1、BSI Standards PublicationBS ISO 13379-2:2015Condition monitoring anddiagnostics of machines Data interpretation anddiagnostics techniquesPart 2: Data-driven applicationsBS ISO 13379-2:2015 BRITISH STANDARDNational forewordThis British Standard is the UK implementation of ISO 13379-2:2015.Together wi
2、th BS ISO 13379-1:2012 and BS ISO 13379-3 it supersedesBS ISO 13379:2003, which will be withdrawn upon publication of BSISO 13379-3.The UK participation in its preparation was entrusted to TechnicalCommittee GME/21/7, Mechanical vibration, shock and conditionmonitoring - Condition monitoring.A list
3、of organizations represented on this committee can beobtained on request to its secretary.This publication does not purport to include all the necessaryprovisions of a contract. Users are responsible for its correctapplication. The British Standards Institution 2015. Published by BSI StandardsLimite
4、d 2015ISBN 978 0 580 81416 7ICS 17.160Compliance with a British Standard cannot confer immunity fromlegal obligations.This British Standard was published under the authority of theStandards Policy and Strategy Committee on 31 May 2015.Amendments issued since publicationDate Text affectedBS ISO 13379
5、-2:2015 ISO 2015Condition monitoring and diagnostics of machines Data interpretation and diagnostics techniques Part 2: Data-driven applicationsSurveillance et diagnostic dtat des machines Interprtation des donnes et techniques de diagnostic Partie 2: Systmes guids par les donnesINTERNATIONAL STANDA
6、RDISO13379-2First edition2015-04-01Reference numberISO 13379-2:2015(E)BS ISO 13379-2:2015ISO 13379-2:2015(E)ii ISO 2015 All rights reservedCOPYRIGHT PROTECTED DOCUMENT ISO 2015All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any
7、form or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address below or ISOs member body in the country of the requester.ISO copyright officeCase postale 5
8、6 CH-1211 Geneva 20Tel. + 41 22 749 01 11Fax + 41 22 749 09 47E-mail copyrightiso.orgWeb www.iso.orgPublished in SwitzerlandBS ISO 13379-2:2015ISO 13379-2:2015(E)Foreword ivIntroduction v1 Scope . 12 Normative references 13 Terms and definitions . 24 Procedure to implement data-driven monitoring . 2
9、4.1 Principle of data-driven monitoring methods . 24.2 Asset critical failures and process parameters selection . 34.3 Data cleaning and resampling 34.3.1 General 34.3.2 Interpolation errors 34.3.3 Data quality issues . 34.3.4 Data resampling 44.4 Model development 44.4.1 General 44.4.2 Definition o
10、f models and selection of relevant inputs . 44.4.3 Selection of relevant operating conditions and data 44.4.4 Preparation of the model tests 54.5 Model performance evaluation . 54.6 Alarm setting 55 Procedure to implement data-driven diagnosis 65.1 General . 65.2 Automated pattern classification app
11、roach . 65.3 Simplified automated signature classification approach . 76 General recommendations to implement data-driven monitoring methods 8Annex A (informative) Example of data-driven monitoring application 9Annex B (informative) Example of data-driven diagnostic application 11Bibliography .12 IS
12、O 2015 All rights reserved iiiContents PageBS ISO 13379-2:2015ISO 13379-2:2015(E)ForewordISO (the International Organization for Standardization) is a worldwide federation of national standards bodies (ISO member bodies). The work of preparing International Standards is normally carried out through
13、ISO technical committees. Each member body interested in a subject for which a technical committee has been established has the right to be represented on that committee. International organizations, governmental and non-governmental, in liaison with ISO, also take part in the work. ISO collaborates
14、 closely with the International Electrotechnical Commission (IEC) on all matters of electrotechnical standardization.The procedures used to develop this document and those intended for its further maintenance are described in the ISO/IEC Directives, Part 1. In particular the different approval crite
15、ria needed for the different types of ISO documents should be noted. This document was drafted in accordance with the editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).Attention is drawn to the possibility that some of the elements of this document may be the subject of
16、patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of any patent rights identified during the development of the document will be in the Introduction and/or on the ISO list of patent declarations received (see www.iso.org/patents).Any trade name u
17、sed in this document is information given for the convenience of users and does not constitute an endorsement.For an explanation on the meaning of ISO specific terms and expressions related to conformity assessment, as well as information about ISOs adherence to the WTO principles in the Technical B
18、arriers to Trade (TBT), see the following URL: Foreword - Supplementary information.The committee responsible for this document is ISO/TC 108, Mechanical vibration, shock and condition monitoring, Subcommittee SC 5, Condition monitoring and diagnostics of machine systems.ISO 13379 consists of the fo
19、llowing parts, under the general title Condition monitoring and diagnostics of machines Data interpretation and diagnostics techniques: Part 1: General guidelines Part 2: Data-driven applications Part 3: Knowledge-based applicationsiv ISO 2015 All rights reservedBS ISO 13379-2:2015ISO 13379-2:2015(E
