CN117349639B - Identification method and device for charging behavior of electric bicycle - Google Patents
Identification method and device for charging behavior of electric bicycle Download PDFInfo
- Publication number
- CN117349639B CN117349639B CN202311640877.2A CN202311640877A CN117349639B CN 117349639 B CN117349639 B CN 117349639B CN 202311640877 A CN202311640877 A CN 202311640877A CN 117349639 B CN117349639 B CN 117349639B
- Authority
- CN
- China
- Prior art keywords
- load data
- event
- time
- preset time
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000001052 transient effect Effects 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 30
- 238000000605 extraction Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application relates to the technical field of non-intrusive load identification and discloses an identification method and device for charging behaviors of an electric bicycle; the method comprises the following steps: acquiring real-time load data in a user room, wherein the real-time load data comprises active power, reactive power, even current harmonics and odd current harmonics; extracting event characteristics of a load event based on the real-time load data; the load event comprises a transient event and a steady state event, wherein the transient event indicates that the electric bicycle exists in the user room and is in a starting charging state, and the steady state event indicates that the electric bicycle exists in the user room and is in an ending charging state; adding event characteristics of the load event into a characteristic model library; and on-line identification of the charging behavior of the electric bicycle is performed based on the characteristic model library. The method provided by the application can realize the on-line identification of the electric bicycle only by acquiring the load data of the user, does not need the cooperation of the user, and is simple to operate and cost-saving.
Description
Technical Field
The disclosure relates to the technical field of non-intrusive load identification, in particular to an identification method and device for charging behaviors of an electric bicycle.
Background
Because the installation and maintenance of electric bicycle fills electric pile in some areas are untimely, lead to filling electric pile damage or unable normal use, the user has to carry out electric bicycle's charging in the room, and then has also led to more and more conflagration incidents.
At present, the monitoring technical means aiming at the electric bicycle mainly comprises the following two modes, wherein the first mode is to analyze the image information of a camera in an elevator based on an image recognition technology so as to realize detection and alarm of the electric bicycle in the elevator, but the scene of 'flying charge' or 'portable charger charge' cannot be dealt with; the second type is to install 2.4G vehicle management label in the battery, install 2.4G card reader in every entrance, when the car owner carries the battery to get into indoor, the card reader gathers vehicle label information, realizes prohibiting to carry the warning that the battery charges to the home, but easily arouses owner's lucky mind, increases substantially equipment cost.
Therefore, how to effectively detect whether there is electric bicycle charging in the room is a problem to be solved.
Disclosure of Invention
In view of the above, embodiments of the present application provide a method and an apparatus for identifying a charging behavior of an electric bicycle, which aim to solve the above-mentioned problems or at least partially solve the above-mentioned problems.
In a first aspect, an embodiment of the present application provides a method for identifying a charging behavior of an electric bicycle, where the method includes: acquiring real-time load data in a user room, wherein the real-time load data comprises active power, reactive power, even current harmonics and odd current harmonics; extracting event characteristics of a load event based on the real-time load data; the load event comprises a transient event and a steady-state event, wherein the transient event represents that the real-time load data is suddenly changed, and the steady-state event represents that the real-time load data is slowly changed; the event characteristics of the transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time; wherein the first preset time is less than the second preset time; the event characteristics of the steady-state event comprise the step size of each load data and the ramp rate of each load data; adding event characteristics of the load event into a characteristic model library; and on-line identification of the charging behavior of the electric bicycle is performed based on the characteristic model library.
In a second aspect, an embodiment of the present application further provides an identification device for a charging behavior of an electric bicycle, where the device includes: the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring real-time load data in a user room, and the real-time load data comprises active power, reactive power, even current harmonics and odd current harmonics; the processing module is used for extracting event characteristics of the load event based on the real-time load data; the load event comprises a transient event and a steady-state event, wherein the transient event represents that the real-time load data is suddenly changed, and the steady-state event represents that the real-time load data is slowly changed; the event characteristics of the transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time; wherein the first preset time is less than the second preset time; the event characteristics of the steady-state event comprise the step size of each load data and the ramp rate of each load data; adding event characteristics of the load event into a characteristic model library; and on-line identification of the charging behavior of the electric bicycle is performed based on the characteristic model library.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the steps of the first aspect described above.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the steps of the first aspect described above.
