Intelligent Charging Pile Metering Method and System Based on Internet of Things Technology

Abstract

The present invention relates to the technical field of electric energy consumption monitoring, and in particular to an intelligent charging pile metering method and system based on Internet of Things technology. The method comprises: obtaining charging data during the charging process of multiple vehicles; obtaining the battery aging parameter at each moment according to the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, and the difference between the accumulated electric energy consumption and the theoretical electric energy demand, and further obtaining the capacity change factor in combination with the change in battery temperature and the ambient temperature; clustering the charging process according to the difference in electric energy consumption between each two charging processes and the difference in the similarity between the capacity change factor and the SOC value; and using the difference in electric energy consumption between the current charging process of the target vehicle and the charging process in its cluster, correcting the electric energy consumption of the current charging process of the target vehicle to obtain the corrected electric energy consumption. The present invention improves the accuracy of the electric energy consumption metering result.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy consumption monitoring, and in particular to an intelligent charging pile metering method and system based on Internet of Things technology. Background Art

[0002] With the increasing popularity of electric vehicles and the development of new energy technologies, the construction of electric vehicle charging facilities has become a vital component of the new energy vehicle industry. As a core component of electric vehicle charging facilities, the accuracy of the measurement methods and the stability of the system are crucial to the user experience of electric vehicles and the operation and management of charging facilities.

[0003] In the metering process of existing charging piles, smart electronic electricity meters are usually used to measure the current and voltage flowing through the charging pile during charging, and record various parameters of the charging process, such as charging time and charging amount, to calculate the consumed electricity. Through the existing Internet of Things technology, all charging pile-related data in the area are centrally collected and analyzed, and then the electricity consumption data of a single charging pile is uniformly analyzed and managed.

[0004] The batteries installed in electric two-wheeled and three-wheeled vehicles will age over a long period of use, affecting the battery storage capacity of the electric vehicle and the power loss during charging, thereby reducing the electric vehicle's range and consuming more electricity during charging. Therefore, when evaluating them based solely on the collected power consumption data, there is no reference, which can easily lead to increased power consumption and errors in the measurement results. Summary of the Invention

[0005] In order to solve the problem of errors in the measurement results of existing methods when measuring power loss, the purpose of the present invention is to provide a smart charging pile measurement method and system based on Internet of Things technology. The technical solutions adopted are as follows:

[0006] In a first aspect, the present invention provides a method for detecting anomalies in multivariate time series data based on a multi-head graph attention network, the method comprising the following steps:

[0007] Obtain charging time, power consumption, battery temperature, ambient temperature, and SOC value during the charging process of several vehicles, including the target vehicle;

[0008] The battery aging parameter at each moment of each charging process is obtained based on the difference between the charging time corresponding to each moment and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand. The capacity change factor at the corresponding moment is obtained by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter.

[0009] Calculating a difference index between each two charging processes based on the difference in electric energy consumption and the difference in similar situations between the capacity change factor and the SOC value; and clustering all charging processes using the difference index;

[0010] The difference in electric energy consumption between the current charging process of the target vehicle and the charging process in the cluster where the target vehicle is located is used to correct the electric energy consumption of the current charging process of the target vehicle to obtain the corrected electric energy consumption.

[0011] Preferably, obtaining the battery aging parameter at each moment in each charging process according to the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, and the difference between the accumulated power consumption at each moment and the theoretical power demand, includes:

[0012] Calculating a first difference between the charging time corresponding to the candidate time and the theoretical charging time, and a second difference between the accumulated power consumption at the candidate time and the theoretical power demand;

[0013] Normalizing the arithmetic square root of the sum of the squares of the first difference and the second difference to obtain the battery aging parameter at the candidate moment;

[0014] The candidate time is any time during any charging process of any vehicle among the multiple vehicles.

[0015] Preferably, the method of combining the battery temperature change at each moment in each charging process, the ambient temperature, and the battery aging parameter to obtain the capacity change factor at the corresponding moment includes:

[0016] For any charging process:

[0017] Performing curve fitting on the SOC values at all moments in any charging process to obtain a corresponding SOC curve; processing the SOC curve using a first-order derivative to obtain an instantaneous slope of the SOC value at each moment; recording the moment when the instantaneous slope is 0 as a first characteristic moment;

[0018] Using the battery aging parameter at the first characteristic moment as a weight, performing weighted summation on the battery temperatures at all first characteristic moments in any charging process to obtain a critical temperature of any charging process;

[0019] For any first characteristic moment: combining the battery temperature, the ambient temperature and the critical temperature at any first characteristic moment, determining the capacity change factor at any first characteristic moment.

[0020] Preferably, the determining the capacity change factor at any first characteristic moment by combining the battery temperature, the ambient temperature, and the critical temperature at any first characteristic moment includes:

[0021] calculating a third difference between the battery temperature at any one of the first characteristic moments and the critical temperature;

[0022] Calculate the sum of the ambient temperature at any first characteristic moment and a preset adjustment parameter, and determine the ratio between the third difference and the sum as the capacity change factor at any first characteristic moment; wherein the preset adjustment parameter is a value greater than 0.

