Fault intensity diagnosis (FID) plays a pivotal role in monitoring and maintaining mechanical devices within complex industrial systems.As current FID methods are based on chain of thought without considering dependencies among target classes.To capture and explore dependencies, we propose a hierarchical knowledge guided fault intensity diagnosis framework (HKG) inspired by the tree of thought, which is amenable to any representation learning methods.The HKG uses graph convolutional networks to map the hierarchical topological graph of class representations into a set of interdependent global hierarchical classifiers, where each node is denoted by word embeddings of a class.These global hierarchical classifiers are applied to learned deep features extracted by representation learning, allowing the entire model to be end-toend learnable.In addition, we develop a re-weighted hierarchical knowledge correlation matrix (Re-HKCM) scheme by embedding inter-class hierarchical knowledge into a data-driven statistical correlation matrix (SCM) which effectively guides the information sharing of nodes in graphical convolutional neural networks and avoids over-smoothing issues.The Re-HKCM is derived from the

Anomalous sound detection (ASD) is one of the most significant tasks of mechanical equipment monitoring and maintaining in complex industrial systems. In practice, it is vital to efficiently identify abnormal status of the working mechanical system, which can further facilitate the failure troubleshooting. In this paper, we propose a multi-pattern adversarial learning one-class classification framework, which allows us to use both the generator and the discriminator of an adversarial model for efficient ASD. The core idea is to learn reconstructing the normal patterns of acoustic data through two different patterns from auto-encoding generators, which succeeds in generalizing the fundamental role of a discriminator from identifying real and fake data to distinguishing between regional and local pattern reconstructions. Moreover, we design a novel balanceable detection strategy using both generators and a discriminator to achieve anomaly detection efficiently. Furthermore, we present a global filter layer for long-term interactions in the frequency domain space, which directly learns from the original data without introducing any human priors. Extensive experiments are performed on four real-world datasets from different industrial domains (three cavitation datasets from SAMSON AG, and one existing publicly) for anomaly detection, all showing superior results and outperform recent state-of-the-art ASD methods.

The behavior of embedded hardware and software systems is determined by at least three dimensions: control flow, data aspects, and real-time requirements. To specify the different dimensions of a system with the best-suited techniques, the formal language CSP-OZ-DC (Hoenicke and Maier, 2005) integrates communicating sequential processes (CSP) (Hoare, 1985), Object-Z (OZ) (Smith, 2000), and duration calculus (DC) (Zhou and Hansen, 2004) into a declarative formalism equipped with a unified and compositional semantics. In this paper, we provide evidence that CSP-OZ-DC is a convenient language for modeling systems of industrial relevance. To this end, we examine the emergency message handling in the European train control system (ETCS) as a case study with uninterpreted constants and infinite data domains. We automatically verify that our model ensures real-time safety properties, which crucially depend on the system's data handling. Related work on ETCS case studies focuses on stochastic examinations of the communication reliability (Hermanns et al., 2005; Zimmermann and Hommel, 2005). The components' data aspects are neglected, though

Abstract Model checking of real-time systems against Duration Calculus (DC) specifications requires the translation of DC formulae into automata-based semantics. The existing algorithms provide a limited DC coverage and do not support compositional verification. We propose a translation algorithm that advances the applicability of model checking tools to realistic applications. Our algorithm significantly extends the subset of DC that can be checked automatically. The central part of the algorithm is the automatic decomposition of DC specifications into sub-properties that can be verified independently. The decomposition is based on a novel distributive law for DC. We implemented the algorithm in a tool chain for the automated verification of systems comprising data, communication, and real-time aspects. We applied the tool chain to verify safety properties in an industrial case study from the European Train Control System (ETCS).