Resampling-based production line fault judgment method integrated with feature selection algorithm
A technology of integrating features and selecting algorithms, applied in the direction of comprehensive factory control, instrumentation, comprehensive factory control, etc., can solve problems such as few high-dimensional industrial big data characteristics, and achieve high accuracy, good robustness, and applicable scenarios strong effect
Active Publication Date: 2019-10-01
TONGJI UNIV
View PDF11 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of the above inventions only involve fault prediction at the equipment layer, and there are few studies on the characteristics of high-dimensional industrial big data in complex manufacturing environments, which are not suitable for manufacturing environments represented by semiconductor manufacturing systems
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
Embodiment
[0043] Such as figure 1 Shown is a flow chart of a production line fault judgment method based on a resampling integrated feature selection algorithm in the present invention. Specifically, the method in this embodiment includes the following steps:
[0044] Step 1) Reconstruct the sample space of the imbalanced data set (IDS) based on the resampling algorithm.
[0045]In a specific embodiment, since the semiconductor manufacturing system includes a plurality of processing equipment, in order to collect the operating state of each device in real time, a plurality of operating state acquisition devices are configured for each device to collect the operating state parameters in real time, and at the same time the state parameters The corresponding production line status is marked. Since the failure samples in production records only account for a small part, it is necessary to determine a suitable model to predict the state of the production line.
[0046] Step101: Perform dat...
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 relates to a resampling-based production line fault judgment method integrated with a feature selection algorithm. The method comprises the following steps: 1, building new sample subspaces with an imbalanced data set (IDS) based on a resampling method; 2, performing feature selection on the sample subspaces with a random forest algorithm to obtain feature subsets of the subspaces; 3, combining the feature subsets of the subspaces into a new feature space set; 4, performing dimension reduction on the new feature space set by using a denoising auto-encoder to obtain the input of aprediction model; and 5, building a fault prediction model by adopting the random forest algorithm according to the input of the prediction model, and performing real-time fault monitoring and judgement on a production line by using the fault prediction model. Compared with the prior art, the method has the advantages of high accuracy and high robustness.
Description
technical field [0001] The invention relates to the technical field of fault judgment in the chip manufacturing process of a semiconductor manufacturing enterprise, in particular to a production line fault judgment method based on a resampling integrated feature selection algorithm. Background technique [0002] With the widespread application of smart electronic devices in people's lives, the global semiconductor market has developed rapidly in recent years. However, unlike the situation in which the proportion of the integrated circuit design industry in the industrial structure has increased significantly, the proportion of the wafer manufacturing industry has not changed much, and wafer manufacturers are still facing severe market challenges. [0003] During the manufacturing process of the semiconductor production line, there may be some events that are not arranged according to the established scheduling plan, such as production line failure, emergency orders, etc. Th...
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 IPC IPC(8): G05B19/418
CPCG05B19/41875G05B2219/31357Y02P90/02
Inventor 乔非朱雪初孙晓彬
Owner TONGJI UNIV