Method for optimizing charging efficiency of vehicle-mounted charger
By real-time monitoring and analysis of the current data of the vehicle charger, combined with electromagnetic interference evaluation, and using machine learning models to adjust the charging current, the charging efficiency and safety of the vehicle charger in high-temperature and low-temperature environments and electromagnetic interference is solved, achieving more efficient and safe charging process.
Patent Information
- Application Number
- CN202411063114.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-01
AI Technical Summary
When the on-board charger is reduced in high-temperature or low-temperature environments, and when it is close to high-voltage wires or other strong electromagnetic field areas, electromagnetic interference may cause inaccurate current sensor data, which will affect charging safety and battery life.
Through multiple current sensors, the charging process is monitored in real time, the data set is established and divided into subsets of normal and abnormal current values, the electromagnetic interference level is comprehensively analyzed, the current sensor data accuracy is evaluated using machine learning models, and the charging current is adjusted according to the analysis results to ensure that Safety of the charging process.
Dynamically optimize the charging efficiency in high-temperature and low-temperature environments, improve the reliability of current sensor data, enhance the anti-interference ability of the system, avoid overcharging or overdischarge of the battery caused by electromagnetic interference, and ensure the safety and stability of the charging process.
Smart Images

Figure CN118876754A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of on-board chargers, and in particular to a method for optimizing the charging efficiency of an on-board charger. Background Art
[0002] An on-board charger is a device installed inside an electric vehicle to convert alternating current (AC) into direct current (DC) and charge the battery pack. Its main function is to use an external power source (such as a home socket or a public charging station) to provide energy to the electric vehicle battery, thereby ensuring that the vehicle has sufficient power supply during driving. An on-board charger usually has an intelligent charging management system that can optimize the charging process, improve charging efficiency, and extend battery life.
[0003] When the charging efficiency of the on-board charger is optimized in high or low temperature environments, the efficiency of the chemical reaction inside the battery is reduced under these conditions, which may lead to slower charging speed, increased energy loss, and even shortened battery life.
[0004] The temperature management system is used to optimize the charging efficiency in high and low temperature environments, such as adjusting the battery temperature during the charging process to keep it in the optimal operating range. In addition, an intelligent charging management system is used to adjust the charging current and voltage in real time according to the battery status and environmental conditions to ensure that the battery is charged within a safe and efficient range. However, when charging near high-voltage power lines or other areas with strong electromagnetic fields, electromagnetic interference may make the current sensor data inaccurate, resulting in improper adjustment of the charging current, causing overcharging or over-discharging of the battery, which in turn damages the battery or causes safety accidents. Summary of the invention
[0005] The purpose of the present invention is to provide a method for optimizing the charging efficiency of a vehicle-mounted charger to solve the shortcomings of the background technology.
[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for optimizing the charging efficiency of a vehicle charger, comprising the following steps:
[0007] S1: The charging process of the on-board charger is monitored in real time through a number of current sensors, and the current monitored by each current sensor is collected to establish a data set;
[0008] S2: setting a standard current value of the on-board charger under normal charging conditions according to historical current data, and dividing the data set into an abnormal current value subset and a normal current value subset according to the standard current value;
[0009] S3: Comprehensively analyze the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment to evaluate the accuracy of the current sensor data;
[0010] S4: dividing the accuracy of the current sensor data into accurate data, possibly accurate data and inaccurate data;
[0011] S5: Further analyze the possible accuracy data of the current sensor, and adjust the charging current according to the analysis result to ensure the safety of the charging process.
[0012] Preferably, in S2, a standard current value of the on-board charger under normal charging is set according to historical current data, and the data set is divided into an abnormal current value subset and a normal current value subset according to the standard current value, specifically:
[0013] Extract and clean historical current data from a historical database, calculate the mean and standard deviation of the historical current data, and set the mean of the historical current data as a standard current value;
[0014] Start the data acquisition system to collect the current data of the current charging process in real time;
[0015] Traverse the real-time data set, compare each real-time current data with the standard current value, if the real-time current data is less than the standard current value, store it in the normal current value subset and mark it as 0 in the original data set;
[0016] If the real-time current data is greater than or equal to the standard current value, it is stored in the abnormal current value subset and marked as 1 in the original data set;
[0017] The normal current value subset and the abnormal current value subset are respectively stored in a preset data storage structure.
