A new approach to detecting the process changes for multistage systems

The study aims to develop a new control chart model suitable for monitoring the process quality of multistage manufacturing systems.Considering both the auto-correlated process outputs and the correlation occurring between neighboring stages in a multistage manufacturing system, we first propose a new multiple linear regression model to describe their relationship. Then, the multistage residual EWMA and CUSUM control charts are used to monitor the overall process quality of multistage systems. Moreover, an overall run length (ORL) concept is adopted to compare the detecting performance for various multistage residual control charts. Finally, a numerical example with oxide thickness measurements of a three-stage silicon wafer manufacturing process is given to demonstrate the usefulness of our proposed multistage residual control charts in the Phase II monitoring. A computerized algorithm can also be written based on our proposed scheme for the multistage residual EWMA/CUSUM control charts and it may be further converted to an expert and intelligent system. Hopefully, the results of this study can provide a better alternative for detecting process change and serve as a useful guideline for quality practitioners when monitoring and controlling the process quality of multistage systems with auto-correlated data.     

A method of sensor fault detection and identification

A method of Bayesian belief network (BBN)-based sensor fault detection and identification is presented. It is applicable to processes operating in transient or at steady-state. A single-sensor BBN model with adaptable nodes is used to handle cases in which process is in transient. The single-sensor BBN model is used as a building block to develop a multi-stage BBN model for all sensors in the process under consideration. In the context of BBN, conditional probability data represents correlation between process measurable variables. For a multi-stage BBN model, the conditional probability data should be available at each time instant during transient periods. This requires generating and processing a massive data bank that reduces computational efficiency. This paper presents a method that reduces the size of the required conditional probability data to one set. The method improves the computational efficiency without sacrificing detection and identification effectiveness. It is applicable to model- and data-driven techniques of generating conditional probability data. Therefore, there is no limitation on the source of process information. Through real-time operation and simulation of two processes, the application and performance of the proposed BBN method are shown. Detection and identification of different sensor fault types (bias, drift and noise) are presented. For one process, a first-principles model is used to generate the conditional probability data, while for the other, real-time process data (measurements) are used.     

Evaluating the reliability level of virtual metrology results for flexible process control: a novelty detection-based approach

The purpose of virtual metrology (VM) in semiconductor manufacturing is to support process monitoring and quality control by predicting the metrological values of every wafer without an actual metrology process, based on process sensor data collected during the operation. Most VM-based quality control schemes assume that the VM predictions are always accurate, which in fact may not be true due to some unexpected variations that can occur during the process. In this paper, therefore, we propose a means of evaluating the reliability level of VM prediction results based on novelty detection techniques, which would allow flexible utilization of the VM results. Our models generate a high-reliability score for a wafer’s VM prediction only when its process sensor values are found to be consistent with those of the majority of wafers that are used in model building; otherwise, a low-reliability score is returned. Thus, process engineers can selectively utilize VM results based on their reliability level. Experimental results show that our reliability generation models are effective; the VM results for wafers with a high level of reliability were found to be much more accurate than those with a low level.     

Adaptive modelling for adaptive water quality management in the Great Barrier Reef region,Australia

The development and use of a Bayesian Belief Network (BBN) model, within an adaptive management process for the management of water quality in the Mackay Whitsunday region of Queensland, Australia is described. The management goal is firstly to set achievable targets for water quality entering the Great Barrier Reef lagoon from the Mackay Whitsunday natural resource management region and then secondly to define and implement a strategy to achieve these targets. The BBN serves as an adaptive framework that managers and scientists may use to articulate what they know about the managed system. It then provides a tool to guide where, when and what interventions (including research) are most likely to achieve management outcomes. Importantly the BBN provides a platform for collective learning.BBN estimates of total suspended sediment (TSS) loads and event mean concentrations (EMCs) were compared to observed data and results from current best practice models. The BBN estimates were reasonable relative to empirical observations. Example results from the BBN are thereafter used to illustrate the use of the model in estimating the likelihood of exceeding water quality targets with and without proposed actions to improve water quality. Example results are also used to illustrate what spatial or land use elements might contribute most to exceeding water quality targets. Finally key limitations of the tool are discussed and important learnings from the process are highlighted.     

加权k最近邻重构分析的工业过程故障诊断

k--最近邻(k--nearest neighbor, k--NN)是一种有效的基于数据驱动的故障检测方法, 该方法在工业过程监视方面已经得到了广泛的应用. 但在过程中存在故障时, 精确地寻找故障根源和识别故障变量是故障诊断的重要目标, 也是保证工业过程安全生产的重要任务. 本文在k--NN故障检测技术的基础上, 提出了一种加权的k--NN重构方法, 对使控制指标减小最大(maximize reduce index, MRI)的过程变量依次进行重构, 进而确定发生故障的传感器. 根据理论分析并结合数值仿真对提出的方法进行了验证, 数值仿真先从精度方面验证了该方法能够有效地对故障传感器数值进行重构, 然后验证了该方法不仅适用于单一传感器 故障诊断, 对于同时发生或者因变量相关性而传播的传感器故障也具有很好的效果. 最后, 该方法被成功应用于TE(Tennessee Eastman)化工过程.     