[0023] Preferably, the calculating of the difference index between each two charging processes according to the difference in electric energy consumption between each two charging processes and the difference in similar situations between the capacity change factor and the SOC value includes:

[0024] For any two charging processes:

[0025] Calculate the Pearson correlation coefficient between the capacity change factor sequence and the SOC value sequence corresponding to each charging process, and record it as the first correlation coefficient corresponding to each charging process; wherein the capacity change factor sequence corresponding to each charging process is composed of the capacity change factors at all moments in each charging process, and the SOC value sequence corresponding to each charging process is composed of the SOC values at all moments in each charging process;

[0026] Obtaining characteristic difference values corresponding to the arbitrary two charging processes based on a matching relationship between instantaneous slopes corresponding to each moment on the SOC curves corresponding to the arbitrary two charging processes;

[0027] According to the first difference between the first correlation coefficients corresponding to the arbitrary two charging processes, the second difference between the power consumption in the arbitrary two charging processes and the characteristic difference value, a difference index between the arbitrary two charging processes is obtained, and the first difference, the second difference and the characteristic difference value are all positively correlated with the difference index.

[0028] Preferably, obtaining the characteristic difference value corresponding to the arbitrary two charging processes based on the matching relationship between the instantaneous slopes corresponding to each moment on the SOC curves corresponding to the arbitrary two charging processes includes:

[0029] Changing the matching relationship between the values in the first slope sequence and the second slope sequence by translation, respectively obtaining the difference between the two data in each matching pair; the first slope sequence and the second slope sequence are respectively the instantaneous slopes corresponding to all moments on the SOC curve corresponding to one of the two charging processes;

[0030] Calculate the average value of the differences corresponding to all matching pairs obtained after each translation, and record it as the difference value of each translation; the step length of each translation is the preset step length;

[0031] The minimum difference value of all translations is determined as the characteristic difference value corresponding to any two charging processes.

[0032] Preferably, clustering all charging processes using the difference index includes: clustering all charging processes using a K-means clustering algorithm based on the difference index between every two charging processes.

[0033] Preferably, the method of correcting the electric energy consumption of the target vehicle during the current charging process by utilizing the difference in electric energy consumption between the target vehicle during the current charging process and the charging process in the cluster where the target vehicle is located to obtain the corrected electric energy consumption includes:

[0034] Calculating an average value of the electric energy consumption of all charging processes in the cluster where the target vehicle is currently charging; recording the difference between the average value and the electric energy consumption of the target vehicle during the current charging process as a fourth difference;

[0035] multiplying a normalized result of the minimum value of all the feature difference values and the fourth difference value as an adjustment value;

[0036] The electric energy consumption of the target vehicle during the current charging process is corrected using the adjustment value to obtain the corrected electric energy consumption.

[0037] Preferably, the using the adjustment value to correct the electric energy consumption of the target vehicle during the current charging process to obtain the corrected electric energy consumption includes:

[0038] The sum of the electric energy consumption of the target vehicle during the current charging process and the adjustment value is determined as the corrected electric energy consumption.

[0039] In a second aspect, the present invention provides a multivariate time series data anomaly detection system based on a multi-head graph attention network, the system comprising:

[0040] a data acquisition module for acquiring charging time, power consumption, battery temperature, ambient temperature, and SOC value during charging of a plurality of vehicles, wherein the plurality of vehicles includes a target vehicle;

[0041] The first calculation module is configured to obtain a battery aging parameter at each moment of each charging process based on the difference between the charging time corresponding to each moment of each charging process and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand; and to obtain a capacity change factor at the corresponding moment by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter;

[0042] a clustering module for calculating a difference index between each two charging processes based on the difference in electric energy consumption and the difference in similarity between the capacity change factor and the SOC value between the two charging processes; and clustering all charging processes using the difference index;

[0043] The correction module is used to correct the electric energy consumption of the current charging process of the target vehicle by using the difference in electric energy consumption between the current charging process of the target vehicle and the charging process in the cluster where it is located, so as to obtain the corrected electric energy consumption.

[0044] The present invention has at least the following beneficial effects:

[0045] The present invention first collects the charging time, power consumption, battery temperature, ambient temperature and SOC value of multiple vehicles during multiple charging processes, analyzes the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, and the difference between the accumulated power consumption at each moment and the theoretical power demand, and obtains the battery aging parameters at each moment in each charging process. This operation avoids the error in power consumption data caused by the increase in actual parameters of electric vehicles with the increase in usage time and the differences between different electric vehicles themselves, making the elements in the cluster more representative when clustering is performed later; then, by combining the changes in battery temperature at each moment in each charging process The capacity change factor is determined based on the difference in energy consumption between each two charging processes and the difference in similar situations between the capacity change factor and the SOC value, and the difference index between different charging processes is determined. The charging processes are clustered accordingly. This operation avoids the data distortion caused by obtaining the relationship between the SOC value at a single moment and the temperature by analyzing the difference in battery loss of different electric vehicles and the impact of temperature differences on basic battery parameters. Finally, the energy consumption data is cleaned in real time according to the difference in energy consumption between the current charging process of the target vehicle and the charging process in its cluster, which improves the accuracy of cleaning and the credibility of the charging pile metering process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only 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.

