Safe commercial power switch control method and device
The safe mains switch control method addresses the inefficiency of existing power control devices by using real-time data collection and analysis to identify and prevent unsafe electrical use, ensuring timely disconnection and safety.
Patent Information
- Application Number
- CN202411346906.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2024-12-20
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing power control devices struggle to respond timely and effectively to situations where residents use electrical appliances that exceed the line carrying capacity or use common appliances incorrectly, leading to high-risk situations.
A safe mains switch control method involving real-time collection of electricity consumption data, low-pass filtering, normalization, and analysis using a Seq2point model and recognition algorithm to identify improper use, disconnecting power if necessary.
Ensures timely and effective safety of electricity use by disconnecting power when residents use appliances incorrectly or exceed line capacity, preventing high-risk situations.
Smart Images
Figure CN119171386A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of mains power control devices, and in particular to a safe mains power switch control method and device. Background Art
[0002] Residential electricity is the electricity that residents need to use for family life, study, entertainment, etc., specifically to meet various needs such as lighting, cooking, cooling and heating. At present, in order to strengthen the effective management of residential electricity and ensure the safety of electricity use, power control devices are usually installed at the meter boxes of individual users to control the power supply of the household; and corresponding power control devices are installed at the main distribution boxes or main switches serving multiple households (such as apartment buildings, residential areas, etc.) to centrally manage the power distribution and safety of multiple households.
[0003] In some application scenarios, a high-frequency collector or a low-frequency collector is set in the power control device to collect the residents' power consumption behavior information, and send the power consumption behavior information to the power supply management party, so as to optimize the power management strategy and realize the rational use of power resources. In addition, in the existing usage scenarios, it is usually manually implemented by the power control device according to specific needs to connect or disconnect the power of a single or multiple households to ensure the safety of power use, but the efficiency of implementing operations such as connection or disconnection is low. When residents use electrical appliances that exceed the line carrying capacity or use common electrical appliances incorrectly, high-risk situations may occur, and existing technologies are difficult to respond in a timely and effective manner.
[0004] To this end, we propose a method and device for controlling a mains switch that can further ensure the safety of residents' electricity use. Summary of the invention
[0005] The main purpose of the present invention is to propose a safe AC power switch control method and device, aiming to solve the technical problem in the prior art that when residents use electrical appliances that exceed the line carrying capacity or use common electrical appliances incorrectly, high-risk situations may occur and it is difficult to respond in a timely and effective manner.
[0006] To achieve the above object, the present invention provides a safe mains switch control method, comprising the following steps: Step S1: collect the user's electricity consumption behavior information in real time, perform low-pass filtering algorithm processing on the collected electricity consumption behavior information to remove high-frequency noise, retain the main trend of the data, and perform normalization processing algorithm on the low-pass filtering algorithm to output normalized data; Step S2: input the normalized data into the Seq2point model to decompose and obtain the relevant data of each electrical appliance currently used by a single household, and output the decomposed data; Step S3: Input the decomposed data into the recognition algorithm for processing to determine whether the residents have used electrical appliances that exceed the line carrying capacity, or have used common electrical appliances incorrectly. If the judgment result is yes, the electricity connection for the household can be disconnected. If the judgment result is no, the electricity connection for the household will remain connected.
[0007] Optionally, the electricity consumption behavior information is total load data , total voltage value And the total current value .
[0008] Optionally, the calculation formula of the low-pass filtering algorithm is as follows: In the above formula, The total load data collected , total voltage value Or total current value , is the smoothing coefficient and , For the previous time step of value, is the exponential moving average of the current time point, and is the output sequence after low-pass filtering algorithm processing.
[0009] Optionally, the Seq2point model includes an input layer, a coding layer and an output layer, and the normalized data is input into the input layer in the form of a sliding window. The input data in the input layer is The first data matrix of the encoding layer includes multiple convolutional layers, each of the convolutional layers includes a ReLU nonlinear activation function, the output layer is a fully connected layer, and the fully connected layer includes a linear activation function.
[0010] Optionally, the convolution layer includes a padding value, a convolution kernel, and a step size, the padding value is 0, and the shape of the convolution kernel is , is the height of the convolution kernel, 3 is the width of the convolution kernel, a is the serial number of the convolution kernel, and the step size is 1; Filling values are added around the first data matrix input into the convolutional layer to expand the first data matrix into a second data matrix to expand into The convolution kernel traverses the second data matrix with a step size of 1 to process and obtain a first output matrix, which can be input into a convolution layer or an output layer.