[0018] Preferably, in S3, a comprehensive analysis is performed on the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment to evaluate the accuracy of the current sensor data, specifically:
[0019] The electromagnetic interference index is generated according to the electromagnetic interference level of the surrounding environment. The method for obtaining the electromagnetic interference index is:
[0020] Electromagnetic interference sensors are arranged in the monitoring area to ensure that all possible interference sources are covered. Electromagnetic signals are collected at a fixed sampling frequency fs, and the signal strength and time are recorded. The collected signal sequence is recorded as x[n], where n is the index of the sampling point.
[0021] The collected signal is denoised, and the long-term collected signal is divided into several time windows of fixed length. Each time window contains N sampling points. A window function w[n] is applied to each time window. For each time window signal xw[n]=x[n]*w[n] after applying the window function, a fast Fourier transform is performed to convert the time domain signal into the frequency domain signal. The specific conversion expression is: Where X(k) is the value of the frequency signal at the kth frequency point, x(n) is the value of the time domain signal at the nth sample point, N is the total number of signal sample points, and e -j2πft / N is the kernel function of the Fourier transform, where j is the imaginary unit;
[0022] Calculate the amplitude spectrum of the frequency domain signal |X(k)|, which represents the signal strength of different frequency components. The specific calculation expression is: Where Re(X(k)) 2 is the real part of X(k), IM(X(k)) 2 is the imaginary part of X(k); draw a spectrum diagram to show the relationship between frequency and amplitude, identify the interference frequency peak in the spectrum and its corresponding amplitude, and extract the main interference frequency in the spectrum; set the threshold T of the interference amplitude, count the number and intensity of frequency components greater than or equal to the threshold, and establish the corresponding data set K. The calculation expression of the electromagnetic interference index is: Where EM is the electromagnetic interference index.
[0023] Preferably, the real-time current value and the electromagnetic interference index are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the current sensor data predicted by each group of first eigenvectors as a prediction target, and minimizes the sum of the prediction errors of the accuracy value labels of all current sensor data as a training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the current sensor data is determined according to the model output results.
[0024] Preferably, in S4, the accuracy of the current sensor data is divided into accuracy data, possible accuracy data and inaccuracy data, specifically:
[0025] Comparing the accuracy value of the acquired current sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the accuracy value of the current sensor data with the first standard threshold and the second standard threshold respectively;
[0026] If the accuracy value of the current sensor data is greater than the second standard threshold, the current sensor data is classified as accurate data; if the accuracy value of the current sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the current sensor data is classified as possibly accurate data; if the accuracy value of the current sensor data is less than the first standard threshold, the current sensor data is classified as inaccurate data.
[0027] Preferably, in S5, the possible accuracy data of the current sensor is further analyzed, and the charging current is adjusted according to the analysis result, specifically:
[0028] When the output data of the current sensor is divided into possible accuracy data, that is, the accuracy value of the current sensor data generated in a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the accuracy values generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established. Let Dpossible be the set of possible accuracy data. For each possible accuracy data point CR z ∈Dpossibled,CR z It is the accuracy value within the data set that is greater than or equal to the first standard threshold and less than or equal to the second standard threshold.
[0029] Preferably, the mean μ and standard deviation σ of the possible accuracy data set are calculated, and a safety threshold α is set to determine whether the data deviates from the safety range. For each data point CR z , if its value exceeds the range of α×σ of the mean value μ, then the data point is considered to be abnormal; if |CR z -μ|>α×σ, then CR z It is considered that there may be an abnormality, and the adjusted charging current is calculated. Assuming the current charging current is Icurrent, the adjustment coefficient β is calculated according to the number and deviation degree of abnormal data points, and the charging current is adjusted according to the set ratio g and deviation degree; the specific calculation expression is: Wherein, n is the total number of data in the set, and the adjusted charging current Iadjusted is: Iadjusted=β*Icurrent; wherein the adjustment coefficient β ranges from 0 to 1.
