https://www.mdu.se/

mdu.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 15) Show all publications
Andersson, T., Bohlin, M., Ahlskog, M. & Olsson, T. (2024). Interpretable ML model for quality control of locks using counterfactual explanations. In: : . Paper presented at 2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024). , Article ID 7.
Open this publication in new window or tab >>Interpretable ML model for quality control of locks using counterfactual explanations
2024 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an interpretable machinelearning model for anomaly detection in door locks using torque data. The model aims to replace the human tactile sense in the quality control process, reducing repetitive tasks and improving reliability. The model achieved an accuracy of 96%, however, to gain social acceptance and operators' trust, interpretability of the model is crucial. The purpose of this study was to evaluate anapproach that can improve interpretability of anomalousclassifications obtained from an anomaly detection model. Weevaluate four instance-based counterfactual explanators, three of which, employ optimization techniques and one uses, a less complex, weighted nearest neighbor approach, which serve as ourbaseline. The former approaches, leverage a latent representation of the data, using a weighted principal component analysis, improving plausibility of the counter factual explanations andreduces computational cost. The explanations are presentedtogether with the 5-50-95th percentile range of the training data, acting as a frame of reference to improve interpretability. All approaches successfully presented valid and plausible counterfactual explanations. However, instance-based approachesemploying optimization techniques yielded explanations withgreater similarity to the observations and was therefore concluded to be preferable despite the higher execution times (4-16s) compared to the baseline approach (0.1s). The findings of this study hold significant value for the lock industry and can potentially be extended to other industrial settings using timeseries data, serving as a valuable point of departure for further research.

Keywords
—Explainable artificial intelligence, Counterfactual explanation, Anomaly detection, Principal component analysis
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-66503 (URN)
Conference
2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024)
Funder
Knowledge Foundation, No 20200132 01 H
Note

In press

Available from: 2024-04-24 Created: 2024-04-24 Last updated: 2024-04-26Bibliographically approved
Andersson, T., Bohlin, M., Ahlskog, M. & Olsson, T. (2024). Interpretable ML model for quality control of locks using counterfactual explanations. In: : . Paper presented at 2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024). , Article ID 7.
Open this publication in new window or tab >>Interpretable ML model for quality control of locks using counterfactual explanations
2024 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an interpretable machinelearning model for anomaly detection in door locks using torque data. The model aims to replace the human tactile sense in the quality control process, reducing repetitive tasks and improving reliability. The model achieved an accuracy of 96%, however, to gain social acceptance and operators' trust, interpretability of the model is crucial. The purpose of this study was to evaluate anapproach that can improve interpretability of anomalousclassifications obtained from an anomaly detection model. Weevaluate four instance-based counterfactual explanators, three of which, employ optimization techniques and one uses, a less complex, weighted nearest neighbor approach, which serve as ourbaseline. The former approaches, leverage a latent representation of the data, using a weighted principal component analysis, improving plausibility of the counter factual explanations andreduces computational cost. The explanations are presentedtogether with the 5-50-95th percentile range of the training data, acting as a frame of reference to improve interpretability. All approaches successfully presented valid and plausible counterfactual explanations. However, instance-based approachesemploying optimization techniques yielded explanations withgreater similarity to the observations and was therefore concluded to be preferable despite the higher execution times (4-16s) compared to the baseline approach (0.1s). The findings of this study hold significant value for the lock industry and can potentially be extended to other industrial settings using timeseries data, serving as a valuable point of departure for further research.

