Method, device and server for charging starting battery of pure electric bus

Abstract

The present invention provides a method, device, and server for charging the starting battery of a pure electric bus, relating to the technical field of pure electric buses. The method comprises: using a power battery monitoring system to monitor the power battery of the pure electric bus according to an initial monitoring time interval, and waking up the electronic controller and instrument by sending a voltage wake-up signal when the power battery is in a healthy state of power; using the electronic controller to activate the DC-DC system and charge the starting battery when the instrument detects that the starting battery is in a low state of power; combining the battery voltage and temperature information during the current charging process with historical cloud bus data, and determining an optimized target monitoring time interval and target charging duration through integrated learning processing. The target monitoring time interval and target charging duration are then used to perform the next round of charging on the starting battery of the pure electric bus. This invention can significantly improve charging efficiency while saving costs.

Description

Technical Field

[0001] The present invention relates to the technical field of pure electric buses, and in particular to a method, device and server for charging a starting battery of a pure electric bus. Background Art

[0002] For existing pure electric buses, some electrical equipment will still be working after the key is turned off, which causes the power of the starting battery to be consumed. The pure electric bus cannot recharge the starting battery during long-term parking, resulting in the problem that the pure electric bus cannot be re-turned to start the vehicle due to the power supply of the starting battery after a long period of parking. At present, relevant technologies have proposed that the starting battery can be continuously charged by installing solar cells, or by adding a control module that detects the starting battery voltage in real time, so that when the starting battery is low and the power battery is sufficient, the power battery can be used to charge the starting battery. However, installing solar cells will take up more space, and the control module will consume the power of the starting battery while monitoring the power, resulting in a high frequency of battery recharge and low efficiency of single recharge. Summary of the Invention

[0003] In view of this, an object of the present invention is to provide a method, device and server for charging the starting battery of a pure electric bus, which can significantly improve the charging efficiency while saving costs.

[0004] In a first aspect, an embodiment of the present invention provides a method for charging a starting battery of a pure electric bus, the method comprising: monitoring the power level of the power battery of the pure electric bus according to an initial monitoring time interval through a preset power battery monitoring system, and waking up the electronic controller and the instrument by sending a voltage wake-up signal when the power battery is in a healthy power state; activating the DCDC system using the electronic controller, and monitoring the power level of the starting battery using the instrument, and when the instrument detects that the starting battery is in a low power state, charging the starting battery based on the initial charging time through the DCDC system; storing the voltage information and temperature information of the battery during the current charging, and combining the voltage information and temperature information with cloud bus historical data, and determining an optimized target monitoring time interval and target charging time through integrated learning processing, so as to use the target monitoring time interval and target charging time to perform the next round of charging processing on the starting battery of the pure electric bus.

[0005] In one embodiment, the steps of performing power monitoring processing on the power battery of a pure electric bus according to an initial monitoring time interval by means of a preset power battery monitoring system include: when the power battery monitoring system monitors that the power battery's power is less than a preset power percentage or the power battery has a fault, ending the monitoring process; when the power battery monitoring system monitors that the power battery's power is not less than a preset power percentage and the power battery has no fault, determining that the power battery is in a healthy power state.

[0006] In one embodiment, a meter is used to monitor the power level of a starting battery. When the meter detects that the starting battery is in a low-power state, the starting battery is recharged by a DCDC system based on an initial recharge duration. The steps include: when it is detected that the power level of the starting battery is not less than a preset power value, determining that the starting battery is in a healthy power state and terminating the recharge process; when it is detected that the power level of the starting battery is less than the preset power value, determining that the starting battery is in a low-power state, and the DCDC system performing voltage conversion to convert the high-voltage power of the power battery into low-voltage power to recharge the starting battery.

[0007] In one embodiment, after the step of determining that the starting battery is in a low-power state, the step includes: performing statistical analysis and processing on the power monitoring results of the starting battery. If the monitoring results of two adjacent power monitorings both indicate that the starting battery is in a low-power state, it is determined that the power battery is abnormal, the charging process is terminated, and an alarm is prompted on the instrument to prompt the user to replace the starting battery.