SR-30 turbojet engine real-time sensor health monitoring using neural networks,and Bayesian belief networks

This paper describes the use of artificial intelligence-based techniques for detecting and isolating sensor failures in a turbojet engine. Specifically, three artificial intelligence (AI) techniques are employed: artificial neural networks (NNs), statistical expectations, and Bayesian belief networks (BBNs). These techniques are combined into an overall system that is capable of distinguishing between sensor failure and engine failure—a critical capability in the operation of turbojet engines. The turbojet engine used in this study is an SR-30 developed by Turbine Technologies. Initially, NNs were designed and trained to recognize sensor failure in the engine. The increased random noise output from failing sensors was used as the key indicator. Next, a Bayesian statistical method was used to recognize sensor failure based on the bias error occurring in the sensors. Finally, a BBN was developed to interpret the results of the NN and statistical evaluations. The BBN determines whether single or multiple sensor failures signify engine failure, or whether sensor failures represent separate, unrelated incidences. The BBN algorithm is also used to distinguish between bias and noise errors on sensors used to monitor turbojet performance. The overall system is demonstrated to work equally well during start-up and main-stage operation of the engine. Results show that the method can efficiently detect and isolate single or multiple sensor failures within this dynamic environment.     

High-speed train fault detection with unsupervised causality-based feature extraction methods

With the development of smart sensors, large amount of operating data collected from a complex system as a high-speed train providing opportunities in efficient and effective fault detection and diagnosis (FDD). The data brings also challenges in the FDD modelling process, since the various signals may be redundant, useless and noisy for the FDD modelling of a specific sub-system. The data-driven methods suffer also from the curse of dimensionality. Feature dimension reduction can reduce the dimension of the monitoring dataset and eliminate the useless information. Different from the classical methods based on the correlation among variables, recent studies have shown that causality-based methods can make the FDD model more explanatory and robust. From the adjacency matrix of the causal network diagram, three unsupervised causality-based feature extraction methods for FDD in the braking system of a high-speed train are proposed in this paper. By constructing the causal network diagram among the raw monitoring feature variables through the causal discovery algorithm, the proposed methods extract informative features based on the causal adjacency matrix or the full causal adjacency matrix proposed in this work. These methods are adopted for fault detection with real dataset collected from the braking system in a high-speed train to verify their effectiveness. The experimental results show that the proposed causality-based feature extraction methods are effective and have certain advantages in comparison with the classical correlation-based methods. Especially, the feature extraction method based on the correlation matrix constructed from full causal adjacency matrix achieves better and stable results than the benchmark methods in the experiment.     

Inferential control of product quality attributes—application to food cooking extrusion process

Reducing product quality variability is one of the most important issues for the process industry. As product quality attributes (PQAs) are often measured in a laboratory using off-line sensors, direct feedback control is not feasible unless expensive on-line sensors are used. Inferential control provides a means to the solution of this type of problem without the cost of expensive sensors. This paper reports a successful application of control of product quality attributes in a food cooking extruder. It covers the essential steps in achieving the control objective: (1) identifying the influential variables that can be measured on-line and have significant impact on the product quality attributes; (2) estimating a dynamic model between the influential variables and the PQAs for on-line prediction of product quality; (3) on-line feedback control using the influential variables. Experimental results demonstrate that the designed control system not only maintains the quality of the products but also automatically brings the PQAs to user's specification.     

A Bayesian support tool for morphological design

Dynamic computer based support tools for the conceptual design phase have provided a long-standing challenge to develop. This is largely due to the ‘fluid’ nature of the conceptual design phase. Design evaluation methods, which form the basis of most computer design support tools, provide poor support for multiple outcomes. This research proposes a stochastic-based support tool that addresses this problem. A Bayesian Belief Network (BBN) is used to represent the causal links between design variables. Included in this research is an efficient method for learning a design domain network from previous design data in the structure of a morphological design chart. This induction algorithm is based on information content. A user interface is proposed to support dynamically searching the conceptual design space, based on a partial design specification. This support tool is empirically compared against a more traditional search process. While no compelling evidence is produced to support the stochastic-based approach, an interesting broader design search behaviour emerges from observations of the use of the stochastic design support tool.     

