Judgment method, system and device for home-entry charging of electric bicycle and storage medium

Abstract

The invention discloses an electric bicycle home-entry charging judgment method, system and device and a storage medium, and belongs to the field of electric bicycle charging, and the method comprises the following steps: S1, constructing an energy consumption characteristic function when an electric bicycle is in a charging state; s2, acquiring household total electricity utilization power, and generating a total electricity quantity data sequence according to the household total electricity utilization power; s3, abrupt change point detection is carried out on the total electric quantity data sequence, and energy consumption abrupt change characteristics caused by non-electric bicycle power utilization in the total electric quantity data sequence are removed; s4, performing energy consumption feature extraction on the total electric quantity data sequence after elimination; and S5, comparing the extracted energy consumption characteristics with the energy consumption characteristic function, and judging whether an electric bicycle is charged in a home or not according to a comparison result. And the situation that the electric bicycle is charged to the home in the family can be quickly and accurately judged.

Description

Technical Field

[0001] The present invention belongs to the field of electric bicycle charging, and relates to a method, system, device and storage medium for judging the charging of electric bicycles entering households. Background Art

[0002] With the increasing contradiction between the travel needs of urban residents and traffic congestion, electric bicycles have gained people's favor due to their advantages such as flexible driving, low carbon and low cost, and have become an indispensable means of transportation in the city. However, with the increase in the number of electric bicycles, their safety problems have also followed. Frequent incidents such as fires, smoke, and explosions have brought huge losses to people's lives and property. In order to effectively manage the fire accidents caused by electric bicycle charging, it is necessary to require standardized parking and charging of electric bicycles, severely investigate and punish the illegal parking and charging behaviors of electric bicycles, and timely eliminate potential safety hazards.

[0003] Among many incidents, the fire caused by electric bicycles entering buildings for charging or placement has become a major hazard affecting residential safety. At present, some communities respond to this problem by installing mechanical vehicle blocking systems in elevator passages or at the layer / car door. The core solution lies in relying on monitoring cameras and image recognition technology to identify and detect the input images in real time. Once an electric vehicle is detected entering the elevator, the system will turn on the warning light and voice alarm, and link the elevator control system to suspend the elevator operation and directly prohibit the electric vehicle from going upstairs and entering the household.

[0004] However, the application scenario of the above solution is only applicable to the scenario where the whole electric bicycle enters the household through the elevator for charging, and is not applicable to the scenario where the charging battery is removed, does not enter the household through the elevator or "enters the household for charging" by means of flying wires, etc. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned disadvantages of the prior art, and provide a method, system, device and storage medium for judging the charging of electric bicycles entering households, which can quickly and accurately judge the situation of electric bicycles entering households for charging in the family.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A method for judging the charging of electric bicycles entering households includes the following processes: S1, constructing an energy consumption characteristic function when the electric bicycle is in a charging state; S2, obtaining the total household electricity power, and generating a total electricity quantity data sequence according to the total household electricity power; S3, performing mutation point detection on the total electricity quantity data sequence, and removing the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption in the total electricity quantity data sequence; S4. Extract energy consumption characteristics from the total power consumption data sequence after elimination. S5. Compare the extracted energy consumption characteristics with the energy consumption characteristic function, and determine whether there is a situation where an electric bicycle is charged indoors in the household according to the comparison result.

[0007] Preferably, the specific process of constructing the energy consumption characteristic function when the electric bicycle is in the charging state is as follows: Obtain the charging data of various electric bicycles under different charging conditions, and generate an energy consumption characteristic function describing the electric bicycle in the charging state through statistical analysis or machine learning methods.

[0008] Preferably, the specific process of obtaining the total household power consumption and generating the total power consumption data sequence according to the total household power consumption is as follows: Obtain the total household power consumption at fixed time intervals, perform discrete summation on the total household power consumption to generate the cumulative power consumption, and arrange the cumulative power consumption in chronological order to form the total power consumption data sequence.

[0009] Preferably, the specific process of detecting mutation points in the total power consumption data sequence and eliminating the energy consumption mutation characteristics caused by non-electric bicycle power consumption in the total power consumption data sequence is as follows: Calculate the moving average value of the total power consumption data sequence; Calculate the residual between each data value in the total power consumption data sequence and the moving average value, and perform standardization processing on the residual, and calculate the Z-score of the standardized residual; Identify mutation points according to the absolute value of the Z-score of the standardized residual, and eliminate the mutation points whose absolute value of the Z-score exceeds the preset threshold.

