Conventional fault detection methods in photovoltaic systems face limitations when dealing with emerging monitoring systems that produce vast amounts of high-dimensional data across various domains. Accordingly, great interest appears within the international scientific community for the application of artificial intelligence methods, which are seen as a highly promising solution for effectively managing large datasets for detecting faults. In this review, more than 620 papers published since 2010 on artificial intelligence methods for detecting faults in photovoltaic systems are analyzed. To extract major research trends, in particular to detect most promising algorithms and approaches overcoming excessive time calculations, a conventional bibliographic survey would have been extremely difficult to complete. That is why this study proposes to carry out a review with an innovative approach based on a statistical method named Bibliometric and a Expert qualitative content analysis. This methodology consists of three stages. First, a collection of data from databases is carried out with all precautions to achieve a large, robust, high-quality database. Second, multiple bibliometric indicators are chosen based on the objectives to be achieved and analyzed to assess their real impact, such as the quantity and nature of publications, collaborative connections among organizations, researchers, and countries or most cited articles. Finally, the Expert qualitative content analysis carried out by experts identifies the current and emerging research topics that have the greatest impact on fault detection in photovoltaic systems using artificial intelligence.

Checking the diagnosability of a timed discrete-event system usually consists in determining whether a single fault event can always be identified with certainty after a finite amount of time. The aim of this article is to extend this type of analysis to more complex behaviors, called event patterns, and to propose an effective method to check diagnosability with the use of model-checking techniques. To do so, we propose to convert the pattern diagnosability problem into checking a linear-time property over a specific time Petri net.

Predictive process monitoring is at the intersection of machine learning and process mining. This subfield of process mining leverages historical data generated from process executions to make predictions about the ongoing process. One of the predictive process monitoring tasks with high interest is predicting the remaining cycle time of process instances. Recently, deep neural networks, particularly long short-term memory, have attracted much attention due to their ability to learn relevant features automatically and predict with high accuracy. While these models require data defined in the Euclidean space, graph neural networks have the advantage of handling data that can be represented as graphs. This paper proposes the use of graph neural network models to predict the remaining cycle time, which has not yet been studied in the literature. The proposed models are evaluated on real-life event logs and compared to a state-of-the-art long short-term memory model. The results show that graph neural network models can improve prediction accuracy, particularly for complex processes.