Control relevant issues in semiconductor manufacturing: Overview with some new results

The quality control of integrated circuit (IC) processing is becoming more and more important as the wafer becomes larger and the feature size shrinks. However, an advanced IC fabrication process consists of 300+ steps with scarce and usually difficult quality measurements. Thus product yield may not be realized until months into production while in-line measurements are available on the order of a millisecond. The series production nature and measurement setup lead to a unique process control problem. In this work, typical disturbances are explained and the possibility for inferential control is explored. This leads to a control architecture with multiple layers in a cascade structure. Next, the rapid thermal processing (RTP) is used to illustrate recipe generation and control structure design at the tool level. The resultant multivariable controller gives satisfactory setpoint tracking for a triangular-like temperature program. Effective delay in a feedback loop at the process level is also clarified which can be used to design a run-to-run controller or to prioritize the measurement queue for the metrology tool. In order to prolong the time between maintenance and to reduce rework, process trend monitoring of a tool is essential. Instead of using entire batch data, a key process variable is identified and an index is computed to capture dynamic behavior of the tool. An IC processing example is used to illustrate this approach and results clearly indicate that process trend is well predicted using the index-based time-series model. Finally, future research directions for improved semiconductor manufacturing are also described.     

Multivariate statistical process control of an industrial fluidised-bed reactor

Multivariate statistical process control (MSPC) is a tool for the comprehensive monitoring of the performance of a manufacturing process. There is now a real need to demonstrate the applicability of MSPC to complex manufacturing processes and highlight the benefits that can be derived from its implementation. Alongside this, is the increasing interest in predicting quality or important chemical quality variables associated with product yield and production. This paper demonstrates the performance monitoring potential of MSPC and the predictive capability of canonical variates analysis and projection to latent structures by application to an industrial fluidised-bed reactor.     

High temperature resistant antireflective moth-eye structures for infrared radiation sensors

The Fresnel reflections occurring at the interfaces of a silicon wafer shall be drastically reduced by reactive ion beam etching of so called moth-eye structures into both surfaces of the wafer. This kind of impedance matching is advantageous to a multilayer interference system when the silicon wafer shall be used as an entrance window for high temperature thermopile infrared radiation sensors and emitters. The transmission was measured to be increased by more then 60%, compared to a polished silicon wafer.The authors wish to thank Dr. Albrecht Lerm, and Jürgen Müller, Institute for Physical High Technology, for their advice making these investigations.     

E+H组合式过程测控装置及实时监控系统设计

Endress+Hauser(E+H)工业现场仪表广泛应用于石油、冶金、电力、生命科学等多个核心行业,具有可靠集成、精准测量、交互式数据管理等特点。为提高实验装置工业适用性,培养学生熟练运用工业级传感器和过程监控的操作技能,将这类传感器引入实验室,设计了一套E+H组合式过程测控装置与实时监控系统。系统以过程控制涉及的典型对象为基础,以PLC为控制主体,组合装配多类工业级E+H传感器完成检测与控制,并具备实时组态控制显示和远程可视化监控功能。可实现自主设计并完成工业过程中常见的液位、流量、温度、溶液PH等控制量的测控实验,为自动化、测控技术、传感器等相关专业课程提供综合实验平台。     

Mining and visualising ordinal data with non-parametric continuous BBNs

Data mining is the process of extracting and analysing information from large databases. Graphical models are a suitable framework for probabilistic modelling. A Bayesian Belief Net (BBN) is a probabilistic graphical model, which represents joint distributions in an intuitive and efficient way. It encodes the probability density (or mass) function of a set of variables by specifying a number of conditional independence statements in the form of a directed acyclic graph. Specifying the structure of the model is one of the most important design choices in graphical modelling. Notwithstanding their potential, there are only a limited number of applications of graphical models on very complex and large databases. A method for mining ordinal multivariate data using non-parametric BBNs is presented. The main advantage of this method is that it can handle a large number of continuous variables, without making any assumptions about their marginal distributions, in a very fast manner. Once the BBN is learned from data, it can be further used for prediction. This approach allows for rapid conditionalisation, which is a very important feature of a BBN from a user’s standpoint.     

Understanding Indirect Causal Relationships in Node‐Link Graphs

To find correlations and cause and effect relationships in multivariate data sets is central in many data analysis problems. A common way of representing causal relations among variables is to use node‐link diagrams, where nodes depict variables and edges show relationships between them. When performing a causal analysis, analysts may be biased by the position of collected evidences, especially when they are at the top of a list. This is of crucial importance since finding a root cause or a derived effect, and searching for causal chains of inferences are essential analytic tasks when investigating causal relationships. In this paper, we examine whether sequential ordering influences understanding of indirect causal relationships and whether it improves readability of multi‐attribute causal diagrams. Moreover, we see how people reason to identify a root cause or a derived effect. The results of our design study show that sequential ordering does not play a crucial role when analyzing causal relationships, but many connections from/to a variable and higher strength/certainty values may influence the process of finding a root cause and a derived effect.     

