed time series parameters;

[0025] LSTM prediction networks are used to process temporal features through an improved gating mechanism to achieve temporal analysis of component states.

[0026] The remaining useful life calculation subunit is used to calculate and predict the remaining useful life based on the component degradation evolution curve and failure threshold.

[0027] The fault risk assessment subunit is used to calculate the health status based on the amount of degradation and to output the fault warning level by matching the five-level fault warning level.

[0028] The model optimization subunit is used to optimize the parameters of the prediction model using the Adam optimizer and the joint loss function.

[0029] As a preferred embodiment of the present invention, the dynamic adjustment model includes a road condition identification sub-model and a power optimization sub-model:

[0030] The road condition recognition sub-model identifies the current road type, gradient, and congestion status based on the received road condition information;

[0031] The power optimization sub-model dynamically adjusts the output voltage and current of the DC-DC converter based on road condition identification results and battery status information.

[0032] The control execution module includes:

[0033] The power regulation unit is used to regulate the output power of the DC-DC converter;

[0034] The protection control unit performs overvoltage, overcurrent, and overheat protection actions based on the output of the predictive maintenance unit and real-time electrical and physical state parameters.

[0035] The mode switching unit is used to automatically switch between charging and discharging modes and power levels.

[0036] As a preferred embodiment of the present invention, the present invention further includes a storage module for storing historical electrical parameters and physical states, model parameters and fault records.

[0037] As a preferred embodiment of the present invention, the protection control unit performs graded protection actions in conjunction with the fault warning level:

[0038] When the fault warning level is level two, the output power will be reduced to the rated value of the preset level one ratio, and the cooling system will be controlled to run at the preset low speed.

[0039] When the fault warning level is level three, the output power will be reduced to the rated value of the preset level two ratio, and the cooling system will be controlled to run at the preset high speed.

[0040] When the fault warning level is level four, the preset non-critical load output is shut down;

[0041] When the fault warning level is level 5, the main circuit relay is disconnected, triggering a vehicle fault alarm and uploading data to the cloud.

[0042] Compared with related technologies, the integrated charger for intelligent DC-DC converters for new energy vehicles provided by this invention has the following advantages:

[0043] 1. This invention reduces the redundant structure of traditional independent equipment and lowers energy transmission losses by integrating an on-board charger, DC-DC converter, and high-voltage power distribution unit; at the same time, the dynamic adjustment model optimizes power distribution based on road conditions and battery status, further improving energy utilization efficiency and achieving equipment miniaturization and lightweighting.

[0044] 2. This invention utilizes multiple sensors to collect electrical and physical parameters in real time, combines LSTM networks to predict the remaining lifespan and failure risk of components, and implements overvoltage, overcurrent, and overheat protection through a graded protection mechanism to provide early warning of potential faults, avoid sudden failures, and ensure the stable operation of the vehicle's power system.

[0045] 3. This invention accurately determines road type, slope and congestion status through a road condition recognition sub-model, and dynamically adjusts the output power in conjunction with battery health and temperature parameters to match different driving conditions. A linear transition algorithm is used when switching modes to avoid voltage and current surges, thereby improving user experience and device adaptability.

[0046] In summary, this invention achieves high efficiency, high reliability, and intelligent adaptation of new energy vehicle charging equipment by integrating multiple modules to reduce energy loss, using multiple sensors and intelligent algorithms to predict faults and implement graded protection to improve safety, and dynamically adjusting power based on road conditions and battery status and optimizing mode switching through a linear transition algorithm. Attached Figure Description

[0047] Fig. 1 A connection diagram of the overall module of the integrated charger for intelligent DC-DC converters for new energy vehicles provided by the present invention;

[0048] Fig. 2 This is a diagram showing the internal unit connection relationships of the machine learning module provided by the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “group,” “class,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0051] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0052] Please refer to the following: Figs. 1-2 A smart DC-DC converter integrated charger for new energy vehicles, including:

[0053] The main circuit module integrates an on-board charger unit, a DC-DC converter unit, and a high-voltage power distribution unit. The on-board charger unit is used to convert external AC power into DC power, the DC-DC converter unit is used to convert high-voltage DC power into low-voltage DC power, and the high-voltage power distribution unit is used to distribute and protect the high-voltage power.

