Currently, detecting and isolating faults in hybrid systems is often done manually with the help of human operators. In this paper we present a novel model-based diagnosis approach for automatically diagnosing hybrid systems. The approach has two parts: First, modelling dynamic system behaviour is done through well-known state space models using differential equations. Second, from the state space models we calculate Boolean residuals through an observer-pattern. The novelty lies in implementing the observer pattern through the use of a symbolic system description specified in satisfiability theory modulo linear arithmetic. With this, we create a static situation for the diagnosis algorithm and decouple modelling and diagnosis. Evaluating the system description generates one Boolean residual for each component. These residuals constitute the fault symptoms. To find the minimum cardinality diagnosis from these symptoms we employ Reiter’s diagnosis lattice.For the experimental evaluation we use a simulation of the Tennessee Eastman process and a simulation of a four-tank model. We show that the presented approach is able to identify all injected faults.

Cyber-Physical Systems (CPS) are systems that connect physical components with software components. CPS used for production are called Cyber-Physical Production Systems (CPPS). Since the complexity of these systems can be very high, finding the cause of an error takes a lot of effort. In this paper, a data-driven approach to identify causal dependencies in cyber-physical production systems (CPPS) is presented. The approach is based on two different layers of learning algorithms: one low-level layer that processes the direct machine data and a higher-level learning layer that processes the output of the low-level layer. The low-level layer is based on different learning modules that can process differently typed data (continuous, discrete or both). The high-level learning algorithms are based on rule-based and case-based reasoning. Thus, causal dependencies are detected allowing the plant operator to find the error cause quickly.

Computer-aided assistance systems are entering the world of work and production. Such systems utilize augmented- and virtual-reality for operator training and live guidance as well as mobile maintenance and support. This is particularly important in the modern production reality of ever-changing products and `lot size one' customization of production.This paper focuses on the application of machine learning approach to extend the functionality of assistance systems. Machine learning provides tools to analyse large amounts of data and extract meaningful information. The goal here is to recognize the movement of an operator which would enable automatic display of instructions relevant to them.We present the challenges facing machine learning applications in human-centered assistance systems and a framework to assess machine learning approaches feasible for this scenario. The approach is assessed on a historical data set and then deployed in a work station for live testing. The post-hoc, or historical, analysis yields promising results. The ad-hoc, or live, analysis is a complex task and the results are affected by multiple factors, most of which are introduced by the human influence.The contribution of this paper is an approach to adapt state- of-the-art machine learning to operator movement recognition with a special focus on approaches to spatial time series data pre-processing. Presented experiment results validate the approach and show that it performs well in a real-world scenario.

Outlier detection is one of the most widely used technique to identify abnormal behavior in raw data. The sense of abnormal deviation mentioned here accounts not only for human made or system errors that naturally occur as part of the data but also as seldomly occuring events. In this paper, we propose a new algorithm called Grid Based Outlier Detection (GBOD) to find the hidden outliers in large data sets. In contrast to existing grid based methods which are limited to only some statistical based approaches, the GBOD algorithm is raised with two alternations to figure out different range of outliers depending on the interest of the user. First, the number of points in a local grid cell is used to decide whether a point is an outlier or not. In a second step, this approach is extended to method that assigns an outlier score to each data point. The simple design makes this algorithm extremely efficient for large data sets.

Modern combine harvesters often stay beyond their theoretic optimal performance during harvesting operations. Explanations and remedies for this reduced efficiency are difficult to find, as the actual performance is influenced by a variety of different parameters. This paper presents a continuous analysis of machine-provided data streams in order to assess potential reasons (i.e. anomalies) and to identify suggestions for optimization. To this end, new sensor data-based machine learning algorithms are being developed, applied and evaluated.

Model-based approaches are very often used for diagnosis in production systems. And since the manual creation of behavior models is a tough task, many learning algorithms have been constructed for the automatic model identification. Most of them are tested and evaluated on artificial datasets on personal computers only. However, the implementation on cyber-physical production systems puts additional requirements on learning algorithms, for instance the real-time aspect or the usage of memory space. This paper analyzes the requirements on learning algorithms for cyber-physical production systems and presents an appropriate online learning algorithm, the Online Timed Automaton Learning Algorithm, OTALA. It is the first online passive learning algorithm for timed automata which in addition copes without negative learning examples. An analysis of the algorithm and comparison with offline learning algorithms completes this contribution.

