B. Subathra

S. Sairam, Seshadhri Srinivasan, G. Marafioti et al.

This paper presents an eXplainable Fault Detection and Diagnosis System (XFDDS) for incipient faults in PV panels. The XFDDS is a hybrid approach that combines the model-based and data-driven framework. Model-based FDD for PV panels lacks high fidelity models at low irradiance conditions for detecting incipient faults. To overcome this, a novel irradiance based three diode model (IB3DM) is proposed. It is a nine parameter model that provides higher accuracy even at low irradiance conditions, an important aspect for detecting incipient faults from noise. To exploit PV data, extreme gradient boosting (XGBoost) is used due to its ability to detecting incipient faults. Lack of explainability, feature variability for sample instances, and false alarms are challenges with data-driven FDD methods. These shortcomings are overcome by hybridization of XGBoost and IB3DM, and using eXplainable Artificial Intelligence (XAI) techniques. To combine the XGBoost and IB3DM, a fault-signature metric is proposed that helps reducing false alarms and also trigger an explanation on detecting incipient faults. To provide explainability, an eXplainable Artificial Intelligence (XAI) application is developed. It uses the local interpretable model-agnostic explanations (LIME) framework and provides explanations on classifier outputs for data instances. These explanations help field engineers/technicians for performing troubleshooting and maintenance operations. The proposed XFDDS is illustrated using experiments on different PV technologies and our results demonstrate the perceived benefits.

B. Sreram, Seshadhri Srinivasan, B. Subathra et al.

Networked automation systems (NAS) are characterized by confluence of control, computation, communication and Information (C3I) technologies. Design decisions of one domain are affected by the constraints posed by others. Reliable NAS design should address the requirements of the system, and simultaneously meet the constraints posed by other domains and this is called co-design in literature. Co-design requires clear definition of interfaces among these domains. Control design in NAS is affected by the timing imperfections posed by other domains. In this investigation, we first study the different sources of timing imperfections in NAS, and classify them based on their occurrence. The concept of jitter is used to define the timing imperfections induced by various system components. Using this analysis, we classify the jitter based on their behavior and domain of occurrence. Our analysis shows that the jitter induced in NAS can be classified based on domain as- hardware, software and communication. Next, we use this analysis to model the jitter from the components of NAS. Modeling timing imperfections helps in capturing the interfaces among the domains, and we use the concept of design contracts to capture the interfaces. Design contracts describe the semantic mapping among the domains and are specified using the jitter margins. Implementing design contracts requires knowledge of the jitter margin and, the results from control theory are used to this extent.