CN118033208B - Intelligent air switch - Google Patents
Intelligent air switch Download PDFInfo
- Publication number
- CN118033208B CN118033208B CN202410440805.1A CN202410440805A CN118033208B CN 118033208 B CN118033208 B CN 118033208B CN 202410440805 A CN202410440805 A CN 202410440805A CN 118033208 B CN118033208 B CN 118033208B
- Authority
- CN
- China
- Prior art keywords
- current
- load line
- power
- load
- switch gate
- 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
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims description 41
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000005612 types of electricity Effects 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010409 ironing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01H—ELECTRIC SWITCHES; RELAYS; SELECTORS; EMERGENCY PROTECTIVE DEVICES
- H01H71/00—Details of the protective switches or relays covered by groups H01H73/00 - H01H83/00
- H01H71/04—Means for indicating condition of the switching device
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R15/00—Details of measuring arrangements of the types provided for in groups G01R17/00 - G01R29/00, G01R33/00 - G01R33/26 or G01R35/00
- G01R15/12—Circuits for multi-testers, i.e. multimeters, e.g. for measuring voltage, current, or impedance at will
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application discloses an intelligent air switch, and belongs to the technical field of air switches. An intelligent air switch comprising: the switch gate, the household line is connected to the inlet wire end, and the load line is connected to the outlet wire end; the current detector is arranged at the outlet end of the switch gate and is used for detecting the current of the load line; the power detector is arranged at the outlet end of the switch gate and used for detecting the power of the load line; the data processing device is arranged at one side of the switch gate, collects current data and power data detected by the current detector, identifies the current utilization device working on each load line according to the detected current data, and records the power utilization of the current utilization device; and the data display is arranged on one side of the switch gate and used for displaying the power consumption of each type of electric appliance in the household. In the technical scheme provided by the application, the functions of the intelligent ammeter and the air switch are integrated, so that two devices are not required to be installed during installation, and the installation efficiency is increased.
Description
Technical Field
The application relates to the technical field of electric switches, in particular to an intelligent air switch.
Background
The existing intelligent air switch can automatically trip to play a role in protecting when the line is overloaded, so that the current overload of the load line is avoided to cause fire. However, the current household electric meter can only display the electricity consumption of the user in a certain period of time. For example, what the average power usage of the user is between the points per day. Therefore, the user can only know the total electricity consumption of the user in the period of time, but cannot accurately acquire the specific electricity consumption of different electric appliances, and when the user performs electricity consumption supervision, the user cannot reasonably design the electricity saving strategy according with the actual situation of the user because of the lack of the electricity consumption of each electric appliance, so that the electricity saving mode of the user cannot be designed and adjusted based on the actual electricity consumption situation.
Disclosure of Invention
The summary of the application is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. The summary of the application is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In order to solve the technical problems mentioned in the background section above, the present application provides an intelligent air switch, comprising:
the switch gate, the household line is connected to the inlet wire end, and the load line is connected to the outlet wire end;
The current detector is arranged at the outlet end of the switch gate and is used for detecting the current of the load line;
the power detector is arranged at the outlet end of the switch gate and used for detecting the power of the load line;
the current frequency detector is arranged at the outlet end of the switch gate and is used for detecting the current frequency of the load line;
the voltage detector is arranged at the outlet end of the switch gate and used for detecting the voltage of the load line;
The data processing device is arranged on one side of the switch gate, and is used for collecting current, power, current frequency and voltage of each load wire and identifying the current consumer on each load wire to obtain the power of the corresponding current consumer;
and the data display is arranged on one side of the switch gate and displays the electricity consumption of each type of electric appliance.
In the technical scheme provided by the application, the functions of the intelligent ammeter and the air switch are integrated, so that two devices are not required to be installed during installation, and the installation efficiency is increased. In addition, in a specific test, the power consumption of each load line is detected, and different devices are identified by detecting the current of the load line, so that the power consumption of each electric appliance can be obtained in this way. Furthermore, the user can adjust his own power saving strategy according to the power consumption of each electric appliance provided.
The current detector comprises a current transformer and a Hall current sensor.
The current transformer is the most commonly used current detection device, can well detect the current passing through a load line, and the Hall current sensor can detect the current frequency of the current; and different electrical consumers are not necessarily required for the frequency of the current generated. For example, refrigerators and washing machines, the frequency characteristics of the current they produce are related to the frequency of the current they have in their interior compressor. The other electric appliances, such as televisions and computers, also have special current frequency characteristics, so that the type of the electric appliance of each load line can be well identified by identifying the current frequency characteristics.
