Fault Diagnosis in Intelligent Greenhouse Control with Decomposed Neural Models
نویسندگان
چکیده
The novel approach to the intelligent greenhouse control is based on predictive thermal models and actuator action plans to increase control performance. As operating the actuators essentially changes the thermal dynamics, the overall thermal model is decomposed into sub-models based on the state of the actuators. For the intelligent control it is essential to know the actuator configuration to select the most appropriate sub-model, but unfortunately information available about actuator states is not reliable enough to be directly applicable. This paper proposes a method to detect the difference between the believed and the actual state of the greenhouse and to identify the most likely model for the actual state. The method can be used to support the intelligent control in case of actuator malfunction or other accidents and is also suitable to provide possible reasons of the malfunctions to support the greenhouse personnel to take the necessary repair actions.
منابع مشابه
AN INTELLIGENT FAULT DIAGNOSIS APPROACH FOR GEARS AND BEARINGS BASED ON WAVELET TRANSFORM AS A PREPROCESSOR AND ARTIFICIAL NEURAL NETWORKS
In this paper, a fault diagnosis system based on discrete wavelet transform (DWT) and artificial neural networks (ANNs) is designed to diagnose different types of fault in gears and bearings. DWT is an advanced signal-processing technique for fault detection and identification. Five features of wavelet transform RMS, crest factor, kurtosis, standard deviation and skewness of discrete wavelet co...
متن کاملA Novel Intelligent Fault Diagnosis Approach for Critical Rotating Machinery in the Time-frequency Domain
The rotating machinery is a common class of machinery in the industry. The root cause of faults in the rotating machinery is often faulty rolling element bearings. This paper presents a novel technique using artificial neural network learning for automated diagnosis of localized faults in rolling element bearings. The inputs of this technique are a number of features (harmmean and median), whic...
متن کاملDeveloping A Fault Diagnosis Approach Based On Artificial Neural Network And Self Organization Map For Occurred ADSL Faults
Telecommunication companies have received a great deal of research attention, which have many advantages such as low cost, higher qualification, simple installation and maintenance, and high reliability. However, the using of technical maintenance approaches in Telecommunication companies could improve system reliability and users' satisfaction from Asymmetric digital subscriber line (ADSL) ser...
متن کاملOnline Monitoring and Fault Diagnosis of Multivariate-attribute Process Mean Using Neural Networks and Discriminant Analysis Technique
In some statistical process control applications, the process data are not Normally distributed and characterized by the combination of both variable and attributes quality characteristics. Despite different methods which are proposed separately for monitoring multivariate and multi-attribute processes, only few methods are available in the literature for monitoring multivariate-attribute proce...
متن کاملResearch on Engineering Machinery Fault Diagnosis Based on Neural Network
Because of the product variety and structure complexity of the engineering machinery, it was difficult to meet the requirements of fault detection and maintenance for the traditional diagnosis technologies. In order to improve the diagnostic level, the intelligent control technology of neural network and its application in engineering machinery fault diagnosis were studied. The basic concepts o...
متن کامل