[0010] Preferably, the specific process of extracting energy consumption characteristics from the total power consumption data sequence after elimination is as follows: Define window parameters; Extract the active power and reactive power within the window of the total power consumption data sequence after elimination through sliding window analysis, calculate the difference sequences of the active power and reactive power, and extract subsequences from the difference sequences of the active power and reactive power; Match the subsequences with the predefined electric bicycle charging template and calculate the matching degree.

[0011] Preferably, the calculation process of the matching degree is as follows: Calculate the Euclidean distance between the subsequence and the electric bicycle charging template; If the Euclidean distance is less than the preset threshold, it is determined that the current window contains the electric bicycle charging load characteristics and is marked as a match.

[0012] Preferably, the specific process of comparing the extracted energy consumption characteristics with the energy consumption characteristic function and determining whether there is a situation where an electric bicycle is charged indoors in the household according to the comparison result is as follows: Calculate the total energy consumption within the window marked as a match; Compare the total energy consumption with the energy consumption characteristic function; If the matching degree of the total energy consumption in multiple discontinuous time periods with the energy consumption characteristic function exceeds the preset threshold, it is determined that there is a situation where an electric bicycle is charged indoors in the household.

[0013] A judgment system for electric bicycle charging indoors, comprising: An energy consumption characteristic function construction module, configured to construct an energy consumption characteristic function when the electric bicycle is in a charging state; A total power data sequence generation module, configured to obtain the total household electricity consumption power and generate a total power data sequence according to the total household electricity consumption power; A mutation feature elimination module, configured to perform mutation point detection on the total power data sequence and eliminate the energy consumption mutation features caused by non-electric bicycle electricity consumption in the total power data sequence; An energy consumption feature extraction module, configured to extract energy consumption features from the total power data sequence after elimination; A fitting judgment module, configured to compare the extracted energy consumption features with the energy consumption characteristic function, and judge whether there is a situation of electric bicycle charging indoors according to the comparison result.

[0014] A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the judgment method for electric bicycle charging indoors are implemented.

[0015] A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the judgment method for electric bicycle charging indoors are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention first constructs an energy consumption characteristic function when the electric bicycle is in a charging state. Since the electric bicycle has a specific power change pattern during charging (such as constant current charging and constant voltage charging stages), these power change patterns are manifested as obvious local features on the power curve. By observing and recording these features, an accurate energy consumption characteristic function can be constructed, which can describe the energy consumption change of the electric bicycle during the charging process. A total power data sequence of the total household electricity consumption power is generated. In the total power data sequence, in addition to the energy consumption characteristics of the electric bicycle charging, there may also be mutation points of the energy consumption of other electrical equipment (such as the turning on or off of other devices). These mutation points may interfere with the identification of the electric bicycle charging characteristics. Through mutation point detection, these energy consumption mutation features caused by non-electric bicycle electricity consumption can be eliminated from the total power data sequence, thereby improving the identification accuracy. After eliminating the energy consumption mutation features of non-electric bicycle electricity consumption, energy consumption features are extracted from the remaining total power data sequence. These features include the specific power change pattern when the electric bicycle is charging. The extracted energy consumption features are compared with the energy consumption characteristic function. If the two match highly, it can be quickly judged that there is a situation of electric bicycle charging indoors. Description of the Drawings

[0017] Figure 1 Flowchart of the method for judging the charging of an electric bicycle entering a household in Embodiment 1 of the present invention; Figure 2 Flowchart of the method for judging the charging of an electric bicycle entering a household in Embodiment 2 of the present invention. Detailed implementation manners

[0018] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0019] Embodiment 1: As Figure 1 shown, the method for judging the charging of an electric bicycle entering a household in this embodiment includes the following steps: Construct an energy consumption characteristic function when the electric bicycle is in a charging state.

[0020] Obtain the total household electricity power, and generate a total electricity quantity data sequence according to the total household electricity power.

[0021] Perform mutation point detection on the total electricity quantity data sequence, and eliminate the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption in the total electricity quantity data sequence.