In a household, there are generally a plurality of electric appliances, if all the electric appliances work simultaneously, too many electric appliances are compounded on each load line, and it is difficult to analyze the electric appliances working through the current frequency characteristic and the current characteristic. The application provides the following technical scheme for solving the problem:
the switch gate is provided with a plurality of, is connected with the load line that is connected with the different regions of a branch pipe on every switch gate.
In this scheme, the switch floodgate has set up a plurality of, and then can form the load line of a plurality of different regions of being in charge of, so just to the domestic electrical apparatus, carry out the subregion setting, so can effectually increase the accuracy to the power consumption supervision.
The data display is a touch screen display.
The data display is arranged as a touch screen display, so that the data display forms a functional module which enables a user to interact with the data processing device to realize information interaction. The user can input some instructions or label information through the data display to guide the data processing device to the processing process of the data.
The data processing device is internally provided with a data prediction model, and the type of the corresponding electric appliance and the electric consumption of the corresponding electric appliance on each load line are analyzed according to the current, the power, the current frequency and the voltage of each load line.
The electricity consumption characteristics of users are very complex in practice, and in order to increase the accuracy of prediction, data such as current, current frequency, power, voltage and the like need to be collected, so that it is difficult to find the relationship between the electricity consumption characteristics and the electricity consumption types from complex data when processing the data. Aiming at the problem, the application provides the following technical scheme:
The data processing device analyzes the electricity consumption of each electric appliance by the following steps:
Step 1: collecting current, current frequency, power and voltage of each load line, and preprocessing the current, the current frequency, the power and the voltage to obtain electricity utilization characteristics of each load line;
Step 2: establishing a data prediction model constructed based on a support vector machine, and training and evaluating the data prediction model;
Step 3: and inputting the electricity utilization characteristics of each load wire into a data prediction model to obtain the corresponding electricity utilization device of each load wire and the corresponding power ratio thereof, and calculating the electricity consumption of each type of electricity utilization device.
In the technical scheme provided by the application, the corresponding prediction model is established by adopting the support vector machine, so that decision boundaries can be found in complex data, and further, different electrical appliance types can be accurately classified.
Different types of data have different expression modes and corresponding orders of magnitude are different, so that when the data fluctuate, the data processing model cannot accurately analyze the fluctuation condition of the corresponding data.
Step1 comprises the following steps:
Step 11: collecting current data a 1, voltage data a 2, current frequency a 3, and power a 4 of each load line;
Step 12: the current data a 1, the voltage data a 2, the current frequency a 3, and the power a 4 of the load line are normalized.
According to the technical scheme provided by the application, all collected data are subjected to normalization processing, so that after normalization, all data can be measured under a unified standard, and when all data fluctuate, the fluctuation condition of the data can be accurately understood and analyzed. Meanwhile, in the application, the type of each electric appliance on the load line and the total amount of the occupied power can be represented by collecting the current, the voltage, the current frequency data and the power, so that the subsequent prediction is used as a corresponding basis. The reason for this is that different electrical appliances produce different current frequencies when they are powered, for example, a refrigerator, the current frequency of which is largely related to the operating current frequency of the compressor in the refrigerator. Correspondingly, the same is true of the air conditioner. It also has unique electricity characteristics for pure resistance electric appliances like incandescent lamps, water heaters, etc., so it can be identified.
In the actual electricity utilization process, the user of electricity utilization still has the condition that multiple electric appliances are used together, and when multiple electric appliances are used together, each current characteristic of various electric appliances can all be compounded on the load line, and the selected electricity utilization characteristic has great difficulty this time, because there are the condition that multiple different combinations probably produce similar electricity utilization characteristics. Aiming at the problem, the application provides the following technical scheme:
The power usage characteristics also include the number and type of power usage connected on each load line.
At the home of the user, part of the electric appliances do not generate great variation. Such as refrigerators, air conditioners, computers, televisions, and the like, the location of such large appliances does not substantially change. Therefore, after purchasing the large-sized electric appliances, the user directly marks the positions of the large-sized electric appliances, and the electric appliances with relatively random positions are downwards marked below all the load lines, so that the total number of the electric appliances under the jurisdiction is known and fixed in advance for each load line, and the accuracy is higher when the electric appliance power consumption is predicted.