[0011] Optionally, the convolution layer includes a feature extraction calculation formula, and the feature extraction calculation formula is as follows: In the above formula, is the first output matrix Line The value of the column element, is the height of the convolution kernel, The width of the convolution kernel, is the second data matrix, is the convolution kernel, , , , Both are index variables used to traverse the elements of input data, convolution kernels, and output feature maps.
[0012] Optionally, the decomposition data is The second output matrix, the The value of is a preset value, and each column element of the second output matrix can represent the electrical load data of an electrical appliance. , Electrical voltage value , Electrical current value and the working time t.
[0013] Optionally, step S3 includes a threshold determination algorithm, the threshold determination algorithm includes a threshold matrix, the threshold matrix includes The first sub-threshold matrix of The second sub-threshold matrix of Each column element of the first sub-threshold matrix is the electrical load data of commonly used electrical appliances. , Electrical voltage value And electrical current value And the preset standard value of the working time t, if the electrical load data of the corresponding column of the second output matrix , Electrical voltage value , Electrical current value If one element of the working time t exceeds a preset standard value, it indicates that the commonly used electrical appliance is in an improperly used state; otherwise, it indicates that the commonly used electrical appliance is in a normal state; Each column element of the second sub-threshold matrix is zero. If the electrical load data of the corresponding column of the second output matrix , Electrical voltage value , Electrical current value And if an element in the working time t exceeds zero, it means that the resident has used electrical appliances that exceed the carrying capacity of the line. Otherwise, it means that the resident has not used electrical appliances that exceed the carrying capacity of the line.
[0014] The present invention also discloses a safe mains switch control device, which is used to implement the safe mains switch control method as described above, and comprises a box and a PCBA board, wherein the PCBA board is installed in the box, and the PCBA board is integrated with a low-frequency collector and a main control chip, wherein the main control chip stores a low-pass filtering algorithm, a normalization processing algorithm, a Seq2point model, and a recognition algorithm; The low-frequency collector and the main control chip are both electrically connected to one or more residential power buses.
[0015] Optionally, the PCBA board is further integrated with a communication module, and the communication module is electrically connected to the main control chip.
[0016] The technical solution of the present invention has the following beneficial effects: When in use, the total load data of residential electricity consumption is collected in real time through a low-frequency collector. , total voltage value Or total current value The low-frequency collector in this embodiment collects data once per second. The total load data collected by the low-frequency collector is , total voltage value Or total current value The information is input into the main control chip to identify whether the residents have used their commonly used electrical appliances incorrectly, or whether they have used electrical appliances that exceed the line carrying capacity. If the judgment result is yes, the electricity connection of the household can be disconnected. If the judgment result is no, the electricity connection of the household is maintained. In the process of electricity use by residents, the electricity use behavior information of the residents is collected in real time, and the electricity use behavior information is analyzed, processed and identified through the low-pass filtering algorithm, normalization processing algorithm, Seq2point model and recognition algorithm stored in the main control chip. When it is judged that the residents have used their commonly used electrical appliances incorrectly, or whether they have used electrical appliances that exceed the line carrying capacity, the electricity connection of the residents can be disconnected, thereby timely and effectively ensuring the safety of residents' electricity use and avoiding the occurrence of high-risk situations that may be caused by residents using electrical appliances that exceed the line carrying capacity or improper use of commonly used electrical appliances. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.
[0018] Figure 1 The present invention is a flowchart of a safe mains switch control method according to an embodiment of the present invention.
[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0022] In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0023] The present invention provides a safe mains switch control method and device.
[0024] like Figure 1 As shown, in one embodiment of the present invention, the safe mains switch control method comprises the following steps: Step S1: collect the user's electricity consumption behavior information in real time, perform low-pass filtering algorithm processing on the collected electricity consumption behavior information to remove high-frequency noise, retain the main trend of the data, and perform normalization processing algorithm on the low-pass filtering algorithm to output normalized data; Step S2: input the normalized data into the Seq2point model to decompose and obtain the relevant data of each electrical appliance currently used by a single household, and output the decomposed data; Step S3: Input the decomposed data into the recognition algorithm for processing to determine whether the residents have used electrical appliances that exceed the line carrying capacity, or have used common electrical appliances incorrectly. If the judgment result is yes, the electricity connection for the household can be disconnected. If the judgment result is no, the electricity connection for the household will remain connected.