[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0031] 1. The present invention dynamically optimizes the charging efficiency in high and low temperature environments by combining a temperature management system and an intelligent charging management system, and adjusts the charging current based on real-time monitoring and analysis to ensure that the battery is charged within a safe and efficient range. When charging near high-voltage wires or other strong electromagnetic fields, the accuracy of the current sensor data is accurately judged through multi-sensor monitoring, data classification, and electromagnetic interference index evaluation to prevent overcharging or over-discharging of the battery due to electromagnetic interference, thereby avoiding battery damage and safety accidents.
[0032] 2. The present invention sets the standard current value through historical current data, monitors and classifies data in real time, uses machine learning models to evaluate the accuracy of current data, and conducts in-depth analysis of possible accuracy data and dynamically adjusts the charging current to ensure the safety and stability of the charging process. It not only improves the reliability of current sensor data and enhances the anti-interference ability of the system, but also improves the overall performance of the on-board charger and the safety of the charging process, providing a guarantee for efficient and safe charging of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0034] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION
[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] For examples, see Figure 1 As shown, the method for optimizing the charging efficiency of a vehicle charger described in this embodiment includes the following steps:
[0037] S1: The charging process of the on-board charger is monitored in real time through a number of current sensors, and the current monitored by each current sensor is collected to establish a data set;
[0038] S2: setting a standard current value of the on-board charger under normal charging conditions according to historical current data, and dividing the data set into an abnormal current value subset and a normal current value subset according to the standard current value;
[0039] S3: Comprehensively analyze the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment to evaluate the accuracy of the current sensor data;
[0040] S4: dividing the accuracy of the current sensor data into accurate data, possibly accurate data and inaccurate data;
[0041] S5: Further analyze the possible accuracy data of the current sensor, and adjust the charging current according to the analysis result to ensure the safety of the charging process.
[0042] Among them, in S1, the charging process of the on-board charger is monitored in real time through a number of current sensors, and the current monitored by each current sensor is collected to establish a data set, which mainly includes:
[0043] Install multiple current sensors at key locations of the onboard charger (e.g., battery inlet, charging port) to ensure that the entire charging path is covered. Ensure that the sensors are securely mounted and protected from external interference. Assign a unique identifier (ID) to each current sensor for subsequent data collection and analysis. Calibrate the sensors to ensure measurement accuracy.
[0044] Use a data acquisition device (such as a microcontroller, data acquisition card) to connect all current sensors. Configure the sampling frequency of the data acquisition device to ensure that the current changes during the charging process can be monitored in real time.
[0045] Configure data transmission protocols (such as CAN bus, RS485) to transmit sensor data to the central control system. Set up data storage systems (such as databases, cloud storage) to ensure safe and reliable data storage.
[0046] Start the data acquisition system and start collecting data from each current sensor in real time. Record the data of each sensor, including timestamp, sensor ID and current value. Perform preliminary cleaning on the collected data to remove obvious erroneous data and noise. Use filtering algorithms (such as moving average filtering) to smooth the data and reduce high-frequency interference.
[0047] Design the data set structure, including timestamp, sensor ID, current value, and other relevant information (such as ambient temperature, charging status). Create a database table or data file (such as CSV, JSON) to store the data.
[0048] According to the designed data structure, the collected current data is stored in the database or data file to ensure the integrity and consistency of the data and avoid data loss or duplication.
[0049] Use data analysis tools (such as Python, R) to analyze the data set and identify current change trends and anomalies. Generate statistical reports such as average current value, maximum and minimum current values.
[0050] Use visualization tools (such as Matplotlib and Tableau) to generate current change charts to help intuitively understand the current changes during the charging process. Create a real-time monitoring dashboard to display the real-time current data and historical data of each sensor.
[0051] Regularly calibrate the current sensor to ensure the accuracy of data measurement. Check and maintain data acquisition equipment and sensor connections to ensure the normal operation of the system. Regularly update the data set, add new monitoring data, and maintain the real-time and integrity of the data. Back up the data storage system to ensure data security.
[0052] S2: according to the historical current data, a standard current value of the on-board charger under normal charging conditions is set, and the data set is divided into an abnormal current value subset and a normal current value subset according to the standard current value.