[0022] Extract the energy consumption characteristics from the total electricity quantity data sequence after elimination.

[0023] Compare the extracted energy consumption characteristics with the energy consumption characteristic function, and judge whether there is a situation where an electric bicycle enters the household for charging according to the comparison result.

[0024] Embodiment 2: As Figure 2 shown, the method for judging the charging of an electric bicycle entering a household in this embodiment includes the following steps: Construct an energy consumption characteristic function when the electric bicycle is in a charging state.

[0025] Perform real-time detection on the total household electricity power, and generate a total electricity quantity data sequence.

[0026] Perform mutation point detection on the total electricity quantity data sequence, and eliminate the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption in the total electricity quantity data sequence.

[0027] Extract the energy consumption characteristics from the total electricity quantity data sequence after eliminating the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption.

[0028] Compare the extracted energy consumption characteristics with the energy consumption characteristic function to judge whether there is a situation where an electric bicycle enters the household for charging in the household.

[0029] Optionally, in this embodiment, the specific process of constructing the energy consumption characteristic function when the electric bicycle is in the charging state is as follows: By actually measuring the charging processes of multiple electric bicycles under different conditions, collecting data such as charging power, charging time, and battery capacity, and using statistical or machine learning methods, a mathematical function that can describe the charging energy consumption characteristics of the electric bicycle is constructed, which is the energy consumption characteristic function when the electric bicycle is in the charging state. The energy consumption characteristic function can reflect the typical pattern of the electric bicycle's charge level changing over time, specifically as the following process: (1) Data collection.

[0030] (1.1) Select samples: Select representative electric bicycle samples covering different brands, models, and battery types (such as lithium-ion batteries, lead-acid batteries).

[0031] (1.2) Experimental design: Design an experiment to record the charging processes of each electric bicycle under different charging conditions, including the initial charge level, the charge level at the end of charging, and the variation of charging power over time, etc.

[0032] (2) Data processing.

[0033] (2.1) Data cleaning: Remove outliers, such as incorrect data caused by equipment failures or improper operations.

[0034] (2.2) Data collation: Collate the collected data into a unified format for subsequent analysis.

[0035] (3) Statistical analysis.

[0036] There is a relationship between the average power (P avg ) during the charging process of the electric bicycle, the battery capacity (C), the charging time (T), and the charging efficiency (η).

[0037] The total energy consumption (E total ) during the charging process of the electric bicycle can be expressed as the product of the average power and the charging time, that is: E total = P avg × T The average power may be related to the battery capacity and the charging efficiency. In this embodiment, it is assumed that the average power is a function of the battery capacity and the influence of the charging efficiency is considered, that is: P avg = f(C,η) P avg = k × C × η Where k is a constant that needs to be determined through experimental data. f is the average power, P avgIt is a function of the battery capacity C and the charging efficiency η. That is, the value of the average power is jointly determined by the battery capacity and the charging efficiency. The specific form of the function f needs to be determined by methods such as statistical analysis or machine learning on the charging data (including charging power, charging time, battery capacity, etc.) collected from a variety of electric bicycles under different charging conditions, in order to accurately describe the internal relationship between the average power, the battery capacity, and the charging efficiency.

[0038] The charging time is related to the battery capacity and the charging power. In this embodiment, the charging time can be calculated by the total energy consumption and the average power, that is: T = E total / P avg Combining the above relationships, a function describing the charging energy consumption characteristics of the electric bicycle is obtained, that is: E total = k × C × η × T Optionally, in this embodiment, the specific process of real-time detecting the total household power consumption to generate the total power data sequence is as follows: Using a smart meter or a home energy management system, regularly record the total household power consumption to form a time series of power data. These data need to have sufficient time resolution to be able to capture the energy consumption changes within a short period such as when the electric bicycle is charging.

[0039] P ( t ) : The total household power consumption measured at time t (unit: Watt, W).

[0040] Δ t : The sampling time interval (the unit can be seconds, minutes, etc.).

[0041] Et : The cumulative power consumption from time t 0 to time t (unit: Wh, watt-hour).

[0042] E t : The power consumption data point at time t in the time series.

