ARM-based device and method for non-intrusive detection of operating status of household appliances
A technology for operating status and household appliances, applied in the field of non-intrusive detection devices for operating status of household appliances based on ARM, can solve problems such as insufficient and effective utilization, and achieve the effects of low cost, low inference delay, and reduced requirements
Active Publication Date: 2021-11-19
HUNAN UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
As the State Grid Corporation of China calls for the establishment of the Ubiquitous Power Internet of Things, after decades of R&D investment and construction, the State Grid has basically met the requirements of the Ubiquitous Internet of Things on the grid side, but in the user terminals of the power grid, nearly 400 million The data generated by smart meters has not been fully and effectively utilized
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0039] An ARM-based non-intrusive detection device for the running state of household appliances, such as figure 1 Shown, comprise PC host computer and the ARM microprocessor target board that is embedded with Linux, described PC host computer is used for operating system and driver program and the detection program after cross compiling are transplanted to target board; Described target board uses It is used to run the running state detection program of household appliances. Specifically, write a program on the PC host computer to read the deep learning algorithm for household appliance operating status detection, cross-compile the program to the target board, then analyze the total power from the multi-function electric energy meter and display the prediction result; design the hardware part, the target board Including Xunwei Samsung quad-core S5P441...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an ARM-based non-invasive detection method for the operating state of household electrical appliances, comprising the following steps: collecting and predicting the power consumption of the electrical appliances, and then marking the operating states of the electrical appliances according to the power consumption; and normalizing the marked data Processing; build the LSTM neural network model, train, optimize and test the LSTM neural network model; build an embedded development cross-compilation environment, and transplant the embedded Linux system; read the total power consumption of the user's home; quantify the LSTM neural network A model that predicts the operating status of household appliances and displays the results. The invention has a good effect on the identification of the operating status of household appliances, and utilizes the tensorflow lite quantization tool to reduce the hardware requirements for performing deep learning reasoning on the ARM, and the quantized model has smaller binary executable files, which can realize Real-time monitoring of the operating status of household appliances at low cost.
Description
technical field [0001] The invention relates to the field of household electricity monitoring, in particular to an ARM-based non-invasive detection device and method for the running state of household appliances. Background technique [0002] With the continuous improvement of people's living standards, the rapid growth of urban and rural electricity consumption has become an important component of the peak load and even the peak load of the power grid, which has brought challenges to the safe operation of the power grid. As the State Grid Corporation of China calls for the establishment of the Ubiquitous Power Internet of Things, after decades of R&D investment and construction, the State Grid has basically met the requirements of the Ubiquitous Internet of Things on the grid side, but in the user terminals of the power grid, nearly 400 million The data generated by smart meters has not been fully and effectively utilized. Using household electricity power data collected b...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B19/042G06N3/04G06N3/08
CPCG05B19/0423G06N3/08G06N3/044G06N3/045
Inventor 王俊年王扬华于文新廖璟刘俊
Owner HUNAN UNIV OF SCI & TECH