The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect: and extracting event characteristics of the transient event and event characteristics of the steady-state event based on real-time load data in the user room, and further adding the event characteristics of the transient event and the event characteristics of the steady-state event into a characteristic model library, so that the on-line identification of the electric bicycle is performed through the characteristic model library. Through the method provided by the application, the online identification of the charging behavior of the electric bicycle can be realized only by acquiring the load data of the user, the user is not required to cooperate, the operation is simple, and the cost is saved. In addition, the method combines the event characteristics of the transient event and the event characteristics of the steady event to judge the charging behavior of the electric bicycle, so that the online identification of the charging behavior of the electric bicycle can be realized more accurately.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
fig. 1 is a flow chart illustrating a method for identifying a charging behavior of an electric bicycle according to an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating a method for identifying a charging behavior of an electric bicycle according to another embodiment of the present disclosure;
fig. 3 is a block diagram of an identification device for electric bicycle charging behavior according to an embodiment of the present disclosure;
fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that such uses may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "include" and variations thereof are to be interpreted as open-ended terms that mean "include, but are not limited to.
As described in the background art, among urban residents, electric bicycles are increasingly used. However, since the installation and maintenance of the electric bicycle charging piles are not timely in some areas, the charging piles are damaged or cannot be used normally. Users therefore have to charge indoors, which results in more and more fire incidents, and fire departments have to invest a lot of human resources to advertise and check the behavior of charging indoor electric bicycles. However, this approach is inefficient and user compliance is not high. Therefore, a technical solution is urgently needed to realize automatic monitoring.
At present, the monitoring technical means aiming at the electric bicycle mainly comprises the following two modes, wherein the first mode is to analyze the image information of a camera in an elevator based on an image recognition technology so as to realize detection and alarm of the electric bicycle in the elevator, but the scene of 'flying charge' or 'portable charger charge' cannot be dealt with; the second type is to install 2.4G vehicle management label in the battery, install 2.4G card reader in every entrance, when the car owner carries the battery to get into indoor, the card reader gathers vehicle label information, realizes prohibiting to carry the warning that the battery charges to the home, but easily arouses owner's lucky mind, increases substantially equipment cost.
Furthermore, non-invasive load identification is provided, and the technology decomposes the total electricity consumption signal acquired from the intelligent ammeter into the electricity consumption signal of each household appliance by collecting residential electricity consumption data, so that the identification of the household appliances is realized, the normal life of residents is not interfered, and the technology has wide application prospect.
Based on the method, the identification method of the charging behavior of the electric bicycle is provided, the event characteristics of the transient event and the event characteristics of the steady-state event are extracted based on the real-time load data in the user room, and then the event characteristics of the transient event and the event characteristics of the steady-state event are added into a characteristic model library, so that the electric bicycle is identified on line through the characteristic model library. Through the method provided by the application, the on-line identification of the electric bicycle can be realized only by acquiring the load data of the user, the user is not required to cooperate, the operation is simple, and the cost is saved.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flow chart illustrating a method for identifying a charging behavior of an electric bicycle according to an embodiment provided in the present application, and as can be seen from fig. 1, the method may include steps S101 to S104:
step S101: and acquiring real-time load data in the user room.
The load data comprises active power, reactive power, even current harmonics and odd current harmonics.
Specifically, load data in a user room is acquired based on a preset sampling frequency.
More specifically, the preset sampling frequency should include a harmonic frequency contained in the relevant electrical variable in the charging device so as to be able to acquire comprehensive load data.
Step S102: based on the real-time load data, event features of the load event are extracted.
Wherein the load event includes a transient event and a steady state event.
In one embodiment, a transient event indicates that there is an electric bicycle in the user's room in an on state of charge, and a steady state event indicates that there is an electric bicycle in the user's room in an off state of charge.