[0054] The sensor module includes multiple sensor groups, which are respectively set on key components of the main circuit module to collect electrical and physical state parameters of the corresponding components; the key components include, but are not limited to, power devices, inductors, capacitors, input / output ports and housings of the main circuit module.

[0055] The data processing module, connected to the sensor module via a signal cable, is used to receive and preprocess the raw electrical and physical state parameters; the preprocessing includes filtering, calibration, normalization, and feature extraction.

[0056] The machine learning module, connected to the data processing module, has a built-in pre-trained prediction model and dynamic adjustment model, which are used to analyze and calculate the pre-processed electrical parameters and physical state parameters.

[0057] The control execution module is connected to the machine learning module and the main circuit module via a control bus. It is used to receive control commands output by the machine learning module and convert them into drive signals to control the operating state of the main circuit module.

[0058] The communication module connects to the vehicle controller and battery management system via the vehicle network interface to enable data interaction with external systems. It receives road condition information, including road gradient, vehicle speed, and traffic conditions, as well as battery status information, including battery state of charge, health status, and temperature.

[0059] It should be noted that the composition and function of each core module in this charger, the integrated design of the main circuit module reduces the redundancy of traditional independent equipment, the multi-dimensional data collection of the sensor module provides a basis for intelligent analysis, and the modules form a closed loop of data collection, processing, analysis and control through data interaction. This not only realizes the miniaturization of the device, but also lays the hardware and data foundation for subsequent intelligent adjustment and protection, and improves the system integration and collaborative efficiency.

[0060] In this invention, the sensor module includes:

[0061] The voltage sensor group includes an AC voltage sensor located at the AC input terminal, a DC voltage sensor located at the DC output terminal, and node voltage sensors at key nodes of the main circuit, used to collect input voltage. High voltage DC output voltage Low-voltage DC output voltage and node voltages of each critical node (n=1,2,...,N, where N is the number of nodes), and denoted as the voltage feature subset. ;

[0062] A current sensor array, comprising current sensors installed in the main input circuit, the main output circuit, and each branch circuit, is used to collect the total AC input current. DC input total current DC output total current and branch current (m=1,2,...,M, where M is the number of branches), and denoted as the current characteristic subset. ;

[0063] The temperature sensor array includes a contact sensor attached to the surface of the power device, an inductive temperature sensor embedded in the inductive winding, a capacitive temperature sensor attached to the capacitor casing, and an ambient temperature sensor, used to collect the temperature of the power device. (k=1,2,...,K, where K is the number of power devices), inductor temperature capacitor temperature and ambient temperature And denoted as a subset of temperature features. ;

[0064] Vibration sensors are used to collect vibration parameters of key components: MEMS triaxial accelerometers are used, installed on the main circuit module housing and at the mounting locations of key components, to collect vibration acceleration along the X, Y, and Z axes. Then calculate the effective value of vibration. The calculation formula is: , This represents the integral within a set time window; it measures the vibration acceleration along the X, Y, and Z axes. With vibration effective value Let it be a subset of vibration characteristics. ;

[0065] An insulation monitoring sensor is used to monitor the insulation status of a system. It employs a balanced bridge method to monitor the system's insulation status, including a first measurement branch connected in series between the high-voltage positive electrode and ground, and a second measurement branch connected in series between the high-voltage negative electrode and ground. Each measurement branch contains a reference resistor with a known resistance and a controllable switch. By controlling the on / off state of the switch, the voltage at the measurement point under different states is collected, and the insulation resistance is then calculated. Its calculation of insulation resistance Calculated using the following formula: ,in Given the resistance value of the reference resistor, The voltage across the reference resistor is used as the reference value. The voltage value at the measurement point. ( ) represents the high-voltage DC bus voltage; the insulation resistance at each measurement point is... Let it be denoted as the insulation resistance characteristic subset R.

