Intelligent management and abnormity alarm method and system for electric bicycle shed

Abstract

The invention discloses an electric bicycle shed intelligent management and abnormity alarm method and system, and relates to the technical field of electric bicycle charging safety, and the method comprises the following steps: collecting electric bicycle charging information, and carrying out the feature analysis; based on an analysis result, performing charging load detection on the electric vehicle, and performing battery health state evaluation; and giving out fault diagnosis of the single battery of the electric vehicle according to an evaluation result. According to the electric bicycle charging load detection method, verification is carried out in data with the sampling frequency being 1 / 60 Hz, and it is proved that the electric bicycle charging load is accurately detected through the electric bicycle charging load detection method based on the global features.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging safety, and in particular to an electric bicycle shed intelligent management and abnormal alarm method and system. Background Art

[0002] In recent years, with the increase in the number of electric bicycles, the number of electric bicycle fire accidents has also shown a rapid upward trend. The main cause of electric bicycle fires is electrical failure caused by improper battery charging.

[0003] Electric bicycles usually move during the day and park and charge at night. The charging behavior is random and hidden. Therefore, in the actual supervision process, the efficiency and effectiveness of human inspection are low, and it is impossible to effectively prevent electric bicycle fire accidents. How to accurately and efficiently realize the intelligent management of electric bicycle sheds and the alarm of abnormal charging has become an urgent problem to be solved in our society. Summary of the invention

[0004] In view of the problems existing in the existing electric bicycle shed intelligent management and abnormal alarm and system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that it is difficult to supervise electric vehicles.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an electric bicycle shed intelligent management and abnormal alarm method, which includes the following steps:

[0008] Collect electric vehicle charging information and perform feature analysis;

[0009] Based on the analysis results, the charging load of the electric vehicle is tested and the battery health status is evaluated;

[0010] The battery cell fault diagnosis of electric vehicles is given according to the evaluation results.

[0011] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, wherein: the electric vehicle charging information includes the electric vehicle battery type and the electric vehicle charging method;

[0012] The electric vehicle battery types include lead-acid batteries and lithium-ion batteries;

[0013] The electric vehicle charging method includes a constant current charging method, a constant voltage charging method, a staged charging method, a pulse charging method, a reflection charging method and an intermittent charging method.

[0014] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, the step of detecting the charging load of the electric vehicle includes:

[0015] Subtract the minimum values ​​of the total active power P and total reactive power Q at the power inlet from each other to obtain the signal after removing the base load. and

[0016] By differentially and Partial clustering greater than the detection threshold, and two sets of clustering sets are obtained respectively and calculate The mean of the largest category and with The largest category corresponds to the time index The mean of the middle class Generate a signal combining active power and reactive power;

[0017] The subsequences of the signal L' are obtained by bilateral filtering, state transition removal, Savitzky-Golay filtering and piecewise linear representation, and each subsequence is judged whether it meets the heuristic set rules, and the subsequences containing the constant voltage charging stage of the electric bicycle are screened out;

[0018] Merge the subsequences containing the constant voltage charging stage of the electric bicycle that are adjacent in time, and use bilateral filtering, state transition removal and Savitzky-Golay filtering on the subsequence of the total reactive power Q corresponding to the time index of the merged subsequence to obtain the signal H', and use median filtering on the difference of H' to obtain the signal H".

[0019] It is determined whether each subsequence in H" that is continuously greater than zero meets the preset condition to finely locate the duration of the constant voltage charging stage, and combined with whether the next subsequence containing the constant voltage stage subsequence in the signal L' meets the preset condition to determine the health status of the battery.

[0020] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, the step of detecting the charging load of the electric vehicle also includes:

[0021] Through Gaussian bilateral filtering, that is, both smoothing functions are Gaussian functions, where the calculation formula for the bilateral filtering weight is:

[0022]

[0023] Where i represents the spatial position index of the target sample; j represents the spatial position index of the neighborhood sample; f i and fj Represent the sample values ​​of the target sample and the neighborhood sample respectively; σ d and σ r Represent the smoothing factors in the spatial domain and distance domain respectively;

[0024] The closer the spatial position and sample value of the neighborhood sample are to the target sample, the greater the weight of the neighborhood sample, otherwise the smaller the weight. The output of the bilateral filtering algorithm is the weighted value of the neighborhood sample, which is specifically expressed as:

[0025]

[0026] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, it also includes:

[0027] The specific steps for the state conversion of the power signal, that is, the step change of the power signal, are as follows:

[0028] Detect the state transition that occurs in the signal, that is, the amplitude of the signal change ΔZ' τ Compare with the threshold c set by heuristic method. If the signal change amplitude is greater than or equal to the threshold, the load operation state is changed. If the signal change amplitude is less than the threshold, the load operation state is not changed.