[0047] Figure 1 This is a flow chart of a smart charging pile metering method based on Internet of Things technology provided by an embodiment of the present invention;

[0048] Figure 2 This is a structural block diagram of an intelligent charging pile metering system based on Internet of Things technology provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of the smart charging pile metering method and system based on Internet of Things technology proposed by the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of the smart charging pile metering method and system based on Internet of Things technology provided by the present invention is described in detail below with reference to the accompanying drawings.

[0052] Example of smart charging pile metering method based on Internet of Things technology:

[0053] The specific scenario targeted by this embodiment is: during the charging process of a two-wheeled or three-wheeled electric vehicle, the batteries installed in the two-wheeled or three-wheeled electric vehicle will age over time, affecting the battery storage capacity of the electric vehicle and the power loss during the charging process, thereby reducing the electric vehicle's range and consuming more power during charging. In this case, if the evaluation is based solely on the power consumption data of a single electric vehicle, without a reference, it is easy to increase power consumption and cause errors in the measurement results. Therefore, it is necessary to clean the actual power loss data to ensure the accuracy and credibility of the measurement results.

[0054] This embodiment proposes a smart charging pile metering method based on Internet of Things technology, such as Figure 1 As shown, the smart charging pile metering method based on Internet of Things technology of this embodiment includes the following steps:

[0055] Step S1, obtaining charging time, power consumption, battery temperature, ambient temperature and SOC value during the charging process of several vehicles, wherein the several vehicles include a target vehicle.

[0056] The BMS used in charging two-wheeled or three-wheeled electric vehicles is simpler than that used in larger electric vehicles because it manages fewer battery cells, but its core functions are similar. A BMS, or Battery Management System (BMS), is an electronic system that monitors and protects the battery pack. It monitors battery voltage, current, temperature, and other relevant data in real time, and provides balanced management and protection for the battery components.

[0057] First, data is collected from multiple vehicles during a preset time period, including the charging duration, accumulated energy consumption, battery temperature, ambient temperature, and SOC (State of Charge) value for each charging process. The collected data includes the target vehicle, i.e., the vehicle whose energy consumption is to be corrected. It should be noted that the multiple vehicles in this embodiment are all of the same type and model, with the same battery parameters such as the rated maximum storage capacity, maximum rated current, and voltage. In this embodiment, the preset time period is the most recent month; in specific applications, the user can set the preset time period based on specific circumstances. In this embodiment, the data collection frequency is once per second, meaning that for any charging process, the charging duration, energy consumption, battery temperature, ambient temperature, and SOC value are collected every second. The number of vehicles collected is 200; in specific applications, the user can set this frequency based on specific circumstances.

[0058] At this point, this embodiment has obtained the charging duration, power consumption, battery temperature, ambient temperature, and SOC value at each moment during each charging process for multiple vehicles. It should be noted that the charging duration at each moment is the duration from the start of the current charge to that moment, and the power consumption at each moment is the cumulative power consumption from the start of the current charge to that moment.

[0059] Step S2, according to the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand, obtain the battery aging parameter at each moment in each charging process; combined with the change of battery temperature at each moment in each charging process, the ambient temperature and the battery aging parameter, obtain the capacity change factor at the corresponding moment.

[0060] When measuring the energy consumption of different electric vehicles, the actual parameters of electric vehicles change with the increase of usage time, and the degree of change varies among different electric vehicles. Therefore, there are certain errors in the energy consumption data generated during the comparison process, resulting in a decrease in the accuracy of the energy consumption data for a certain charging process corresponding to the current charging pile.

[0061] Since the total mileage of different electric vehicles varies, the battery will suffer a certain amount of battery loss during the continuous charging and discharging process, which will cause the actual storage capacity to decrease. At the same time, the actual current generated by the charging pile and passing through the battery will change, which will cause the actual charging efficiency to change. In order to avoid the impact of the battery's own loss on the actual energy consumption measurement of the charging pile, it is necessary to correct the collected energy consumption to eliminate the impact of the loss. At the same time, since the remaining storage capacity of actual electric vehicles before charging is different, the difference between the rated storage capacity of the battery and the remaining storage capacity before charging is obtained, thereby obtaining the theoretical energy demand and the theoretical charging time when the parameters such as the charging pile power are consistent.

[0062] Next, this embodiment is described by taking a moment in a charging process of a vehicle as an example. The method provided in this embodiment can be used to process other moments of the vehicle and all moments in the charging process of other vehicles.