[0066] It should be noted that by refining the deployment location, acquisition parameters, and data processing methods of each sensor group, comprehensive monitoring of the main circuit's electrical performance (voltage, current), component status (temperature, vibration), and system safety (insulation) is achieved. The multi-dimensional feature subset provides accurate input for the subsequent state prediction and dynamic adjustment of the machine learning module, ensuring the integrity of monitoring and laying a data foundation for intelligent control, thereby improving the accuracy and comprehensiveness of system state perception.

[0067] In this invention, the machine learning module includes:

[0068] Predictive maintenance units, based on electrical and physical condition parameters, use predictive models to predict the remaining service life and potential failure risks of each component.

[0069] The dynamic energy distribution unit combines road condition information and battery status information to generate a DC-DC output power regulation strategy through a dynamic adjustment model;

[0070] The model update unit is used to optimize the prediction model and the dynamic adjustment model online based on actual operating data. The parameter update formula is as follows: ,in For the updated parameters, For parameters before the update, For learning rate, Here, represents the parameter of the i-th local model, and N represents the number of models participating in the aggregation.

[0071] It should be noted that by setting up a machine learning module, the predictive maintenance unit can predict the status of components, the dynamic energy distribution unit can optimize power regulation, and the model update unit can support online algorithm iteration. The collaboration of these three components not only ensures the system's forward-looking maintenance and efficient energy management, but also improves the intelligence level and long-term applicability of the solution by adapting to different working conditions through model self-optimization.

[0072] In this invention, the predictive maintenance unit includes:

[0073] The input feature processing subunit receives the timing parameters of electrical parameters and physical state parameters preprocessed by the data processing module. The timing parameters include voltage feature subset, current feature subset, temperature feature subset, vibration feature subset and insulation resistance feature subset, and each feature subset is standardized to the interval [0-1].

[0074] The LSTM prediction network consists of an input layer, three hidden layers, and two output layers. The input layer has a 16-dimensional dimension (corresponding to 16 feature parameters), and each hidden layer contains 64 LSTM units. The hidden layers process temporal features through an improved gating mechanism of the LSTM units. The core computations include the input gate, forget gate, output gate, and cell state update, as shown below:

[0075] The forgetting gate is used to determine the proportion of a cell's state from previous time steps that is retained. ,in The output of the forget gate at time t is a value between 0 and 1, with more information retained as it approaches 1. Here is the forget gate weight matrix. Output of the hidden layer at the previous moment With current input The concatenated vector, Input features for the current time step. For the offset of the forget gate, ( () is the Sigmoid activation function;

[0076] The input gate and candidate cell state are used to determine the input and update of new information at the current moment. , ,in, The output of the input gate at time t is used to control the proportion of new information input; Let represent the candidate cell state at time t. , These are the weight matrices corresponding to the input gate and the cell state, respectively. , These are the biases corresponding to the input gate and the cell state, respectively. It is the hyperbolic tangent activation function;

[0077] Cell state updates are used to fuse historical information with current information. ,in This represents the cell state at time t. This represents the cell state at the previous moment. This is element-wise multiplication;

[0078] Output gate: determines the output of the current cell state. , ,in, The output of the output gate at time t. This is the output vector of the hidden layer at the current time. This is the weight matrix of the output gate. For the output gate bias;

[0079] The remaining useful life calculation subunit extracts long-term dependent features through a fully connected layer to fit the component degradation amount. The temporal evolution curve (specifically, the degradation amount mapped through fully connected layers) , (Calculated for fully connected layers), combined with a preset failure threshold. The predicted remaining useful life is calculated using the following formula. :

[0080] ,in For degradation rate, The preset credit limit lifespan, The preset collection interval;

[0081] The fault risk assessment subunit calculates health status based on the amount of degradation. The formula is Set five levels of fault warning, including Level 1 no warning, Level 2 minor warning, Level 3 moderate warning, Level 4 severe warning, and Level 5 emergency warning; match the health status with the five warning levels to output the predicted fault warning level F for the corresponding component;

[0082] The model optimization subunit uses the Adam optimizer and a joint loss function: We perform parameter optimization, where MSE is the mean squared error and CE is the cross-entropy loss.

