A grey neural simulation method for civil buildings with non-artificial cold and heat sources at room temperature is disclosed

A technology of civil architecture and simulation methods, applied in neural learning methods, design optimization/simulation, biological neural network models, etc., can solve problems such as large prediction errors, unstable performance, and regardless of the impact of system development, and achieve improved accuracy , improve the utilization rate, and improve the effect of simulation accuracy

Active Publication Date: 2019-01-25
ZHEJIANG UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

After decades of research, the gray forecasting method has also been continuously improved and improved. The univariate gray forecasting model GM(1,1) is widely used and simple in modeling, but this model does not consider the influence of relevant factors on the development of the system.
The multivariate gray prediction model is represented by GM(1, N), and its modeling process fully considers the influence of relevant factors on the system. However, the traditional GM(1, N) model has unstable performance and strict requirements on the range of data changes. insufficient
Generally speaking, the gray prediction method is simple in modeling and requires a small amount of data. However, if the array contains abnormalities, mutations, or large disturbances, it will have a great adverse effect on the prediction results, resulting in large prediction errors.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A grey neural simulation method for civil buildings with non-artificial cold and heat sources at room temperature is disclosed
  • A grey neural simulation method for civil buildings with non-artificial cold and heat sources at room temperature is disclosed
  • A grey neural simulation method for civil buildings with non-artificial cold and heat sources at room temperature is disclosed

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The present invention will be further described below in conjunction with specific examples, but the present invention is not limited to these specific implementations. Those skilled in the art will realize that the present invention covers all alternatives, modifications and equivalents as may be included within the scope of the claims.

[0077] The present invention combines the optimized multi-variable gray prediction OGM (1, N) model with the BP neural network method, and uses measured data and a typical annual meteorological database as the data basis to develop a simulation for the indoor temperature of civil buildings with non-artificial cold and heat sources. method (OGMBPT for short). The training data of OGMBPT adopts the relevant data measured in accordance with the "Civil Building Indoor Heat and Humidity Environment Evaluation Standard" GBT50785-2012. The simulated meteorological parameter set of OGMBPT uses local typical year outdoor meteorological data c...

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

No PUM Login to view more

Abstract

A grey neural simulation method for civil buildings with non-artificial cold and heat sources at room temperature includes: step 1, collecting and grouping the measured data, step 2, constructing theindoor temperature OGM (1, N) simulation model, step 3, constructing the indoor temperature BP neural network simulation model, and step 4, simulating the indoor temperature OGMBPT and outputting theresult. The invention adopts the combination of the optimized multivariable grey OGM (1, N) simulation model and the BP neural network, groups the measured data and constructs the room temperature OGM(1, N) simulation model respectively, so as to achieve the effect of reducing the influence of the data disturbance on the simulation result. The measured data and the OGM (1, N) simulation results are input into the BP neural network at room temperature to construct the secondary simulation model, and the advantages are complementary, so as to improve the overall simulation accuracy, and the limited measured data are fully utilized to maximize the room temperature law contained in the data.

Description

technical field [0001] The invention belongs to the field of building heat and humidity environment simulation, and in particular relates to a simulation method for gray prediction of indoor temperature of civil buildings with non-artificial cold and heat sources and a neural network. Background technique [0002] Non-artificial cold and heat sources refer to rooms or areas that do not use artificial cold and heat sources, but only use natural adjustment or mechanical ventilation to regulate the heat and humidity environment. The Standard for Evaluation of Indoor Heat and Humidity Environment in Civil Buildings (GBT 50785-2012) provides two methods, calculation method and graphical method, to evaluate the indoor thermal and humid environment of non-artificial cold and heat sources. It is an important indoor heat and humidity environment parameter and an important basis for evaluation. According to the "Civil Building Indoor Thermal and Humid Environment Evaluation Standard"...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50G06N3/08
CPCG06N3/084G06F30/13G06F30/20
Inventor 杨玉兰余贝尔李洋邰惠鑫仲利强张振彦
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products