Control chart pattern recognition using an optimized neural network and efficient features

Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This study investigates the design of an accurate system for control chart pattern (CCP) recognition from two aspects. First, an efficient system is introduced that includes two main modules: the feature extraction module and the classifier module. The feature extraction module uses the entropies of the wavelet packets. These are applied for the first time in this area. In the classifier module several neural networks, such as the multilayer perceptron and radial basis function, are investigated. Using an experimental study, we choose the best classifier in order to recognize the CCPs. Second, we propose a hybrid heuristic recognition system based on particle swarm optimization to improve the generalization performance of the classifier. The results obtained clearly confirm that further improvements in terms of recognition accuracy can be achieved by the proposed recognition system.     

Control chart pattern recognition using RBF neural network with new training algorithm and practical features

The control chart patterns are the most commonly used statistical process control (SPC) tools to monitor process changes. When a control chart produces an out-of-control signal, this means that the process has been changed. In this study, a new method based on optimized radial basis function neural network (RBFNN) is proposed for control chart patterns (CCPs) recognition. The proposed method consists of four main modules: feature extraction, feature selection, classification and learning algorithm. In the feature extraction module, shape and statistical features are used. Recently, various shape and statistical features have been presented for the CCPs recognition. In the feature selection module, the association rules (AR) method has been employed to select the best set of the shape and statistical features. In the classifier section, RBFNN is used and finally, in RBFNN, learning algorithm has a high impact on the network performance. Therefore, a new learning algorithm based on the bees algorithm has been used in the learning module. Most studies have considered only six patterns: Normal, Cyclic, Increasing Trend, Decreasing Trend, Upward Shift and Downward Shift. Since three patterns namely Normal, Stratification, and Systematic are very similar to each other and distinguishing them is very difficult, in most studies Stratification and Systematic have not been considered. Regarding to the continuous monitoring and control over the production process and the exact type detection of the problem encountered during the production process, eight patterns have been investigated in this study. The proposed method is tested on a dataset containing 1600 samples (200 samples from each pattern) and the results showed that the proposed method has a very good performance.     

Control chart pattern recognition using feature-based learning vector quantization

The reported learning vector quantization (LVQ) network-based control chart pattern (CCP) recognizers in literature use raw process data as the input vector and can recognize six basic CCPs only. In this paper, an LVQ network-based CCP recognizer is presented that can recognize eight basic CCPs, using seven extracted shape features from the pattern data as the input vector. The recognition performance of this recognizer is compared with the LVQ network-based recognizer that uses raw process data as the input vector. The results show that the feature-based recognizer results in substantially better recognition performance than the raw data-based recognizer. The confusion matrix reveals that the recognition performance of the feature-based recognizer can be improved further if any feature that is more powerful in discriminating shift and trend pattern can be identified. Comparison of performances of LVQ network-based and multilayer perceptrons (MLP) network-based recognizers (both using extracted features as input vector) reveals that the LVQ network-based recognizer requires much lesser learning time than the MLP network-based recognizer, but results in little inferior recognition performance.     

Control chart pattern recognition using K-MICA clustering and neural networks

Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This paper presents a novel hybrid intelligent method (HIM) for recognition of the common types of control chart pattern (CCP). The proposed method includes two main modules: a clustering module and a classifier module. In the clustering module, the input data is first clustered by a new technique. This technique is a suitable combination of the modified imperialist competitive algorithm (MICA) and the K-means algorithm. Then the Euclidean distance of each pattern is computed from the determined clusters. The classifier module determines the membership of the patterns using the computed distance. In this module, several neural networks, such as the multilayer perceptron, probabilistic neural networks, and the radial basis function neural networks, are investigated. Using the experimental study, we choose the best classifier in order to recognize the CCPs. Simulation results show that a high recognition accuracy, about 99.65%, is achieved.     