[0083] It should be noted that by refining the functions and algorithm logic of each sub-unit of the predictive maintenance unit, standardizing input features to ensure data consistency, improving the LSTM network to accurately capture temporal features, combining fully connected layers and formula calculations to achieve remaining lifetime prediction and five-level fault warning, and using the Adam optimizer and joint loss function to improve model accuracy, the overall system achieves accurate prediction of component status and continuous model optimization, providing reliable support for the system's forward-looking maintenance and enhancing operational safety and stability.

[0084] In this invention, the dynamic adjustment model includes a road condition identification sub-model and a power optimization sub-model, specifically:

[0085] The traffic condition recognition sub-model identifies the current road type, gradient, and congestion status based on the received traffic information, specifically:

[0086] Road type identification involves acquiring road condition information, including vehicle speed, acceleration, braking frequency, and distance; and extracting feature vectors from this road condition information. This includes the average vehicle speed within a set time window. Vehicle speed variance Average distance from the vehicle in front and braking frequency The probability of each road type is calculated using a softmax classifier. The formula is: ,in This is a classification weight matrix (corresponding to 3 road types, including urban roads, highways, and mountain roads). This is the classification bias vector; the category corresponding to the maximum probability of each road type is taken as the road condition recognition result.

[0087] Slope calculation is based on vehicle dynamics equilibrium equations, combined with acceleration and resistance parameters to calculate road slope. The formula is ,in Let m be the vehicle's acceleration, and m be the vehicle's mass. This is expressed as the vehicle's driving resistance (its calculation formula is...). , Indicates air density, (where A represents the air resistance coefficient, A represents the vehicle's frontal area), and g is the acceleration due to gravity.

[0088] Congestion status is determined by quantifying the current traffic condition using a congestion index, and a traffic condition assessment value is calculated. The formula is ;in The current free-flow velocity of the road;

[0089] A preset congestion state group is provided, including smooth traffic, slow traffic, and congestion. The traffic state assessment value is compared with the preset congestion state group to output the corresponding congestion state.

[0090] The power optimization sub-model dynamically adjusts the output voltage and current of the DC-DC converter based on road condition identification results and battery status information, specifically:

[0091] The baseline power is calculated based on the current low-voltage load requirements and the battery's basic state, using the following formula: ;in As the reference output power, Based on the actual power requirements of current low-voltage electrical equipment, The power factor is the standby power factor, and SOC is the battery state of charge.

[0092] The road condition correction factor is calculated by dynamically adjusting the base power based on road gradient and congestion conditions. The expression is: ;in , These are the correction factors for uphill and downhill slopes, respectively. This is a congestion correction factor;

[0093] It should be noted that the reserve power factor Uphill and downhill correction factors , With battery state correction factor Specific values ​​need to be determined by those skilled in the art through routine experiments;

[0094] The battery state correction factor is calculated by performing a secondary correction based on the battery health status and temperature parameters. The expression is as follows: Where SOH represents the battery's state of health. The current temperature of the battery. For the optimal operating temperature of the battery, , , These are the correction coefficients for the corresponding parameters;

[0095] The target output parameters are determined, and the final output parameters are calculated based on the above correction results. The final output parameters include the target output power. Target output voltage Target output current ,expression:

[0096] , , ;

[0097] in Indicates the reference output voltage. This represents the correction factor for the output voltage based on the battery's health status.

