Survey on iterative learning control, repetitive control, and run-to-run control

Fault detection and diagnosis in process data using one-class support vector machines

Deep convolutional neural network model based chemical process fault diagnosis

A deep belief network based fault diagnosis model for complex chemical processes

Mapping flood-prone areas is a key activity in flood disaster management. In this paper, we propose a new flood susceptibility mapping technique. We employ new ensemble models based on bagging as a meta-classifier and K-Nearest Neighbor (KNN) coarse, cosine, cubic, and weighted base classifiers to spatially forecast flooding in the Haraz watershed in northern Iran. We identified flood-prone areas using data from Sentinel-1 sensor. We then selected 10 conditioning factors to spatially predict floods and assess their predictive power using the Relief Attribute Evaluation (RFAE) method. Model validation was performed using two statistical error indices and the area under the curve (AUC). Our results show that the Bagging–Cubic–KNN ensemble model outperformed other ensemble models. It decreased the overfitting and variance problems in the training dataset and enhanced the prediction accuracy of the Cubic–KNN model (AUC=0.660). We therefore recommend that the Bagging–Cubic–KNN model be more widely applied for the sustainable management of flood-prone areas.

Flood Detection and Susceptibility Mapping Using Sentinel-1 Remote Sensing Data and a Machine Learning Approach: Hybrid Intelligence of Bagging Ensemble Based on K-Nearest Neighbor Classifier

It has been recognized that effective fault detection techniques can help semiconductor manufacturers reduce scrap, increase equipment uptime, and reduce the usage of test wafers. Traditional univariate statistical process control charts have long been used for fault detection. Recently, multivariate statistical fault detection methods such as principal component analysis (PCA)-based methods have drawn increasing interest in the semiconductor manufacturing industry. However, the unique characteristics of the semiconductor processes, such as nonlinearity in most batch processes, multimodal batch trajectories due to product mix, and process steps with variable durations, have posed some difficulties to the PCA-based methods. To explicitly account for these unique characteristics, a fault detection method using the k-nearest neighbor rule (FD-kNN) is developed in this paper. Because in fault detection faults are usually not identified and characterized beforehand, in this paper the traditional kNN algorithm is adapted such that only normal operation data is needed. Because the developed method makes use of the kNN rule, which is a nonlinear classifier, it naturally handles possible nonlinearity in the data. Also, because the FD-kNN method makes decisions based on small local neighborhoods of similar batches, it is well suited for multimodal cases. Another feature of the proposed FD-kNN method, which is essential for online fault detection, is that the data preprocessing is performed automatically without human intervention. These capabilities of the developed FD-kNN method are demonstrated by simulated illustrative examples as well as an industrial example.

Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes

Run-to-run (RtR) control technology has received tremendous interest in semiconductor manufacturing. Exponentially weighted moving average (EWMA), double-EWMA, and internal model control (IMC) filters are recognized methods for online RtR estimation. In this paper, we consider recursive least squares (RLS) as an alternative for online estimation and RtR control. The relationship between EWMA-type and RLS-type estimates is analyzed and verified with simulations. Because measurement delay is almost inevitable in semiconductor manufacturing, we discuss and compare the performance of EWMA, RtR-IMC, and RLS controllers in handling measurement delay and measurement noise for processes with a deterministic drift. An ad hoc solution is proposed to handle measurement delay for processes with time-varying drifts. The results are illustrated through several simulations and a shallow trench isolation (STI) etch process as an industrial example.

Recursive least squares estimation for run-to-run control with metrology delay and its application to STI etch process

With growing demand for effective management of abnormal situations in process industry, disturbance detection and classification has drawn considerable interest from researchers in both industry and academia. In this paper, a disturbance detection and classification method is developed using Bayesian statistics. The theoretical derivation of the proposed method as well as its practical implementation are provided. With the introduction of preand post-change windows, detection and classification are achieved simultaneously in the proposed method through matching the posterior probability pattern to predefined patterns. An overlapping window mechanism is incorporated into the proposed method to minimize detection and classification delay. A simulation example is given to illustrate the robustness and effectiveness of the proposed disturbance detection method. One application of the proposed Bayesian disturbance detection and classification algorithm is a Bayesian enhanced exponentially weighted moving average (B-EWMA) state estimator which improves state estimation in the run-to-run control of semiconductor manufacturing processes. The superior performance of B-EWMA compared to the conventional EWMA is demonstrated using an industrial example

A Bayesian Approach for Disturbance Detection and Classification and Its Application to State Estimation in Run-to-Run Control

In the past decade, both physical and data-driven models have been developed to investigate the valve stiction behavior. In this work, we compare different data-driven models against a well established physical model. The comparison is carried out in several aspects, including model assumptions, valve signatures generated by the models, and closed-loop behavior when valve models are included in a closed-loop system. A new semi-physical model is proposed based on a thorough analysis of the physical model and its effectiveness in simulating valve stiction is demonstrated.

Valve stiction modeling: First-principles vs data-drive approaches

Data-driven soft sensors have been widely used in both academic research and industrial applications for predicting hard-to-measure variables or replacing physical sensors to reduce cost. It has been shown that the performance of these data-driven soft sensors can be greatly improved by selecting only the vital variables that strongly affect the primary variables, rather than using all the available process variables. In this work, a comprehensive evaluation of different variable selection methods for soft sensor development is presented. The following seven variable selection methods are considered: stepwise regression (SR), partial least squares with regression coefficients (PLS-BETA), PLS with variable importance in projection (PLS-VIP), uninformative variable elimination with PLS (UVE-PLS), genetic algorithm with PLS (GA-PLS), least absolute shrinkage and selection operator (Lasso), and competitive adaptive reweighted sampling with PLS (CARS-PLS). Their strengths and limitations for soft sensor development are examined using a simulated case study and an industrial case study. Independent tuning datasets are used to optimize each method and to analyze the sensitivity of each method to its tuning parameters. Then independent test datasets are used to compare the prediction performances of PLS soft sensors developed based on different variable selection methods.

Qinghua He

Papers

Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes

Recursive least squares estimation for run-to-run control with metrology delay and its application to STI etch process

A Bayesian Approach for Disturbance Detection and Classification and Its Application to State Estimation in Run-to-Run Control

Valve stiction modeling: First-principles vs data-drive approaches

Comparison of different variable selection methods for partial least squares soft sensor development