[0063] Specifically, any moment in any charging process of any of the several vehicles is recorded as a candidate moment, and the first difference between the charging time corresponding to the candidate moment and the theoretical charging time, and the second difference between the accumulated power consumption at the candidate moment and the theoretical power demand are calculated respectively; the arithmetic square root of the sum of the squares of the first difference and the second difference is normalized to obtain the battery aging parameter at the candidate moment. It should be noted that the duration corresponding to the candidate moment is the duration from the start of the current charge to the candidate moment. The theoretical charging time and the theoretical power demand are set by the implementer according to the battery parameters.

[0064] In this embodiment, a specific calculation formula for the battery aging parameter is given. The battery aging parameter at the rth moment during the i-th charging process of any vehicle can be expressed as:

[0065]

[0066] in, represents the battery aging parameter at the rth moment during the i-th charging process of the vehicle, The first difference represents the difference between the charging time corresponding to the rth moment in the i-th charging process of the vehicle and the theoretical charging time; represents the difference between the accumulated power consumption at the rth moment during the i-th charging process of the vehicle and the theoretical power demand, that is, the second difference; norm() represents the normalization function.

[0067] It represents the arithmetic square root of the sum of the squares of the first difference and the second difference, that is, the eigenvalues are combined and normalized using the Euclidean norm. When the difference between the charging time corresponding to the rth moment in the i-th charging process of the vehicle and the theoretical charging time is greater, and the difference between the accumulated power consumption and the theoretical power demand is also greater, it means that the health of the battery is lower, that is, the battery aging parameter is greater.

[0068] By adopting the above method, the battery aging parameters of the vehicle at each moment during each charging process can be obtained.

[0069] For each charging process, the numerical value of SOC should theoretically increase linearly, but in the actual charging process, it is affected by external factors such as current and voltage fluctuations generated when the inverter of the charging pile converts AC and DC power, temperature, etc. Among them, the influence of ambient temperature on the actual energy consumption of the charging pile is the most obvious. For example, at low temperatures, the chemical reaction rate inside the battery decreases, resulting in a weakening of the battery's charging and discharging capabilities, thereby reducing the battery's available capacity, causing the energy demand to decrease or even approach 0, shortening the actual charging time. As charging progresses, the temperature of the electric vehicle battery gradually exceeds the ambient temperature, and the battery capacity gradually approaches the actual level, but this process takes time, which increases the time required for the charging process, thereby increasing the consumed energy. At this time, since the influence of temperature on battery capacity has a corresponding time, obtaining its relationship with temperature based only on the SOC value at a single moment is prone to data distortion, resulting in external factors still interfering in the final result.

[0070] There is a corresponding threshold between the change in battery capacity and temperature during the charging process, that is, the battery capacity will only change with temperature when the temperature is lower than a certain temperature threshold.

[0071] Next, this embodiment is described by taking a charging process as an example. Other charging processes can be processed using the method provided in this embodiment.

[0072] Specifically, for any charging process:

[0073] A corresponding SOC curve is obtained by performing curve fitting on the SOC values at all moments in any charging process. The abscissa of the SOC curve represents the acquisition time, and the ordinate represents the SOC value at the corresponding acquisition time. Curve fitting is a conventional technique and will not be described in detail here. The SOC curve is processed using a first-order derivative to obtain the instantaneous slope of the SOC value at each moment. The moment when the instantaneous slope is 0 is recorded as the first characteristic moment, thus obtaining multiple first characteristic moments.

[0074] The battery aging parameter at the first characteristic moment is used as a weight, and the weighted sum of the battery temperatures at all first characteristic moments in any charging process is performed to obtain the critical temperature of any charging process.

[0075] For any first characteristic moment: calculate the difference between the battery temperature at any first characteristic moment and the critical temperature, and record the difference as the third difference; determine the ratio of the third difference to the ambient temperature at any first characteristic moment as the capacity change factor at any first characteristic moment.

[0076] In this embodiment, a specific calculation formula for the capacity change factor is given. The capacity change factor at the jth first characteristic moment in the i-th charging process can be expressed as:

[0077]

[0078] in, represents the capacity change factor at the jth first characteristic moment in the i-th charging process, represents the battery temperature at the jth first characteristic moment in the i-th charging process, N represents the number of first characteristic moments in the i-th charging process, represents the battery aging parameter at the jth first characteristic moment in the i-th charging process, represents the ambient temperature at the jth first characteristic moment in the i-th charging process, Indicates preset adjustment parameters.

[0079] In this embodiment, the preset adjustment parameter is introduced into the calculation formula of the capacity change factor to prevent the denominator from being 0. The preset adjustment parameter is a value greater than 0. In specific applications, the implementer sets the preset adjustment parameter according to the actual ambient temperature. Characterizes the critical temperature of the i-th charging process. represents the third difference, that is, the difference between the battery temperature at the jth first characteristic moment in the i-th charging process and the critical temperature. This value can be positive or negative. When it is less than 0, it means that the battery temperature is lower than the critical temperature, and the probability of a capacity change is greater. When the battery temperature is greater than or equal to 0, the probability of a capacity change is smaller. At the same time, the lower the ambient temperature, the greater the probability of a capacity change, that is, the larger the capacity change factor.