[0098] During the adjustment process, the rate of change of each output parameter is calculated, and a maximum allowable change threshold is preset. If the rate of change is greater than the preset maximum allowable change threshold, the preset allowable change limit value corresponding to the output parameter is taken to ensure the smoothness and stability of power adjustment.

[0099] It should be noted that the road condition recognition sub-model accurately determines the road type, slope and congestion status, and the output parameters are dynamically adjusted by combining the multi-level correction mechanism (baseline power + road condition correction + battery status correction) of the power optimization sub-model. At the same time, the smoothness of the adjustment is ensured by the preset change threshold. This not only achieves accurate matching of energy distribution with driving conditions and battery status, but also improves the stability of power adjustment and enhances the energy efficiency and adaptability of the system.

[0100] In this invention, the control execution module includes a power regulation unit, a protection control unit, and a mode switching unit, as detailed below:

[0101] The power regulation unit is used to regulate the output power of the DC-DC converter, specifically:

[0102] Composed of a digital signal processor and a drive circuit, it achieves dynamic matching of output power by adjusting the switching duty cycle of the power devices in a closed loop. The process is as follows:

[0103] Collect the measured voltage and current at the output terminal of the DC-DC converter, and calculate the actual output power. The formula is: Combined with the target power output from the machine learning module Calculate the power deviation: ;

[0104] Then, a PI control algorithm is used to generate the duty cycle correction value, as shown in the formula: Among them are proportionality coefficient The integral coefficient;

[0105] Let the current duty cycle be denoted as And update it using the duty cycle correction value according to the following formula: Define constraint rules, including boundary constraints and step size constraints; where boundary constraints , Indicates the maximum threshold for duty cycle; step size constraint: ;

[0106] The protection control unit, based on the output of the predictive maintenance unit and real-time electrical and physical state parameters, executes overvoltage, overcurrent, and overheat protection actions. The specific process is as follows:

[0107] Set overpressure threshold, overcurrent threshold, and overheat threshold respectively; the overpressure threshold is calculated using the formula... , Indicates the rated voltage of the component. This represents the overvoltage coefficient, used to reserve a certain safety margin in voltage; the overcurrent threshold is calculated using the formula... , Indicates the rated current of the component. This represents the overcurrent coefficient, used to reserve a certain safety margin in the current; the overheat threshold is calculated using the formula... , Indicates the rated operating temperature of the component. Indicates the superheated temperature difference;

[0108] Protection is triggered when any of the following conditions are continuously met for a preset time:

[0109] If so, the corresponding component indicates an output overvoltage;

[0110] The corresponding component indicates an output overcurrent.

[0111] or power device temperature This indicates that the device is overheating and the duration exceeds a preset duration threshold.

[0112] Based on the fault warning level F output by the predictive maintenance unit, graded protection actions are performed:

[0113] No action is taken when the fault warning level is Level 1;

[0114] When the fault warning level is level two, the output power will be reduced to the rated value of the preset level one ratio (e.g., 80%), and the matching cooling system will be operated at the preset low speed.

[0115] When the fault warning level is level three, the output power will be reduced to the rated value of the preset level two ratio (e.g., 50%), and the matching cooling system will be operated at the preset high speed.

[0116] When the fault warning level is level four, the preset non-critical load output will be shut down, and only the minimum voltage of the power system will be maintained;

[0117] When the fault warning level is level 5, the main circuit relay is immediately cut off, triggering the vehicle fault alarm, which is displayed on the vehicle's instrument panel and the data is uploaded to the cloud.

[0118] The mode switching unit is used to automatically switch between charging and discharging modes and power levels, specifically:

[0119] Define the mode switching criteria:

[0120] Charging mode: When , When the battery is at a low power threshold and an external AC power source is detected, the system switches to charging mode and executes a constant current / constant voltage charging strategy.

[0121] Standby mode: When , This indicates that when the battery is fully charged and there is no low-voltage load power requirement, it switches to standby mode.

