Main Article Content
Cultivation of tomato plant under hydroponics system in the greenhouse is suitable way to improve fruit quality since it is easier to control environmental parameters. In this system, water and nutrition are two important things for plant to growth. In the tropical area such as Indonesia, air temperature is main constraint in the plant production system. Increasing air temperature inside the greenhouse has positive correlation to the raising temperature of nutrient solution which affected to the ability of the plant to absord the nutrition. The effective way to anticipate increasing of its temperature is by using the cooling system of nutrient solution before circulated to the plant. This paper presented the application of Articificial Neural Network (ANN) to estimate the temperature of nutrient solution which was cooled on day-night time and circulated to the plant. ANN models, called time delay neural network, consist of 3 layers with 4 input nodes and 1 output node. As input model were t (time), Tg(i) (air temperature inside the greenhouse on time i), Tt(i) (temperature of nutrient solution in the tank on time i), Tb(i-1) (temperature of nutrient solution in the plant plots on time i-1) and as output model was Tb(i) (temperature of nutrient solution in the plant plots on time i). The model was developed well with validation result better than heat transfer model previously indicated by coefficient determination (R2) of 0.9498.
Keywords: cooling, nutrient solution, hydroponic, tomato, artificial neural network
Diterima: 15 Juni 2010;Disetujui: 30 juli 2010
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).