In another embodiment, the transient event indicates that the real-time load data has suddenly changed, and the steady state event indicates that the real-time load data has slowly changed.
Step S103: and adding the event characteristics of the load event into a characteristic model library.
Step S104: and on-line identification of the charging behavior of the electric bicycle is performed based on the feature model library.
Specifically, the characteristics in the characteristic model library are trained based on a subtractive clustering (Subtractive Clustering, SC) algorithm, an electric bicycle identification model is built, and then the electric bicycle is identified on line based on the electric bicycle identification model.
In one embodiment, the feature model library is trained based on the SC algorithm, and after the electric bicycle identification model is built, the electric bicycle identification model outputs yes or no, so as to determine whether the electric bicycle exists in the user room. For example, if the electric bicycle identification model output is yes, determining that an electric bicycle exists in the user room; and outputting the electric bicycle identification model as no, and determining that the electric bicycle does not exist in the user room.
As can be seen from the method shown in fig. 1, the method extracts the event characteristics of the transient event and the event characteristics of the steady-state event based on the real-time load data in the user room, and further adds the event characteristics of the transient event and the event characteristics of the steady-state event into the characteristic model library, so that the on-line identification of the electric bicycle is performed through the characteristic model library. Through the method provided by the application, the on-line identification of the electric bicycle can be realized only by acquiring the load data of the user, the user is not required to cooperate, the operation is simple, and the cost is saved.
In some embodiments of the present application, the extraction manner of the event features of the transient event and the event features of the slow-release event are different.
In some embodiments of the present application, the event characteristics of the transient event are related to abrupt changes in the load data. In particular, the event characteristics of the transient event are related to abrupt changes in active power, abrupt changes in reactive power, abrupt changes in even current harmonics, and abrupt changes in odd current harmonics.
Specifically, event characteristics of a transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time. Wherein the first preset time is less than the second preset time.
Optionally, considering that the transient event occurrence time is short, the first preset time takes a value of 3s. Optionally, the second preset time takes a value of 10s.
More specifically, event characteristics of transient events include: the method comprises the steps of deviation of active power in a first preset time, deviation of active power in a second preset time, deviation of reactive power in the first preset time, deviation of reactive power in the second preset time, deviation of even current harmonic in the first preset time, deviation of even current harmonic in the second preset time, deviation of odd current harmonic in the first preset time and deviation of odd current harmonic in the second preset time.
In one embodiment, the deviation of the active power over the first preset time is determined based on the following formula:
wherein,representing the average value of the active power at time k in a first preset time,/>Representing a first preset time,/for a first time>Representing the deviation of the active power within a first preset time,/or->Indicates the current time, ++>Is shown inLoad data of time.
When the deviation in the first preset time is detected, as the first preset time is shorter, a certain error exists in the feature extraction, and the electric bicycle is wrongly distinguished, after the deviation in the first preset time is detected, the second preset time is introduced, and the difference in the second preset time is further detected.
Specifically, the difference in active power over the second preset time period is determined based on the following formula:
wherein,representing the difference of the active power within a second preset time,/or->Indicating the current time, N indicating said second preset time,/for>Represents the average value of the active power at time k+1,/->And representing the average value of the active power at the moment k in a first preset time.
It should be noted that, the specific extraction modes of the deviation of the reactive power in the first preset time, the deviation of the even current harmonic in the first preset time, and the deviation of the odd current harmonic in the first preset time are the same as the extraction mode of the deviation of the active power in the first preset time, and the extraction modes of the deviation of the active power in the first preset time can be referred to, which are not repeated herein.
Similarly, the difference value of the reactive power in the second preset time, the difference value of the even current harmonic in the second preset time, and the extraction mode of the odd current harmonic in the second preset time are the same as the extraction mode of the difference value of the active power in the second preset time, and the extraction mode of the difference value of the active power in the second preset time can be referred to, so that the embodiment of the application will not be described herein.