[0025] In this embodiment, the electricity consumption behavior information is specifically the total load data. , total voltage value And the total current value Specifically, electricity consumption information is collected through a low-frequency collector, which collects the total load data of residential users once a second. , total voltage value And the total current value The low-frequency collector is usually equipped with a high-performance analog-to-digital converter (ADC), which can quickly and accurately convert analog signals (such as voltage and current) into digital signals. In addition, the low-frequency collector is also equipped with a software algorithm, and the collected data can be processed by the built-in software algorithm to calculate parameters such as total load, voltage and current. It is worth noting that the low-frequency collector is a mature existing technology and will not be described in detail in this embodiment.
[0026] The calculation formula of the above low-pass filtering algorithm is as follows: In the above formula, The total load data collected , total voltage value Or total current value , is the smoothing coefficient and , For the previous time step of value, is the exponential moving average at the current time point, and is the output sequence after low-pass filtering algorithm processing. In this embodiment, the total load data collected by the low-frequency collector is , total voltage value Or total current value , processed by a low-pass filtering algorithm to independently filter out the total load data , total voltage value Or total current value High frequency noise in the .
[0027] In addition, the calculation formula of the normalization algorithm is as follows: in , the total load data collected by the low-frequency collector , total voltage value And the total current value , respectively, after being processed by the low-pass filtering algorithm and output After subtracting the minimum value of the sequence, the sequence is divided by the difference between the maximum value and the minimum value of the sequence, and normalization is performed to improve the efficiency and stability of neural network training.
[0028] The above Seq2point model includes an input layer, an encoding layer, and an output layer. The normalized data is input into the input layer in the form of a sliding window. The input data in the input layer is The first data matrix of , the encoding layer includes multiple convolutional layers, each convolutional layer includes a ReLU nonlinear activation function, the output layer is a fully connected layer, and the fully connected layer includes a linear activation function. Specifically, the number of convolutional layers is 3, and the convolutional layer includes a padding value, a convolution kernel, and a stride, where the padding value is 0 and the shape of the convolution kernel is , is the height of the convolution kernel, 3 is the width of the convolution kernel, a is the serial number of the convolution kernel, and the number of convolution kernels is 3, and the step length is 1. In this embodiment, the input layer or the convolution layer of the previous serial number inputs the first data matrix to the convolution layer of the next serial number, and then the convolution layer fills the surrounding of the input first data matrix with filling values, so that the first data matrix is expanded to the second data matrix, thereby expanding to The convolution kernel traverses the second data matrix with a step size of 1 to process and obtain a first output matrix. The first output matrix can be input into the convolution layer or the output layer to perform subsequent feature extraction operations through the convolution layer, or output the decomposed data through the output layer.
[0029] Furthermore, the above convolutional layer includes a feature extraction calculation formula, which is as follows: In the above formula, is the first output matrix Line The value of the column element, is the height of the convolution kernel, The width of the convolution kernel, is the second data matrix, is the convolution kernel, , , , are index variables used to traverse the elements of input data, convolution kernels, and output feature maps. Specifically, Indicates that the element is in the second data matrix OK, Indicates that the element is in the second data matrix List, This element is represented by List, This element is represented by List. Represents the first output matrix after processing by the convolutional layer.
[0030] In this embodiment, the decomposed data is The second output matrix, The value of is a preset value, and each column element of the second output matrix can represent the electrical load data of an electrical appliance. , Electrical voltage value , Electrical current value And the working time t. Specifically, The value of is set according to the actual situation. For example, according to the survey structure of multiple households' electricity consumption, it is confirmed to be 60, and the electrical load data of 60 kinds of electrical appliances can be decomposed from the residential electricity consumption. , Electrical voltage value , Electrical current value and the working time t.