Further: step2 comprises the following steps:
Step 21: obtaining possible combination types of the electric appliances on the load lines according to the number and types of the electric appliances connected on each load line, wherein each combination type represents a label, and constructing an original problem according to the number of the combination types;
; i=1, 2 … n, n is an integer, n > 1, i represents the sample index, w is the normal vector of the hyperplane, b is the intercept of the hyperplane, x i is the eigenvector of the ith sample, y i is the set of corresponding class labels;
Step 22: a lagrangian function was introduced:
I and j represent indexes of samples, α i、αj represent lagrangian multipliers, L represents lagrangian functions, and K represents kernel functions, respectively;
Step 23: solving a dual problem, and finding an optimal Lagrangian multiplier alpha i;
；
max a w (α) represents the value of the maximization objective function w (α) with respect to the lagrange multiplier α, w (α) being the objective function of the dual problem corresponding to the original optimization problem;
the following constraint conditions are satisfied:
；
0≤αi≤C，i=1……n，
k (x i,xj) is a kernel function for calculating the inner product between samples, C represents a penalty function;
Step 24: and constructing a decision function according to the optimal alpha i to predict:
Wherein sign is a label, and x represents an unknown sample to be classified.
According to the technical scheme provided by the application, the objective function can reach the optimal decision under the constraint condition meeting limit by calculating the optimal Lagrange multiplier, so that the prediction result is more accurate.
The label items are the number and corresponding type of the work of the electrical appliances on the load line.
Because most of the appliances in the user's home are known, the tag items can be obtained only by corresponding arrangement and combination.
The switch gate is arranged in the shell.
Compared with the prior art, the invention has the following beneficial effects:
the application provides an intelligent switch capable of accurately calculating the electricity consumption of each electric appliance in a household.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application.
In addition, the same or similar reference numerals denote the same or similar elements throughout the drawings. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
In the drawings:
FIG. 1 is a perspective view of an intelligent air switch;
FIG. 2 is a front view of the intelligent air switch;
FIG. 3 is a flowchart showing the steps of the data processing apparatus analyzing the power consumption of each electrical appliance.
Reference numerals:
1. a housing; 2. a switch gate; 3. a home line; 4. a load line; 5. a data display.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Referring to fig. 1 and 2, an intelligent air switch includes: the device comprises a housing 1, a switch gate 2, a current detector, a power detector, a current frequency detector, a voltage detector, a data processing device and a data display 5.
The switch gate 2 is an existing air switch, and has a wire inlet end and a wire outlet end, the wire inlet end is connected to the wire inlet 3, and electric power on the electric network is transmitted to the switch gate 2 through the wire inlet 3, so that power is finally supplied to a user. The outlet terminal is connected to a load line 4. The load line 4 is a line to which each of the electric appliances in the user's home is connected.
More specifically, the switch dampers 2 are provided in plurality, and the load line 4 of each switch damper 2 corresponds to one area of the user's home. For example, there are 2 bedrooms, a kitchen, a living room and a bathroom in a certain user's home, and each room is correspondingly provided with a load line 4 as a main line, and the appliances in the room are connected to the load line 4 by corresponding line connection modes. So that the switch gate 2 controls the power supply of the corresponding electric appliance in the room, and naturally can also manage and monitor the power supply condition of the electric appliance in the room.
And the current detector is arranged at the outlet end of the switch gate 2 and is used for detecting the current of the load line 4. Because the current data to some extent represents the type of different electrical consumer. For example, when each of the electric appliances uses electricity individually, the electricity consumption condition of the corresponding electric appliance can be determined according to the magnitude of the current. However, when a plurality of electric appliances are operated simultaneously, the judgment cannot be made by only depending on the magnitude of the current. For this purpose, in the present solution: a power detector, a current frequency detector, and a voltage detector are also included to detect power, current frequency, and voltage, respectively.
In some embodiments the current detector is a current transformer and the current frequency detector is a hall current sensor. The current transformer is capable of detecting the magnitude of the current. The hall current sensor is then able to detect the current frequency. Essentially, a corresponding voltage detector should also be provided on the current detector for detecting the voltage. The power detector is arranged at the outlet end of the switch gate 2, and the voltage detection device is arranged at the outlet end of the switch gate 2.