20、)IntroductionThis part of ISO 13379 contains general procedures that can be used to determine the condition of a machine relative to a set of baseline parameters. Changes from the baseline values and comparison to alarm criteria are used to indicate anomalous behaviour and to generate alarms: this i
21、s usually designated as condition monitoring. Additionally, procedures that identify the cause(s) of the anomalous behaviour are given in order to assist in the determination of the proper corrective action: this is usually designated as diagnostics. ISO 2015 All rights reserved vBS ISO 13379-2:2015
22、BS ISO 13379-2:2015Condition monitoring and diagnostics of machines Data interpretation and diagnostics techniques Part 2: Data-driven applications1 ScopeThis part of ISO 13379 gives procedures to implement data-driven monitoring and diagnostic methods to facilitate the work of analysis carried out
23、by specialist staff typically located in a monitoring centre.Although some of the steps are embedded in existing tools, it is essential to be aware of the following steps for optimum use: selection of the asset, the critical failures and the available process parameters; data cleaning and resampling
24、; model development; model initialization and tuning; model performance evaluation; diagnostics process.The implementation of these steps does not require a thorough knowledge of the statistical methods. It does require the competence first to build the training models and then to carry out monitori
25、ng and diagnostics processes.The training in data-driven monitoring is carried out on equipment that is exhibiting normal behaviour. In that case, the principle of fault detection is to compare observed data to estimated data. A difference (called residuals) between an observed and expected values o
26、f the parameters reveals the presence of an anomaly, which can be related either to equipment or instrument.The training in data-driven diagnosis is carried out both on equipment that is exhibiting normal behaviour and failures. The principle of the method is not to detect the deviation of a paramet
27、er but to identify a fault by comparison of the observed situation to the faults learnt during the training phase. The technique usually applied is pattern recognition followed by pattern classification.Data can be available from the data historian of the distributed control system (DCS) or from spe
28、cialized monitoring systems.2 Normative referencesThe following documents, in whole or in part, are normatively referenced in this document and are indispensable for its application. For dated references, only the edition cited applies. For undated references, the latest edition of the referenced do
29、cument (including any amendments) applies.ISO 13372, Condition monitoring and diagnostics of machines VocabularyISO 13379-1, Condition monitoring and diagnostics of machines Data interpretation and diagnostics techniques Part 1: General guidelinesINTERNATIONAL STANDARD ISO 13379-2:2015(E) ISO 2015 A
30、ll rights reserved 1BS ISO 13379-2:2015ISO 13379-2:2015(E)3 Terms and definitionsFor the purposes of this document, the terms and definitions given in ISO 13372 and ISO 13379-1 apply.4 Procedure to implement data-driven monitoring4.1 Principle of data-driven monitoring methodsAdvanced statistical me
31、thods that simultaneously consider multiple plant signals and model the underlying relationship between them are beginning to replace the classical methods for condition monitoring which are based on the observation of trends of individual signals.These monitoring methods rely on the same principle
32、to detect a fault, which is to compare observed data to estimated data.Prior to the monitoring phase, it is required to build the model of the normal equipment behaviour, during a training phase. Faults can thus often be detected as deviations between an observed and an expected value of the paramet
33、ers of the system.Figure 1 shows an example of an application on a gas turbine. The objective is to detect abnormal shaft displacements after a shut down. Several inputs are considered in the model: active and reactive power and bearing displacements.Keygreen trainingblue monitoringred predictionFig
34、ure 1 Gas turbine displacement magnitude and residual2 ISO 2015 All rights reservedBS ISO 13379-2:2015ISO 13379-2:2015(E)Data-driven monitoring methods generally applied are Auto associative kernel regression (AAKR), cluster and partial least square (PLS), support vector machine (SVM), and/or Mahala
35、nobis-Taguchi (MT) methods.4.2 Asset critical failures and process parameters selectionThe procedure for the implementation of data-driven monitoring is precisely described in ISO 17359. It includes two main audits: equipment audit: identify equipment and its function; reliability and criticality au
36、dit: produce a reliability block diagram, establish equipment criticality and perform failure modes, effects and criticality analysis.Once this preliminary study is carried out and the list of the critical faults is identified, it is necessary to list the process data available in the data historian
37、 or in specialized monitoring systems. An example would be a vibration monitoring system.It might be necessary to consider the installation of additional sensors or location of existing sensors if the detection scope of the critical faults is not completely covered.4.3 Data cleaning and resampling4.
