Unlock instant, AI-driven research and patent intelligence for your innovation.

Piecewise linear representation-based single-variable alarm system performance evaluation method and system

An alarm system, piecewise linear technology, applied in the direction of alarm, resources, office automation, etc., can solve the problems of large error in performance indicators, affecting the effectiveness and accuracy of the alarm system, and not reflecting the performance of the alarm system well

Inactive Publication Date: 2020-10-20
SHANDONG UNIV OF SCI & TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is very effective for stationary data but poor for non-stationary data, especially for non-stationary data in actual industrial applications. The performance index obtained by this method has a large error and cannot reflect the performance of the alarm system well. If If it is not resolved, it will seriously affect the effectiveness and accuracy of the alarm system performance evaluation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Piecewise linear representation-based single-variable alarm system performance evaluation method and system
  • Piecewise linear representation-based single-variable alarm system performance evaluation method and system
  • Piecewise linear representation-based single-variable alarm system performance evaluation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Such as figure 1 As shown, Embodiment 1 of the present disclosure provides a method for evaluating the performance of a univariate alarm system based on a piecewise linear representation, comprising the following steps:

[0042] Given a predetermined number K of data segments, cluster adjacent data samples with the same trend to obtain historical data for univariate x(t) A piecewise linear representation of , where t∈[1,T];

[0043] Through hypothesis testing, judge the kth data segment is the normal working condition data segment or the abnormal working condition data segment, where k∈[1,K];

[0044] After dividing all data segments into normal, abnormal and undefined data segments, the performance index of the alarm system is calculated according to the division results.

[0045] Cluster adjacent data samples with the same trend, specifically:

[0046] Using piecewise linear representations (PLRs) to convert historical data into Divided into several short time...

Embodiment 2

[0107] Embodiment 2 of the present disclosure provides a univariate alarm system performance evaluation system based on piecewise linear representation, including:

[0108] The data acquisition module is configured to: acquire the alarm history data of the alarm system;

[0109] The data segmentation module is configured to: cluster adjacent data samples with the same trend according to the number of preset data segments to obtain a segmented linear representation of historical data;

[0110] The data segment classification module is configured to: judge the attributes of each data segment through hypothesis testing, including at least two attributes of the normal working condition data segment and the abnormal working condition data segment;

[0111] The performance evaluation module is configured to: calculate each performance index of the alarm system according to the obtained attributes of each data segment.

[0112] The working method of the evaluation system is the same...

Embodiment 3

[0114] Embodiment 3 of the present disclosure provides a medium on which a program is stored. When the program is executed by a processor, the steps in the method for evaluating the performance of a single-variable alarm system based on piecewise linear representation as described in Embodiment 1 of the present disclosure are implemented. , the steps are specifically:

[0115] Obtain the alarm history data of the alarm system;

[0116] According to the number of preset data segments, cluster adjacent data samples with the same trend to obtain a segmented linear representation of historical data;

[0117] Through hypothesis testing, determine the attributes of each data segment, including at least two attributes of the normal working condition data segment and the abnormal working condition data segment;

[0118] Each performance index of the alarm system is calculated according to the obtained attributes of each data segment.

[0119] The more detailed steps are the same as ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a piecewise linear representation-based single-variable alarm system performance evaluation method and system, and belongs to the technical field of alarm monitoring of the process industry. Piecewise linear representation is adopted to segment a time sequence, adjacent data samples with the same trend are clustered, and each segment is represented by a fitting straight line; a sample mean value of each data segment and a confidence interval of the mean value are calculated, and the sample mean value is compared with an alarm threshold through hypothesis testing so as todivide normal and abnormal number working condition data segments; and the real alarm number, the interference alarm number, the false alarm rate, the missing report rate, the false alarm duration ratio and the missing alarm duration ratio of the alarm system are calculated according to the division result. The method is also suitable for stable and non-stable data segments, and is more effectivethan an existing method in the aspect of detecting normal data and abnormal data segments, and meanwhile, the false alarm duration ratio and the missed alarm duration ratio provided by the inventionare of great significance in improving the accuracy and effectiveness of performance evaluation of an alarm system.

Description

technical field [0001] The disclosure relates to the technical field of alarm monitoring in the process industry, in particular to a performance evaluation method and system for a single-variable alarm system based on a piecewise linear representation. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Alarm systems help operators detect potentially abnormal and dangerous conditions in a variety of large process industries such as refineries, petrochemical facilities, and power plants. A well-designed and well-performing alarm system is critical to process safety and plant operating efficiency. However, the performance of most industrial alarm systems today is far from industry standards, and many industrial alarm systems contain too many nuisance alarms. Therefore, the performance evaluation of the alarm system and the quantification of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06Q10/06G06Q10/10G06Q50/26G08B29/00G08B31/00
CPCG06Q10/0639G06Q10/103G06Q50/26G08B29/00G08B31/00G06F18/2321
Inventor 王建东王振周东华白星振
Owner SHANDONG UNIV OF SCI & TECH