In the embodiment of the application, the first preset time and the second preset time are introduced, and the error judgment of the transient event can be avoided by calculating the difference value of the deviation of each load data at the first preset time and the second preset time, so that the event characteristics of the transient event can be acquired more accurately, and the follow-up identification of the electric bicycle based on the event characteristics of the transient event can be performed accurately.
In other embodiments of the present application, the event characteristics of the steady state event are related to the ramp of load data. Specifically, the event characteristics of a steady state event are related to the ramp rate of active power, the ramp rate of reactive power, the ramp rate of even current harmonics, and the ramp rate of odd current harmonics.
In one embodiment, the real-time load data is filtered based on a recursive least squares filter (Recursive Least Square, RLS) to obtain filtered load data; and extracting event characteristics of the steady-state event based on the filtered load data.
Specifically, the event characteristics of the steady-state event include the step size of each load data and the ramp rate of each load data.
More specifically, the event characteristics of a steady state event include: step size of active power, ramp rate of active power; step size of reactive power and ramp rate of reactive power; step size of even current harmonic wave and ramp rate of even current harmonic wave; step size of odd current harmonic and ramp rate of odd current harmonic.
In one embodiment, the step size of the active power is determined based on the following equation:
wherein,step size, indicative of active power, +.>Maximum value of active power within 1s representing the end of transient event,/->Representing the minimum of active power within 1s before the transient event begins.
In one embodiment, the ramp rate of the active power is determined based on the following formula:
wherein,ramp rate representing active power, +.>Maximum value of active power within 1s representing the end of steady state event,/->Representing the minimum value of active power within 1s before the start of a steady state event, +.>The time difference between the start ramp time and the end ramp time of the active power is indicated.
It should be noted that, the specific extraction modes of the step size of the reactive power, the step size of the even current harmonic and the step size of the odd current harmonic are the same as the extraction mode of the step size of the active power, and reference may be made to the extraction mode of the step size of the active power.
Similarly, the ramp rate of the reactive power, the ramp rate of the even current harmonic, and the ramp rate of the odd current harmonic are the same as the ramp rate of the active power, and reference may be made to the ramp rate extraction method of the active power, which is not described in detail herein.
In some embodiments of the present application, the specific process of filtering real-time load data based on a recursive least squares filter is as follows:
1) Initializing data, namely initializing a filter weight coefficient W, and setting an initial value to 0; initializing a covariance matrix C, and initially setting the covariance matrix C as an identity matrix; and initializing forgetting factor gamma for controlling the iteration speed.
2) Signal x is initialized.
3) Data prediction, predicting an output y' (t) by using a current weight coefficient W and a current input signal x (t), and considering that the tail part is overlapped with other devices, accumulating a step change event signal change quantity delta x (t):
4) Calculating an error, namely calculating an error between an actual value and a predicted value:
5) Updating weights and covariance matrix:
；
；
where W (t+1) is the updated weight and C (t+1) is the updated covariance matrix.
6) And (3) repeating the steps 3-5, and outputting a filtered signal y, namely load data in the embodiment of the application.
In the embodiment of the application, the real-time load data is filtered through the recursive least square filter, so that the interference signals are removed, purer load data are obtained, and further, the feature extraction based on the filtered load data is more accurate.
In some embodiments of the present application, features in a feature model library are trained based on an SC algorithm, and a specific implementation process for establishing an electric bicycle identification model is as follows:
each feature data point F (k), k=1, 2, …,，/>representing the number of features in feature space } as a candidate point for a cluster center, any data with many neighboring data points will have a high density value D (k), the density of each feature data point being defined as shown in the following formula:
in the formula, R represents Euclidean distance and defines adjacent normal number, and when the data of adjacent points larger than R does not have any contribution to potential D (k), the distance set by r is the distance corresponding to the power grid noise.