[0043] The time series of power data E t can be obtained by integrating the power data P ( t ), but in actual operation, since the power consumption is regularly recorded by a smart meter or a home energy management system, a discrete summation method is adopted. The specific formula is as follows: ​​

[0044] In the above formula: P represents the total household power consumption measured at time (in Watts, W), that is, the power consumption of the household at a certain moment. t represents the current moment, which is used to determine the cut-off time point for calculating the cumulative power consumption.

[0045] Here, represents the time of the t th sampling point starting from 0, where l is a non-negative integer. This formula calculates the sum of the power of all sampling points multiplied by the time interval Δ l during the period from 0 to t 0 to t to obtain the cumulative power consumption t . Et .

[0046] To form a time series E t , the cumulative power consumption t is read at fixed time intervals Δ Et and used as a data point in the time series. At t = t 0 + n Δ t (where n is a non-negative integer), the data point in the time series can be expressed as: , obtaining a power consumption time series n with respect to time E n , that is, the total power data series, which contains sufficient time resolution to capture energy consumption changes during short periods such as electric bicycle charging.

[0047] Optionally, in this embodiment, the specific process of detecting mutation points in the total power data series and removing the energy consumption mutation characteristics caused by non-electric bicycle power consumption is as follows: Use a mutation point detection algorithm (such as a density-based algorithm) to analyze the total power data series and extract those mutation points that do not conform to the conventional power consumption pattern. These mutation points often correspond to energy consumption changes during non-electric bicycle charging. The specific implementation process is as follows: (1) Calculate the moving average.

[0048] First, use the moving average (MovingAverage, MA) to smooth the data to more easily identify points that deviate from the conventional pattern. The moving average is a commonly used time series data smoothing technique that helps understand the overall trend of the data.​​

[0049] Let the total power consumption data sequence be X ={ x 1, x 2, …, xn}, where xj represents the power consumption value at the j -th time point. A moving average sequence m with a window size of MA can be calculated as ma 1, ma 2, …, ma n-m+1}, where:

[0050] (2) Calculate the residuals.

[0051] Next, calculate the residuals or deviations between the original data points and their corresponding moving averages, which can help identify which points deviate significantly from the overall trend. The original data points refer to each data value in the total power consumption data sequence. Specifically, they are the cumulative power consumption data obtained by discrete summation of the total household power consumption recorded at fixed time intervals during the process of obtaining the total household power consumption. These cumulative power consumption values are arranged in chronological order to form the total power consumption data sequence, and each cumulative power consumption value in the sequence is an original data point. They reflect the cumulative power consumption situation of the household at different times, and then the residuals are calculated by comparing with the moving averages to screen out the points that deviate from the normal power consumption pattern.

[0052] Let the residual sequence be R ={ r 1, r 2, …, r n-m+1}, where:

[0053] In the above formula: is the -th element in the residual sequence , representing the residual (deviation) between the original data point in the total power consumption data sequence and its corresponding moving average ; is the i -th element in the moving average sequence MA, which is the result of calculating the moving average of the total power consumption data sequence with a window size of m .

[0054] When specifically calculating the moving average sequence: .

[0055] That is, by averaging the total power data series within a certain window range, a moving average value series is obtained, which is used for subsequent comparison with the original data points to calculate the residual.

[0056] (3) Standardized residuals.

[0057] In order to more easily identify outliers, the residuals are standardized. This is usually done by calculating the standard deviation (SD) of the residuals and calculating the ratio of each residual to the standard deviation (i.e., the Z score).

[0058] Assume the standard deviation of the residual is SD ,but:

[0059] in Represents the mean of the residual sequence. In this embodiment, since the moving average has smoothed the data, use SD An unbiased estimate of (Because in theory should be close to 0).

[0060] Represents the total power data sequence The total number of data points in the total power data series. data.

[0061] Then, calculate the Z-score for each standardized residual:

[0062] (4) Identify mutation points.

[0063] Finally, the mutation point is identified according to the absolute value of the Z score of the standardized residual. In this embodiment, a threshold is set, where the threshold can be based on a certain quantile of the normal distribution (such as 3 standard deviations, i.e. | z i |>3), or adjust according to the specific situation of the data.

[0064] If the absolute value of the Z score at a certain time point exceeds the set threshold, the point is considered to be a mutation point, which may indicate a power consumption pattern that does not conform to the normal situation, and the mutation point corresponding to the absolute value of the Z score is eliminated.

