This work focuses on the use of information concerning expertise through intelligent systems applied in the industrial domain. With the emergence of Industry 4.0, a revolutionary era of data digitization has unfolded, allowing for real-time capture of discrete event sequences that encompass various aspects such as failures, deviations from normal performance, and optimal behavior. In this context, the utilization of V-nets as a powerful tool for diagnostic analysis is explored, leveraging their formalism to construct temporal patterns that reveal the true energy performance capabilities of scalable computing systems. While empirical testing on specific systems is currently lacking, the remarkable significance of this innovative formalism becomes evident, offering numerous advantages, including the identification of simultaneous events, detection of partial event sequences, and discernment of false positives. This research pushes the boundaries of knowledge and optimization in scalable computing systems within the realm of Industry 4.0, effectively bridging the gap between theoretical analysis and practical applications. Furthermore, it boldly asserts that the experimental success observed in smaller systems can confidently be extended to larger machines and parallel computing systems, opening pathways to transformative advancements.