Valid

GB/T 22394.2-2021Condition monitoring and diagnostics of machines - Data interpretation and diagnostics techniques - Part 2: Data-driven applications (English PDF)

机器状态监测与诊断数据判读与诊断技术第2部分：数据驱动的应用

Preview PDF

This is a limited preview

Buy now to download the full PDF (24 pages)

Need quotation for your management?

Get a formal quotation for GB/T 22394.2-2021 in 30 minutes.

Issued by

State Administration for Market Regulation, China National Standardization Administration

Level / Type

National · Recommended

Issue date

May 21, 2021

Implementation date

December 1, 2021

Scope

GB/T 22394.2-2021 is the English-translated version of 机器状态监测与诊断数据判读与诊断技术第2部分：数据驱动的应用.

GB/T 22394.2-2021 is the Chinese standard "Condition monitoring and diagnostics of machines - Data interpretation and diagnostics techniques - Part 2: Data-driven applications".

Its scope clause reads: This part of GB/T 22394 gives the process of implementing data-driven monitoring and diagnostic methods to help professionals, especially monitoring The professional staff of the center conduct analysis work.

Although some steps have been embedded in the existing tools, in order to better use it, it is still necessary to pay attention to the following steps. ---The selection of assets, critical failures and available process parameters; ---Data cleaning and resampling; ---Model development; ---Model initialization and adjustment; ---Model performance evaluation; ---Diagnostic process.

The implementation of these steps does not require comprehensive knowledge of statistical methods, but requires the ability to first establish a training model and apply the model to monitoring And the ability of the diagnostic process.

Implement data-driven monitoring model training on machines in normal working conditions. The principle of fault monitoring is to combine the observed data with the estimated data According to comparison.

The difference between the observed value of the parameter and the expected value (called residual) indicates that there is an abnormality, which may be related to the equipment or instrument. related.

Implement data-driven diagnostic model training on machines in normal working and faulty states. The principle of the diagnostic method is not to detect The deviation of the parameters is to identify the fault by comparing the observed conditions with the faults learned in the training phase.

Commonly used techniques The technique is pattern recognition and pattern classification. The data can be taken from the historical data of the distributed control system (DCS), or from a specific monitoring system. Its clauses include terms and definitions.

Found what you need?

Document preview — GB/T 22394.2-2021

National Standard of the People's Republic of China

Classification: J 04

Issued by: State Administration for Market Regulation, China National Standardization Administration

Foreword
Introduction
1 Scope
2 Normative references
3 Terms and definitions
4 The process of implementing data-driven monitoring
4.1 Principle of data-driven monitoring method
4.2 Asset critical failure and process parameter selection
4.3 Data cleaning and resampling
4.3.1 General
4.3.2 Interpolation error
4.3.3 Data quality issues
4.3.4 Data resampling
4.4 Model development
4.4.1 General
4.4.2 Definition of the model and selection of related inputs
4.4.3 Selection of relevant working conditions and data
4.4.4 Model test preparation
4.5 Model performance evaluation
4.6 Alarm setting
5 The process of implementing data-driven diagnostics
5.1 General
5.2 Automatic mode classification method
5.3 Simplified automatic feature classification method
6 General recommendations for implementing data-driven monitoring methods
Appendix A (informative appendix) Data-driven monitoring application example
Appendix B (informative appendix) Data-driven diagnostic application example

1 Scope

This part of GB/T 22394 gives the process of implementing data-driven monitoring and diagnostic methods to help professionals, especially monitoring

The professional staff of the center conduct analysis work.

Although some steps have been embedded in the existing tools, in order to better use it, it is still necessary to pay attention to the following steps.

---The selection of assets, critical failures and available process parameters;

---Data cleaning and resampling;

---Model development;

---Model initialization and adjustment;

---Model performance evaluation;

---Diagnostic process.

The implementation of these steps does not require comprehensive knowledge of statistical methods, but requires the ability to first establish a training model and apply the model to monitoring

And the ability of the diagnostic process.

Implement data-driven monitoring model training on machines in normal working conditions. The principle of fault monitoring is to combine the observed data with the estimated data

According to comparison. The difference between the observed value of the parameter and the expected value (called residual) indicates that there is an abnormality, which may be related to the equipment or instrument.

related.

Implement data-driven diagnostic model training on machines in normal working and faulty states. The principle of the diagnostic method is not to detect

The deviation of the parameters is to identify the fault by comparing the observed conditions with the faults learned in the training phase. Commonly used techniques

The technique is pattern recognition and pattern classification.

The data can be taken from the historical data of the distributed control system (DCS), or from a specific monitoring system.

2 Normative references

The following documents are indispensable for the application of this document. For dated reference documents, only the dated version applies to this article

Pieces. For undated reference documents, the latest version (including all amendments) is applicable to this document.

ISO 13372 Machine Condition Monitoring and Diagnostic Vocabulary (Conditionmonitoringanddiagnosticsofmachines-Vo- cabulary)

ISO 13379-1 Machine Condition Monitoring and Diagnosis Data Interpretation and Diagnosis Technology Part 1.General (Condition monitoringanddiagnosticsofmachine-Datainterpretationanddiagnosticstechniques-Part 1.Gen- eralguidelines)

3 Terms and definitions

The terms and definitions defined by ISO 13372 and ISO 13379-1 apply to this document.

GB/T 23901.1 | GB/T 22393 | GB/T 21487.1 | GB/T 18258 | GB/T 22394.1 | […]

......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 24 pages — is available in the English PDF.

Referenced standards

Normative references

ISO 13372 · ISO 13379

How to Download GB/T 22394.2-2021

1
Add to cart
Click "Download PDF" on this page and choose "Buy this standard". You can add more standards before checkout.
2
Checkout
Enter your email and billing details. Payment is processed securely by Stripe (cards or bank transfer). Prefer bank details? Request a quotation (min. order $300).
3
Instant delivery (0–9 sec)
Delivery is automatic: within seconds of payment you'll receive an email with a secure download link. The link stays valid for 72 hours.
4
Invoice included
A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.