[0008] In one embodiment, before combining the voltage information, temperature information and cloud bus historical data and determining the optimized target monitoring time interval and target power replenishment duration through integrated learning processing, the method includes: performing data cleaning processing on the voltage information and temperature information to remove outliers and noise values, and performing feature extraction and normalization processing on the cleaned data to determine the target feature data.

[0009] In one embodiment, the voltage information, temperature information and cloud bus historical data are combined, and the steps of determining the optimized target monitoring time interval and target power replenishment duration through integrated learning processing include: combining the linear regression model and the long short-term memory network model in series, gradually decomposing the target feature data, analyzing the linear features and nonlinear features in the target feature data respectively, and determining the optimized target monitoring time interval and target power replenishment duration.

[0010] In one embodiment, a linear regression model and a long short-term memory network model are serially combined to gradually decompose the target feature data, and the linear features and nonlinear features in the target feature data are analyzed respectively to determine the optimized target monitoring time interval and target power replenishment duration, including: performing preliminary division on the target feature data to determine the first linear feature and the first nonlinear feature; performing linear regression processing on the first linear feature using the linear regression model, and determining the residual value of the linear regression as the second nonlinear feature; performing nonlinear feature analysis processing on the first nonlinear feature and the second nonlinear feature using the long short-term memory network model to determine the optimized target monitoring time interval and target power replenishment duration.

[0011] In one embodiment, the target feature data is preliminarily divided and the step of determining the first linear feature and the first nonlinear feature includes: respectively calculating the Pearson correlation coefficients between voltage and time, temperature and time, and charging time and voltage and temperature in the target feature data; when the Pearson correlation coefficient corresponding to the target feature data approaches 0, the target feature data is determined to be the first nonlinear feature; when the Pearson correlation coefficient corresponding to the target feature data approaches 1 or -1, the target feature data is determined to be the first linear feature.

[0012] In one embodiment, after determining the optimized target monitoring time interval and target charging time, the following steps are included: analyzing the historical travel information of the user's vehicle and the license plate restriction information of the current area based on the cloud bus historical data; if the analysis result shows that the user travels every other day, the preset power percentage of the power battery monitoring is reduced to a preset percentage threshold, and the target monitoring time interval and target charging time are recalculated to increase the priority of the user's travel.

[0013] In a second aspect, an embodiment of the present invention further provides a starting battery charging device for a pure electric bus, and the device method includes: a power monitoring module, which monitors the power battery of the pure electric bus according to an initial monitoring time interval through a preset power battery monitoring system, and wakes up the electronic controller and the instrument by sending a voltage wake-up signal when the power battery is in a healthy power state; a battery charging module, which uses an electronic controller to activate the DCDC system and uses an instrument to monitor the power of the starting battery. When the instrument detects that the starting battery is in a low power state, the starting battery is charged based on the initial charging time through the DCDC system; a charging optimization module, which stores the voltage information and temperature information of the battery during the current charging, and combines the voltage information and temperature information with the cloud bus historical data, and determines the optimized target monitoring time interval and target charging time through integrated learning processing, so as to use the target monitoring time interval and target charging time to perform the next round of charging processing on the starting battery of the pure electric bus.

[0014] In a third aspect, an embodiment of the present invention further provides a server, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0015] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0016] The embodiments of the present invention bring the following beneficial effects:

[0017] The embodiments of the present invention provide a method, device and server for charging the starting battery of a pure electric bus. The method uses a preset power battery monitoring system to monitor the power of the pure electric bus according to the initial monitoring time interval. When the power battery is in a healthy power state, the electronic controller and the instrument are awakened by sending a voltage wake-up signal. The electronic controller then activates the DCDC system and the instrument monitors the power of the starting battery. When the instrument detects that the starting battery is in a low power state, the starting battery is recharged based on the initial charging time through the DCDC system. The battery is charged and finally the voltage and temperature information of the battery during the current charging process is stored. The voltage and temperature information are combined with the historical data of the cloud bus. Through integrated learning processing, the optimized target monitoring time interval and target charging duration are determined. The target monitoring time interval and target charging duration are used to perform the next round of charging processing on the starting battery of the pure electric bus. The embodiment of the present invention can use the original power battery monitoring system of the pure electric bus to regularly detect the starting battery voltage and dynamically adjust the wake-up interval, thereby further saving power, saving costs, and significantly improving the charging efficiency.