[0029] Each detected state transition is removed from the original signal, which is specifically expressed as:

[0030]

[0031] Where τ represents the time index of the analyzed sample, Z' represents the signal after bilateral filtering, ΔZ' represents the differential signal of Z', and L represents the time series signal after the state transition is removed;

[0032] Smooth useless fluctuations in the signal. The specific steps are:

[0033] Given a local symmetric data window n=[l -m ,l -m+1 ,...,l0,...,l m-1 ,l m ], then the signal after SG filtering is:

[0034]

[0035] In the formula, p<2m, which indicates the order of the least squares polynomial, a k Represents the coefficients of the polynomial, so the goal of SG filtering is to minimize the error, which can be specifically expressed as:

[0036]

[0037] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, the step of evaluating the battery health status includes constant voltage charging stage detection, which is specifically expressed as:

[0038] Through the top-down PLR algorithm, for a time series L' of length N, define the first sample point l'1 and the last sample l' N is the initial segmentation point, and then a linear discrete signal I of length N is generated, where the first sample point i1 is equal to l'1 and the last sample point i N Equal to l' N , the remaining sample points are assigned linearly;

[0039] Subtract signal L' from signal I point by point to obtain the difference between the two signals, and determine whether there is a point in the differential signal with an amplitude greater than the threshold h set by the heuristic method. If not, signal L' can be directly represented linearly by signal I. If so, determine the new segmentation point of signal L' according to the index of the point with the maximum amplitude;

[0040] Then update the signal I and iterate to obtain new segmentation points until the amplitudes of all points in the differential signal are less than the threshold h. At this time, the signal L' can be represented by the piecewise linear signal I.

[0041] As a preferred solution of the electric bicycle shed intelligent management and abnormal alarm method of the present invention, a method for diagnosing battery monomer faults of electric vehicles is provided, including:

[0042]

[0043]

[0044]

[0045] In the formula, Precision represents the precision rate, Recall represents the recall rate, and F1-score represents the F1 score.

[0046] In a second aspect, an embodiment of the present invention provides an electric bicycle shed intelligent management and abnormal alarm system, which includes an information collection module, a feature analysis module, and a health assessment module;

[0047] The information collection module is used to collect various information during the charging process of the electric vehicle;

[0048] The feature analysis module is used to analyze the collected charging information and extract feature data that is helpful for evaluating the battery health status;

[0049] The health assessment module is used to assess the aging or degradation state of the battery.

[0050] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned electric bicycle shed intelligent management and abnormal alarm method is implemented.

[0051] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned electric bicycle shed intelligent management and abnormal alarm method is implemented.

[0052] The beneficial effects of the present invention are as follows: through the electric bicycle charging load detection method, it is verified in the data with a sampling frequency of 1 / 60Hz, proving that the electric bicycle charging load detection method based on global features accurately detects the electric bicycle charging load; and it is verified in the data with a sampling frequency of 1Hz. Almost no illegal charging behavior of electric bicycles is missed. It is worth noting that the input of the algorithm is the power data in the sliding window, so it can basically feedback the charging behavior online 20 to 45 minutes after the start of the constant voltage charging stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0054] Figure 1 The figure is a flow chart of the intelligent management and abnormal alarm method of the electric bicycle shed.

[0055] Figure 2 The present invention is a flow chart of the charging load detection method for the intelligent management and abnormal alarm method of the electric bicycle shed.

[0056] Figure 3 Schematic diagram of bilateral filtering for the smart management and abnormal alarm method of electric bicycle shed.

[0057] Figure 4 The schematic diagram of state transition removal for the electric bicycle shed intelligent management and abnormal alarm method is shown.

