Artificial intelligence-based method for monitoring the degree of resumption of work and production in enterprises
An artificial intelligence, enterprise technology, applied in neural learning methods, data processing applications, instruments, etc., can solve the problems of energy consumption monitoring, inability to predict the level of resumption of work and production, inability to distinguish energy consumption levels, etc., to improve the effect of training
Active Publication Date: 2020-11-06
STATE GRID ZHEJIANG ELECTRIC POWER +1
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The invention solves the problems that the existing technology can only monitor the current energy consumption, and the energy consumption monitoring during the period of resumption of work and production is relatively weak, and the energy consumption level of various industries cannot be distinguished, and the level of resumption of work and production cannot be further predicted. , to provide an artificial intelligence-based method for monitoring the degree of resumption of work and production, which is conducive to effectively improving the monitoring and prediction capabilities of resumption of work and production
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 1
[0056] An artificial intelligence-based method for monitoring the degree of resumption of work and production of enterprises (see attached figure 1 And attached figure 2 ), including the following steps:
[0057] Step 1: Obtain the historical energy consumption data of enterprises in the target area, and select the historical resumption data from the historical energy consumption data;
[0058] Step 2: Classify the target enterprises for the first time according to the energy consumption type of the target enterprises, and fit the historical resumption data of the target enterprises to form a fitting curve for resumption of work;
[0059] Step 3: Set several typical curves of resumption of work as the cluster centers, select the parameters of the typical curves and the fitted curves as the dimension values, perform cluster analysis according to the Euclidean distance between the dimension values, and determine the cluster centers;
[0060] Step 4, using the parameters of th...
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 present invention involves a monitoring method based on artificial intelligence -based enterprise re -production and re -production. The point of its technical solution is that when the neural network used is trained, the neural network pruning method based on coordinates is used, To maintain a sensitivity score for each layer in the neural network, keep the pruning rate of other layers unchanged. The correct classification rate obtained by the two rounds of network training after the branches is the sensitivity score of the layer;Step 2, pruning the layer with the highest sensitivity score and updating the corresponding sensitivity scores; pruning steps 3, calculate the current pruning rate of the current pruning network, if it meets the requirements of the compression rate, fine -tune the network, then fine -tune the network, Finally get the compressed neural network; otherwise, return the pruning step 2.The invention can effectively improve the accuracy of neural network prediction through the optimization of neural networks, thereby improving the monitoring and predictive ability of re -production and production.
Description
technical field [0001] The invention belongs to a method for monitoring the resumption of work and production of an enterprise, and relates to a method for monitoring the degree of resumption of work and production of an enterprise based on artificial intelligence. Background technique [0002] At the end of 2019, the new crown virus pneumonia caused a large number of enterprises to shut down for a long time. Therefore, for the grid load, the change of the overall energy efficiency of the region is not consistent with the past experience. In the past time period, the large change of the load is often limited to During the long holiday and the period before and after the long holiday, the overall change trend of energy consumption level has been complicated during the resumption of work and production. The monitoring of energy consumption level is closely related to the epidemic situation, resumption of work and production, and production industries. Therefore, the energy cons...
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): G06Q10/06G06N3/08G06K9/62
CPCG06Q10/06G06N3/082G06F18/23213
Inventor 张宏达马亮陈仕军胡若云裘炜浩林森叶方斌欧阳柳
Owner STATE GRID ZHEJIANG ELECTRIC POWER