[0018] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A schematic flow chart of a method for charging a starting battery of a pure electric bus provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a specific process of a method for charging a starting battery of a pure electric bus provided by an embodiment of the present invention;

[0023] Figure 3 A schematic structural diagram of a starting battery charging device for a pure electric bus provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] At present, for existing pure electric buses, some electrical equipment will still be working after the key is turned off, which will cause the power of the starting battery to be consumed. The pure electric bus cannot recharge the starting battery during long-term parking, resulting in the problem that the pure electric bus cannot be re-started by turning the key again after being parked for a long time due to the power supply of the starting battery. Related technologies have proposed that the starting battery can be continuously charged by installing solar cells, or by adding a control module that detects the starting battery voltage in real time, so that when the starting battery is out of power and the power battery is sufficient, the starting battery can be charged by the power battery. However, installing solar cells will take up more space, and the control module that detects the battery voltage in real time is always working and consumes the power of the starting battery, resulting in a high frequency of battery recharging and low efficiency of single recharging. In addition, frequent charging and discharging will also have an irreversible effect on the battery life. Based on this, the starting battery recharging method, device and server for pure electric buses provided by the present invention can use the original power battery monitoring system of the pure electric bus to regularly detect the starting battery voltage and dynamically adjust the wake-up interval, thereby further saving power, saving costs and significantly improving the recharging efficiency.

[0027] See also Figure 1 The flowchart of a method for charging a starting battery of a pure electric bus is shown in FIG. 1 , which mainly includes the following steps S102 to S106:

[0028] Step S102: The power battery of the pure electric bus is monitored for power according to the initial monitoring time interval by a preset power battery monitoring system. When the power battery is in a healthy power state, the electronic controller and the instrument are awakened by sending a voltage wake-up signal. In one embodiment, when the power battery monitoring system detects that the power battery power is less than a preset power percentage or the power battery fails, the monitoring process ends; when the power battery monitoring system detects that the power battery power is not less than a preset power percentage and the power battery is not faulty, it is determined that the power battery is in a healthy power state. In actual application, the preset power percentage can be set to 20% during initial monitoring, and the initial monitoring time interval can be set to 4 hours. That is, during the first monitoring, when the pure electric bus is turned off by turning off the key, the power battery monitoring system (BMS) on the pure electric bus will automatically wake up every 4 hours to monitor the status of the power battery. When the power battery power SOC is ≥20%, the BMS will wake up every 4 hours and output a voltage signal to wake up the instrument and ECU controller of the pure electric bus.

[0029] Furthermore, the cloud bus historical travel data of vehicle users and license plate restrictions can be combined. In emergency and special circumstances, although the power battery SOC is less than 20%, the user is likely to travel the next day. Under the premise that the power battery is fault-free, intelligent decision-making can allow the power battery to recharge the starting battery with too low voltage (such as less than 20V) to a certain extent, so as to meet the user's travel priority.

[0030] In step S104, the DCDC system is activated using an electronic controller, and the power level of the starting battery is monitored using an instrument. When the instrument detects that the starting battery is in a low power state, the starting battery is recharged based on the initial recharge duration through the DCDC system. In one embodiment, when the power level of the starting battery is detected to be no less than a preset power value, the starting battery is determined to be in a healthy power state and the recharge process is terminated. When the power level of the starting battery is detected to be less than a preset power value, the starting battery is determined to be in a low power state, and the DCDC system performs voltage conversion to convert the high voltage of the power battery into low voltage to recharge the starting battery. In addition, the power monitoring results of the starting battery are statistically analyzed. If the monitoring results of two adjacent power monitorings both indicate that the starting battery is in a low power state, the power battery is determined to be abnormal, the recharge process is terminated, and an alarm is issued on the instrument to prompt the user to replace the starting battery.

