Process-Driven and Flow-Based Processing of Industrial Sensor Data

Kammerer, Klaus; Pryss, Rüdiger; Hoppenstedt, Burkhard; Sommer, Kevin; Reichert, Manfred

doi:10.3390/s20185245

Cited by 17 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CPS introduce new approaches, e.g., for condition monitoring or predictive maintenance based on recorded sensor data [5]. Massive amounts of data, different data formats, sampling rates, and data quality are among the challenges that come with using sensor data [9]. Existing works use different types of data for the discovery of events and activities at different levels [2].…”

Section: Related Workmentioning

confidence: 99%

Method to Identify Process Activities by Visualizing Sensor Events

Weyers

Seiger

Weber

2023

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

With the onset of the Internet of Things (IoT) everyday objects suddenly become data sources equipped with sensors measuring the object's properties and surroundings. However, the lack of processawareness in IoT environments (e.g., smart factories) prevents the adoption of more sophisticated process analysis and optimization. One hurdle is the differing abstraction level of low-level sensor data and process-level activities. We propose a method to identify activities step-by-step from raw IoT data using visualizations. By relying on minimal process knowledge, we discover process activities from sensor events. These activities are represented by specific sequences of sensor events-Activity Signatures-that serve as a basis for finding similar activities. We demonstrate the method's validity with a proof of concept in a smart factory.

show abstract

Section: Related Workmentioning

confidence: 99%

Method to Identify Process Activities by Visualizing Sensor Events

Weyers

Seiger

Weber

2023

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

show abstract

“…Event abstraction aims at bridging the gap in the level of detail at which data is recorded and at which it is analyzed [1,34,48]. Especially IoT sensors are capable of producing data at a very fine-grained level [49], which may not be suitable for process mining. Related work proposes to use, e.g., Complex Event Processing (CEP) [2,50], clustering [51], supervised machine learning [4,51,52] or combinations together with expert knowledge [53] to bridge this abstraction gap [54].…”

Section: Process Event Extraction and Abstraction From Iot Datamentioning

confidence: 99%

An Interactive Method for Detection of Process Activity Executions from IoT Data

2023

View full text Add to dashboard Cite

The increasing number of IoT devices equipped with sensors and actuators pervading every domain of everyday life allows for improved automated monitoring and analysis of processes executed in IoT-enabled environments. While sophisticated analysis methods exist to detect specific types of activities from low-level IoT data, a general approach for detecting activity executions that are part of more complex business processes does not exist. Moreover, dedicated information systems to orchestrate or monitor process executions are not available in typical IoT environments. As a consequence, the large corpus of existing process analysis and mining techniques to check and improve process executions cannot be applied. In this work, we develop an interactive method guiding the analysis of low-level IoT data with the goal of detecting higher-level process activity executions. The method is derived following the exploratory data analysis of an IoT data set from a smart factory. We propose analysis steps, sensor-actuator-activity patterns, and the novel concept of activity signatures that are applicable in many IoT domains. The method shows to be valuable for the early stages of IoT data analyses to build a ground truth based on domain knowledge and decisions of the process analyst, which can be used for automated activity detection in later stages.

show abstract

“…With the advent of the fourth industrial revolution, called Industrie 4.0 (I4.0), the domain of industrial automation transforms rapidly due to increased digitization of processes and the ever-increasing amount of available data in production. Leveraging this data to adjust machine parameters and production plants is vital for an efficient and flexible production [ 1 , 2 ].…”

Section: Integration Of Systems and Accessibility Of Data As Prerementioning

confidence: 99%

Model-Driven Approach for Realization of Data Collection Architectures for Cyber-Physical Systems of Systems to Lower Manual Implementation Efforts

Trunzer

Vogel‐Heuser

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

Data collection from distributed automated production systems is one of the main prerequisites to leverage information gain from data analysis in the context of Industrie 4.0, e.g., for the optimization of product quality. However, the realization of data collection architectures is associated with immense implementation efforts due to the heterogeneity of systems, protocols, and interfaces, as well as the multitude of involved disciplines in such projects. Therefore, this paper contributes with an approach for the model-driven generation of data collection architectures to significantly lower manual implementation efforts. Via model transformations, the corresponding source code is automatically generated from formalized models that can be created using a graphical domain-specific language. The automatically generated architecture features support for various established IIoT protocols. In a lab-scale evaluation and a unique generalized extrapolation study, the significant effort savings compared to manual programming could be quantified. In conclusion, the proposed approach can successfully mitigate the current scientific and industrial challenges to enable wide-scale access to industrial data.

show abstract

Process-Driven and Flow-Based Processing of Industrial Sensor Data

Cited by 17 publications

References 34 publications

Method to Identify Process Activities by Visualizing Sensor Events

Method to Identify Process Activities by Visualizing Sensor Events

An Interactive Method for Detection of Process Activity Executions from IoT Data

Model-Driven Approach for Realization of Data Collection Architectures for Cyber-Physical Systems of Systems to Lower Manual Implementation Efforts

Contact Info

Product

Resources

About