It should be noted that in this embodiment, each switch gate 2 is monitored, so the current detector, the power detector, the current frequency detector and the voltage detector are all disposed on the load line 4 of each switch gate 2 correspondingly.
The data processing device is arranged on one side of the switch gate 2 and is used for collecting the current, the power, the current frequency and the voltage of each load wire 4 and identifying the current consumer working on each load wire 4 so as to obtain the power of the current consumer.
In general, in the design of a user's switchgear, the switch gates 2 are generally arranged side by side, so it is necessary to arrange a data processing device on one side of these switch gates 2 to ensure that the upper and lower ends of the switch gates 2 can pass freely through the service line 3 or the load line 4. And the data processing device is respectively connected with the current detector and the power detector in a signal way and can collect current data and power data detected by the current detector. How the data processing device obtains the power consumption of the application appliance according to the current data and the power data is described later.
A data display 5 provided at one side of the switching gate 2 for displaying the power consumption of each type of electric appliances in the home. The data display 5 is a touch screen display. Specifically, a data prediction model is built in the data processing device, and the type of the corresponding electric appliance and the electric consumption of the corresponding electric appliance on each load line 4 are analyzed according to the current, the power, the current frequency and the voltage of each load line 4.
Referring to fig. 3, the data prediction model is constructed based on a support vector machine. The data processing device analyzes the electricity consumption of each electric appliance, and the electricity consumption is realized through the following steps:
step 1: and collecting the current, the current frequency, the power and the voltage of each load line, and preprocessing the current, the current frequency, the power and the voltage to obtain the electricity utilization characteristics of each load line.
In step 1, the current frequency, the power and the voltage of each load line are collected, and are realized by the current detector, the power detector, the current frequency detector and the voltage detector. Because, in actual current planning, load lines do not interfere with each other, it is a separate matter for the data processing apparatus to process the electricity data on each load line. Based on this, assuming that there are k load lines in the user's home, the k load lines are actually all calculated by the aforementioned technical means.
Step1 comprises the following steps:
step 11: current a 1, voltage a 2, current frequency a 3, and power a 4 of the load line are collected for each load line.
Step 12: the current data a 1, the voltage data a 2, the current frequency a 3, and the power a 4 of the load line are normalized.
The normalization of current data a 1, voltage data a 2, current frequency a 3, and load line power a 4 is not discussed here. This part is the existing embodiment.
In a more specific embodiment, in step 1, it is also necessary to collect the number and type of electrical appliances connected on each load line. Specifically, in each user's home, the fixed electric appliances in each room will not change in position, but the electric appliances with some positions being changed can also be recorded. In general, the consumer in the user's home does not substantially change every day.
For this purpose, the electricity consumption characteristics further include the number and type a 5 of the electric appliances connected to each load line, and the recording of the number and type a 5 of the electric appliances is implemented by adopting the following scheme:
S1: the user inputs the electrical appliances fixed at home into a 5 under the corresponding load line. For example, there are 1 air conditioner in the bedroom, 1 refrigerator in the kitchen, 1 television in the living room, and 1 computer in the study room. These appliances are fixed, as are the lighting devices in the various rooms.
S2, inputting the non-fixed electric appliance into A 5 below all load lines in the user' S home.
There are also many non-stationary appliances in the user's home, such as blowers, ironing clothes, and charging heads.
Thus, through the scheme, the types of combinations of the electrical appliance use which can appear are limited under each load line, and the electrical appliance can be found only in limited possibility when the number of the electrical appliance is calculated or fitted.
Step 2: and establishing a data prediction model constructed based on the support vector machine, and training and evaluating the data prediction model.
Step2 comprises the following steps:
Step 21: obtaining possible combination types of the electric appliances on the load lines according to the number and types of the electric appliances connected on each load line, wherein each combination type represents a label, and constructing an original problem according to the number of the combination types;
Or/> ; I=1, 2 … n, n is an integer, n > 1, i denotes the sample index, w is the normal vector of the hyperplane, b is the intercept of the hyperplane, x i is the eigenvector of the ith sample, and y i is the set of corresponding class labels.
Specifically, the support vector machine classification method is mainly applicable to the problem of one two classifications in the use process. Therefore, in this embodiment, y i corresponds to a set of tags. Then, a one-to-one strategy is employed to address the multi-label classification problem. That is, the type of combination of the electrical appliances possible on the load line is determined according to the number and type of electrical appliances connected on the load line. Each combination type represents a set of tags. A binary vector is used to represent the set of labels for each sample. The length of the vector is equal to the number of different labels in the set of labels, each element indicating the presence or absence of the corresponding label (1 indicating the presence, 0 indicating the absence). A multi-label classifier is constructed that treats each different label as an independent classification problem. Training a plurality of two classifiers, each classifier being used to determine whether the sample belongs to a corresponding tag.