[0031] In actual application, the initial charging time can be set to 1 hour, and the preset power value can be set to 24V. That is to say, after the instrument wakes up, it can detect the starting battery voltage value. When the starting battery voltage is lower than 24V, the instrument sends the starting battery charging CAN bus signal to the ECU controller. The ECU controller outputs a voltage signal and sends a CAN bus signal to activate the high-voltage DCDC system on the pure electric bus. The DCDC system can convert the high voltage of the power battery into a low voltage of 27.5V to charge the starting battery. The instrument also shows that the starting battery is being charged, and the charging is 1 hour at a time. After 1 hour of charging, the power is automatically cut off and the charging stops. When the power battery SOC is less than 20%, the power battery needs to be protected to avoid over-discharge. The BMS wakes up every 4 hours and no longer outputs a voltage signal to wake up the instrument and ECU controller. The DCDC no longer charges the starting battery. In addition, before or during the charging process, if the BMS detects a power battery fault, the BMS will stop outputting the voltage wake-up signal and stop charging. The DCDC system includes a DC converter, which can convert the high voltage electricity of the power battery into low voltage electricity according to the low voltage enable signal sent by the DCDC system, and use the low voltage electricity to power the starting battery.

[0032] In step S106, the voltage and temperature information of the battery during the current charging process is stored, and the voltage and temperature information are combined with the historical data of the cloud bus. Through integrated learning processing, the optimized target monitoring time interval and target charging duration are determined, so that the target monitoring time interval and target charging duration can be used to perform the next round of charging processing on the starting battery of the pure electric bus.

[0033] See also Figure 2 The schematic diagram of a specific process flow of a method for recharging the starting battery of a pure electric bus shows that the starting battery voltage can be detected by utilizing the pure electric bus's existing power battery monitoring system (BMS), electronic control unit (ECU), and DCDC system (i.e., DC-DC converter). Compared with the prior art method of adding a control module for real-time starting battery voltage detection, the present invention's solution of periodically detecting the starting battery voltage can also save more power, as the control module for real-time battery voltage detection is also constantly operating and consumes the starting battery's power. In addition, the power battery monitoring system also incorporates a unique data analysis model that can dynamically update the monitoring time interval and the duration of the starting battery recharging. The advantages of this analysis method are:

[0034] 1. Dynamically adjust the monitoring time interval: Dynamically adjust the BMS wake-up interval based on factors such as the historical voltage data of the starting battery, ambient temperature, and vehicle usage frequency to prevent the monitoring system from being constantly activated and consuming the starting battery's power. In addition, different vehicles, different battery health conditions, and different users' historical driving habits require different optimal monitoring time intervals. Therefore, it is necessary to dynamically adjust and determine the target monitoring time interval to avoid starting the monitoring system too frequently, which will increase power consumption or extend the monitoring time, and the starting battery power shortage will affect the user's normal travel.

[0035] 2. Dynamically adjust the charging time: Since the remaining power of the tram is different each time it stops, and the remaining power may vary greatly, if the charging time is fixed, when the power of the starting battery is low, the starting battery may still not reach the safe voltage range after charging. When the power of the starting battery is high, it may cause overcharging, thereby affecting the battery life.

[0036] Furthermore, the embodiment of the present invention also provides an implementation method for optimizing the monitoring time interval and the recharging time, as shown in (A) to (B) below:

[0037] (A) Data cleaning is performed on voltage and temperature information to remove outliers and noise values. Feature extraction and normalization are then performed on the cleaned data to determine the target feature data. Specifically, feature extraction can extract useful time-related features from data such as voltage and temperature, and normalization can normalize the data to the same scale, thereby facilitating algorithm processing.