[0065] In this embodiment, the specific process of extracting energy consumption characteristics from the total power data sequence excluding the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption is as follows: Design feature extraction algorithm (including sliding window analysis, etc.) for identifying subsequences matching the charging energy consumption characteristics of electric bicycles from the total power data sequence. An exemplary process is as follows: (1) Define sliding window parameters.

[0066] Window length W: The number of consecutive data points covered by the window, determined according to the average duration of the electric bicycle charging process, for example, set to 360 data points (corresponding to 1 hour if the sampling frequency is 1 minute / point).

[0067] Step size S: The number of data points the window moves each time, for example, set to 10 data points (corresponding to 10 minutes).

[0068] (2) Initialize the window and variables.

[0069] Initialize an empty window W init , with a length of W.

[0070] Initialize a counter i = 0, used to control the movement of the window.

[0071] Initialize a matching flag array M, used to record whether each window position matches the charging characteristics of the electric bicycle, with an initial value of all false.

[0072] (3) Sliding window analysis.

[0073] For each data point dj in the total power data sequence D, perform the following steps: (3.1) Data loading: Load the data covered by the window from D, that is, W = D i : i + W].

[0074] (3.2) Feature extraction: Calculate the average active power and the average reactive power in the window:

[0075]

[0076] Calculate the difference sequences of the active power and the reactive power and , and extract subsequences:

[0077]

[0078] Identify the difference subsequences of the subsequences.

[0079] In the above formulas: W : Represents the window length. When calculating the average active power and the average reactive power in the formula, W is used as the divisor to calculate the average power within the window. Essentially, it is the number of data points covered by the window, i.e., the window length.

[0080] : Represents the total electricity data sequence D within which, the active power value corresponding to the k -th data point within the range covered by the window.

[0081] : Represents the total electricity data sequence D within which, the reactive power value corresponding to the k -th data point within the range covered by the window.

[0082] k : Is an index variable used to traverse the data points within the range covered by the window. Its value range is from i to , i is the index of the starting position of the window in the total electricity data sequence D . By k , it sequentially points to each data point within the window, and then performs calculation operations such as summing the active power and reactive power corresponding to the data points within the window.

[0083] (3.3) Template matching.

[0084] Match the extracted subsequence with a predefined electric bicycle charging template (such as the differential template in the constant voltage stage).

[0085] Calculate the Euclidean distance ΔS between the subsequence ( T i ) and the electric bicycle charging template ( S i ) using the formula The correlation coefficient between the subsequence and the charging template Ψ :

[0086]

[0087] In the formula, is the mean of the subsequence, characterizing the average level of power or current during the charging process.

[0088] (3.4) Matching judgment: If ΔS < η (where η is a preset threshold, such as 0.2), it is considered that the current window contains the charging load characteristics of an electric bicycle, and M[i] = true is set, which means it is marked as a match.

[0089] (3.5) Window movement: Update the index i = i + S, and slide the window to the next position.

[0090] (3.6) Repeat steps: Repeat steps 3.1 to 3.5 until the entire total power data sequence D is traversed.

[0091] (3.7) Result output: Output the matching flag array M, where the positions marked as true indicate that the energy consumption characteristics of an electric bicycle are detected in the window, and the energy consumption characteristics of the electric bicycle are extracted.

[0092] During the above sliding window analysis process: i : is an index variable used to mark the starting position of the sliding window in the total power data sequence D In the process of window movement, i The value of will be updated according to certain rules, so that the window can slide sequentially on the total power data sequence. After each slide, the starting position of the window in the data sequence is determined by determined.

[0093] S : represents the step size of the sliding window, that is, the number of data points that the window moves each time. For example, set S to 10 data points (assuming a sampling frequency of 1 minute / point, corresponding to 10 minutes). Then, each time the window moves, its starting position index i will increase S The value of, and the window will slide on the total power data sequence according to the step size S for analyzing data at different positions.

[0094] Optionally, in this embodiment, the specific process of comparing the extracted energy consumption characteristics with the energy consumption characteristic function to determine whether there is a situation where an electric bicycle enters the household for charging in the household is as follows: Compare the extracted energy consumption characteristics with the electric bicycle charging energy consumption characteristic function to calculate the similarity or matching degree. If the similarity or matching degree exceeds the preset threshold, it is considered that there is a situation where an electric bicycle enters the household for charging in the household. An exemplary processing process is as follows: For each window marked as true, calculate its corresponding total energy consumption E window , which can be obtained by accumulating or integrating the power data within the window.