[0058] Figure 5 The PLR ​​schematic diagram of the electric bicycle shed intelligent management and abnormal alarm method. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0063] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0064] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Example 1

[0066] Reference Figure 1 to Figure 5, which is the first embodiment of the present invention, and provides an electric bicycle shed intelligent management and abnormal alarm method, comprising the following steps:

[0067] S1. Collect electric vehicle charging information and perform feature analysis.

[0068] The electric vehicle charging information includes the electric vehicle battery type and the electric vehicle charging method;

[0069] The electric vehicle battery types include lead-acid batteries and lithium-ion batteries;

[0070] The electric vehicle charging method includes a constant current charging method, a constant voltage charging method, a staged charging method, a pulse charging method, a reflection charging method and an intermittent charging method;

[0071] When the electric bicycle battery is charged at a constant current, pulse width modulation technology is used to control and maintain the constant output current of the charging system until the battery is charged in the later stage. The control measures are relatively simple, but since the batteries used in daily life are liquid batteries with electrolytes inside, the electrolytes undergo chemical reactions during the charging process, producing more gas, which impacts the plates and threatens the healthy use of the battery, especially in the later stage of charging, when the charging voltage is too high and the charging current is too large;

[0072] When the electric bicycle battery is charged at a constant voltage, the charging system outputs a constant voltage. In the early stage of charging, the battery terminal voltage is low and the charging current is large. As the battery power increases, the terminal voltage will gradually increase, and the difference between the charging system output voltage and the battery voltage will gradually decrease. The charging system output current will also decrease. At the end of charging, only a small current will flow into the battery.

[0073] The two-stage charging method uses a constant current and then constant voltage charging strategy. First, a constant current is used to charge the battery until the voltage reaches a preset value, and then a constant voltage is used to complete the remaining charging of the battery. This method is mainly used for lithium-ion battery charging.

[0074] The pulse charging method uses pulse current to charge the battery. The charging speed is controlled by selecting the appropriate pulse current amplitude and duty cycle. This charging method uses a large constant current to charge the battery rapidly. The setting of the charging interval can eliminate the polarization of the battery. The charging and stopping cycles are repeated until the battery is fully charged.

[0075] The reflection charging method is improved from the pulse charging method. After the positive pulse charging is completed, the negative pulse is immediately connected to achieve short-term discharge of the battery, further improve the polarization phenomenon, and improve the charging efficiency of the battery.

[0076] The intermittent variable current constant voltage charging method relies on constant current charging and pulse charging. Once the charging voltage upper limit is reached, charging is stopped immediately. After a certain time interval, the above operation is repeated to increase the charging amount. In the later stage of charging, the difference between the charging voltage and the battery voltage is small, and constant voltage charging is used to fully charge the battery.

[0077] S2. Based on the analysis results, the charging load of the electric vehicle is tested and the battery health status is evaluated.

[0078] The steps for charging load detection of electric vehicles include:

[0079] Subtract the minimum values ​​of the total active power P and total reactive power Q at the power inlet from each other to obtain the signal after removing the base load. and

[0080] By differentially and Partial clustering greater than the detection threshold, and two sets of clustering sets are obtained respectively and calculate The mean of the largest category and with The largest category corresponds to the time index The mean of the middle class Generate a signal that integrates active power and reactive power, in which the state transition edges of the main electrical loads are removed, and the gentle slope trend of the constant voltage charging stage is more obvious;

[0081] The subsequences of the signal L' are obtained by bilateral filtering, state transition removal, Savitzky-Golay filtering and piecewise linear representation, and each subsequence is judged whether it meets the heuristic set rules, and the subsequences containing the constant voltage charging stage of the electric bicycle are screened out;

[0082] Merge the subsequences containing the constant voltage charging stage of the electric bicycle that are adjacent in time, and use bilateral filtering, state transition removal and Savitzky-Golay filtering on the subsequence of the total reactive power Q corresponding to the time index of the merged subsequence to obtain the signal H', and use median filtering on the difference of H' to obtain the signal H".

[0083] It is determined whether each subsequence in H" that is continuously greater than zero meets the preset condition to finely locate the duration of the constant voltage charging stage, and combined with whether the next subsequence containing the constant voltage stage subsequence in the signal L' meets the preset condition to determine the health status of the battery.