[0038] (B) The linear regression model and the long short-term memory network model are serially combined to gradually decompose the target feature data. The linear features and nonlinear features in the target feature data are analyzed respectively to determine the optimized target monitoring time interval and target power replenishment time. For details, see (1) to (4) below:

[0039] (1) Perform a preliminary division on the target feature data to determine the first linear feature and the first nonlinear feature. Specifically, the Pearson correlation coefficients between voltage and time, temperature and time, and charging time and voltage and temperature in the target feature data can be calculated respectively: when the Pearson correlation coefficient corresponding to the target feature data approaches 0, the target feature data is determined to be the first nonlinear feature; when the Pearson correlation coefficient corresponding to the target feature data approaches 1 or -1, the target feature data is determined to be the first linear feature. Coefficient (denoted as r) is a statistic that measures the degree of linear correlation between two variables. Its value range is between -1 and 1. r=1 indicates that there is a completely positive linear correlation between the two variables, r=-1 indicates that there is a completely negative linear correlation between the two variables, and r=-0 indicates that there is no linear correlation between the two variables. However, the Pearson correlation coefficient can only reflect the linear relationship between the variables and cannot accurately capture the nonlinear relationship. The existing method of capturing the linear relationship requires drawing a scatter plot and then observing the nonlinear trend of the scatter plot, but this solution requires a high computing power. Therefore, the present invention uses the Pearson correlation coefficient to roughly divide the target feature data, determine the first linear feature and the first nonlinear feature, and then use the linear regression model and the long short-term memory network model in series to perform secondary division processing.

[0040] In one embodiment, the voltage generally rises gradually during the charging process. If the charging system is constant current charging, the voltage may increase linearly with time, but if the internal resistance or other characteristics of the battery change, the voltage change may be nonlinear; the temperature generally rises gradually as the charging process proceeds, but the temperature change may be affected by multiple factors such as ambient temperature, battery capacity, charging current, etc. These factors may cause the temperature change to show a nonlinear relationship; the relationship between the charging time and the voltage and temperature may be more complicated. Under constant current charging, the charging time may show a linear relationship with the voltage change, but if the current changes during the charging process (for example, due to changes in battery voltage), the charging time may show a nonlinear relationship with the voltage and temperature.

[0041] (2) The linear regression model is used to perform linear regression processing on the first linear feature, and the residual value of the linear regression is determined as the second nonlinear feature. In one embodiment, when the data presents a linear relationship, linear regression can be used to predict the monitoring time interval and the recharging time. By determining the residual value as the second nonlinear feature through this scheme, the data relationship can be gradually decomposed to reduce the complexity.

[0042] (3) The first nonlinear feature and the second nonlinear feature are subjected to nonlinear feature analysis and processing using the long short-term memory network model to determine the optimized target monitoring time interval and target power replenishment duration. The long short-term memory network model is suitable for processing time series data with long-term dependencies and can capture complex nonlinear relationships. In addition, after determining the optimized target monitoring time interval and target power replenishment duration, the parameters of the linear regression model and the long short-term memory network model can also be cross-validated.

[0043] (4) Analyze the historical travel information of the user's vehicle and the license plate restriction information of the current area based on the historical data of the cloud bus. If the analysis result shows that the user travels every other day, the preset power percentage of the power battery monitoring is reduced to the preset percentage threshold, and the target monitoring time interval and the target charging time are recalculated to improve the priority of the user's travel. In other words, using the cloud historical data, in addition to judging whether to use the power battery to charge the starting battery, the preset power percentage is reduced to improve the user's travel priority. When the priority change is detected, the target monitoring time interval and the target charging time are also required to be recalculated.

[0044] Regarding the method for charging the starting battery of a pure electric bus provided in the above embodiment, an embodiment of the present invention provides a device for charging the starting battery of a pure electric bus, see Figure 3 The schematic diagram of the structure of a starting battery charging device for a pure electric bus is shown in FIG. The device includes the following parts:

[0045] The power monitoring module 302 monitors the power battery of the pure electric bus according to the initial monitoring time interval through the preset power battery monitoring system, and wakes up the electronic controller and instrument by sending a voltage wake-up signal when the power battery is in a healthy state of power;

[0046] The battery recharge module 304 activates the DCDC system using an electronic controller and monitors the charge level of the starting battery using a meter. When the meter detects that the starting battery is in a low charge state, the DCDC system recharges the starting battery based on the initial recharge time.