38、3.1 GeneralIn order to build a robust model, one shall first collect data covering all the operating conditions in which the system is expected to run and for which signal validation is desired. These data are historical data that have been collected and stored. In fact, they might not always repres
39、ent the real plant state due to several anomalies that commonly occur, including interpolation errors, random data errors, missing data, loss of significant figures, stuck data, and others. Data should always be checked and corrected.WARNING Caution shall be taken before deleting data.4.3.2 Interpol
40、ation errorsThe first problem usually encountered when using historical data for model training is that available conditioned data do not correspond to actual data, but instead, data resulting from compression routines normally implemented in data archival programs. Generally, the data historian cre
41、ates a data archive that is a time series database. However, all of the data are not stored at each collection time. Only data values that have changed by more than a specified tolerance are stored along with their time stamp. This method requires much less storage but results in a loss of data fide
42、lity. When data are extracted from the historian, data values between logged data points are calculated through either a simple linear interpolation or a step at the time of the second data point. The resulting data appear to be a saw-tooth time series and the correlations between sensors might be s
43、everely changed.As a conclusion, data collected for model training should be actual data and tolerances should be set as small as possible or not used.4.3.3 Data quality issuesSeveral of the most common data quality issues are: missing data; noisy or random data; defective sensors for which the data
44、 value is not updated or is out of calibration; unreasonable data values (out of range). ISO 2015 All rights reserved 3BS ISO 13379-2:2015ISO 13379-2:2015(E)Most of these data problems can be visually identified or can be detected by a data clean-up utility. These utilities remove bad data or replac
45、e it with the most probable data value using an algorithm. It is most common to delete all bad data observations from the training data set. Most software systems include automated tools for data clean-up; these tools easily identify extreme outlying data but are typically insensitive to data errors
46、 that occur within the expected region of operation. The addition of bad data points in a training set can invalidate a model.4.3.4 Data resamplingOnce the data have been cleaned, it might be necessary to resample the data at a lower rate determined by the selected operation modes. Thus, it is advis
47、ed to keep all the time stamps to characterize the transients of the significant operating parameters (e.g. run down of a machine) whereas under steady-state operation, a sample every 10 min (obtained by average or not) might be sufficient.4.4 Model development4.4.1 GeneralModel development is not t
48、rivial. There are several steps that need to be performed including: selecting relevant features; selecting relevant operating regions and training data; preparing the model tests.Construction of a data-driven model requires: a set of parameters (sensors) which focus on a specific type of fault (mec
49、hanical, electrical, thermal, etc.); data samples for a period during which the machine is known to be in good health.4.4.2 Definition of models and selection of relevant inputsOnce the quality of the data has been validated, model features shall be defined. Features may be the raw sensor values themselves or derived from the sensor values (exponentially weighted moving averages, means, kurtosis, etc.). A large process plant may possess hundreds of parameters that require monitoring for the assessment of critical