[0084] The steps of charging load detection for electric vehicles also include:

[0085] Through Gaussian bilateral filtering, that is, both smoothing functions are Gaussian functions, where the calculation formula for the bilateral filtering weight is:

[0086]

[0087] Where i represents the spatial position index of the target sample; j represents the spatial position index of the neighborhood sample; f i and f j Represent the sample values ​​of the target sample and the neighborhood sample respectively; σ d and σ r Represent the smoothing factors in the spatial domain and distance domain respectively;

[0088] The closer the spatial position and sample value of the neighborhood sample are to the target sample, the greater the weight of the neighborhood sample, otherwise the smaller the weight. The output of the bilateral filtering algorithm is the weighted value of the neighborhood sample, which is specifically expressed as:

[0089]

[0090] like Figure 3 As shown in the figure, the signal is generated by the active power signal and the reactive power signal. It can be observed that the difference between the signal after filtering and the signal before filtering is small, and the bilateral filtering retains the trend and integrity of the signal. In the enlarged figure, it is further found that the bilateral filtering retains the step change caused by the load state conversion in the signal, the edge information is retained, the small fluctuations in the signal are smoothed, the noise is effectively removed, and the gentle slope characteristics corresponding to the constant voltage stage of charging of the electric bicycle are retained for further identification.

[0091] Also includes,

[0092] The specific steps for the state conversion of the power signal, that is, the step change of the power signal, are as follows:

[0093] Detect the state transition that occurs in the signal, that is, the amplitude of the signal change ΔZ' τ Compare with the threshold c set by heuristic method. If the signal change amplitude is greater than or equal to the threshold, the load operation state is changed. If the signal change amplitude is less than the threshold, the load operation state is not changed.

[0094] Each detected state transition is removed from the original signal, which is specifically expressed as:

[0095]

[0096] Where τ represents the time index of the analyzed sample, Z' represents the signal after bilateral filtering, ΔZ' represents the differential signal of Z', and L represents the time series signal after the state transition is removed;

[0097] Smooth useless fluctuations in the signal. The specific steps are:

[0098] Given a local symmetric data window n=[l -m ,l -m+1 ,...,l0,...,l m-1 ,l m ], then the signal after SG filtering is:

[0099]

[0100] In the formula, p<2m, which indicates the order of the least squares polynomial, a k Represents the coefficients of the polynomial, so the goal of SG filtering is to minimize the error, which can be specifically expressed as:

[0101]

[0102] like Figure 4 As shown, except for the edge caused by the load state conversion in the signal, the small fluctuations and trend characteristics of the electric bicycle charging load are retained.

[0103] The steps of battery health status assessment include constant voltage charging stage detection, which is specifically expressed as:

[0104] Through the top-down PLR algorithm, for a time series L' of length N, define the first sample point l'1 and the last sample l' N is the initial segmentation point, and then a linear discrete signal I of length N is generated, where the first sample point i1 is equal to l'1 and the last sample point i N Equal to l' N , the remaining sample points are assigned linearly;

[0105] Subtract signal L' from signal I point by point to obtain the difference between the two signals, and determine whether there is a point in the differential signal with an amplitude greater than the threshold h set by the heuristic method. If not, signal L' can be directly represented linearly by signal I. If so, determine the new segmentation point of signal L' according to the index of the point with the maximum amplitude;

[0106] Then update the signal I and iterate to obtain new segmentation points until the amplitudes of all points in the differential signal are less than the threshold h. At this time, the signal L' can be represented by the piecewise linear signal I.

[0107] like Figure 5 As shown in the figure, after segmenting the time series signal through PLR, several subsequences with different trend characteristics are formed. Based on experience, the detection rule of the subsequence containing the gentle slope of the constant voltage charging stage of the electric bicycle is defined as follows:

[0108] (1) The difference between the end point and the start point of the subsequence is less than;

[0109] (2) The time span between the end point and the start point of the subsequence is.

[0110] When an electric bicycle is in the constant-voltage charging stage, the decreasing slope of active power and the increasing slope of reactive power are significantly different from those of other typical household appliance loads. Taking into account the characteristics of the small amplitude change and long duration of the ramp power, the above detection rules are set to distinguish those subsequences that are not related to the constant-voltage charging stage, and roughly detect all subsequences that include the constant-voltage charging stage of an electric bicycle.

[0111] S3. Provide a battery cell fault diagnosis for the electric vehicle based on the evaluation results.