[0053] Extract and clean historical current data from a historical database, calculate the mean and standard deviation of the historical current data, and set the mean of the historical current data as a standard current value;
[0054] Start the data acquisition system to collect the current data of the current charging process in real time;
[0055] Traverse the real-time data set, compare each real-time current data with the standard current value, if the real-time current data is less than the standard current value, store it in the normal current value subset and mark it as 0 in the original data set;
[0056] If the real-time current data is greater than or equal to the standard current value, it is stored in the abnormal current value subset and marked as 1 in the original data set;
[0057] The normal current value subset and the abnormal current value subset are stored in the preset data storage structure respectively. The historical database is updated regularly to add new normal and abnormal current data to maintain the real-time and integrity of the data.
[0058] S3: Comprehensively analyze the real-time current values in the abnormal current value subset and the electromagnetic interference level of the surrounding environment to evaluate the accuracy of the current sensor data.
[0059] The electromagnetic interference index is generated according to the electromagnetic interference level of the surrounding environment. The method for obtaining the electromagnetic interference index is:
[0060] Electromagnetic interference sensors are arranged in the monitoring area to ensure that all possible interference sources are covered. Electromagnetic signals are collected at a fixed sampling frequency fs, and the signal strength and time are recorded. The collected signal sequence is recorded as x[n], where n is the index of the sampling point.
[0061] The collected signal is denoised to remove background noise and other irrelevant signals, and the signal collected over a long period of time is divided into several time windows of fixed length (such as 1 second) for segmented processing, each time window contains N sampling points.
[0062] A window function w[n], such as a Hanning window or a Hamming window, is applied to each time window to reduce spectrum leakage. The role of the window function is to weight the signal so that the influence of boundary effects on the spectrum is reduced.
[0063] For each time window signal xw[n]=x[n]*w[n] after applying the window function, a fast Fourier transform is performed to convert the time domain signal into a frequency domain signal; the specific conversion expression is: Where X(k) is the value of the frequency signal at the kth frequency point, x(n) is the value of the time domain signal at the nth sample point, N is the total number of signal sample points, and e -j2πft / N is the kernel function of the Fourier transform, where j is the imaginary unit;
[0064] Calculate the amplitude spectrum of the frequency domain signal |X(k)|, which represents the signal strength of different frequency components. The specific calculation expression is: Where Re(X(k)) 2 is the real part of X(k), IM(X(k)) 2 is the imaginary part of X(k);
[0065] Draw a spectrum diagram to show the relationship between frequency and amplitude, identify the interference frequency peak in the spectrum and its corresponding amplitude, and extract the main interference frequency in the spectrum;
[0066] Set the threshold T of the interference amplitude, count the number and intensity of frequency components greater than or equal to the threshold, and establish the corresponding data set K. The calculation expression of the electromagnetic interference index is: Where EM is the electromagnetic interference index.
[0067] The larger the electromagnetic interference index, the higher the electromagnetic interference intensity in the environment. These interferences will introduce a lot of noise into the measurement signal of the current sensor. These noise signals will be superimposed on the real current signal, causing the output data of the sensor to have obvious fluctuations and errors, deviating from the actual current value. As the electromagnetic interference index increases, the impact of the interference signal becomes more significant, which significantly reduces the accuracy and reliability of the current sensor data, making data analysis and decision-making processes more difficult.
[0068] The real-time current value and the electromagnetic interference index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the current sensor data predicted by each group of first eigenvectors as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all current sensor data as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the current sensor data is determined according to the model output results.
[0069] The method for obtaining the accuracy value of the current sensor data is: from the first eigenvector training data of the trained machine learning model, obtain the corresponding function expression: CR=f1(SQ, EM); where f1 is the output function of the model, SQ is the real-time current value, EM is the electromagnetic interference index, and CR is the accuracy value of the current sensor data.
[0070] S4: Classify the accuracy of the current sensor data into accurate data, possibly accurate data and inaccurate data.
[0071] Comparing the accuracy value of the acquired current sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the accuracy value of the current sensor data with the first standard threshold and the second standard threshold respectively;
[0072] If the accuracy value of the current sensor data is greater than a second standard threshold, classifying the current sensor data as accuracy data;
[0073] If the accuracy value of the current sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, classifying the current sensor data into possible accuracy data;
[0074] If the accuracy value of the current sensor data is less than the first standard threshold, the current sensor data is classified as inaccurate data.
[0075] S5: Further analyze the possible accuracy data of the current sensor, and adjust the charging current according to the analysis result to ensure the safety of the charging process.