In fact, in the foregoing solution, only a simple classification method is provided, and when there is only one electrical apparatus on the load line, the original problem is constructed in step 21, that is, the electrical apparatus is used, or both the two cases are not used. When two electric appliances exist, 4 conditions of simultaneous use, simultaneous closing, one use and the other non-use exist, the corresponding label type is increased along with the increase of the electric appliance types on the load line, and the number of the corresponding classifier is required to be increased.
Step 22: a lagrangian function was introduced:
I and j represent indexes of samples, α i、αj represent lagrangian multipliers, L represents lagrangian functions, and K represents kernel functions, respectively;
Step 23: solving a dual problem, and finding an optimal Lagrangian multiplier alpha i;
；
max a w (α) represents the value of the maximization objective function w (α) with respect to the lagrange multiplier α, w (α) being the objective function of the dual problem corresponding to the original optimization problem;
the following constraint conditions are satisfied:
；
0≤αi≤C，i=1……n，
k (x i,xj) is a kernel function for calculating the inner product between samples, C represents a penalty function;
Step 24: and constructing a decision function according to the optimal alpha i to predict:
Wherein sign is a label, and x represents an unknown sample to be classified.
According to the technical scheme provided by the application, the objective function can reach the optimal decision under the constraint condition meeting the constraint condition by calculating the optimal Lagrange multiplier. And the prediction result is more accurate. After model creation, training of the data prediction model is required. The data set for model training is as follows:
A large number of already labeled datasets are first collected, of which x i={A1、A2、A3、A4、A5},yi is the corresponding label. These tags consist of the number of appliances and the proportion of power occupied by the number of appliances, for example tag 1 is: {1 refrigerator, 1 boiler, 70%, 30% }, then representing tag 1 indicates that the number of refrigerators and boilers is 1, and the power ratio is 70% and 30%, respectively.
Step 3: and inputting the preprocessed electricity utilization characteristics into a data prediction model to obtain corresponding electricity utilization devices and corresponding power duty ratios thereof.
After training and evaluating the support vector machine, the intelligent space switch can convert the electricity consumption data into the power duty ratio of the corresponding electric appliances in real time, and then calculate the electricity consumption of all the corresponding electric appliances.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (4)
1. An intelligent air switch, its characterized in that: comprising the following steps:
The switch gate is provided with a wire inlet end and a wire outlet end, the wire inlet end is used for being connected with a household wire, and the wire outlet end is used for being connected with a load wire;
The current detector is arranged at the outlet end of the switch gate and is used for detecting the current of the load line;
the power detector is arranged at the outlet end of the switch gate and used for detecting the power of the load line;
the current frequency detector is arranged at the outlet end of the switch gate and is used for detecting the current frequency of the load line;
the voltage detector is arranged at the outlet end of the switch gate and used for detecting the voltage of the load line;
The data processing device is arranged on one side of the switch gate and is used for collecting the current, the power, the current frequency and the voltage of each load wire and identifying the current consumer on each load wire which is working so as to obtain the power of the corresponding current consumer;
the data display is arranged on one side of the switch gate and used for displaying the electricity consumption of each type of electric appliance;
the data processing device is internally provided with a data prediction model, and the data prediction model analyzes the type of the corresponding electric appliance and the electric consumption of the corresponding electric appliance on each load line according to the current, the power, the current frequency and the voltage of each load line;
The data processing device analyzes the electricity consumption of each electric appliance by the following steps:
Step 1: collecting current, current frequency, power and voltage of each load line, and preprocessing the current, the current frequency, the power and the voltage to obtain electricity utilization characteristics of each load line;
Step 2: establishing a data prediction model constructed based on a support vector machine, and training and evaluating the data prediction model;