A tailored model of a system is the prerequisite for various analysis tasks, such as anomaly detection, fault identification, or quality assurance. This paper deals with the algorithmic learning of a system’s behavior model given a sample of observations. In particular, we consider real-world production plants where the learned model must capture timing behavior, dependencies between system variables, as well as mode switches—in short: hybrid system’s characteristics. Usually, such model formation tasks are solved by human engineers, entailing the well-known bunch of problems including knowledge acquisition, development cost, or lack of experience. Our contributions to the outlined field are as follows. (1) We present a taxonomy of learning problems related to model formation tasks. As a result, an important open learning problem for the domain of production system is identified: The learning of hybrid timed automata. (2) For this class of models, the learning algorithm HyBUTLA is presented. This algorithm is the first of its kind to solve the underlying model formation problem at scalable precision. (3) We present two case studies that illustrate the usability of this approach in realistic settings. (4) We give a proof for the learning and runtime properties of HyBUTLA.

This paper presents a novel approach for data acquisition in distributed, heterogeneous automation systems as a basis for new condition monitoring, anomaly detection and visualization applications. The described solution enables process data acquisition in real time Ethernet systems, using the Precision Time Protocol (PTP) from IEEE 1588 for synchronization and the OPC Unified Architecture for data presentation. As a proof of concept the architecture is implemented using standard hardware components and a x86/x64 architecture without any special operating system. As verified later this setup already achieves a synchronization accuracy of <;10ms, sufficient for the majority of production processes to be monitored.

This paper presents a novel model-based approach for the prediction of energy consumption in production plants in order to detect anomalies. A special Ethernet-based data acquisition approach is implemented that features real-time sampling of process and energy data. Hybrid timed automaton models of the supervised production plant are generated and executed in parallel to the system by using data samples as model input. According to comparisons of predicted energy consumption with the production plant observations, anomalies can be detected automatically. An evaluation within a small factory shows that anomalies of 10 % differences in energy consumption, wrong control sequences and wrong timings can be detected with a minimum accuracy of 98 %. With this approach, downtimes of production systems can be shortened and atypical energy consumptions can be detected and adjusted to optimal operation.

The increasing complexity of today's production systems and the variety of model-based approaches to their monitoring, diagnosis and testing emphasize the importance of the modeling step. Modeling is mostly done manually, in a costly and time-consuming way. In this paper, an alternative that comes from the learning theory is given: an automated procedure for identifying behavior models from recorded observations. Assuming the system's structure is known, the algorithm presented here is capable of learning behavior models for its components. The algorithm accounts for probabilistic, timing, discrete and continuous aspects of the given system, using the modeling formalism of hybrid automata. The practical usability of identified models is demonstrated using an anomaly detection application for a real production system.

The study of the neuronal correlates of the spontaneous alternation in perception elicited by bistable visual stimuli is promising for understanding the mechanism of neural information processing and the neural basis of visual perception and perceptual decision-making. In this paper we apply a sparse nonnegative tensor factorization (NTF) based method to extract features from the local field potential (LFP) in monkey visual cortex for decoding its bistable structure-from-motion (SFM) perception. We apply the feature extraction approach to the multichannel time-frequency representation of intracortical LFP data collected from the middle temporal area (MT) in a macaque monkey performing a SFM task. The advantages of the sparse NTF based feature extraction approach lies in its capability to yield components common across the space, time and frequency domains and at the same time discriminative across different conditions without prior knowledge of the discriminative frequency bands and temporal windows for a specific subject. We employ the support vector machines (SVM) classifier based on the features of the NTF components to decode the reported perception on a single-trial basis. Our results suggest that although other bands also have certain discriminability, the gamma band feature carries the most discriminative information for bistable perception, and that imposing the sparseness constraints on the nonnegative tensor factorization improves extraction of this feature.

This paper aims to understand how the discriminative information of neuronal population activity evolves and accumulates over time. We present two classes of approaches namely the probability-based and response-based approaches to predict the perceptual reports of a trained macaque monkey on a single-trial basis by integrating neural signals from multiple electrodes across time. We extend the probability-based integration originally using only the quadratic discriminant analysis (QDA) by considering also the linear discriminant analysis (LDA) and logistic regression methods. Furthermore, we introduce the response-based integration for the QDA, LDA and logistic regression methods. Experimental examples demonstrate the effectiveness of these approaches for determining the perceptual state of a brain under study by integrating its localized spatiotemporal neuronal activity.