Neural network fault detection and diagnosis in deep-trough hydroponic systems

A system for real-time detection and diagnosis of specific mechanical, sensor and plant (biological) failures is developed. The feedforward neural network methodology is used as the main tool for the development of the fault detection model and its capabilities are explored and validated. In the process of designing the fault detection neural network model, a new technique for neural network designing and training parameterization is developed, based on the heuristic optimization method of genetic algorithms. Furthermore, the ways specific stress situations of the plants influence the root-zone microenvrironment are explored. Sensor and actuator faults are detected and diagnosed in sufficient time that the fault detection model can be applied on-line as a reliable supervisor of the operation of an unattended deep-trough hydroponic system. Biological faults were not detected in general. The only biological fault that was detected was related to the transpiration of the plants. It seems that the interaction between plants and their root-zone microenvironment is not equally balanced, as the condition of the plants is highly influenced by the conditions in their root zone microenvironment, while these microenvironment conditions (as they are represented by the measurable variables) are not influenced in the same degree by the conditions of the plants. Finally, the genetic algorithm system developed here can be successfully applied to a combinatorial problem such as deciding the best neural network architecture, activation functions and training algorithm for a specific model.