Refine
Labor/Institute
Keywords
- Artificial Intelligence (4)
- Fahrerassistenzsystem (4)
- ITS (Intelligent Transportation Systems) (4)
- Prozesssteuerung (4)
- Bayesian Networks (3)
- Künstliche Intelligenz (3)
- OOBN (3)
- Bayes Networks (1)
- DCS (1)
- Fehlererkennung (1)
- Fragebogen (1)
- Lernstil (1)
- Papierindustrie (1)
- Prozessanalyse (1)
- Prozessmodell (1)
- Prozessüberwachung (1)
Document Type
- Conference Proceeding (6)
- Article (3)
- Part of a Book (1)
Language
- English (10)
Has Fulltext
- no (10)
We discuss the use of a hybrid system utilizing Object Oriented Bayesian networks and influence diagrams for probabilistic reasoning under uncertainties in industrial process operations. The Bayesian networks are used for condition monitoring and root cause analysis of process operation. The recommended decision sequence of corrective actions and observations is obtained following the "myopic" approach. The BN inference on most probable root cause is used in an influence diagram for taking decisions on urgency of corrective actions vs. delivery deadline. The build-in chain of causality from root cause to process faults can provide the user with explanation facility and a simulation tool of the effect of intended actions.
Learning Style Classification by Using Bayesian Networks Based on the Index of Learning Style
(2023)
We present an application, where extensions of existing methods for decision-theoretic troubleshooting are used for industrial process operation and asset management. The extension includes expected average cost of asset management actions, prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand.
The increasing complexity of large-scale industrial processes and the struggle for cost reduction and higher profitability means automated systems for processes diagnosis in plant operation and maintenance are required. We have developed a methodology to address this issue and have designed a prototype system on which this methodology has been applied. The methodology integrates decision-theoretic troubleshooting with risk assessment for industrial process control. It is applied to a pulp digesting and screening process. The process is modeled using generic object-oriented Bayesian networks (OOBNs). The system performs reasoning under uncertainty and presents to users corrective actions, with explanations of the root causes. The system records users’ actions with associated cases and the BN models are prepared to perform sequential learning to increase its performance in diagnostics and advice.
Applications of object-oriented Bayesian networks for causal analysis of process disturbances
(2003)
We discuss a hybrid approach for causal analysis of disturbances in industrial process operation. It represents a combination of OOBN with first level diagnostic packages and physical models serving as agents in the system design and providing evidence for automated reasoning on abnormality in process operation. The aim is causal analysis of non-measurable disturbances as a decision advice complement to the distributed control system (DCS). The approach includes prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand. The methodology has been applied on a screening process with a pressure-flow network in a Pulp Mil.
An Object Oriented Bayesian Network for recognition of maneuver in highway traffic has demonstrated an acceptably high recognition performance on a prototype car with a Linux PC having an i7 processor. This paper is focusing on keeping the high recognition performance of the original OOBN, while evaluating alternative modelling techniques and their impact on the memory and time requirements of an ECU-processor for automotive applications. New challenges are faced, when the prediction horizon is to be further extended.
This paper presents a novel application of artificial cognitive systems to traffic scene understanding and early recognition of highway maneuvers. This is achieved by use of Bayesian networks for knowledge representation, to mimic the human reasoning on situation analysis and to manage inherited uncertainties in the automotive domain, that requires efficient and effective analysis of high volume and frequency data streams. The maneuver recognition uses features, analyzing the observed vehicles behavior and available free space on the target lane. Dynamic Bayesian networks (DBN) capture the motion of the own and surrounding vehicles as a dynamic process, following the trend development of lateral motion features. The static and dynamic models for maneuver recognition are statistically evaluated with real highway driving data sequences. The DBN demonstrates earlier recognition (∼ 1.1 seconds) and higher accuracy (1.12% error rate) with more stable performance than the static models. The system is deployed on an experimental vehicle, where a Divide-and-conquer approach to inference in object-oriented Bayesian networks is introduced and its implementation is shown to require computation time of 0.15 milliseconds and ROM memory ∼ 10 2 kilobytes. The promising performance evaluation results are confirmed by test drives in real highway traffic.
We outline the challenges of situation awareness with early and accurate recognition of traffic maneuvers and how to assess them. This includes also an overview of the available data and derived situation features,handling of data uncertainties, modelling and the approach for maneuver recognition. An efficient and effective solution, meeting the automotive requirements, is successfully deployed and tested on a prototype car. Test driving results show that earlier recognition of intended maneuver is feasible on average 1 second (and up to 6.72 s) before the actual lane-marking crossing. The even earlier maneuver recognition is dependent on the earlier recognition of surrounding vehicles.
This paper presents an application of Bayesian networks where early recognition of traffic maneuver intention is achieved using features of lane change, representing the relative dynamics between vehicles on the same lane and the free space to neighbor vehicles back and front on the target lane. The classifiers have been deployed on the automotive target platform, which has severe constraints on time and space performance of the system. The test driving has been performed with encouraging results. Even earlier recognition is possible by considering the trend development of features, characterizing the dynamic driving process. The preliminary test results confirm feasibility.