[0112] The methods for diagnosing battery cell faults of electric vehicles include:

[0113]

[0114]

[0115]

[0116] In the formula, Precision represents the precision rate, Recall represents the recall rate, and F1-score represents the F1 score.

[0117] The precision rate represents the ratio of the number of correctly identified electric bicycle charging loads to the number of identified electric bicycle charging loads; the recall rate represents the ratio of the number of correctly identified electric bicycle charging loads to the actual number of electric bicycle charging loads; the F1 score represents a harmonic average of the precision rate and the recall rate.

[0118] Since the charging time of an electric bicycle can be up to 12 hours, and the constant voltage charging stage may span 12 o'clock in the morning, this embodiment adopts a sliding window with a window length of 48 hours to ensure that each analysis includes the complete charging process. Table 1 shows the comparison of the detection results of the method proposed in this topic and the detection results of the comparative method.

[0119] Table 1: Comparison of the test results of this embodiment and the test results of the comparative method

[0120]

[0121] The accuracy and F1 score of this embodiment are higher than those of the comparison method, the false detection rate is lower, and the overall effect is better. The main reason is that after the proposed electric bicycle charging subsequence is identified, a refined processing step is taken in combination with the load characteristics of the reactive power amplitude gradually decreasing and the decreasing speed gradually slowing down. This step can filter out the misidentified subsequences and determine the operating time period of the constant voltage charging stage.

[0122] In summary, the electric bicycle charging load detection method based on global features was verified in data with a sampling frequency of 1 / 60Hz, proving that the electric bicycle charging load detection method accurately detected the electric bicycle charging load; and it was verified in data with a sampling frequency of 1Hz. Almost no illegal charging behavior of electric bicycles was missed. It is worth noting that the input of the algorithm is the power data within the sliding window, so it can basically feedback the charging behavior online 20 to 45 minutes after the start of the constant voltage charging stage.

[0123] Example 2

[0124] On the basis of the first embodiment, this embodiment further provides an electric bicycle shed intelligent management and abnormal alarm system, including 8. an information collection module, a feature analysis module, and a health assessment module;

[0125] The information collection module is used to collect various information during the charging process of the electric vehicle;

[0126] The feature analysis module is used to analyze the collected charging information and extract feature data that is helpful for evaluating the battery health status;

[0127] The health assessment module is used to assess the aging or degradation state of the battery.

[0128] This embodiment also provides a computer device, which is suitable for the case of the intelligent management and abnormal alarm method of electric bicycle shed, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent management and abnormal alarm method of electric bicycle shed proposed in the above embodiment.

[0129] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0130] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing intelligent management and abnormal alarm of an electric bicycle shed as proposed in the above embodiment is implemented.

[0131] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent management and abnormal alarm of electric bicycle shed, characterized by: The following steps are included: Collect electric vehicle charging information and perform feature analysis; Based on the analysis results, the charging load of the electric vehicle is tested and the battery health status is evaluated; The battery cell fault diagnosis of electric vehicles is given according to the evaluation results.

2. The electric bicycle shed intelligent management and abnormal alarm method according to claim 1, characterized in that: The electric vehicle charging information includes the electric vehicle battery type and the electric vehicle charging method; The electric vehicle battery types include lead-acid batteries and lithium-ion batteries; The electric vehicle charging method includes a constant current charging method, a constant voltage charging method, a staged charging method, a pulse charging method, a reflection charging method and an intermittent charging method.

3. The electric bicycle shed intelligent management and abnormal alarm method according to claim 2, characterized in that: The steps for charging load detection of electric vehicles include: Subtract the minimum values ​​of the total active power P and total reactive power Q at the power inlet from each other to obtain the signal after removing the base load. and By differentially and Partial clustering greater than the detection threshold, and two sets of clustering sets are obtained respectively and calculate The mean of the largest category and with The largest category corresponds to the time index The mean of the middle class Generate a signal combining active power and reactive power; The subsequences of the signal L' are obtained by bilateral filtering, state transition removal, Savitzky-Golay filtering and piecewise linear representation, and each subsequence is judged whether it meets the heuristic set rules, and the subsequences containing the constant voltage charging stage of the electric bicycle are screened out; Merge the subsequences containing the constant voltage charging stage of the electric bicycle that are adjacent in time, and use bilateral filtering, state transition removal and Savitzky-Golay filtering on the subsequence of the total reactive power Q corresponding to the time index of the merged subsequence to obtain the signal H', and use median filtering on the difference of H' to obtain the signal H". It is determined whether each subsequence in H" that is continuously greater than zero meets the preset condition to finely locate the duration of the constant voltage charging stage, and combined with whether the next subsequence containing the constant voltage stage subsequence in the signal L' meets the preset condition to determine the health status of the battery.