Step 3: inputting the electricity utilization characteristics of each load wire into a data prediction model to obtain an electricity utilization device corresponding to each load wire and a corresponding power ratio thereof, and calculating the electricity consumption of each type of electricity utilization device;
Step1 comprises the following steps:
Step 11: collecting current a 1, voltage a 2, current frequency a 3, and power a 4 of each load line;
Step 12: normalizing the current A 1, the voltage A 2, the current frequency A 3 and the power A 4 of each load line;
The electricity utilization characteristics also comprise the number and the type of the electric appliances connected on each load line;
Step2 comprises the following steps:
Step 21: obtaining possible combination types of the electric appliances on the load lines according to the number and types of the electric appliances connected on each load line, wherein each combination type represents a label, and constructing an original problem according to the number of the combination types;
Or/> ; I=1, 2 … n, n is an integer, n > 1, i represents the sample index, w is the normal vector of the hyperplane, b is the intercept of the hyperplane, x i is the eigenvector of the ith sample, y i is the set of corresponding class labels;
Step 22: a lagrangian function was introduced:
I and j represent indexes of samples, α i、αj represent lagrangian multipliers, L represents lagrangian functions, and K represents kernel functions, respectively;
Step 23: solving a dual problem, and finding an optimal Lagrangian multiplier alpha i;
；
max a w (α) represents the value of the maximization objective function w (α) with respect to the lagrange multiplier α, w (α) being the objective function of the dual problem corresponding to the original optimization problem;
the following constraint conditions are satisfied:
；
0≤αi≤C，i=1……n，
k (x i,xj) is a kernel function for calculating the inner product between samples, C represents a penalty function;
Step 24: and constructing a decision function according to the optimal alpha i to predict:
Wherein sign is a label, and x represents an unknown sample to be classified;
The label item comprises the number and the type of the electric appliances working on the load line;
The recording of the number and type A 5 of the electric appliances is realized by adopting the following scheme:
S1: the user inputs the electric appliances fixed in the home into the A 5 below the corresponding load line;
S2, inputting the non-fixed electric appliance into A 5 below all load lines in the user' S home;
determining the possible combination types of the electric appliances on the load line according to the number and the types of the electric appliances connected on the load line;
each combination type represents a set of tags;
Using a binary vector to represent the tag set for each sample;
the length of the vector is equal to the number of different labels in the label set;
The tag includes the appliance type, the number of appliances, and the power duty cycle of each appliance.
2. The intelligent air switch of claim 1, wherein: the current detector is a current transformer, and the current frequency detector is a Hall current sensor.
3. The intelligent air switch of claim 1, wherein: the switch gate is provided with a plurality of, is connected with the load line that is connected with the different regions of a branch pipe on every switch gate.
4. The intelligent air switch of claim 1, wherein: the data display is a touch screen display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410440805.1A CN118033208B (en) | 2024-04-12 | 2024-04-12 | Intelligent air switch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410440805.1A CN118033208B (en) | 2024-04-12 | 2024-04-12 | Intelligent air switch |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118033208A CN118033208A (en) | 2024-05-14 |
| CN118033208B true CN118033208B (en) | 2024-06-18 |
Family
ID=91000889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410440805.1A Active CN118033208B (en) | 2024-04-12 | 2024-04-12 | Intelligent air switch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118033208B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106872824A (en) * | 2017-02-15 | 2017-06-20 | 宁波华创锐科智能科技有限公司 | A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics |
| CN207368634U (en) * | 2017-11-08 | 2018-05-15 | 盛世乐居（亚东）智能科技有限公司 | Intelligent air switchs |
| CN114236234A (en) * | 2021-11-17 | 2022-03-25 | 国网天津市电力公司 | Electrical appliance characteristic identification method based on fundamental wave and harmonic wave mixed criterion |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101875329B1 (en) * | 2017-06-12 | 2018-07-05 | 한국과학기술원 | Forecasting apparatus and method for power consumption |
| CN107832705A (en) * | 2017-11-08 | 2018-03-23 | 天津大学 | A kind of non-intrusion type load recognition methods based on canonical correlation analysis |
| CN108054589A (en) * | 2017-12-08 | 2018-05-18 | 深圳市田言智能科技有限公司 | A kind of infrared intelligent socket reminded with working condition |