The first cluster center Xc (1) is selected as the highest-density data point in space, as shown in the following formula:
the remaining data points are corrected based on the following equation:
in the method, in the process of the invention,is->Maximum density point corresponding to (a), is->Is->Is a previous value of (2). Thus, data points near the center of the selected cluster may have very low potential values and will not be selected in subsequent iterations, after decreasing all data point potentials within the cluster, the next cluster center will correspond to the modified maximum density value. This iterative process continues until all data points are selected to end.
In order to more clearly illustrate the identification method of the charging behavior of the electric bicycle provided in the embodiment of the present application, the following is fully illustrated with reference to fig. 2:
collecting real-time load data, wherein the real-time load data comprises: active power, reactive power, even current harmonics, odd current harmonics; detecting a load event based on real-time load data, extracting event characteristics of the transient event if the load event is the transient event, adding the event characteristics of the transient event into a characteristic model library, and identifying the electric bicycle based on the characteristic model library; if the load event does not belong to the transient event, filtering the real-time load data based on the RLS filter, detecting whether the load event is a steady-state event, if the load event is the steady-state event, extracting event characteristics of the steady-state event, adding the event characteristics of the steady-state event into a characteristic model library, and completing identification of the electric bicycle based on the characteristic model library.
In the embodiment of the application, the event characteristics of the transient event and the event characteristics of the steady-state event are extracted based on the real-time load data in the user room, and then the event characteristics of the transient event and the event characteristics of the steady-state event are added into the characteristic model library, so that the on-line identification of the electric bicycle is performed through the characteristic model library. Through the method provided by the application, the on-line identification of the electric bicycle can be realized only by acquiring the load data of the user, the user is not required to cooperate, the operation is simple, and the cost is saved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention. Furthermore, the terms "include" and variations thereof are to be interpreted as open-ended terms that include, but are not limited to.
In an embodiment, an identification device for electric bicycle charging behavior is provided, where the identification device for electric bicycle charging behavior corresponds to the identification method for electric bicycle charging behavior in the above embodiment one by one. As shown in fig. 3, the processing apparatus includes: an acquisition module 301 and a processing module 302. The functional modules are described in detail as follows:
the acquiring module 301 is configured to acquire real-time load data in a user room, where the real-time load data includes active power, reactive power, even current harmonics, and odd current harmonics;
a processing module 302, configured to extract event characteristics of a load event based on real-time load data; the load event comprises a transient event and a steady-state event, wherein the transient event represents that the real-time load data is suddenly changed, and the steady-state event represents that the real-time load data is slowly changed; adding event characteristics of the load event into a characteristic model library; and on-line identification of the charging behavior of the electric bicycle is performed based on the feature model library.
In some embodiments of the present application, the event characteristics of the transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time; wherein the first preset time is less than the second preset time.
In some embodiments of the present application, the deviation of the respective load data over the first preset time is determined based on the following formula:
wherein,mean value of the individual load data at time k in a first predetermined time, +.>Representing a first preset time,/for a first time>Representing the deviation of the respective load data within a first preset time,/for a first preset time>Indicates the current time, ++>Is indicated at->Load data of time.
In some embodiments of the present application, the difference in each load data over the second preset time period is determined based on the following formula:
wherein,representing the difference of the respective load data within a second preset time,/for each load data>Indicating the current time, N indicating a second preset time,/i>Mean value of the individual load data at time k+1,/->The average value of each load data at the time k in the first preset time is represented.
In some embodiments of the present application, the processing module 302 is specifically configured to filter the real-time load data based on a recursive least squares filter, and obtain filtered load data; and extracting event characteristics of the steady-state event based on the filtered load data.
In some embodiments of the present application, the event characteristics of the steady state event include a step size of each load data and a ramp rate of each load data.
In some embodiments of the present application, the step size of each load data is determined based on the following formula:
wherein,step size, which represents the respective load data, +.>Maximum value of corresponding load data within 1s representing the end of transient event,/->Representing the minimum value of the corresponding load data within 1s before the transient event begins.
In some embodiments of the present application, the ramp rate of each load data is determined based on the following formula:
wherein,indicative of the ramp rate of the respective load data, +.>Maximum value of corresponding load data within 1s representing the end of steady-state event,/->Representing the minimum value of the corresponding load data within 1s before the start of the steady state event,/i>The time difference between the start time and the end time of the corresponding load data is represented.