Keywords
—Explainable artificial intelligence, Counterfactual explanation, Anomaly detection, Principal component analysis
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-66504 (URN)
Conference
2024 8th International Conference on Artificial Intelli-gence, Automation and Control Technologies (AIACT 2024)
Funder
Knowledge Foundation, No 20200132 01 H
Note

In press

Available from: 2024-04-24 Created: 2024-04-24 Last updated: 2024-04-26Bibliographically approved
Andersson, T., Bohlin, M., Olsson, T. & Ahlskog, M. (2022). Comparison of Machine Learning’s- and Humans’- Ability to Consistently Classify Anomalies in Cylinder Locks. In: IFIP Advances in Information and Communication Technology: WG 5.7 International Conference on Advances in Production Management Systems, APMS 2022. Paper presented at WG 5.7 International Conference on Advances in Production Management Systems, APMS 2022, Gyenongju, South Korea, 25-29 September, 2022 (pp. 27-34). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>Comparison of Machine Learning’s- and Humans’- Ability to Consistently Classify Anomalies in Cylinder Locks
2022 (English)In: IFIP Advances in Information and Communication Technology: WG 5.7 International Conference on Advances in Production Management Systems, APMS 2022, Springer Science and Business Media Deutschland GmbH , 2022, p. 27-34Conference paper, Published paper (Refereed)
Abstract [en]

Historically, cylinder locks’ quality has been tested manually by human operators after full assembly. The frequency and the characteristics of the testing procedure for these locks wear the operators’ wrists and lead to varying results of the quality control. The consistency in the quality control is an important factor for the expected lifetime of the locks which is why the industry seeks an automated solution. This study evaluates how consistently the operators can classify a collection of locks, using their tactile sense, compared to a more objective approach, using torque measurements and Machine Learning (ML). These locks were deliberately chosen because they are prone to get inconsistent classifications, which means that there is no ground truth of how to classify them. The ML algorithms were therefore evaluated with two different labeling approaches, one based on the results from the operators, using their tactile sense to classify into ‘working’ or ‘faulty’ locks, and a second approach by letting an unsupervised learner create two clusters of the data which were then labeled by an expert using visual inspection of the torque diagrams. The results show that an ML-solution, trained with the second approach, can classify mechanical anomalies, based on torque data, more consistently compared to operators, using their tactile sense. These findings are a crucial milestone for the further development of a fully automated test procedure that has the potential to increase the reliability of the quality control and remove an injury-prone task from the operators.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2022
Keywords
Binary classification, Cylinder lock, Machine learning, Multiple experts, Torque data, Cylinders (shapes), Learning algorithms, Quality assurance, Quality control, Torque, Expected lifetime, Human abilities, Human operator, Machine-learning, Multiple expert, Tactile sense, Testing procedure, Locks (fasteners)
National Category
Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-60550 (URN)10.1007/978-3-031-16407-1_4 (DOI)000869718800004 ()2-s2.0-85140472723 (Scopus ID)9783031164064 (ISBN)
Conference
WG 5.7 International Conference on Advances in Production Management Systems, APMS 2022, Gyenongju, South Korea, 25-29 September, 2022
Available from: 2022-11-03 Created: 2022-11-03 Last updated: 2024-04-26Bibliographically approved
Ramentol, E., Olsson, T. & Barua, S. (2021). Machine Learning Models for Industrial Applications. In: Konstantinos Kyprianidis and Erik Dahlquist (Ed.), AI and Learning Systems: . IntechOpen
Open this publication in new window or tab >>Machine Learning Models for Industrial Applications
2021 (English)In: AI and Learning Systems / [ed] Konstantinos Kyprianidis and Erik Dahlquist, IntechOpen , 2021Chapter in book (Refereed)
Abstract [en]

More and more industries are aspiring to achieve a successful production using the known artificial intelligence. Machine learning (ML) stands as a powerful tool for making very accurate predictions, concept classification, intelligent control, maintenance predictions, and even fault and anomaly detection in real time. The use of machine learning models in industry means an increase in efficiency: energy savings, human resources efficiency, increase in product quality, decrease in environmental pollution, and many other advantages. In this chapter, we will present two industrial applications of machine learning. In all cases we achieve interesting results that in practice can be translated as an increase in production efficiency. The solutions described cover areas such as prediction of production quality in an oil and gas refinery and predictive maintenance for micro gas turbines. The results of the experiments carried out show the viability of the solutions.