[0047] The charging optimization module 306 stores the voltage and temperature information of the battery during the current charging process, combines the voltage and temperature information with the historical data of the cloud bus, and determines the optimized target monitoring time interval and target charging duration through integrated learning processing. The target monitoring time interval and target charging duration are then used to perform the next round of charging processing on the starting battery of the pure electric bus.

[0048] The starting battery charging device for the pure electric bus provided in the embodiment of the present application can significantly improve the charging efficiency while saving costs.

[0049] In one embodiment, when performing the step of monitoring the power battery of a pure electric bus through a preset power battery monitoring system according to an initial monitoring time interval, the power monitoring module 302 is further used to: end the monitoring process when the power battery monitoring system monitors that the power battery is less than a preset power percentage or the power battery fails; when the power battery monitoring system monitors that the power battery is not less than a preset power percentage and the power battery has no faults, determine that the power battery is in a healthy power state.

[0050] In one embodiment, when the starting battery is monitored for power using an instrument, and when the instrument detects that the starting battery is in a low-power state, the starting battery is recharged based on the initial recharge time by the DCDC system, the battery recharge module 304 is further used to: when it is detected that the power level of the starting battery is not less than a preset power value, determine that the starting battery is in a healthy power state and end the recharge process; when it is detected that the power level of the starting battery is less than the preset power value, determine that the starting battery is in a low-power state, and the DCDC system performs voltage conversion to convert the high-voltage electricity of the power battery into low-voltage electricity to recharge the starting battery.

[0051] In one embodiment, after determining that the starting battery is in a low-battery state, the battery charging module 304 is further configured to perform statistical analysis on the battery power monitoring results of the starting battery. If the monitoring results of two consecutive battery power monitoring operations both indicate that the starting battery is in a low-battery state, it is determined that the power battery is abnormal, the charging process is terminated, and an alarm is issued on the instrument to prompt the user to replace the starting battery.

[0052] In one embodiment, before combining the voltage information, temperature information and cloud bus historical data and determining the optimized target monitoring time interval and target power replenishment duration through integrated learning processing, the power replenishment optimization module 306 is further used to: perform data cleaning processing on the voltage information and temperature information to remove outliers and noise values, and perform feature extraction and normalization processing on the cleaned data to determine the target feature data.

[0053] In one embodiment, when combining voltage information, temperature information and cloud bus historical data to determine the optimized target monitoring time interval and target power replenishment duration through integrated learning processing, the power replenishment optimization module 306 is also used to: combine the linear regression model and the long short-term memory network model in series, gradually decompose the target feature data, analyze the linear features and nonlinear features in the target feature data respectively, and determine the optimized target monitoring time interval and target power replenishment duration.

[0054] In one embodiment, when the linear regression model and the long short-term memory network model are serially combined to gradually decompose the target feature data, the linear features and nonlinear features in the target feature data are analyzed respectively, and the optimized target monitoring time interval and target power replenishment duration are determined, the above-mentioned power replenishment optimization module 306 is also used to: perform preliminary division on the target feature data to determine the first linear feature and the first nonlinear feature; use the linear regression model to perform linear regression processing on the first linear feature, and determine the residual value of the linear regression as the second nonlinear feature; use the long short-term memory network model to perform nonlinear feature analysis processing on the first nonlinear feature and the second nonlinear feature to determine the optimized target monitoring time interval and target power replenishment duration.

[0055] In one embodiment, when performing the step of performing preliminary division on the target feature data and determining the first linear feature and the first nonlinear feature, the above-mentioned power replenishment optimization module 306 is further used to: respectively calculate the Pearson correlation coefficients between voltage and time, temperature and time, and power replenishment duration and voltage and temperature in the target feature data; when the Pearson correlation coefficient corresponding to the target feature data approaches 0, it is determined that the target feature data is the first nonlinear feature; when the Pearson correlation coefficient corresponding to the target feature data approaches 1 or -1, it is determined that the target feature data is the first linear feature.