[0095] Assume that the charging process within the window is continuous, and the relationship between the window length W (in minutes) and the charging time T (in hours) is T = 60W.

[0096] Use E window to estimate the total energy consumption k , C , η , that is . Here k , C , η is the combined estimated value.

[0097] Judge the charging of electric bicycles indoors: If the energy consumption characteristics of electric bicycle charging are detected in multiple discontinuous time periods (that is, there are multiple scattered true marks in M), calculate the total energy consumption of the corresponding window, compare the total energy consumption with the energy consumption characteristic function. If the matching degree of the total energy consumption of these time periods and the energy consumption characteristic function exceeds a preset threshold (such as 0.8), it can be judged that there is a situation of electric bicycle charging indoors in the family.

[0098] Embodiment 3: In this embodiment, a judgment system for electric bicycle charging indoors is provided. The judgment system for electric bicycle charging indoors can be used to implement the above-mentioned judgment method for electric bicycle charging indoors. Specifically, the judgment system for electric bicycle charging indoors includes an energy consumption characteristic function construction module, a total power data sequence generation module, a mutation feature elimination module, an energy consumption feature extraction module, and a fitting judgment module.

[0099] Among them, the energy consumption characteristic function construction module is used to construct an energy consumption characteristic function when the electric bicycle is in a charging state.

[0100] The total power data sequence generation module is used to obtain the total household power consumption and generate a total power data sequence according to the total household power consumption.

[0101] The mutation feature elimination module is used to detect mutation points in the total power data sequence and eliminate the energy consumption mutation features caused by non-electric bicycle power consumption in the total power data sequence.

[0102] The energy consumption feature extraction module is used to extract energy consumption features from the total power data sequence after elimination.

[0103] The fitting judgment module is used to compare the extracted energy consumption features with the energy consumption characteristic function and judge whether there is a situation of electric bicycle charging indoors in the family according to the comparison result.

[0104] Embodiment 4: In this embodiment, a terminal device is provided. The terminal device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function. The processor described in the embodiments of the present invention can be used for the operation of the method for judging the charging of an electric bicycle indoors, including: constructing an energy consumption characteristic function when the electric bicycle is in a charging state; obtaining the total household power consumption, and generating a total power consumption data sequence according to the total household power consumption; performing mutation point detection on the total power consumption data sequence, and removing the energy consumption mutation characteristics caused by non-electric bicycle power consumption in the total power consumption data sequence; extracting energy consumption characteristics from the total power consumption data sequence after removal; comparing the extracted energy consumption characteristics with the energy consumption characteristic function, and judging whether there is a situation of charging an electric bicycle indoors in the household according to the comparison result.

[0105] Embodiment 5: In this embodiment, a computer-readable storage medium (Memory) is provided. The computer-readable storage medium is a memory device in the terminal device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, and the operating system of the terminal is stored in this storage space. And, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed Random Access Memory (RAM), or a non-volatile memory, such as at least one disk memory.

[0106] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the method for judging the charging of an electric bicycle at home in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: constructing an energy consumption characteristic function when the electric bicycle is in a charging state; obtaining the total household power consumption, and generating a total power consumption data sequence according to the total household power consumption; performing mutation point detection on the total power consumption data sequence, and removing the energy consumption mutation characteristics caused by non-electric bicycle power consumption in the total power consumption data sequence; performing energy consumption characteristic extraction on the total power consumption data sequence after removal; comparing the extracted energy consumption characteristics with the energy consumption characteristic function, and judging whether there is a situation of charging an electric bicycle at home according to the comparison result.

[0107] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the specified functions in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or a plurality of processes and / or boxes. Figure 1 one process or a plurality of processes and / or boxes Figure 1 steps for realizing the functions specified in one box or a plurality of boxes.

[0111] In the above embodiments of the present application, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0112] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

[0113] It should be understood that the above description is for the purpose of illustration and not limitation. By reading the above description, many embodiments and many applications other than the provided examples will be apparent to those skilled in the art.