[0076] When the output data of the current sensor is divided into possible accuracy data, that is, the accuracy value of the current sensor data generated in a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the accuracy values generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established. Let Dpossible be the set of possible accuracy data. For each possible accuracy data point CR z ∈Dpossibled,CR z It is the accuracy value within the data set that is greater than or equal to the first standard threshold and less than or equal to the second standard threshold.
[0077] Calculate the mean μ and standard deviation σ of the possible accuracy data set, set the safety threshold α to determine whether the data deviates from the safety range, and for each data point CR z , if its value exceeds the range of α×σ of the mean value μ, then the data point is considered to be abnormal;
[0078] If |CR z -μ|>α×σ, then CR z It is considered that there may be an abnormality, and the adjusted charging current is calculated. Assuming the current charging current is Icurrent, the adjustment coefficient β is calculated according to the number and deviation degree of abnormal data points, and the charging current is adjusted according to the set ratio g and deviation degree; the specific calculation expression is: Wherein, n is the total number of data in the set, and the adjusted charging current Iadjusted is: Iadjusted=β*Icurrent; wherein the adjustment coefficient β ranges from 0 to 1, ensuring that the adjusted current is within a reasonable range.
[0079] In this application, by further analyzing the possible accuracy data, calculating the average and standard deviation, setting a safety threshold to determine the data deviation, and calculating the adjustment coefficient according to the number of abnormal data points and the degree of deviation, the charging current is adjusted. This method can dynamically adjust the charging current, avoid safety issues caused by inaccurate data due to electromagnetic interference, ensure the stability and safety of the charging process, and improve the reliability of the current sensor data and the overall performance of the charging system.
[0080] In this embodiment, the charging process of the on-board charger is monitored in real time by several current sensors, and the current monitored by each current sensor is collected to establish a data set; the standard current value of the on-board charger under normal charging conditions is set according to the historical current data, and the data set is divided into an abnormal current value subset and a normal current value subset according to the standard current value; the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment are comprehensively analyzed to evaluate the accuracy of the current sensor data; the accuracy of the current sensor data is divided into accuracy data, possible accuracy data and inaccuracy data; the possible accuracy data of the current sensor is further analyzed, and the charging current is adjusted according to the analysis results to ensure the safety of the charging process. It can not only dynamically detect and correct the data deviation caused by electromagnetic interference during the charging process, but also optimize the charging current in real time, ensure the stability and safety of the charging process, and improve the reliability of the current sensor data and the overall performance of the charging system.
[0081] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0082] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0083] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0084] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the systems, devices and units described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0086] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A method for optimizing the charging efficiency of a vehicle charger. Features: The following steps are involved: S1: The charging process of the on-board charger is monitored in real time through a number of current sensors, and the current monitored by each current sensor is collected to establish a data set; S2: setting a standard current value of the on-board charger under normal charging conditions according to historical current data, and dividing the data set into an abnormal current value subset and a normal current value subset according to the standard current value; S3: Comprehensively analyze the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment to evaluate the accuracy of the current sensor data; S4: dividing the accuracy of the current sensor data into accurate data, possibly accurate data and inaccurate data; S5: Further analyze the possible accuracy data of the current sensor, and adjust the charging current according to the analysis result to ensure the safety of the charging process.
2. A method for optimizing charging efficiency of a vehicle charger according to claim 1, Features: In S2, the standard current value of the on-board charger under normal charging is set according to the historical current data, and the data set is divided into an abnormal current value subset and a normal current value subset according to the standard current value, specifically: Extract and clean historical current data from a historical database, calculate the mean and standard deviation of the historical current data, and set the mean of the historical current data as a standard current value; Start the data acquisition system to collect the current data of the current charging process in real time; Traverse the real-time data set, compare each real-time current data with the standard current value, if the real-time current data is less than the standard current value, store it in the normal current value subset and mark it as 0 in the original data set; If the real-time current data is greater than or equal to the standard current value, it is stored in the abnormal current value subset and marked as 1 in the original data set; The normal current value subset and the abnormal current value subset are respectively stored in a preset data storage structure.