[0122] Energy recovery mode: When a braking signal is detected (the vehicle controller outputs the braking level) and When switching to energy recovery mode, the braking kinetic energy is converted into electrical energy to feed back into the battery; among which... This indicates the maximum allowable charge threshold for battery recycling;

[0123] Mode switching transition control:

[0124] Specifically, a linear power transition algorithm is adopted to avoid voltage / current surges during mode switching. The formula is as follows: td; where This indicates the output power before the switch. The output power of the target mode is represented by td, and the current transition duration is represented by td. Indicates the mode switching transition time, and This is used to ensure stable output during the switching process, with no significant voltage fluctuations.

[0125] The mode status is maintained by setting a corresponding status register for each mode, which records the upper and lower limits of output voltage, upper and lower limits of output current, and protection threshold adaptation.

[0126] It should be noted that by clarifying the specific implementation logic of each unit in the control execution module, the power regulation unit dynamically matches the output power with closed-loop control, the protection control unit performs graded protection in conjunction with the fault warning level, and the mode switching unit achieves smooth switching through judgment conditions and linear transition algorithms. The three work together to ensure the accuracy of power regulation, the gradient of system protection, and the stability of mode switching, thus comprehensively improving the reliability and adaptability of equipment operation.

[0127] The present invention also includes a storage module for storing historical electrical parameters and physical states, model parameters and fault records;

[0128] It should be noted that the historical electrical parameters and physical states include subsets of voltage characteristics (input voltage, high and low voltage output voltage, etc.), current characteristics (input and output current, branch current, etc.), temperature characteristics (power devices, inductors, ambient temperature, etc.), vibration characteristics (triaxial acceleration and RMS value), and insulation resistance characteristics collected by the sensor module; model parameters cover the weight matrix, bias, correction coefficients, etc. of the prediction model and dynamic adjustment model in the machine learning module, as well as the parameters after iterative optimization by the model update unit; fault records include information such as the fault warning level output by the predictive maintenance unit, the fault types and occurrence times of overvoltage / overcurrent / overheating triggered by the protection control unit, and handling measures.

[0129] The above formulas are all calculated using dimensionless processing (such as standardization), and only numerical values ​​are used in the calculation. The formulas are based on a large amount of measured data and optimized by software simulation, which fits the actual working conditions. The preset parameters in the formulas are set by those skilled in the art according to actual needs.

[0130] This solution can be implemented through software, hardware, or a combination thereof. The relevant program can be stored on a computer-readable medium (such as a USB flash drive, hard drive, optical disc, etc.), and when loaded and executed, it can achieve the aforementioned functions.

[0131] It should be noted that the execution order of each implementation step is determined by the functional logic and is not a limitation; the unit division in this article is a logical functional division, which can be adjusted according to actual needs.