Place, publisher, year, edition, pages
IntechOpen, 2021
Keywords
Machine learning, Prediction, Regression methods, Maintenance, Degradation prediction
National Category
Engineering and Technology Computer Systems
Identifiers
urn:nbn:se:mdh:diva-53974 (URN)10.5772/intechopen.93043 (DOI)978-1-78985-878-5 (ISBN)978-1-78985-877-8 (ISBN)
Available from: 2021-04-22 Created: 2021-04-22 Last updated: 2021-09-02Bibliographically approved
Aslanidou, I., Zaccaria, V., Rahman, M., Oostveen, M., Olsson, T. & Kyprianidis, K. (2018). Towards an Integrated Approach for Micro Gas Turbine Fleet Monitoring, Control and Diagnostics. In: : . Paper presented at Global Power and Propulsion Forum 2018, Zurich, Switzerland.
Open this publication in new window or tab >>Towards an Integrated Approach for Micro Gas Turbine Fleet Monitoring, Control and Diagnostics
Show others...
2018 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Real-time engine condition monitoring and fault diagnostics results in reduced operating and maintenance costs and increased component and engine life. Prediction of faults can change the maintenance model of a system from a fixed maintenance interval to a condition based maintenance interval, further decreasing the total cost of ownership of a system. Technologies developed for engine health monitoring and advanced diagnostic capabilities are generally developed for larger gas turbines, and generally focus on a single system; no solutions are publicly available for engine fleets. This paper presents a concept for fleet monitoring finely tuned to the specific needs of micro gas turbines. The proposed framework includes a physics-based model and a data-driven model with machine learning capabilities for predicting system behaviour, combined with a diagnostic tool for anomaly detection and classification. The integrated system will develop advanced diagnostics and condition monitoring for gas turbines with a power output under 100 kW.

National Category
Aerospace Engineering
Research subject
Energy- and Environmental Engineering
Identifiers
urn:nbn:se:mdh:diva-43169 (URN)
Conference
Global Power and Propulsion Forum 2018, Zurich, Switzerland
Available from: 2019-04-21 Created: 2019-04-21 Last updated: 2020-10-22Bibliographically approved
Olsson, T. (2015). A Data-Driven Approach to Remote Fault Diagnosis of Heavy-duty Machines. (Doctoral dissertation). Västerås: Mälardalen University
Open this publication in new window or tab >>A Data-Driven Approach to Remote Fault Diagnosis of Heavy-duty Machines
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Heavy-duty machines are equipment constructed for working under rough conditions and their design is meant to withstand heavy workloads. However, the last decades technical development in cheap electronically components have lead to an increase of electrical systems in traditionally mainly mechanical systems of heavy-duty machines. As the complexity of these machines increases, so does the complexity of detecting and diagnosing machine faults. However, the addition of new electrical systems, such as on-board computational power and telematics, makes it possible to add new sensors that measure signals relevant for fault detection and diagnosis, and to process signals on-board or off-board the machines.

In this thesis, we address the diagnostic problem by investigating data-driven methods for remote diagnosis of heavy-duty machines, where a part of the analysis is performed on-board the machine (fault detection), while another part is performed off-board the machine (fault classification). We propose a diagnostic framework where we use a novel combination of methods for each step in the diagnosis. On-board the machine, we have used logistic regression as an anomaly detector to detect faults that will lead to a stream of individual cases classified as anomalous or not. Then, either on-board or off-board, we can use a probabilistic anomaly detector to identify whether the stream of cases is truly anomalous when we look at the stream of cases as a group. The anomalous group of cases is called a composite case. Thereafter, off-board the machine, each anomalous individual case is classified into a fault type using a case-based reasoning approach to fault diagnosis. In the final step, we fuse the individual classifications into a single aggregated classification for the composite case. In order to be able to assess the reliability of a diagnosis, we also propose a novel case-based approach to estimating the reliability of probabilistic predictions. It can, for instance, be used for assessing the confidence of the classification of a composite case given historical data of the predictive reliability.

Place, publisher, year, edition, pages
Västerås: Mälardalen University, 2015
Series
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 189
Series
SICS Dissertation Series, ISSN 1101-1335 ; 73
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-29097 (URN)978-91-7485-234-9 (ISBN)
Public defence
2015-11-10, Omega, Mälardalens högskola, Västerås, 14:00 (English)
Opponent
Supervisors
Available from: 2015-09-22 Created: 2015-09-22 Last updated: 2018-01-11Bibliographically approved
Olsson, T. & Holst, A. (2015). A Probabilistic Approach to Aggregating Anomalies for Unsupervised Anomaly Detection with Industrial Applications. In: Proceedings of the Twenty-Eighth International Florida Artificial Intelligence Research Society Conference: . Paper presented at The 28th International FLAIRS Conference Flairs-28, 18 May 2015, Hollywood, Florida, United States (pp. 434-439). Hollywood, Florida, United States: AAAI
Open this publication in new window or tab >>A Probabilistic Approach to Aggregating Anomalies for Unsupervised Anomaly Detection with Industrial Applications
2015 (English)In: Proceedings of the Twenty-Eighth International Florida Artificial Intelligence Research Society Conference, Hollywood, Florida, United States: AAAI , 2015, p. 434-439Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a novel, unsupervised approach to detecting anomalies at the collective level. The method probabilistically aggregates the contribution of the individual anomalies in order to detect significantly anomalous groups of cases. The approach is unsupervised in that as only input, it uses a list of cases ranked according to its individual anomaly score. Thus, any anomaly detection algorithm can be used for scoring individual anomalies, both supervised and unsupervised approaches. The applicability of the proposed approach is shown by applying it to an artificial data set and to two industrial data sets — detecting anomalously moving cranes (model-based detection) and anomalous fuel consumption (neighbour-based detection).

Place, publisher, year, edition, pages
Hollywood, Florida, United States: AAAI, 2015
Keywords
Anomaly Detection, Anomaly Aggregation, Collective Anomaly, Group Anomaly
National Category
Engineering and Technology Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-28160 (URN)
Conference
The 28th International FLAIRS Conference Flairs-28, 18 May 2015, Hollywood, Florida, United States
Projects
ITS-EASY Post Graduate School for Embedded Software and Systems
Available from: 2015-06-08 Created: 2015-06-08 Last updated: 2018-01-11Bibliographically approved
Olsson, T., Xiong, N., Källström, E., Holst, A. & Funk, P. (2015). Fault Diagnosis via Fusion of Information from a Case Stream. In: Case-Based Reasoning Research and Development. Proceeding of the the 23th International Conference on Case-Based Reasoning (ICCBR-2015): . Paper presented at 23th International Conference on Case-Based Reasoning (ICCBR-2015), 28th September-30th September 2015, Frankfurt am Main, Germany (pp. 275-289).
Open this publication in new window or tab >>Fault Diagnosis via Fusion of Information from a Case Stream
Show others...
2015 (English)In: Case-Based Reasoning Research and Development. Proceeding of the the 23th International Conference on Case-Based Reasoning (ICCBR-2015), 2015, p. 275-289Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a novel approach to fault diagnosis applied to a stream of cases. The approach uses a combination of case-based reasoning and information fusion to do classification. The approach consists of two steps. First, we perform local anomaly detection on-board a machine to identify anomalous individual cases. Then, we monitor the stream of anomalous cases using a stream anomaly detector based on a sliding window approach. When the stream anomaly detector identifies an anomalous window, the anomalous cases in the window are classified using a CBR classifier. Thereafter, the individual classifications are aggregated into a composite case with a single prediction using a information fusion method. We compare three information fusion approaches: simple majority vote, weighted majority vote and Dempster-Shafer fusion. As baseline for comparison, we use the classification of the last identified anomalous case in the window as the aggregated prediction.

Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9343
Series
Lecture Notes in Artificial Intelligence
Keywords
Case-based Reasoning, Information Fusion, Anomaly Detection, Fault Diagnosis
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-29085 (URN)10.1007/978-3-319-24586-7_19 (DOI)000367594000019 ()2-s2.0-84952023366 (Scopus ID)978-3-319-24585-0 (ISBN)
Conference
23th International Conference on Case-Based Reasoning (ICCBR-2015), 28th September-30th September 2015, Frankfurt am Main, Germany
Available from: 2015-09-22 Created: 2015-09-22 Last updated: 2018-01-11Bibliographically approved
Olsson, T., Gillblad, D., Funk, P. & Xiong, N. (2014). Case-Based Reasoning for Explaining Probabilistic Machine Learning. International Journal of Computer Science & Information Technology (IJCSIT), 6(2), 87-101
Open this publication in new window or tab >>Case-Based Reasoning for Explaining Probabilistic Machine Learning
2014 (English)In: International Journal of Computer Science & Information Technology (IJCSIT), ISSN 0975-4660, E-ISSN 0975-3826, Vol. 6, no 2, p. 87-101Article in journal (Refereed) Published
Abstract [en]

This paper describes a generic framework for explaining the prediction of probabilistic machine learning algorithms using cases. The framework consists of two components: a similarity metric between cases that is defined relative to a probability model and an novel case-based approach to justifying the probabilistic prediction by estimating the prediction error using case-based reasoning. As basis for deriving similarity metrics, we define similarity in terms of the principle of interchangeability that two cases are considered similar or identical if two probability distributions, derived from excluding either one or the other case in the case base, are identical. Lastly, we show the applicability of the proposed approach by deriving a metric for linear regression, and apply the proposed approach for explaining predictions of the energy performance of households.

Keywords
Case-based Reasoning, Case-based Explanation, Artificial Intelligence, Decision Support, Machine Learning
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-26442 (URN)10.5121/ijcsit (DOI)
Projects
ITS-EASY Post Graduate School for Embedded Software and SystemsCREATE ITEA2
Available from: 2014-10-31 Created: 2014-10-31 Last updated: 2017-12-05Bibliographically approved
Olsson, T., Gillblad, D., Funk, P. & Xiong, N. (2014). Explaining probabilistic fault diagnosis and classification using case-based reasoning. In: Case-Based Reasoning Research and Development: 22nd International Conference, ICCBR 2014, Cork, Ireland, September 29, 2014 - October 1, 2014. Proceedings. Paper presented at 22nd International Conference, ICCBR 2014, Cork, Ireland, September 29, 2014 - October 1, 2014. (pp. 360-374).
Open this publication in new window or tab >>Explaining probabilistic fault diagnosis and classification using case-based reasoning
2014 (English)In: Case-Based Reasoning Research and Development: 22nd International Conference, ICCBR 2014, Cork, Ireland, September 29, 2014 - October 1, 2014. Proceedings, 2014, p. 360-374Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes a generic framework for explaining the prediction of a probabilistic classifier using preceding cases. Within the framework, we derive similarity metrics that relate the similarity between two cases to a probability model and propose a novel case-based approach to justifying a classification using the local accuracy of the most similar cases as a confidence measure. As a basis for deriving similarity metrics, we define similarity in terms of the principle of interchangeability that two cases are considered similar or identical if two probability distributions, derived from excluding either one or the other case in the case base, are identical. Thereafter, we evaluate the proposed approach for explaining the probabilistic classification of faults by logistic regression. We show that with the proposed approach, it is possible to find cases for which the used classifier accuracy is very low and uncertain, even though the predicted class has high probability.

Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 8765
Keywords
Case-based Explanation, Classification, Machine Learning, Artificial intelligence, Classification (of information), Computer aided diagnosis, Fault detection, Learning systems, Probability, Probability distributions, Case based, Case-based approach, Logistic regressions, Probabilistic classification, Probabilistic classifiers, Probabilistic fault diagnosis, Probability modeling, Similarity metrics, Case based reasoning
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:mdh:diva-27478 (URN)2-s2.0-84921634116 (Scopus ID)978-3-319-11208-4 (ISBN)978-3-319-11209-1 (ISBN)
Conference
22nd International Conference, ICCBR 2014, Cork, Ireland, September 29, 2014 - October 1, 2014.
Available from: 2015-02-06 Created: 2015-02-06 Last updated: 2015-09-22Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-9890-4918

Search in DiVA

Show all publications