In some embodiments of the present application, the processing module 302 is specifically configured to train the feature model library based on a subtractive clustering algorithm to generate an electric bicycle identification model; and on-line identification of the charging behavior of the electric bicycle is performed based on the electric bicycle identification model.
It should be noted that, the identification device of the charging behavior of any electric bicycle can be used to implement the identification method of the charging behavior of the electric bicycle in a one-to-one correspondence manner, and will not be described herein again.
Fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, at the hardware level, the electronic device comprises a processor, optionally together with an internal bus, a network interface, a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory to the memory and then operates the computer program to form the identification device of the charging behavior of the electric bicycle on a logic level. And the processor is used for executing the program stored in the memory and particularly used for executing the method.
The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The electronic device may execute the identification method for the charging behavior of the electric bicycle provided in the embodiments of the present application, and implement the function of the identification device of the electric bicycle in the embodiment shown in fig. 1, which is not described herein again.
The embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to execute the identification method for charging behavior of an electric bicycle provided by the embodiments of the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other identical elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (4)
1. An identification method of charging behavior of an electric bicycle is characterized by comprising the following steps:
acquiring real-time load data in a user room, wherein the real-time load data comprises active power, reactive power, even current harmonics and odd current harmonics;
extracting event characteristics of a load event based on the real-time load data; the load event comprises a transient event and a steady-state event, wherein the transient event represents that the real-time load data is suddenly changed, and the steady-state event represents that the real-time load data is slowly changed; the event characteristics of the transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time; wherein the first preset time is less than the second preset time; the event characteristics of the steady-state event comprise the step size of each load data and the ramp rate of each load data;
adding event characteristics of the load event into a characteristic model library;
based on the characteristic model library, carrying out online identification on the charging behavior of the electric bicycle;
the deviation of the respective load data in the first preset time is determined based on the following formula:
wherein,mean value of the individual load data at time k in a first predetermined time, +.>Representing said first preset time, < > and->Representing the respective load data at the firstDeviation within a preset time, < >>The current time is indicated as such,is indicated at->Load data of time;
the difference value of each load data in the second preset time period is determined based on the following formula:
wherein,representing the difference of said respective load data within a second preset time,/for a second preset time period>Indicating the current time, N indicating said second preset time,/for>Mean value of the individual load data at time k+1,/->Representing the average value of each load data at the moment k in a first preset time;
the step size of each load data is determined based on the following formula:
wherein,step size, which represents the respective load data, +.>Maximum value of corresponding load data within 1s representing the end of transient event,/->Representing a minimum value of corresponding load data within 1s before the transient event begins;
the ramp rate of each load data is determined based on the following formula:
wherein,representing the ramp rate of said respective load data, < >>Maximum value of corresponding load data within 1s representing the end of steady-state event,/->Representing the minimum value of the corresponding load data within 1s before the start of the steady state event,/i>The time difference between the start time and the end time of the corresponding load data is represented.
2. The method of claim 1, wherein extracting event features of a load event based on the real-time load data comprises:
filtering the real-time load data based on a recursive least square filter to obtain filtered load data;
and extracting event characteristics of the steady-state event based on the filtered load data.
3. The method according to claim 1 or 2, wherein the performing on-line recognition of the electric bicycle charging behavior based on the feature model library includes:
training the characteristic model library based on a subtractive clustering algorithm to generate an electric bicycle identification model;
and on-line identification of the charging behavior of the electric bicycle is performed based on the electric bicycle identification model.
