Rapid prediction method for facility agriculture environment factor

A technology of environmental factors and prediction methods, which is applied in the field of rapid prediction of environmental factors of facility agriculture and the field of rapid prediction of facility agricultural meteorological factors based on a single hidden layer model, which can solve the problem of easily falling into local minimum point learning rate and slow neural network training. , application limitations and other problems, to overcome the complexity of calculation and even difficult to achieve, solve the effect of slow training speed and fast training speed
CN104200282AInactive Publication Date: 2014-12-10NANJING UNIV OF INFORMATION SCI & TECH
1 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING UNIV OF INFORMATION SCI & TECH
Publication Date
2014-12-10
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a rapid prediction method for a facility agriculture environment factor. The rapid prediction method comprises the following steps of: selecting a training sample according to historical sample data, generating a training set and a test set, and carrying out normalization processing on training sample data in the training set and the test set; establishing a single-hidden layer extreme learning machine prediction model to obtain trained parameters; testing by virtue of the single-hidden layer extreme learning machine prediction model, and evaluating the predication value of the test set according to the obtained trained parameters; carrying out error calculation on the predicated value and the actually-measured value of the test set, and evaluating the generalization ability of the single-hidden layer extreme learning machine prediction model. According to the rapid prediction method disclosed by the invention, the defect that the traditional mechanism modelling calculation is complex and even if difficult to realize is overcome, the training speed is fast, the globally optimal solution can be acquired, the defects of low training speed, liability to fall into a local minimum point, and the like in the prior art are solved, and the training speed is greatly increased on the basis of keeping the model accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention discloses a method for rapidly predicting environmental factors of facility agriculture, in particular to a method for rapidly predicting meteorological factors of facility agriculture based on a single hidden layer model, and relates to the field of forecasting environment factors of facility agriculture. Background technique

[0002] Facility agriculture is a comprehensive application of engineering equipment technology, biotechnology and environmental technology. According to the environmental conditions required for crop growth and development, it provides a relatively controllable or even the most suitable environment such as temperature and humidity, and to a certain extent gets rid of the dependence on the natural environment. productive agriculture. To achieve a high level of facility agricultural production and optimize facility biological environment control, it is necessary to predict the environmental factors of facility agric...

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