A Method for Monitoring the Operational State of a System

Tomasz Jakub Maniak (Inventor), Rahat Iqbal (Inventor), Faiyaz Doctor (Inventor)

Research output: Patent

Abstract

A method comprises obtaining signals from a plurality of sensors Si, S2, Sn and feeding these into an encoder 12, which translates signals into vectors VE characterising the state of the operational parameters of the monitored system. The encoded vector VE is fed into a translation engine 13 which translates the encoded vector VE into feature space to form a feature vector VF. The feature vector VF is subsequently fed into a residual vector generator 16 which compares the feature vector VF with a predicted vector Vp generated by a prediction engine 14 and thereby output a residual vector VR which characterises any differences between the feature vector VE and the predicted vector Vp. In addition, the feature vector VF may also be fed directly into the prediction engine 14 to update subsequent predictions. The formed residual vector VR may then be input into a computation unit 18 for analysis, such as to determine whether the differences identified between the predicted and feature vectors Vp, VF indicate that there is a fault in the monitored system. Vectors may be encoded as binary numbers where the number of digits corresponds to the number of classes into which measured values may be classified. Markov chains may be used to model the probability of transitions between states.
Original languageEnglish
Patent numberGB2554038A
IPCG05B 23/02 (2006.01)
Priority date4/05/16
Filing date4/05/16
Publication statusPublished - 22 May 2019

Fingerprint

Monitoring
Engines
Markov processes
Sensors

Cite this

Maniak, T. J., Iqbal, R., & Doctor, F. (2019). IPC No. G05B 23/02 (2006.01). A Method for Monitoring the Operational State of a System. (Patent No. GB2554038A).

A Method for Monitoring the Operational State of a System. / Maniak, Tomasz Jakub (Inventor); Iqbal, Rahat (Inventor); Doctor, Faiyaz (Inventor).

IPC No.: G05B 23/02 (2006.01). Patent No.: GB2554038A. May 04, 2016.

Research output: Patent

Maniak, TJ, Iqbal, R & Doctor, F May. 04 2016, A Method for Monitoring the Operational State of a System, Patent No. GB2554038A, IPC No. G05B 23/02 (2006.01).
Maniak TJ, Iqbal R, Doctor F, inventors. A Method for Monitoring the Operational State of a System. G05B 23/02 (2006.01). 2019 May 22.
Maniak, Tomasz Jakub (Inventor) ; Iqbal, Rahat (Inventor) ; Doctor, Faiyaz (Inventor). / A Method for Monitoring the Operational State of a System. IPC No.: G05B 23/02 (2006.01). Patent No.: GB2554038A. May 04, 2016.
@misc{64dfd2065e0c429d93e571311cf53f38,
title = "A Method for Monitoring the Operational State of a System",
abstract = "A method comprises obtaining signals from a plurality of sensors Si, S2, Sn and feeding these into an encoder 12, which translates signals into vectors VE characterising the state of the operational parameters of the monitored system. The encoded vector VE is fed into a translation engine 13 which translates the encoded vector VE into feature space to form a feature vector VF. The feature vector VF is subsequently fed into a residual vector generator 16 which compares the feature vector VF with a predicted vector Vp generated by a prediction engine 14 and thereby output a residual vector VR which characterises any differences between the feature vector VE and the predicted vector Vp. In addition, the feature vector VF may also be fed directly into the prediction engine 14 to update subsequent predictions. The formed residual vector VR may then be input into a computation unit 18 for analysis, such as to determine whether the differences identified between the predicted and feature vectors Vp, VF indicate that there is a fault in the monitored system. Vectors may be encoded as binary numbers where the number of digits corresponds to the number of classes into which measured values may be classified. Markov chains may be used to model the probability of transitions between states.",
author = "Maniak, {Tomasz Jakub} and Rahat Iqbal and Faiyaz Doctor",
year = "2019",
month = "5",
day = "22",
language = "English",
type = "Patent",
note = "GB2554038A; G05B 23/02 (2006.01)",

}

TY - PAT

T1 - A Method for Monitoring the Operational State of a System

AU - Maniak, Tomasz Jakub

AU - Iqbal, Rahat

AU - Doctor, Faiyaz

PY - 2019/5/22

Y1 - 2019/5/22

N2 - A method comprises obtaining signals from a plurality of sensors Si, S2, Sn and feeding these into an encoder 12, which translates signals into vectors VE characterising the state of the operational parameters of the monitored system. The encoded vector VE is fed into a translation engine 13 which translates the encoded vector VE into feature space to form a feature vector VF. The feature vector VF is subsequently fed into a residual vector generator 16 which compares the feature vector VF with a predicted vector Vp generated by a prediction engine 14 and thereby output a residual vector VR which characterises any differences between the feature vector VE and the predicted vector Vp. In addition, the feature vector VF may also be fed directly into the prediction engine 14 to update subsequent predictions. The formed residual vector VR may then be input into a computation unit 18 for analysis, such as to determine whether the differences identified between the predicted and feature vectors Vp, VF indicate that there is a fault in the monitored system. Vectors may be encoded as binary numbers where the number of digits corresponds to the number of classes into which measured values may be classified. Markov chains may be used to model the probability of transitions between states.

AB - A method comprises obtaining signals from a plurality of sensors Si, S2, Sn and feeding these into an encoder 12, which translates signals into vectors VE characterising the state of the operational parameters of the monitored system. The encoded vector VE is fed into a translation engine 13 which translates the encoded vector VE into feature space to form a feature vector VF. The feature vector VF is subsequently fed into a residual vector generator 16 which compares the feature vector VF with a predicted vector Vp generated by a prediction engine 14 and thereby output a residual vector VR which characterises any differences between the feature vector VE and the predicted vector Vp. In addition, the feature vector VF may also be fed directly into the prediction engine 14 to update subsequent predictions. The formed residual vector VR may then be input into a computation unit 18 for analysis, such as to determine whether the differences identified between the predicted and feature vectors Vp, VF indicate that there is a fault in the monitored system. Vectors may be encoded as binary numbers where the number of digits corresponds to the number of classes into which measured values may be classified. Markov chains may be used to model the probability of transitions between states.

M3 - Patent

M1 - GB2554038A

Y2 - 2016/05/04

ER -