Detecting anomalies and de-noising monitoring data from sensors: A smart data approach

When monitoring safety levels in deep pit foundations using sensors, anomalies (e.g., highly correlated variables) and noise (e.g., high dimensionality) exist in the extracted time series data, impacting the ability to assess risks. Our research aims to address the following question: How can we detect anomalies and de-noise monitoring data from sensors in real time to improve its quality and use it to assess geotechnical safety risks? In addressing this research question, we develop a hybrid smart data approach that integrates Extended Isolation Forest and Variational Mode Decomposition models to detect anomalies and de-noise data effectively. We use real-life data obtained from sensors to validate our smart data approach while constructing a deep pit foundation. Our smart data approach can detect anomalies with a root mean square error and signal-to-noise ratio of 0.0389 and 24.09, respectively. To this end, our smart data approach can effectively pre-process data enabling improved decision-making and the management of safety risks.     

Design of inferential sensors in the process industry: A review of Bayesian methods

In many industrial plants, development and implementation of advanced monitoring and control techniques require real-time measurement of process quality variables. However, on-line acquisition of such data may involve difficulties due to inadequacy of measurement techniques or low reliability of measuring devices. To overcome the shortcomings of traditional instrumentation, inferential sensors have been designed to infer process quality indicators from real-time measurable process variables. In recent years, due to the demonstrated advantages of Bayesian methods, interest in investigating the application of these methods for design of inferential sensors has grown. However, the potential of Bayesian methods for inferential modeling practices in the process industry has not yet been fully realized. This paper provides a general introduction to the main steps involved in development and implementation of industrial inferential sensors, and presents an overview of the relevant Bayesian methods for inferential modeling.     

Hybrid causal analysis combining a nonparametric multiplicative regression causality estimator with process connectivity information

Industrial processes are often subjected to abnormal events such as faults or external disturbances which can easily propagate via the process units. Establishing causal dependencies among process measurements has a key role in fault diagnosis due to its ability to identify the root cause of a fault and its propagation path. This paper proposes a hybrid nonlinear causal analysis based on nonparametric multiplicative regression (NPMR) for identifying the propagation of an oscillatory disturbance via control loops. The NPMR causality estimator addresses most of the limitations of the linear model-based methods and it can be applied to both bivariate and multivariate estimations without any modifications to the method parameters. Moreover, the NPMR-based estimations can be used to pinpoint the root cause of a fault. The process connectivity information is automatically integrated into the causal analysis using a specialized search algorithm. Thereby, it enables to efficiently tackle industrial systems with a high level of connectivity and enhance the quality of the results. The proposed approach is successfully demonstrated on an industrial board machine exhibiting oscillations in its drying section due to valve stiction and. The NPMR-based estimator produced highly accurate results with relatively low computational effort compared with the linear Granger causality and other nonlinear causality estimators.     

Data‐Driven Performance Monitoring for Model Predictive Control Using a mahalanobis distance based overall index

This paper proposes a data‐driven approach for model predictive control (MPC) performance monitoring. It explores the I/O data of the MPC system. First, to evaluate the MPC performance and capture the fluctuation of the process variables, we present an overall performance index based on Mahalanobis distance (MDBI) with its deduced benchmark. The Mahalanobis distance can better characterize the change of the process variable in both principal component space and residual space. As the proper vectors of the two spaces are orthogonal, the MDBI eliminates the correlation between the process variables while considering the variables’ characteristics in both spaces simultaneously, which helps evaluate the MPC performance more effectively with fewer monitoring parameters. Furthermore, for the MPC performance diagnosis, we use the MDBI as inputs and construct a support vector machine (SVM) pattern classifier. The classifier can achieve a higher accuracy when recognizing four common performance degradation patterns and determine the root cause of performance degradation. The results of simulations on the Wood‐Berry distillation column process and experiments on NIAT multifunctional experiment platform illustrate the effectiveness of the proposed performance assessment/diagnosis strategies.     

压电晶体传感器激励模型及其在结构健康监测中的应用

在结构健康监测系统中,基于应力波的结构损伤诊断技术是一种主动的局部损伤检测方法.压电晶体传感器作为激励部件可以在结构中引入高频应力波;其同裂纹等局部损伤发生相互作用将产生波动的能量耗散、波形反射以及波形干涉等现象.通过对附着在无约束金属板上的压电晶体传感器(PZT)激励模型的理论分析及有限元数值计算,说明PZT能有效地产生检测应力波,并可将其应用在结构局部损伤检测中.