[0132] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0133] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A new energy vehicle intelligent DCDC converter integrated charger, characterized in that, The application relates to a vehicle power supply system, comprising: a main circuit module integrated with a vehicle-mounted charger unit, a DCDC conversion unit and a high-voltage power distribution unit; a sensor module comprising a plurality of sensor groups arranged on respective key components of the main circuit module for collecting electrical parameters and physical state parameters of the corresponding components; a data processing module connected with the sensor module for receiving and preprocessing the electrical parameters and physical state parameters; wherein the preprocessing comprises filtering, calibration, normalization and feature extraction; a machine learning module connected with the data processing module and internally provided with a trained prediction model and a dynamic adjustment model for analyzing and calculating the preprocessed electrical parameters and physical state parameters; a control execution module connected with the machine learning module and the main circuit module for controlling the operating state of the main circuit module according to the output of the machine learning module; a communication module for realizing data interaction with a vehicle controller and a battery management system and receiving road condition information and battery state information; the machine learning module comprises: a predictive maintenance unit for predicting the remaining service life and potential failure risk of each component based on the preprocessed electrical parameters and physical state parameters through the prediction model; a dynamic energy distribution unit for generating a DCDC output power adjustment strategy through the dynamic adjustment model in combination with the road condition information and battery state information; a model updating unit for online optimizing the prediction model and dynamic adjustment model according to actual operation data; the dynamic adjustment model comprises a road condition recognition submodel and a power optimization submodel: the road condition recognition submodel identifies the current road type, slope and congestion state based on the received road condition information; the power optimization submodel dynamically adjusts the output voltage and current of the DCDC converter according to the road condition recognition result and battery state information; the power optimization submodel dynamically adjusts the output voltage and current of the DCDC converter according to the road condition recognition result and battery state information, specifically: calculating the reference output power according to the current low-voltage load demand and the battery basic state, the formula being ; wherein is the reference output power, is the actual power demand of the current low voltage electrical device, is the reserve power, and SOC is the battery state of charge; Road condition correction coefficient The reference output power is dynamically corrected according to the road slope and congestion state, and the expression is: ; wherein , are respectively uphill and downhill correction coefficients, is a congestion correction coefficient; is a traffic state evaluation value; Battery state correction coefficient The calculation combines the battery state of health with a temperature parameter for a second correction, expressed as ; where SOH is the state of health of the battery, is the current temperature of the battery, is the optimal operating temperature of the battery, , , are correction factors for the corresponding parameters, respectively; Target output parameter determination, calculating a final output parameter, the final output parameter comprising a target output power , a target output voltage , a target output current , an expression: ， ， ； wherein represents a reference output voltage, represents a correction coefficient of the battery state of health to the output voltage.

2. The new energy vehicle intelligent DCDC converter integrated charger according to claim 1, characterized in that, the sensor module comprises: a voltage sensor group for collecting input voltage, output voltage and voltage at each key node; a current sensor group for collecting input current, output current and current at each branch; a temperature sensor group for collecting the temperature of power devices, the temperature of inductors and the ambient temperature; a vibration sensor for collecting vibration parameters of key components; an insulation monitoring sensor for monitoring the insulation state of the system.

3. The new energy vehicle intelligent DCDC converter integrated charger according to claim 1, characterized in that, the predictive maintenance unit comprises: an input feature processing subunit for standardizing the preprocessed time series parameters; an LSTM prediction network for processing time series features through an improved gating mechanism to realize time series analysis of component states; a remaining service life calculation subunit for calculating the predicted remaining service life based on the component degradation quantity evolution curve and the failure threshold; a failure risk assessment subunit for calculating the health degree based on the degradation quantity and matching a five-level failure warning grade to output a failure warning grade; a model optimization subunit for optimizing the prediction model parameters by using an Adam optimizer and a joint loss function.

4. The new energy vehicle intelligent DCDC converter integrated charger according to claim 1, characterized in that, The control execution module comprises: a power regulation unit for regulating the output power of the DC-DC converter; a protection control unit for performing overvoltage, overcurrent, and overheat protection actions according to the output of the predictive maintenance unit and real-time electrical parameters and physical state parameters; a mode switching unit for automatically switching the charging and discharging mode and the power level.

5. The new energy vehicle intelligent DCDC converter integrated charger according to claim 1, characterized in that, Further comprising a storage module for storing historical electrical parameters and physical states, model parameters, and fault records.

6. The new energy vehicle intelligent DCDC converter integrated charger according to claim 4, characterized in that, The protection control unit performs graded protection actions in combination with the fault warning level: When the fault warning level is level two, the output power is reduced to a preset primary proportion of the rated value, and the cooling system is controlled to run at a preset low speed; When the fault warning level is level three, the output power is reduced to a preset secondary proportion of the rated value, and the cooling system is controlled to run at a preset high speed; When the fault warning level is level four, the preset non-critical load output is turned off; When the fault warning level is level five, the main circuit relay is cut off, the vehicle fault alarm is triggered, and the data is uploaded to the cloud.

Images