Fault detection and diagnosis method for chemical sensor array
A chemical sensor and fault detection technology, applied in scientific instruments, gas analyzers' structural details, instruments, etc., can solve problems such as inaccurate analysis results of electronic nose systems, and achieve regression, good sparsity, and reduced complexity. Effect
Pending Publication Date: 2020-12-18
HARBIN INST OF TECH
View PDF2 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to propose a fault detection and diagnosis method for chemical sensor arrays in view of the problem that the sudden failure of chemical sensors in the prior art will lead to serious inaccuracy of the analysis results of the entire electronic nose system
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0032] Specific implementation mode one: refer to figure 1 Specifically explaining this embodiment, a method for detecting and diagnosing a chemical sensor array failure described in this embodiment includes the following steps:
[0033] Step 1: collect the output signal of the chemical sensor array, and combine the historical output signal to form a training set;
[0034] Step 2: use the training set to construct a multiple regression model based on a multivariate correlation vector machine;
[0035] Step 3: Predict the measured value of each sensor in the chemical sensor array by using the trained multiple regression model based on the multivariate correlation vector machine;
[0036] Step 4: Determine whether the measured value of each sensor changes suddenly;
[0037] Step 5: Carry out consistency judgment according to whether there is a sudden change in the measured values of each sensor, and then judge whether the chemical sensor array is operating normally according...
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
Login to View More Abstract
The invention discloses a fault detection and diagnosis method for a chemical sensor array, relates to the field of gas detection, and aims to solve the problem of serious misalignment of an analysisresult of a whole electronic nose system caused by sudden faults of chemical sensors in the prior art, and the method comprises the following steps: 1, collecting output signals of the chemical sensorarray, and combining historical output signals to form a training set; 2, training a multivariate regression model based on a multivariate relevance vector machine by utilizing the training set; 3, predicting the measurement value of each sensor in the chemical sensor array by using the trained multivariable relevance vector machine-based multiple regression model; 4, judging whether the measuredvalue of each sensor is suddenly changed or not; and 5, judging the consistency according to whether the measured value of each sensor is suddenly changed or not, judging whether the chemical sensorarray operates normally or not according to a consistency judgment result, and judging the fault type through a trained multi-classification relevance vector machine classifier if the chemical sensorarray operates abnormally.
Description
technical field [0001] The invention relates to the technical field of gas detection equipment, in particular to a fault detection and diagnosis method for a chemical sensor array. Background technique [0002] The electronic nose is a device for detecting odors. It has the potential to accurately identify the types and concentrations of gases by simulating the human olfactory organs. It has received extensive attention from the scientific and industrial communities since its development. At present, the electronic nose has broad application prospects in the fields of environmental monitoring, disease diagnosis, public safety, robotics, agricultural production and food engineering. The core of the electronic nose system is composed of a chemical detection platform and corresponding machine learning algorithms to identify, classify, quantify and monitor target gases. [0003] With the advantages of high sensitivity, good stability, simple operation, and low cost, chemical se...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01N33/00G06K9/00G06K9/62
CPCG01N33/007G01N33/0031G01N33/0034G01N33/0001G06F2218/12G06F18/2411G06F18/214
Inventor 陈寅生宋凯刘继江金鹏飞张伟岩
Owner HARBIN INST OF TECH