Supervised machine learning (ML) has achieved significant outcomes in the industrial domain, dependent on the availability and accuracy of ground truth labels. However, the usual assumption of a ground truth to exist in the data often represents only an idealization of real-world conditions, as data labeling can be subjective and prone to errors, leading to so-called label noise. Such noise can significantly degrade model performance. Although extensive research has identified methods to improve model robustness against label noise, there is a notable absence of generic, reusable frameworks that allow industrial practitioners to systematically assess model robustness. To address this gap, we extend our previous work and propose a model-agnostic framework designed specifically for evaluating robustness against label noise. Our framework incorporates two distinct label noise perturbation mechanisms: an instance-independent symmetric perturber and an instance-dependent one. We demonstrate the utility of our extended framework through empirical evaluations on two industrial datasets using six relevant time series classification methods from the literature. The results highlight the significant vulnerability of supervised ML models to both noise types and underscore the value of our framework in uncovering these robustness limitations.

Alarm floods remain a challenge in industrial operations, potentially overwhelming human operators with excessive alarm notifications during abnormal situations. To address this, alarm flood classification (AFC) methods utilize historical data to classify recurring alarm patterns automatically. However, the practical utility of these methods may be limited by potential degradation in alarm data quality, resulting from sensor faults, communication errors, or detection delays, which can substantially compromise their classification accuracy and reliability. This paper proposes a novel methodology to systematically analyze the robustness of AFC methods against realistic alarm data quality issues. We introduce four distinct perturbations: missing alarms, false alarms, delayed alarm flood detection, and alarm reordering, to replicate real-world alarm data degradation. We evaluate our methodology using a novel alarm dataset derived from the Tennessee-Eastman process, while examining the robustness of six relevant AFC methods from the literature. The results demonstrate significant variations in robustness across different AFC methods and perturbation types, providing insights into their practical reliability under various realistic scenarios.

Being able to pinpoint the type of anomaly goes beyond basic anomaly detection, which simply flags unusual events. It empowers users to gain a deeper understanding of the problem. However, most recognition/classification algorithms struggle with unknown data (Open Set Recognition (OSR) problem), which poses a critical limitation for industrial applications where unforeseen faults can occur. This paper investigates Siamese Neural Networks (SNNs) for recognizing anomalies in industrial time series data. Our use case involves developing an anomaly detection system for power plant operators. We evaluate the effectiveness of SNN s using real data from a power plant in Germany, and two additional public datasets (MaFaulDa and TEP), demonstrating SNN s as a transferable solution for overcoming the OSR problem in the industrial domain.

The performance of machine learning models can be significantly impacted by variations in data quality. Typically, conventional model testing does not examine how robust the model would be in the face of potential data quality deterioration. In an industrial use case, however, data quality is a pertinent issue, as sensors are susceptible to a variety of technical and external issues that may result in poor data quality over time. In order to develop robust machine learning models, industrial data scientists must understand the sensitivity of their models against data quality issues, through the application of an appropriate and comprehensive testing solution. In this work, we propose a generic framework for systematically analyzing the impact of data quality issues on the performance of machine learning models by intentionally applying gradual perturbations to the original time series data. The evaluation is performed using a benchmark industrial process consisting of multivariate time series from sensors in a complex chemical process.

There is growing interest in building and operating industrial plants from standardized modules described by MTP's (Module Type Package). But this new approach brings with it its own set of new challenges. While in the traditional approach of building an industrial plant, one would deal with individual sensors and actuators, this new approach requires, amongst other things, the management of large pools of modules in the engineering and operation phases of a plant. In this contribution, we analyze these new requirements and report on our approach on building a demonstrator to deal with these new issues.

Big Data technologies enable new possibilities to analyze historical data generated by process plants. One possible application is the development of new types of operator support systems (OSS), which could help plant operators during operations in identifying and dealing with critical situations. The project FEE has the objective to develop such support functions based on Big Data analytics of historical plant data. In this contribution we describe our approach to define software architectures for Big Data enabled OSS in industrial plants.

Dispersed data sources, incompatible data formats and a lack of non-ambiguous and machine readable meta-data are major obstacles in data analytics and data mining projects in process industries. Usually, meta-information is only available in unstructured format optimized for human consumption. This contribution captures common problems when handling data from process plants in analytics, develops the vision of a data collection process supported by a search tool, and describe a search tool for the heterogeneous plant data as a proof-of-concept.

Industrial applications from areas like automation, process control, or power controls have a very long-life time up-to 30 years or even more. Supporting applications developed for such life-times cannot rely on the availability of the hardware the application was originally developed on. Especially FPGA families are updated approximately every 12-18th months. This presents a major challenge if functionality in such long-living applications has to be realized on FPGAs (e.g. for performance reasons): How to avoid considerable re-development efforts when replacing obsolete hardware? Concepts for developing portable FPGA applications that can be easily migrated to new hardware are of crucial importance to answer this challenge. In this paper we review and evaluate different approaches for developing portable FPGA applications.