4. An identification device for the charging behaviour of an electric bicycle, characterized in that it comprises:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring real-time load data in a user room, and the real-time load data comprises active power, reactive power, even current harmonics and odd current harmonics;
the processing module is used for extracting event characteristics of the load event based on the real-time load data; the load event comprises a transient event and a steady-state event, wherein the transient event represents that the real-time load data is suddenly changed, and the steady-state event represents that the real-time load data is slowly changed; the event characteristics of the transient event include: deviation of each load data in a first preset time and difference of each load data in a second preset time; wherein the first preset time is less than the second preset time; the event characteristics of the steady-state event comprise the step size of each load data and the ramp rate of each load data; adding event characteristics of the load event into a characteristic model library; based on the characteristic model library, carrying out online identification on the charging behavior of the electric bicycle;
the deviation of the respective load data in the first preset time is determined based on the following formula:
wherein,mean value of the individual load data at time k in a first predetermined time, +.>Representing said first preset time, < > and->Representing the deviation of the respective load data within a first preset time,/for a first preset time>The current time is indicated as such,is indicated at->Load data of time;
the difference value of each load data in the second preset time period is determined based on the following formula:
wherein,representing the difference of said respective load data within a second preset time,/for a second preset time period>Indicating the current time, N indicating said second preset time,/for>Mean value of the individual load data at time k+1,/->Representing the average value of each load data at the moment k in a first preset time;
the step size of each load data is determined based on the following formula:
wherein,step size, which represents the respective load data, +.>Maximum value of corresponding load data within 1s representing the end of transient event,/->Representing a minimum value of corresponding load data within 1s before the transient event begins;
the ramp rate of each load data is determined based on the following formula:
wherein,representing the ramp rate of said respective load data, < >>Maximum value of corresponding load data within 1s representing the end of steady-state event,/->Representing the minimum value of the corresponding load data within 1s before the start of the steady state event,/i>The time difference between the start time and the end time of the corresponding load data is represented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640877.2A CN117349639B (en) | 2023-12-04 | 2023-12-04 | Identification method and device for charging behavior of electric bicycle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640877.2A CN117349639B (en) | 2023-12-04 | 2023-12-04 | Identification method and device for charging behavior of electric bicycle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117349639A CN117349639A (en) | 2024-01-05 |
| CN117349639B true CN117349639B (en) | 2024-03-08 |
Family
ID=89365259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311640877.2A Active CN117349639B (en) | 2023-12-04 | 2023-12-04 | Identification method and device for charging behavior of electric bicycle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349639B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111244954A (en) * | 2020-03-23 | 2020-06-05 | 广东电科院能源技术有限责任公司 | Non-invasive load identification method and device |
| CN113036754A (en) * | 2021-03-05 | 2021-06-25 | 重庆邮电大学 | Non-invasive load identification method based on improved DAG-SVMS |
| CN113538037A (en) * | 2021-06-16 | 2021-10-22 | 北京市腾河智慧能源科技有限公司 | Method, system, equipment and storage medium for monitoring charging event of battery car |
| CN113567794A (en) * | 2021-09-24 | 2021-10-29 | 国网江苏省电力有限公司营销服务中心 | Electric bicycle indoor charging identification method and system based on dynamic time warping |
| CN113928158A (en) * | 2021-08-31 | 2022-01-14 | 天津大学 | Non-invasive electric bicycle monitoring method and system based on model self-learning |
| WO2022121744A1 (en) * | 2020-12-08 | 2022-06-16 | 浙江大学 | Non-intrusive load identification method based on v-i trajectory map and neural network |
| CN115758234A (en) * | 2022-10-31 | 2023-03-07 | 南方电网电力科技股份有限公司 | Battery car load identification method based on multi-feature fusion and related device thereof |