[0031] Specifically, step S3 includes a threshold determination algorithm, the threshold determination algorithm includes a threshold matrix, and the threshold matrix includes The first sub-threshold matrix of The second sub-threshold matrix of Each column element of the first sub-threshold matrix is the electrical load data of commonly used electrical appliances , Electrical voltage value And electrical current value And the preset standard value of the working time t, if the electrical load data of the corresponding column of the second output matrix , Electrical voltage value , Electrical current value If one element of the working time t exceeds a preset standard value, it indicates that the commonly used electrical appliance is in an improperly used state; otherwise, it indicates that the commonly used electrical appliance is in a normal state; Each column element of the second sub-threshold matrix is zero. If the electrical load data of the corresponding column of the second output matrix is , Electrical voltage value , Electrical current value If an element in the working time t exceeds zero, it means that the resident has used an appliance that exceeds the line carrying capacity, otherwise, it means that the resident has not used an appliance that exceeds the line carrying capacity. It is worth noting that the above-mentioned preset standard value can be manually set by the user or the power supply management party according to actual usage requirements. Since the threshold judgment algorithm is a mature existing technology, it will not be repeated in this embodiment.
[0032] It is worth noting that: in this embodiment, the actual usage data of several households collected is used as a training set, and the training set includes Group electricity usage behavior information, including The group's electricity usage behavior information does not show that commonly used electrical appliances are used incorrectly or that electrical appliances that exceed the line's carrying capacity are used. The group's electricity usage behavior information shows that common electrical appliances are used incorrectly. The group's electricity usage behavior information shows that the use of electrical appliances exceeds the line's carrying capacity. The group electricity usage behavior information shows that commonly used electrical appliances are used incorrectly, and that electrical appliances that exceed the line carrying capacity are used.
[0033] In this embodiment, the calculation formula of the cross entropy loss function used in training the Seq2point model is as follows: in, is the sample size, For the The true label of each sample (0 or 1), For the first The predicted probability of a sample, It measures the average of the squares of the differences between the predicted values and the true values. The cross entropy loss function is suitable for classification problems.
[0034] In addition, the optimizer formula of stochastic gradient descent is as follows: in, are model parameters, is the learning rate, which controls the step size of parameter update. For the The true value of the samples, For the first The predicted value of samples, Loss Function About parameters The gradient here Indicates samples and their labels.
[0035] The present invention also discloses a safe mains switch control device, which is used to implement the safe mains switch control method as described above, including a box and a PCBA board, the PCBA board is installed in the box, the PCBA board is integrated with a low-frequency collector and a main control chip, the main control chip stores a low-pass filtering algorithm, a normalization processing algorithm, a Seq2point model and a recognition algorithm; the low-frequency collector and the main control chip are electrically connected to one or more residential power buses in turn, wherein the multiple residential power buses are connected in parallel. The PCBA board is also integrated with a communication module, and the communication module is electrically connected to the main control chip. Specifically, the communication module specifically adopts a Bluetooth module and / or a wireless communication module, and the user and the power supply manager can set the preset standard value of the threshold judgment algorithm through the Bluetooth module and / or the wireless communication module.
[0036] When in use, the total load data of residential electricity consumption is collected in real time through a low-frequency collector. , total voltage value Or total current value The low-frequency collector in this embodiment collects data once per second. The total load data collected by the low-frequency collector is , total voltage value Or total current value The information is input into the main control chip to identify whether the residents have used their commonly used electrical appliances incorrectly, or whether they have used electrical appliances that exceed the line carrying capacity. If the judgment result is yes, the electricity connection of the household can be disconnected. If the judgment result is no, the electricity connection of the household is maintained. In the process of electricity use by residents, the electricity use behavior information of the residents is collected in real time, and the electricity use behavior information is analyzed, processed and identified through the low-pass filtering algorithm, normalization processing algorithm, Seq2point model and recognition algorithm stored in the main control chip. When it is judged that the residents have used their commonly used electrical appliances incorrectly, or whether they have used electrical appliances that exceed the line carrying capacity, the electricity connection of the residents can be disconnected, thereby timely and effectively ensuring the safety of residents' electricity use and avoiding the occurrence of high-risk situations that may be caused by residents using electrical appliances that exceed the line carrying capacity or improper use of commonly used electrical appliances.
[0037] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.