4. The electric bicycle shed intelligent management and abnormal alarm method according to claim 3, characterized in that: The steps of charging load detection for electric vehicles also include: Through Gaussian bilateral filtering, that is, both smoothing functions are Gaussian functions, where the calculation formula for the bilateral filtering weight is: Where i represents the spatial position index of the target sample; j represents the spatial position index of the neighborhood sample; f i and f j Represent the sample values ​​of the target sample and the neighborhood sample respectively; σ d and σ r Represent the smoothing factors in the spatial domain and distance domain respectively; The closer the spatial position and sample value of the neighborhood sample are to the target sample, the greater the weight of the neighborhood sample, otherwise the smaller the weight. The output of the bilateral filtering algorithm is the weighted value of the neighborhood sample, which is specifically expressed as:

5. The electric bicycle shed intelligent management and abnormal alarm method according to claim 4, characterized in that: Also includes, The specific steps for the state conversion of the power signal, that is, the step change of the power signal, are as follows: Detect the state transition that occurs in the signal, that is, the amplitude of the signal change ΔZ' τ Compare with the threshold c set by heuristic method. If the signal change amplitude is greater than or equal to the threshold, the load operation state is changed. If the signal change amplitude is less than the threshold, the load operation state is not changed. Each detected state transition is removed from the original signal, which is specifically expressed as: Where τ represents the time index of the analyzed sample, Z' represents the signal after bilateral filtering, ΔZ' represents the differential signal of Z', and L represents the time series signal after the state transition is removed; Smooth useless fluctuations in the signal. The specific steps are: Given a local symmetric data window n=[l -m ,l -m+1 ,...,l0,...,l m-1 ,l m ], then the signal after SG filtering is: In the formula, p<2m, which indicates the order of the least squares polynomial, a k Represents the coefficients of the polynomial, so the goal of SG filtering is to minimize the error, which can be specifically expressed as:

6. The electric bicycle shed intelligent management and abnormal alarm method according to claim 5, characterized in that: The steps of battery health status assessment include constant voltage charging stage detection, which is specifically expressed as: Through the top-down PLR algorithm, for a time series L' of length N, define the first sample point l'1 and the last sample l' N is the initial segmentation point, and then a linear discrete signal I of length N is generated, where the first sample point i1 is equal to l'1 and the last sample point i N Equal to l' N , the remaining sample points are assigned linearly; Subtract signal L' from signal I point by point to obtain the difference between the two signals, and determine whether there is a point in the differential signal with an amplitude greater than the threshold h set by the heuristic method. If not, signal L' can be directly represented linearly by signal I. If so, determine the new segmentation point of signal L' according to the index of the point with the maximum amplitude; Then update the signal I and iterate to obtain new segmentation points until the amplitudes of all points in the differential signal are less than the threshold h. At this time, the signal L' can be represented by the piecewise linear signal I.

7. The electric bicycle shed intelligent management and abnormal alarm method according to claim 6, characterized in that: The methods for diagnosing battery cell faults of electric vehicles include: In the formula, Precision represents the precision rate, Recall represents the recall rate, and F1-score represents the F1 score.

8. An electric bicycle shed intelligent management and abnormal alarm system, based on the electric bicycle shed intelligent management and abnormal alarm method according to any one of claims 1 to 7, characterized in that: Including information collection module, feature analysis module, and health assessment module; The information collection module is used to collect various information during the charging process of the electric vehicle; The feature analysis module is used to analyze the collected charging information and extract feature data that is helpful for evaluating the battery health status; The health assessment module is used to assess the aging or degradation state of the battery.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the electric bicycle shed intelligent management and abnormal alarm method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the electric bicycle shed intelligent management and abnormal alarm method described in any one of claims 1 to 7 are implemented.

Images