[0056] In one embodiment, after determining the optimized target monitoring time interval and target charging duration, the charging optimization module 306 is further configured to analyze the user's vehicle travel history and the license plate restriction information in the current area based on historical cloud bus data. If the analysis result indicates that the user travels every other day, the preset power percentage for power battery monitoring is reduced to a preset percentage threshold, and the target monitoring time interval and target charging duration are recalculated to increase the priority of the user's travel.

[0057] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0058] An embodiment of the present invention provides a server. Specifically, the server includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0059] Figure 4 A structural diagram of a server provided in an embodiment of the present invention is provided, wherein the server 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0060] Memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between the system network element and at least one other network element is achieved through at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0061] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0062] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0063] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processing unit (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0064] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be referred to the previous method embodiment and will not be repeated here.

[0065] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0066] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for charging the starting battery of a pure electric bus, characterized in that: The method comprises: By presetting the power battery monitoring system, the power battery of the pure electric bus is monitored according to the initial monitoring time interval, and when the power battery is in a healthy state of power, the electronic controller and instrument are awakened by sending a voltage wake-up signal; activating the DCDC system using the electronic controller and monitoring the power level of the starting battery using the meter; and when the meter detects that the starting battery is in a low power state, recharging the starting battery using the DCDC system based on an initial recharging time; The voltage and temperature information of the battery during the current charging process is stored, and the voltage and temperature information are combined with historical cloud bus data to determine an optimized target monitoring time interval and target charging duration through ensemble learning processing. The target monitoring time interval and target charging duration are then used to perform the next round of charging processing on the starting battery of the pure electric bus. The step of combining the voltage information, the temperature information, and cloud bus historical data to determine an optimized target monitoring time interval and target recharging duration through ensemble learning processing includes: serially combining a linear regression model and a long short-term memory network model to gradually decompose target feature data, analyzing linear features and nonlinear features in the target feature data, and determining the optimized target monitoring time interval and target recharging duration; The step of serially combining the linear regression model and the long short-term memory network model to gradually decompose the target feature data, analyzing the linear features and nonlinear features in the target feature data respectively, and determining the optimized target monitoring time interval and target power replenishment duration includes: performing preliminary division on the target feature data to determine a first linear feature and a first nonlinear feature; performing linear regression processing on the first linear feature using the linear regression model, and determining the residual value of the linear regression as a second nonlinear feature; performing nonlinear feature analysis processing on the first nonlinear feature and the second nonlinear feature using the long short-term memory network model to determine the optimized target monitoring time interval and target power replenishment duration; The step of performing preliminary division on the target feature data and determining the first linear feature and the first nonlinear feature includes: respectively calculating the Pearson correlation coefficients between voltage and time, temperature and time, and charging duration and voltage and temperature in the target feature data; when the Pearson correlation coefficient corresponding to the target feature data approaches 0, determining that the target feature data is the first nonlinear feature; when the Pearson correlation coefficient corresponding to the target feature data approaches 1 or -1, determining that the target feature data is the first linear feature; Among them, after the step of determining the optimized target monitoring time interval and target charging time, it includes: analyzing the historical travel information of the user's vehicle and the license plate restriction information of the current area based on the cloud bus historical data. If the analysis result shows that the user travels every other day, the preset power percentage of the power battery monitoring is reduced to a preset percentage threshold, and the target monitoring time interval and the target charging time are recalculated to improve the priority of the user's travel.

2. The method for replenishing the starting battery of a pure electric bus according to claim 1, characterized in that: The step of performing power monitoring processing on the power battery of the pure electric bus according to the initial monitoring time interval by using the preset power battery monitoring system includes: When the power battery monitoring system detects that the power level of the power battery is less than a preset power percentage or the power battery fails, the monitoring process is terminated; When the power battery monitoring system monitors that the power level of the power battery is not less than a preset power percentage and the power battery has no faults, it is determined that the power battery is in a healthy power state.