3. A method for optimizing charging efficiency of a vehicle charger according to claim 1, Features: In S3, the real-time current value in the abnormal current value subset and the electromagnetic interference level of the surrounding environment are comprehensively analyzed to evaluate the accuracy of the current sensor data, specifically: The electromagnetic interference index is generated according to the electromagnetic interference level of the surrounding environment. The method for obtaining the electromagnetic interference index is: Electromagnetic interference sensors are arranged in the monitoring area to ensure that all possible interference sources are covered. Electromagnetic signals are collected at a fixed sampling frequency fs, and the signal strength and time are recorded. The collected signal sequence is recorded as x[n], where n is the index of the sampling point. The collected signal is denoised, and the long-term collected signal is divided into several time windows of fixed length. Each time window contains N sampling points. A window function w[n] is applied to each time window. For each time window signal xw[n]=x[n]*w[n] after applying the window function, a fast Fourier transform is performed to convert the time domain signal into the frequency domain signal. The specific conversion expression is: Where X(k) is the value of the frequency signal at the kth frequency point, x(n) is the value of the time domain signal at the nth sample point, N is the total number of signal sample points, and e -j2πft / is the kernel function of the Fourier transform, where j is the imaginary unit; Calculate the amplitude spectrum of the frequency domain signal |X(k)|, which represents the signal strength of different frequency components. The specific calculation expression is: Where Re(X(k)) 2 is the real part of X(k), IM(X(k)) 2 is the imaginary part of X(k); draw a spectrum diagram to show the relationship between frequency and amplitude, identify the interference frequency peak in the spectrum and its corresponding amplitude, and extract the main interference frequency in the spectrum; set the threshold T of the interference amplitude, count the number and intensity of frequency components greater than or equal to the threshold, and establish the corresponding data set K. The calculation expression of the electromagnetic interference index is: Where EM is the electromagnetic interference index.
4. A method for optimizing charging efficiency of a vehicle charger according to claim 3, Features: The real-time current value and the electromagnetic interference index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the current sensor data predicted by each group of first eigenvectors as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all current sensor data as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the current sensor data is determined according to the model output results.
5. A method for optimizing charging efficiency of a vehicle charger according to claim 4, Features: In S4, the accuracy of the current sensor data is divided into accurate data, possibly accurate data and inaccurate data, specifically: Comparing the accuracy value of the acquired current sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the accuracy value of the current sensor data with the first standard threshold and the second standard threshold respectively; If the accuracy value of the current sensor data is greater than the second standard threshold, the current sensor data is classified as accuracy data; if the accuracy value of the current sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the current sensor data is classified as possible accuracy data; If the accuracy value of the current sensor data is less than the first standard threshold, the current sensor data is classified as inaccurate data.
6. A method for optimizing charging efficiency of a vehicle charger according to claim 5, Features: In S5, the possible accuracy data of the current sensor is further analyzed, and the charging current is adjusted according to the analysis result, specifically: When the output data of the current sensor is divided into possible accuracy data, that is, the accuracy value of the current sensor data generated in a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the accuracy values generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established. Let Dpossible be the set of possible accuracy data. For each possible accuracy data point CR z ∈Dpossibled,CR z It is the accuracy value within the data set that is greater than or equal to the first standard threshold and less than or equal to the second standard threshold.
7. A method for optimizing charging efficiency of a vehicle charger according to claim 6, Features: Calculate the mean μ and standard deviation σ of the possible accuracy data set, set the safety threshold α to determine whether the data deviates from the safety range, and for each data point CR z , if its value exceeds the range of α×σ of the mean value μ, then the data point is considered to be abnormal; if |CR z -μ|>α×σ, then CR z It is considered that there may be an abnormality, and the adjusted charging current is calculated. Assuming the current charging current is Icurrent, the adjustment coefficient β is calculated according to the number and deviation degree of abnormal data points, and the charging current is adjusted according to the set ratio g and deviation degree; the specific calculation expression is: Wherein, n is the total number of data in the set, and the adjusted charging current Iadjusted is: Iadjusted=β*Icurrent; wherein the adjustment coefficient β ranges from 0 to 1.
Citation Information
Cited By
Power conversion cabinet power control method and system, and power conversion cabinet
CN119283710A
Method and system for multi-section power distribution of direct current charging pile
CN119408450A
Charging pile sudden stop reset control method and system
CN119567931A
