Li Ting, Zhang Man, Ji Yuhan, Sha Sha, Jiang Yiqiong, Li Minzan. Management of CO2 in a tomato greenhouse using WSN and BPNN techniques[J]. International Journal of Agricultural and Biological Engineering, 2015, 8(4): 43-51. DOI: 10.3965/j.ijabe.20150804.1572
Citation: Li Ting, Zhang Man, Ji Yuhan, Sha Sha, Jiang Yiqiong, Li Minzan. Management of CO2 in a tomato greenhouse using WSN and BPNN techniques[J]. International Journal of Agricultural and Biological Engineering, 2015, 8(4): 43-51. DOI: 10.3965/j.ijabe.20150804.1572

Management of CO2 in a tomato greenhouse using WSN and BPNN techniques

  • Rational management of CO2 can improve the net photosynthetic rate of plants, thereby improving crop yield and quality. In order to precisely manage CO2 in a greenhouse, a wireless sensor network (WSN) system was developed to monitor greenhouse environmental parameters in real time, including air temperature, humidity, CO2 concentration, soil temperature, soil moisture, and light intensity. The WSN system includes several sensor nodes, a gateway node, and remote management software. The sensor nodes can collect 0-5 V and 4-20 mA analog signals and universal asynchronous receiver/transmitter (UART) data. The gateway node can process and transmit the data and commands between sensor nodes and remote management software. The remote management software provides a friendly interface between user and machine. Users can inquire about real-time data, and set the parameters of the WSN. The photosynthetic rate of tomato plants were studied in the flowering stage. A LI-6400XT portable photosynthesis analyzer was used to measure the photosynthetic rates of the tomato plants, and the environmental parameters of leaves were controlled according to the presetting rule. The photosynthetic rate prediction model of a single leaf was established based on a back propagation neural network (BPNN). The environmental parameters were used as input neurons after being processed by principal component analysis (PCA), and the photosynthetic rate was taken as the output neuron. The performance of the prediction model was evaluated, and the results showed that the correlation coefficient between the simulated and observed data sets was 0.9899, and root-mean-square error (RMSE) was 1.4686. Furthermore, when different CO2 concentrations were selected as the input to predict the photosynthetic rate, the simulated and observed data showed the same trend. According to the above analysis, it was concluded that the model can be used for quantitative regulation of CO2 for tomato plants in greenhouses.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return