3. The method for replenishing the starting battery of a pure electric bus according to claim 1, characterized in that: The step of monitoring the power level of the starting battery using the meter and, when the meter detects that the starting battery is in a low power state, performing a power replenishment process on the starting battery based on the initial power replenishment duration by the DCDC system includes: When it is monitored that the power level of the starting battery is not less than a preset power value, it is determined that the starting battery is in a healthy power state and the charging process is terminated; When it is monitored that the power level of the starting battery is less than a preset power value, it is determined that the starting battery is in a low power state, and the DCDC system performs voltage conversion to convert the high voltage electricity of the power battery into low voltage electricity to recharge the starting battery.

4. The method for replenishing the starting battery of a pure electric bus according to claim 3, characterized in that: After determining that the starting battery is in a low-battery state, the method further includes: Statistical analysis is performed on the power monitoring results of the starting battery. If the monitoring results of two consecutive power monitorings both indicate that the starting battery is in a low power state, it is determined that the power battery is abnormal, the charging process is terminated, and an alarm is issued on the instrument to prompt the user to replace the starting battery.

5. The method for replenishing the starting battery of a pure electric bus according to claim 1, characterized in that: Before the step of combining the voltage information, the temperature information, and the cloud bus historical data to determine the optimized target monitoring time interval and target power replenishment duration through integrated learning processing, the method includes: Data cleaning is performed on the voltage information and the temperature information to remove abnormal values and noise values, and feature extraction and normalization are performed on the cleaned data to determine target feature data.

6. A starting battery charging device for a pure electric bus, characterized in that: The device method includes: The power monitoring module monitors the power battery of the pure electric bus according to the initial monitoring time interval through the preset power battery monitoring system, and wakes up the electronic controller and instrument by sending a voltage wake-up signal when the power battery is in a healthy state of power; a battery charging module, which activates the DCDC system using the electronic controller and monitors the power level of the starting battery using the meter. When the meter detects that the starting battery is in a low power state, the starting battery is charged based on the initial charging time using the DCDC system; The charging optimization module stores the voltage and temperature information of the battery during the current charging process, combines the voltage and temperature information with historical cloud bus data, and uses integrated learning to determine an optimized target monitoring time interval and target charging duration. The module then uses the target monitoring time interval and target charging duration to perform the next round of charging on the starting battery of the pure electric bus. The step of combining the voltage information, the temperature information, and cloud bus historical data to determine an optimized target monitoring time interval and target recharging duration through ensemble learning processing includes: serially combining a linear regression model and a long short-term memory network model to gradually decompose target feature data, analyzing linear features and nonlinear features in the target feature data, and determining the optimized target monitoring time interval and target recharging duration; The step of serially combining the linear regression model and the long short-term memory network model to gradually decompose the target feature data, analyzing the linear features and nonlinear features in the target feature data respectively, and determining the optimized target monitoring time interval and target power replenishment duration includes: performing preliminary division on the target feature data to determine a first linear feature and a first nonlinear feature; performing linear regression processing on the first linear feature using the linear regression model, and determining the residual value of the linear regression as a second nonlinear feature; performing nonlinear feature analysis processing on the first nonlinear feature and the second nonlinear feature using the long short-term memory network model to determine the optimized target monitoring time interval and target power replenishment duration; The step of performing preliminary division on the target feature data and determining the first linear feature and the first nonlinear feature includes: respectively calculating the Pearson correlation coefficients between voltage and time, temperature and time, and charging duration and voltage and temperature in the target feature data; when the Pearson correlation coefficient corresponding to the target feature data approaches 0, determining that the target feature data is the first nonlinear feature; when the Pearson correlation coefficient corresponding to the target feature data approaches 1 or -1, determining that the target feature data is the first linear feature; Among them, after the step of determining the optimized target monitoring time interval and target charging time, it includes: analyzing the historical travel information of the user's vehicle and the license plate restriction information of the current area based on the cloud bus historical data. If the analysis result shows that the user travels every other day, the preset power percentage of the power battery monitoring is reduced to a preset percentage threshold, and the target monitoring time interval and the target charging time are recalculated to improve the priority of the user's travel.

7. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 5.

Images