Optimal parameter prediction method for multi-model wheat seedling growth chamber based on Kalman filter
A Kalman filter, Kalman filter technology, applied in instruments, simultaneous control of multiple variables, control/regulation systems, etc., can solve problems such as large temperature and humidity ranges
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0056] This embodiment provides a method for predicting optimal parameters of a multi-model wheat seedling growth chamber based on the Kalman filter, see figure 1 , the method includes:
[0057] S1: Collect the temperature, humidity and CO in the growth chamber through the corresponding sensors set in the growth chamber of wheat seedlings 2 Concentration value;
[0058] S2: For temperature, humidity, CO 2 The measured value of the concentration sensor establishes the state equation and observation equation of the Kalman filter system;
[0059] Equation of state:
[0060] x k =AX k-1 +BU k-1 +W k-1 (1)
[0061] Observation equation:
[0062] Z k =HX k +V k (2)
[0063] Among them, X k ,Z k temperature, humidity and CO 2 Concentration predicted value and measured value matrix, A and B are the state parameters connecting k time and k-1 time, U k is a matrix composed of control quantities, W k is the process noise matrix at time k, V k is the observation noise...
Embodiment 2
[0083] The present embodiment provides a method for predicting optimal parameters of a multi-model wheat seedling growth chamber based on a Kalman filter, the method comprising:
[0084] Use corresponding sensors to collect temperature, humidity and CO in the wheat seedling growth chamber 2 concentration;
[0085] First, a certain process noise and measurement noise of the measured value of the sensor are eliminated through the Kalman filter, and then it and other environmental parameters that affect the growth of wheat seedlings include: NaCl concentration, light-to-dark ratio, light cycle, seed weight, etc. Regression (Nonlinear regression, NLR) and multilayer perceptron (Multilayerperceptron, MLP), radial basis function (Radial basis function, RBF) input parameters of the three models to predict the average height and weight of wheat seedlings after a period of growth of wheat seedlings Dry ratio to seed weight. The model with the best fitting effect is selected to predic...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