| CN109034241A (en) * | 2018-07-24 | 2018-12-18 | 南京千智电气科技有限公司 | Load cluster control method and system based on support vector machines |
| CN110514889A (en) * | 2019-07-19 | 2019-11-29 | 浙江万胜智能科技股份有限公司 | A kind of method and system of non-intrusion type household electricity remained capacity |
| CN110412347B (en) * | 2019-08-12 | 2021-04-20 | 贵州电网有限责任公司 | Electricity stealing behavior identification method and device based on non-invasive load monitoring |
| CN110824245A (en) * | 2019-11-12 | 2020-02-21 | 南昌工程学院 | Semi-invasive load monitoring system and method applied to household distribution box and application |
| CN111324790A (en) * | 2020-02-20 | 2020-06-23 | 国网新疆电力有限公司电力科学研究院 | Load type identification method based on support vector machine classification |
| WO2021171303A1 (en) * | 2020-02-26 | 2021-09-02 | Council Of Scientific And Industrial Research | A system and method for energy management of identical appliances using non-intrusive load monitoring technique |
| CN112149510B (en) * | 2020-08-27 | 2022-05-10 | 广东工业大学 | Non-invasive load detection method |
| CN113341262A (en) * | 2021-07-13 | 2021-09-03 | 国网江苏省电力有限公司营销服务中心 | Platformization load data acquisition device |
| CN115982598A (en) * | 2022-11-23 | 2023-04-18 | 深圳供电局有限公司 | Electricity stealing detection method, apparatus, device, medium, and program product |
| CN116522151A (en) * | 2023-07-04 | 2023-08-01 | 深圳市芝电能源科技有限公司 | Semi-supervised load recognition and decomposition method, system and storage medium |
| CN117477771A (en) * | 2023-10-30 | 2024-01-30 | 国网浙江省电力有限公司杭州市临平区供电公司 | Non-invasive dormitory electricity safety monitoring method, system and storage medium |
-
2024
- 2024-04-12 CN CN202410440805.1A patent/CN118033208B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106872824A (en) * | 2017-02-15 | 2017-06-20 | 宁波华创锐科智能科技有限公司 | A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics |
| CN207368634U (en) * | 2017-11-08 | 2018-05-15 | 盛世乐居（亚东）智能科技有限公司 | Intelligent air switchs |
| CN114236234A (en) * | 2021-11-17 | 2022-03-25 | 国网天津市电力公司 | Electrical appliance characteristic identification method based on fundamental wave and harmonic wave mixed criterion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118033208A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Du et al. | A review of identification and monitoring methods for electric loads in commercial and residential buildings | |
| Berges et al. | User-centered nonintrusive electricity load monitoring for residential buildings | |
| KR101828461B1 (en) | Electrical instrument, power management apparatus and method for controlling the same | |
| Froehlich et al. | Disaggregated end-use energy sensing for the smart grid | |
| US8463452B2 (en) | Apparatus using time-based electrical characteristics to identify an electrical appliance | |
| CN111092434B (en) | Residential community power load control method and device based on non-invasive electricity consumption data | |
| Liang et al. | HVAC load disaggregation using low-resolution smart meter data | |
| Abubakar et al. | An overview of non-intrusive load monitoring methodologies | |
| WO2001077696A1 (en) | System and method for estimating power consumption of electric apparatus, and abnormality alarm system utilizing the same | |
| CN108693499A (en) | A kind of user power utilization load identification intelligent electric energy meter detecting system and method | |
| WO2012103485A2 (en) | Signal identification methods and systems | |
| CN102142062A (en) | Method and apparatus for controlling operations of devices based on information about power consumption of the devices | |
| JP2003316922A (en) | Energy information analyzing method, energy information analyzing device, and energy information analyzing system | |
| Liu | Non-intrusive load monitoring | |
| WO2021171303A1 (en) | A system and method for energy management of identical appliances using non-intrusive load monitoring technique | |
| Ghosh et al. | Non-intrusive identification of harmonic polluting loads in a smart residential system | |
| US11125790B2 (en) | Method for operating a power consumption metering system and power consumption metering system | |
| Zhang et al. | Non-intrusive load identification method based on color encoding and improve R-FCN | |
| CN118033208B (en) | Intelligent air switch | |
| Wang et al. | Data-driven assessment of room air conditioner efficiency for saving energy | |
| Butzbaugh et al. | Miscellaneous electric loads: Characterization and energy savings potential | |
| US20140330444A1 (en) | Apparatus Using Time-Based Electrical Characteristics to Identify an Electrical Appliance | |
| Figueiredo | Contributions to electrical energy disaggregation in a smart home | |
| Monacchi et al. | Strategies for domestic energy conservation in Carinthia and Friuli-Venezia Giulia | |
| JP6861578B2 (en) | Load estimation device and load estimation method |
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 |