[0080] By adopting the above method, the capacity variation factor at each first characteristic moment in each charging process can be obtained.

[0081] Step S3, calculating a difference index between each two charging processes based on the difference in power consumption between each two charging processes and the difference in similar situations between the capacity change factor and the SOC value; and clustering all charging processes using the difference index.

[0082] Next, this embodiment evaluates the difference in power consumption between two charging processes, and the difference in similar situations between the capacity variation factor and the SOC value.

[0083] Specifically, the Pearson correlation coefficient between the capacity change factor sequence and the SOC value sequence corresponding to each charging process is calculated, which is recorded as the first correlation coefficient corresponding to each charging process. Each charging process has a first correlation coefficient. The capacity change factor sequence corresponding to each charging process is obtained by arranging the capacity change factors at all moments in each charging process in chronological order, and the SOC value sequence corresponding to each charging process is obtained by arranging the SOC values at all moments in each charging process in chronological order. The method for calculating the Pearson correlation coefficient is existing in the art and will not be further elaborated here.

[0084] For any two charging processes:

[0085] The instantaneous slopes of the SOC values at all moments in one of the two charging processes are arranged in chronological order to obtain a first slope sequence, and the instantaneous slopes of the SOC values at all moments in the other of the two charging processes are arranged in chronological order to obtain a second slope sequence.

[0086] In the initial state, the elements of the first slope sequence and the corresponding positions in the second slope sequence are made to correspond to each other, that is, the first element in the first slope sequence corresponds to the first element in the second slope sequence, and the first element in the first slope sequence and the first element in the second slope sequence constitute a matching pair, the second element in the first slope sequence corresponds to the second element in the second slope sequence, and the second element in the first slope sequence and the second element in the second slope sequence constitute a matching pair, the third element in the first slope sequence corresponds to the third element in the second slope sequence, and the third element in the first slope sequence and the third element in the second slope sequence constitute a matching pair, and so on, the last element in the first slope sequence corresponds to the last element in the second slope sequence, and the last element in the first slope sequence and the last element in the second slope sequence constitute a matching pair, that is, multiple matching pairs are obtained. Then, the first slope sequence is fixed and the second slope sequence is shifted. In this embodiment, the shift step size is 1 each time. That is, the second element in the first slope sequence corresponds to the first element in the second slope sequence, and the second element in the first slope sequence and the first element in the second slope sequence form a matching pair. The third element in the first slope sequence corresponds to the second element in the second slope sequence, and the third element in the first slope sequence and the second element in the second slope sequence form a matching pair. The fourth element in the first slope sequence corresponds to the third element in the second slope sequence, and the fourth element in the first slope sequence and the third element in the second slope sequence form a matching pair. And so on. The last element in the first slope sequence corresponds to the second-to-last element in the second slope sequence, and the last element in the first slope sequence and the second-to-last element in the second slope sequence form a matching pair. In other words, multiple matching pairs are obtained. Then, based on the previous translation result, the second slope sequence is translated again. In this embodiment, the moving step size each time is 1, that is, the third element in the first slope sequence corresponds to the first element in the second slope sequence, and the third element in the first slope sequence and the first element in the second slope sequence constitute a matching pair, the fourth element in the first slope sequence corresponds to the second element in the second slope sequence, and the fourth element in the first slope sequence and the second element in the second slope sequence constitute a matching pair, the fifth element in the first slope sequence corresponds to the third element in the second slope sequence, and the fifth element in the first slope sequence and the third element in the second slope sequence constitute a matching pair, and so on. The last element in the first slope sequence corresponds to the third-to-last element in the second slope sequence, and the last element in the first slope sequence and the third-to-last element in the second slope sequence constitute a matching pair, that is, multiple matching pairs are obtained.According to this method, the second slope sequence is shifted multiple times until no matching pairs exist between the first and second slope sequences. Each shift yields multiple matching pairs. The shifts change the matching relationship between the values in the first and second slope sequences, and the difference between the two data points in each matching pair is obtained. The difference between the two data points in each matching pair is obtained by taking the absolute value of the difference between the two data points as the difference between the two data points. The average of the differences corresponding to all matching pairs obtained after each shift is calculated and recorded as the difference value for each shift. The step size of each shift is a preset step size, which in this embodiment is 1. The minimum difference value across all shifts is determined as the characteristic difference value corresponding to any two charging processes. A difference index between the two charging processes is obtained based on the first difference between the first correlation coefficients corresponding to the two charging processes, the second difference between the energy consumption in the two charging processes, and the characteristic difference value. The first difference, the second difference, and the characteristic difference value are all positively correlated with the difference index.

[0087] Among them, a positive correlation relationship indicates that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by actual application; a negative correlation relationship indicates that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by actual application.

[0088] In this embodiment, a specific calculation formula for the difference index is given. The difference index between the i-th charging process and the v-th charging process can be expressed as:

[0089]

[0090] in, represents the difference index between the i-th charging process and the v-th charging process, represents the energy consumption of the i-th charging process, Indicates the energy consumption of the vth charging process, represents the second difference, represents the first correlation coefficient corresponding to the i-th charging process, represents the first correlation coefficient corresponding to the vth charging process, represents the first difference, represents the characteristic difference value corresponding to the i-th charging process and the v-th charging process, Indicates the absolute value sign.

[0091] When the first difference is smaller, the second difference is also smaller, and the characteristic difference value corresponding to the i-th charging process and the v-th charging process is also smaller, it means that the battery states of the electric vehicle corresponding to the two charging processes are more similar, that is, the difference index between the two charging processes is smaller, and the necessity of clustering them into one category is higher.

[0092] Using this method, we can obtain a difference index between each two charging processes. The smaller the difference index, the more similar the battery state of the electric vehicle is during the two charging processes, meaning the two charging processes are more likely to be clustered into the same category. Therefore, based on the difference index between each two charging processes, we use the K-means clustering algorithm to cluster all charging processes, obtaining multiple clusters. The k value used in the K-means clustering algorithm is obtained using the elbow method and can be customized by the user based on specific circumstances. The K-means clustering algorithm is a state-of-the-art technique and will not be further elaborated on here.

[0093] Step S4 , using the difference in power consumption during the current charging process of the target vehicle and the power consumption during the charging process in the cluster where the target vehicle is located, the power consumption during the current charging process of the target vehicle is corrected to obtain a corrected power consumption.

[0094] The advantage of using the IoT to measure the real-time charging process of charging piles is that it allows for analysis and processing of real-time energy consumption data. If errors exist in the charging pile metering data, the acquired historical charging data can be used to clean up the energy consumption of a specific charge. Next, this embodiment will use the difference in energy consumption between the target vehicle's current charging process and that of the charging processes within its cluster to clean up the target vehicle's current charging process.

[0095] Specifically, the average value of the electric energy consumption of all charging processes within the cluster where the target vehicle's current charging process is located is calculated; the difference between the average value and the electric energy consumption of the target vehicle's current charging process is recorded as a fourth difference; the product of the normalized minimum value of all the characteristic difference values and the fourth difference is used as an adjustment value; the electric energy consumption of the target vehicle's current charging process is corrected using the adjustment value to obtain a corrected electric energy consumption. Specifically, the sum of the electric energy consumption of the target vehicle's current charging process and the adjustment value is determined as the corrected electric energy consumption. The corrected electric energy consumption can be expressed as:

[0096]

[0097] in, Indicates the corrected power consumption. Indicates the current energy consumption of the target vehicle during the charging process. Represents the normalized result of the minimum value of all feature difference values, Indicates the average value of the electric energy consumption of all charging processes in the cluster where the target vehicle is currently charging. Represents the fourth difference.

[0098] It should be noted that there are many methods for normalizing data. This embodiment uses the maximum and minimum normalization method to normalize the minimum value of all feature difference values. The maximum and minimum normalization method is an existing technology and will not be described in detail here.

[0099] This embodiment combines a linear function to clean the current power consumption, using the difference between the average power consumption of all charging processes in the cluster where the target vehicle's current charging process is located and the power consumption of the target vehicle's current charging process as the cleaning amplitude, and using the minimum value of the above-mentioned characteristic difference value as the coefficient, thereby cleaning the original power consumption data. Contains positive and negative values. If the energy consumption of the current charging process is greater than the average value of the energy consumption, the value is negative and combined with the minimum value of the characteristic difference value to obtain the reduction amount, and the original energy consumption level is appropriately reduced. Otherwise, it is appropriately increased when it is positive.

[0100] At this point, this embodiment obtains the corrected power consumption, that is, the cleaning of the power consumption is achieved.

[0101] This embodiment first collects the charging time, power consumption, battery temperature, ambient temperature and SOC value of multiple vehicles during multiple charging processes, analyzes the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, and the difference between the accumulated power consumption at each moment and the theoretical power demand, and obtains the battery aging parameters at each moment in each charging process. This operation avoids the error in the power consumption data caused by the increase in the actual parameters of the electric vehicle with the use time and the differences between different electric vehicles themselves, so that the elements in the cluster are more representative when clustering is performed later; then, by combining the changes in the battery temperature at each moment in each charging process The capacity change factor is determined based on the difference in energy consumption between each two charging processes and the difference in similar situations between the capacity change factor and the SOC value, and the difference index between different charging processes is determined. The charging processes are clustered accordingly. This operation avoids the data distortion caused by obtaining the relationship between the SOC value at a single moment and the temperature by analyzing the difference in battery loss of different electric vehicles and the impact of temperature differences on basic battery parameters. Finally, the energy consumption data is cleaned in real time according to the difference in energy consumption between the current charging process of the target vehicle and the charging process in its cluster, which improves the accuracy of cleaning and the credibility of the charging pile metering process.

[0102] Example of smart charging pile metering system based on Internet of Things technology:

[0103] See Figure 2 , which shows a structural block diagram of an intelligent charging pile metering system based on Internet of Things technology provided by an embodiment of the present invention. The system may include a data acquisition module, a first calculation module, a clustering module and a correction module.

[0104] The data acquisition module is used to obtain charging time, power consumption, battery temperature, ambient temperature and SOC value of a plurality of vehicles during charging, wherein the plurality of vehicles includes a target vehicle;

[0105] The first calculation module is configured to obtain a battery aging parameter at each moment of each charging process based on the difference between the charging time corresponding to each moment of each charging process and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand; and to obtain a capacity change factor at the corresponding moment by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter;

[0106] a clustering module for calculating a difference index between each two charging processes based on the difference in electric energy consumption and the difference in similarity between the capacity change factor and the SOC value between the two charging processes; and clustering all charging processes using the difference index;

[0107] The correction module is used to correct the electric energy consumption of the current charging process of the target vehicle by using the difference in electric energy consumption between the current charging process of the target vehicle and the charging process in the cluster where it is located, so as to obtain the corrected electric energy consumption.

[0108] It should be understood that Figure 2The block diagram of the IoT-based smart charging pile metering system and its modules can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented using hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic, while the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will appreciate that the above-described methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and their modules described herein can be implemented not only using hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field-programmable gate arrays or programmable logic devices, but also using software executed by various types of processors, or a combination of these hardware circuits and software (e.g., firmware).

[0109] For more details about the above modules, please refer to other places in this manual and will not be repeated here.

[0110] In other embodiments, a smart charging pile metering device based on the Internet of Things (IoT) is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to retrieve and execute the executable program code from the memory, causing the device to execute the aforementioned welding control method for a pulse welding machine. The device can be a chip, component, or module. The chip may include a processor and memory connected to each other. The memory is used to store instructions. When the processor retrieves and executes the instructions, the chip can execute the IoT-based smart charging pile metering method provided in the aforementioned embodiments.

[0111] In other embodiments, a computer program product is also provided. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement the smart charging pile metering method based on Internet of Things technology provided in the above embodiment.

[0112] In other embodiments, a computer-readable storage medium is further provided, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the smart charging pile metering method based on Internet of Things technology provided in the above embodiment.

[0113] Among them, the provided systems, electronic devices, computer program products, and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0114] It should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart charging pile metering method based on Internet of Things technology, characterized in that: The method comprises the following steps: Obtain charging time, power consumption, battery temperature, ambient temperature, and SOC value during the charging process of several vehicles, including the target vehicle; The battery aging parameter at each moment of each charging process is obtained based on the difference between the charging time corresponding to each moment and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand. The capacity change factor at the corresponding moment is obtained by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter. Calculating a difference index between each two charging processes based on the difference in electric energy consumption and the difference in similar situations between the capacity change factor and the SOC value; and clustering all charging processes using the difference index; The difference in electric energy consumption between the current charging process of the target vehicle and the charging process in the cluster where the target vehicle is located is used to correct the electric energy consumption of the current charging process of the target vehicle to obtain the corrected electric energy consumption.

2. The smart charging pile metering method based on Internet of Things technology according to claim 1 is characterized in that: The battery aging parameter at each moment in each charging process is obtained based on the difference between the charging time corresponding to each moment in each charging process and the theoretical charging time, and the difference between the accumulated power consumption at each moment and the theoretical power demand, including: Calculating a first difference between the charging time corresponding to the candidate time and the theoretical charging time, and a second difference between the accumulated power consumption at the candidate time and the theoretical power demand; Normalizing the arithmetic square root of the sum of the squares of the first difference and the second difference to obtain the battery aging parameter at the candidate moment; The candidate time is any time during any charging process of any vehicle among the multiple vehicles.

3. The smart charging pile metering method based on Internet of Things technology according to claim 1 is characterized in that: The capacity change factor at the corresponding moment is obtained by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter, including: For any charging process: Performing curve fitting on the SOC values at all moments in any charging process to obtain a corresponding SOC curve; processing the SOC curve using a first-order derivative to obtain an instantaneous slope of the SOC value at each moment; recording the moment when the instantaneous slope is 0 as a first characteristic moment; Using the battery aging parameter at the first characteristic moment as a weight, performing weighted summation on the battery temperatures at all first characteristic moments in any charging process to obtain a critical temperature of any charging process; For any first characteristic moment: combining the battery temperature, the ambient temperature and the critical temperature at any first characteristic moment, determining the capacity change factor at any first characteristic moment.