| CN115958991A (en) * | 2022-12-05 | 2023-04-14 | 中国电力科学研究院有限公司 | Method, device, equipment and medium for monitoring indoor charging of battery car |
| CN115967079A (en) * | 2022-09-27 | 2023-04-14 | 深圳市国电科技通信有限公司 | Method, device and processor for non-invasive load identification of power utilization information |
-
2023
- 2023-12-04 CN CN202311640877.2A patent/CN117349639B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111244954A (en) * | 2020-03-23 | 2020-06-05 | 广东电科院能源技术有限责任公司 | Non-invasive load identification method and device |
| WO2022121744A1 (en) * | 2020-12-08 | 2022-06-16 | 浙江大学 | Non-intrusive load identification method based on v-i trajectory map and neural network |
| CN113036754A (en) * | 2021-03-05 | 2021-06-25 | 重庆邮电大学 | Non-invasive load identification method based on improved DAG-SVMS |
| CN113538037A (en) * | 2021-06-16 | 2021-10-22 | 北京市腾河智慧能源科技有限公司 | Method, system, equipment and storage medium for monitoring charging event of battery car |
| CN113928158A (en) * | 2021-08-31 | 2022-01-14 | 天津大学 | Non-invasive electric bicycle monitoring method and system based on model self-learning |
| CN113567794A (en) * | 2021-09-24 | 2021-10-29 | 国网江苏省电力有限公司营销服务中心 | Electric bicycle indoor charging identification method and system based on dynamic time warping |
| CN115967079A (en) * | 2022-09-27 | 2023-04-14 | 深圳市国电科技通信有限公司 | Method, device and processor for non-invasive load identification of power utilization information |
| CN115758234A (en) * | 2022-10-31 | 2023-03-07 | 南方电网电力科技股份有限公司 | Battery car load identification method based on multi-feature fusion and related device thereof |
| CN115958991A (en) * | 2022-12-05 | 2023-04-14 | 中国电力科学研究院有限公司 | Method, device, equipment and medium for monitoring indoor charging of battery car |
Non-Patent Citations (2)
| Title |
|---|
| 何恒靖 ; 王灏 ; 肖勇 ; 张恒 ; 赵云 ; 周东国 ; .基于Bi-LSTM算法的非侵入式负荷监测模型.南方电网技术.2019,(第02期),全文. * |
| 基于Bi-LSTM算法的非侵入式负荷监测模型;何恒靖;王灏;肖勇;张恒;赵云;周东国;;南方电网技术(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117349639A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105487639A (en) | Method and device for optimizing power consumption of application program and electronic equipment | |
| CN117349639B (en) | Identification method and device for charging behavior of electric bicycle | |
| CN114118595A (en) | Method, system, storage medium and electronic device for power load prediction | |
| CN116879760B (en) | Historical overcharge fault diagnosis method and device for retired power battery | |
| CN117147958A (en) | Method and device for discriminating electricity larceny based on real-time electricity utilization monitoring | |
| CN110579708A (en) | Battery capacity identification method and device, computing equipment and computer storage medium | |
| CN109274562B (en) | Voice instruction execution method and device, intelligent household appliance and medium | |
| CN111509810A (en) | Lithium battery charging state detection method and device and storage medium | |
| CN115567371A (en) | Abnormity detection method, device, equipment and readable storage medium | |
| CN112666477A (en) | Method for determining short circuit in battery, electronic device, and storage medium | |
| CN111016730B (en) | Battery charging detection method and device and terminal equipment | |
| CN116160878B (en) | Battery replacement control system and method, computer readable medium and electronic equipment | |
| CN116306212A (en) | Reactor fault prediction method, device, equipment and storage medium | |
| CN115185987A (en) | Intelligent cable based on key sampling point management data | |
| CN112787386B (en) | Intelligent charging control method, system, charging equipment and computer storage medium | |
| CN114552695A (en) | Charging control system, charging control device, and storage medium | |
| CN114971381A (en) | Intelligent house load management method | |
| CN116862563A (en) | User group feature extraction method, system, equipment and medium | |
| CN115203164A (en) | Intelligent cable based on dynamic reference value management data | |
| CN115078952A (en) | IGBT driving fault detection method and system | |
| CN117650560A (en) | Novel hybrid energy storage configuration method and system for black start power supply | |
| CN118153892A (en) | User side transaction capability assessment method suitable for electric power market transaction | |
| CN117147959A (en) | Electricity larceny prevention analysis method and device | |
| CN116579457A (en) | Charging station energy storage configuration prediction method and device, electronic equipment and medium | |
| Suriya et al. | A Progressive Method to Monitor Power Using IoT |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |