Introduction to the DAMADICS actuator FDI benchmark study

Bartyś, Michał; Patton, Ron J.; Syfert, Michał; Heras, Salvador De Las; Quevedo, Joseba

doi:10.1016/j.conengprac.2005.06.015

Cited by 181 publications

(116 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When a fault occurs, fault detection and isolation is performed using the model residuals. This method, applied to the actuator benchmark [104], was able to detect and isolate 10 abrupt and incipient faults.…”

Section: Smart Diagnosismentioning

confidence: 99%

“…Bartyś et al [104] provided the description and presentation of the actuator benchmark used in fault diagnosis studies within the Development and Application of Methods for Actuator Diagnosis in Industrial Control System (DAMADICS) European Research Training Network. This system is openly available, is FDI method-independent, and based on an accurate study of the phenomena that can lead to likely faults in valve actuator systems.…”

Section: Smart Diagnosismentioning

confidence: 99%

See 1 more Smart Citation

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Capaci

Scali

2015

Processes

View full text Add to dashboard Cite

Abstract:Valve stiction is indicated as one of the main problems affecting control loop performance and then product quality. Therefore, it is important to detect this phenomenon as early as possible, distinguish it from other causes, and suggest the correct action to the operator in order to fix it. It is also very desirable to give an estimate of stiction amount, in order to be able to follow its evolution in time to allow the scheduling of valve maintenance or different operations, if necessary. This paper, in two parts, is a review of the state of the art about the phenomenon of stiction from its basic characterization to smart diagnosis, including modeling, detection techniques, quantification, compensation and a description of commercial software packages. In particular, Part I of the study analyzes the most significant works appearing in the recent literature, pointing out analogies and differences among various techniques, showing more appealing features and possible points of weakness. The review also includes an illustration of the main features of performance monitoring systems proposed by major software houses. Finally, the paper gives indications on future research trends and potential advantages for loop diagnosis when additional measurements are available, as in newly designed plants with valve positioners and smart instrumentation. In Part II, performance of some well-established methods for stiction quantification are compared by applications to different industrial datasets. OPEN ACCESSProcesses 2015, 3 423

show abstract

Section: Smart Diagnosismentioning

confidence: 99%

Section: Smart Diagnosismentioning

confidence: 99%

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Capaci

Scali

2015

Processes

View full text Add to dashboard Cite

show abstract

“…The benchmark contains total 44 types of fault scenarios, but as reported in the literature [9], the misclassification occurs due to overlapping phenomenon among different fault classes.…”

Section: Decision Tree Approachmentioning

confidence: 99%

Decision Tree Based Approach for Fault Diagnosis in Process Control System

2017

IJCCIE

View full text Add to dashboard Cite

Abstract----DecisionTree is one of the most popular classification algorithms in current use in Data Mining and Machine Learning. Decision trees create an easily understandable structure for evaluating complex decisions. In this paper, the performance of the proposed approach based on Single Decision Tree based method is demonstrated on the DAMADICS benchmark problem. An attempt has been made to improve the performance of fault diagnosis task on DAMADICS benchmark.

show abstract

“…The only previous study [24], which was carried out on DAMADICS data using the SOM-based approach, presented a possibility of application of SOM to the faults clusterization, but the results are limited to the analysis of three selected faults. In the present study the process signals were simulated basing on real measurements of diagnostic signals on the actuator system during the evaporisation process in the Lublin sugar factory (Poland) [25], [26]. In order to detect, isolate and identify the faults simulated using DAMADICS benchmark actuator system the SOM-based approach was applied.…”

Section: Introductionmentioning

confidence: 99%

Faults diagnosis using self-organizing maps: A case study on the DAMADICS benchmark problem

Katunin

Amarowicz

Chrzanowski

2015

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-This paper deals with a method of faults detection and identification based on the clusterization of the multiple diagnostic signals. Various types of faults and character of their occurrence were simulated using DAMADICS Benchmark Process Control System. A great advantage of the applied approach based on self-organizing (Kohonen) maps is that even the smallest differences in signals allow for detection, isolation and identification of type of occurred faults with respect to the healthy condition of the investigated system based on the unsupervised learning. It was shown that in some cases the faults, which are undetectable during monitoring of simple heuristic and statistical parameters and other previously applied methods, are recognizable when the approach based on self-organizing maps is applied. The case studies presented in this paper show the faults detection procedure as well as clusterization of types and successful classification of almost all the unique faulty states of the investigated system.

show abstract

Introduction to the DAMADICS actuator FDI benchmark study

Cited by 181 publications

References 9 publications

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Decision Tree Based Approach for Fault Diagnosis in Process Control System

Faults diagnosis using self-organizing maps: A case study on the DAMADICS benchmark problem

Contact Info

Product

Resources

About