4. The smart charging pile metering method based on Internet of Things technology according to claim 3 is characterized in that: The determining the capacity change factor at any first characteristic moment by combining the battery temperature, the ambient temperature, and the critical temperature at any first characteristic moment includes: calculating a third difference between the battery temperature at any one of the first characteristic moments and the critical temperature; Calculate the sum of the ambient temperature at any first characteristic moment and a preset adjustment parameter, and determine the ratio between the third difference and the sum as the capacity change factor at any first characteristic moment; wherein the preset adjustment parameter is a value greater than 0.

5. The smart charging pile metering method based on Internet of Things technology according to claim 3 is characterized in that: The calculating of the difference index between each two charging processes based on the difference in electric energy consumption between each two charging processes and the difference between the capacity change factor and the SOC value in similar situations includes: For any two charging processes: Calculate the Pearson correlation coefficient between the capacity change factor sequence and the SOC value sequence corresponding to each charging process, and record it as the first correlation coefficient corresponding to each charging process; wherein the capacity change factor sequence corresponding to each charging process is composed of the capacity change factors at all moments in each charging process, and the SOC value sequence corresponding to each charging process is composed of the SOC values at all moments in each charging process; Obtaining characteristic difference values corresponding to the arbitrary two charging processes based on a matching relationship between instantaneous slopes corresponding to each moment on the SOC curves corresponding to the arbitrary two charging processes; According to the first difference between the first correlation coefficients corresponding to the arbitrary two charging processes, the second difference between the power consumption in the arbitrary two charging processes and the characteristic difference value, a difference index between the arbitrary two charging processes is obtained, and the first difference, the second difference and the characteristic difference value are all positively correlated with the difference index.

6. The smart charging pile metering method based on Internet of Things technology according to claim 5 is characterized in that: The obtaining of characteristic difference values corresponding to the arbitrary two charging processes based on a matching relationship between instantaneous slopes corresponding to each moment on the SOC curves corresponding to the arbitrary two charging processes includes: Changing the matching relationship between the values in the first slope sequence and the second slope sequence by translation, respectively obtaining the difference between the two data in each matching pair; the first slope sequence and the second slope sequence are respectively the instantaneous slopes corresponding to all moments on the SOC curve corresponding to one of the two charging processes; Calculate the average value of the differences corresponding to all matching pairs obtained after each translation, and record it as the difference value of each translation; the step length of each translation is the preset step length; The minimum difference value of all translations is determined as the characteristic difference value corresponding to any two charging processes.

7. The smart charging pile metering method based on Internet of Things technology according to claim 1 is characterized in that: The clustering of all charging processes by using the difference index includes: clustering all charging processes by using a K-means clustering algorithm based on the difference index between every two charging processes.

8. The smart charging pile metering method based on Internet of Things technology according to claim 6 is characterized in that: The method of correcting the electric energy consumption of the target vehicle during the current charging process by utilizing the difference between the electric energy consumption of the target vehicle during the current charging process and the electric energy consumption of the charging process in the cluster to which the target vehicle belongs, and obtaining the corrected electric energy consumption, includes: Calculating an average value of the electric energy consumption of all charging processes in the cluster where the target vehicle is currently charging; recording the difference between the average value and the electric energy consumption of the target vehicle during the current charging process as a fourth difference; multiplying a normalized result of the minimum value of all the feature difference values and the fourth difference value as an adjustment value; The electric energy consumption of the target vehicle during the current charging process is corrected using the adjustment value to obtain the corrected electric energy consumption.

9. The smart charging pile metering method based on Internet of Things technology according to claim 8 is characterized in that: The method of correcting the electric energy consumption of the target vehicle during the current charging process by using the adjustment value to obtain the corrected electric energy consumption includes: The sum of the electric energy consumption of the target vehicle during the current charging process and the adjustment value is determined as the corrected electric energy consumption.

10. An intelligent charging pile metering system based on Internet of Things technology, characterized in that: The system includes: a data acquisition module for acquiring charging time, power consumption, battery temperature, ambient temperature, and SOC value during charging of a plurality of vehicles, wherein the plurality of vehicles includes a target vehicle; The first calculation module is configured to obtain a battery aging parameter at each moment of each charging process based on the difference between the charging time corresponding to each moment of each charging process and the theoretical charging time, as well as the difference between the accumulated power consumption at each moment and the theoretical power demand; and to obtain a capacity change factor at the corresponding moment by combining the battery temperature change at each moment of each charging process, the ambient temperature, and the battery aging parameter; a clustering module for calculating a difference index between each two charging processes based on the difference in electric energy consumption and the difference in similarity between the capacity change factor and the SOC value between the two charging processes; and clustering all charging processes using the difference index; The correction module is used to correct the electric energy consumption of the current charging process of the target vehicle by using the difference in electric energy consumption between the current charging process of the target vehicle and the charging process in the cluster where it is located, so as to obtain the corrected electric energy consumption.

Images