Claims

1. A method for judging the charging of an electric bicycle indoors, characterized in that, The process includes: Construct the energy consumption characteristic function of the electric bicycle when it is in the charging state; Obtain the total household electricity consumption, and generate a total electricity data sequence based on the total household electricity consumption; Perform mutation point detection on the total power data sequence to remove the energy consumption mutation characteristics caused by non-electric bicycle power consumption in the total power data sequence; Extract energy consumption features from the total power data sequence after elimination; The extracted energy consumption characteristics are compared with the energy consumption characteristic function, and the comparison results are used to determine whether electric bicycles are being charged at home.

2. The judgment method for charging an electric bicycle indoors according to claim 1, characterized in that, The specific process of constructing the energy consumption characteristic function of an electric bicycle when it is in a charging state is as follows: obtaining charging data of a variety of electric bicycles under different charging conditions, and generating an energy consumption characteristic function describing the electric bicycle when it is in a charging state through statistical analysis or machine learning methods.

3. The method for judging the charging of an electric bicycle indoors according to claim 1, characterized in that, The specific process of obtaining the total household electricity consumption and generating a total electricity data sequence based on the total household electricity consumption is as follows: obtaining the total household electricity consumption at fixed time intervals, performing discrete summation on the total household electricity consumption to generate cumulative electricity consumption, and arranging the cumulative electricity consumption in chronological order to form a total electricity data sequence.

4. The judgment method for charging an electric bicycle indoors according to claim 1, wherein The specific process of performing mutation point detection on the total electricity data series and eliminating the energy consumption mutation characteristics caused by non-electric bicycle electricity consumption in the total electricity data series is as follows: calculating the moving average of the total electricity data series; calculating the residual between each data value in the total electricity data series and the moving average, and standardizing the residual to calculate the Z score of the standardized residual; identifying the mutation point according to the absolute value of the Z score of the standardized residual, and eliminating the mutation point whose absolute value of the Z score exceeds the preset threshold.

5. The judgment method for charging an electric bicycle indoors according to claim 1, characterized in that, The specific process of extracting energy consumption characteristics of the total power data sequence after elimination is as follows: defining sliding window parameters; extracting the active power and reactive power of the total power data sequence after elimination within the window through sliding window analysis, calculating the differential sequence of active power and reactive power, and extracting a subsequence from the differential sequence of active power and reactive power; matching the subsequence with the predefined electric bicycle charging template, and extracting the energy consumption characteristics of the electric bicycle within the matching successful window.

6. The judgment method for charging an electric bicycle indoors according to claim 5, wherein The specific process of matching the subsequence with the predefined electric bicycle charging template is as follows: calculating the Euclidean distance between the differential sequence and the predefined electric bicycle charging template; if the Euclidean distance is less than a preset threshold, it is determined that the current window contains the electric bicycle charging load feature and is marked as a match.

7. The judgment method for charging an electric bicycle indoors according to claim 6, characterized in that, The extracted energy consumption characteristics are compared with the energy consumption characteristic function, and the specific process of judging whether an electric bicycle is charged at home is based on the comparison results is as follows: calculating the total energy consumption in the window marked as matching; comparing the total energy consumption with the energy consumption characteristic function; if the matching degree of the total energy consumption of multiple discontinuous time periods with the energy consumption characteristic function exceeds a preset threshold, it is judged that an electric bicycle is charged at home.

8. A judgment system for charging an electric bicycle indoors, characterized in that, include: An energy consumption characteristic function building module is used to build an energy consumption characteristic function when the electric bicycle is in a charging state; A total electricity data sequence generation module is used to obtain the total household electricity power and generate a total electricity data sequence according to the total household electricity power; A mutation feature elimination module, which is used to detect mutation points in the total power data sequence and eliminate the energy consumption mutation features caused by non-electric bicycle power consumption in the total power data sequence; An energy consumption feature extraction module, which is used to extract energy consumption features from the total power data sequence after elimination; A fitting judgment module, which is used to compare the extracted energy consumption features with the energy consumption feature function and judge whether an electric bicycle has been charged at home according to the comparison result.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the judgment method for electric bicycle charging at home according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the judgment method for electric bicycle charging at home according to any one of claims 1 to 7 are implemented.

Images