Claims
1. A safe mains switch control method, characterized in that: The following steps are involved: Step S1: collect the user's electricity consumption behavior information in real time, perform low-pass filtering algorithm processing on the collected electricity consumption behavior information to remove high-frequency noise, retain the main trend of the data, and perform normalization processing algorithm on the low-pass filtering algorithm to output normalized data; Step S2: input the normalized data into the Seq2point model to decompose and obtain the relevant data of each electrical appliance currently used by a single household, and output the decomposed data; Step S3: The decomposed data is input into the recognition algorithm for processing to determine whether the residents have used electrical appliances that exceed the line carrying capacity, or have used common electrical appliances incorrectly. If the judgment result is yes, the electricity connection for the household can be disconnected. If the judgment result is no, the electricity connection for the household will remain connected.
2. A safe mains switch control method according to claim 1, characterized in that: The electricity consumption behavior information is the total load data , total voltage value And the total current value .
3. A safe mains switch control method according to claim 2, characterized in that: The calculation formula of the low-pass filtering algorithm is as follows: In the above formula, The total load data collected , total voltage value Or total current value , is the smoothing coefficient and , For the previous time step of value, is the exponential moving average of the current time point, and is the output sequence after low-pass filtering algorithm processing.
4. A safe mains switch control method according to claim 1, characterized in that: The Seq2point model includes an input layer, a coding layer and an output layer. The normalized data is input into the input layer in the form of a sliding window. The input data in the input layer is The first data matrix of the encoding layer includes multiple convolutional layers, each of the convolutional layers includes a ReLU nonlinear activation function, the output layer is a fully connected layer, and the fully connected layer includes a linear activation function.
5. A safe mains switch control method according to claim 4, characterized in that: The convolution layer includes a padding value, a convolution kernel, and a step size, the padding value is 0, and the shape of the convolution kernel is , is the height of the convolution kernel, 3 is the width of the convolution kernel, a is the serial number of the convolution kernel, and the step size is 1; Filling values are added around the first data matrix input into the convolutional layer to expand the first data matrix into a second data matrix to expand into The convolution kernel traverses the second data matrix with a step size of 1 to process and obtain a first output matrix, which can be input into a convolution layer or an output layer.
6. A safe mains switch control method according to claim 5, characterized in that: The convolutional layer includes a feature extraction calculation formula, which is as follows: In the above formula, is the first output matrix Line The value of the column element, is the height of the convolution kernel, The width of the convolution kernel, is the second data matrix, is the convolution kernel, , , , Both are index variables used to traverse the elements of input data, convolution kernels, and output feature maps.
7. A safe mains switch control method according to claim 1, characterized in that: The decomposition data is The second output matrix, the The value of is a preset value, and each column element of the second output matrix can represent the electrical load data of an electrical appliance. , Electrical voltage value , Electrical current value and the working time t.
8. A safe mains switch control method according to claim 7, characterized in that: The step S3 includes a threshold determination algorithm, the threshold determination algorithm includes a threshold matrix, the threshold matrix includes: The first sub-threshold matrix of The second sub-threshold matrix of Each column element of the first sub-threshold matrix is the electrical load data of commonly used electrical appliances. , Electrical voltage value And electrical current value And the preset standard value of the working time t, if the electrical load data of the corresponding column of the second output matrix , Electrical voltage value , Electrical current value If one element of the working time t exceeds a preset standard value, it indicates that the commonly used electrical appliance is in an improperly used state; otherwise, it indicates that the commonly used electrical appliance is in a normal state; Each column element of the second sub-threshold matrix is zero. If the electrical load data of the corresponding column of the second output matrix , Electrical voltage value , Electrical current value And if an element in the working time t exceeds zero, it means that the resident has used electrical appliances that exceed the carrying capacity of the line. Otherwise, it means that the resident has not used electrical appliances that exceed the carrying capacity of the line.
9. A safe mains switch control device, used to implement the safe mains switch control method according to any one of claims 1 to 8, characterized in that: It includes a box and a PCBA board, wherein the PCBA board is installed in the box, the PCBA board is integrated with a low-frequency collector and a main control chip, and the main control chip stores a low-pass filtering algorithm, a normalization processing algorithm, a Seq2point model and a recognition algorithm; The low-frequency collector and the main control chip are both electrically connected to one or more residential power buses.
10. A safe mains switch control device according to claim 9, characterized in that: The PCBA board is also integrated with a communication module, and the communication module is electrically connected to the main control chip.