Application of the PSO–SVM model for recognition of control chart patterns

Control chart patterns are important statistical process control tools for determining whether a process is run in its intended mode or in the presence of unnatural patterns. Accurate recognition of control chart patterns is essential for efficient system monitoring to maintain high-quality products. This paper introduces a novel hybrid intelligent system that includes three main modules: a feature extraction module, a classifier module, and an optimization module. In the feature extraction module, a proper set combining the shape features and statistical features is proposed as the efficient characteristic of the patterns. In the classifier module, a multi-class support vector machine (SVM)-based classifier is proposed. For the optimization module, a particle swarm optimization algorithm is proposed to improve the generalization performance of the recognizer. In this module, it the SVM classifier design is optimized by searching for the best value of the parameters that tune its discriminant function (kernel parameter selection) and upstream by looking for the best subset of features that feed the classifier. Simulation results show that the proposed algorithm has very high recognition accuracy. This high efficiency is achieved with only little features, which have been selected using particle swarm optimizer.     

Noise tolerance for pattern recognition for statistical process control

This paper describes an investigation into the performance of an algorithmic pattern recognition system for statistical process control applications. The study, based on the application of simulation techniques, investigates whether the system can recognise patterns in the presence of noise, and how much noise the Pattern Recogniser can accept in relation to individual patterns. The level of noise tolerance for each pattern is analysed using simulated data. The simulation procedures are presented and the results are discussed. The pattern recognition system was found to be tolerant of noise, the level of tolerance generally depending on the pattern specification.Notation N _i ith data item from a noise series - x _i ith data item from a number sequence - N _T noise tolerance - _n standard deviation for noise - _s standard deviation for signal - standard deviation - adjacent difference - CL centre-line - i indexing integer - j indexing integer - k total number of samples - l starting point of a pattern on control chart - LCL lower control limit - LNTL lower noise tolerance limit - LOSL lower one sigma limit - LWL lower warning limit - N/S noise to signal ratio - slope slope for trend patterns - UCL upper control limit - UNTL upper noise tolerance limit - UOSL upper one sigma limit - UWL upper warning limit     

A nonparametric control chart based on the Mood statistic for dispersion

Control charts are used as a statistical process control (SPC) to distinct the presence of an assignable cause of variation in the process. The advantage of the nonparametric control charts is that the nonparametric charts can be useful in statistical process control problems when there is a lack of knowledge about the underlying process distribution. In this paper, the nonparametric control chart is considered based on the rank sum statistic for dispersion. In the case of small sample sizes, the exact control limits are derived. For the large sample sizes, the control limits are evaluated by using the normal and saddlepoint approximations. The nonparametric charting statistic is applied for the real data.     

Improved recognition of control chart patterns using artificial neural networks

Recognition of abnormal patterns in control charts provides clues to reveal potential quality problems in the manufacturing processes. One potentially popular approach for recognizing different control chart patterns (CCPs) is to develop heuristics based on various shape features of the patterns. The advantage of this approach is that the users can easily understand how a particular pattern is identified. However, consistency in the recognition performance is found to be considerably poor in the heuristics approach. Since shape features represent the main characteristics of the patterns in a condensed form, artificial neural network (ANN) with features extracted from the process data as input vector representation can facilitate efficient pattern recognition with a smaller network size. In this paper, a set of seven shape features is selected, whose magnitudes are independent of the process mean and standard deviation under a special representation of the sampling interval in the control chart plot. Based on these features, the CCPs are recognized using a multilayered perceptron neural network trained by back-propagation algorithm. The recognizer can recognize all the eight commonly observed CCPs. Extensive performance evaluation of this recognizer is carried out using simulated pattern data. Numerical results indicate that the developed ANN recognizer can perform well in real time process control applications with respect to both recognition accuracy and consistency.     

基于模式识别的脉冲压力自适应控制

脉冲滴丸机压力控制系统是具有非线性、参数时变性和耦合性特征的复杂系统,系统响应要求快速、准确、鲁棒性强,但传统的控制方法如常规的固定参数的PID控制器很难使系统同时达到这种最优控制。因此,提出了将自适应控制、模式识别和PID控制相结合的思想,设计了一种基于模式识别的脉冲压力自适应控制策略,通过在线辩识系统的动态输出,根据系统响应所处的状态,采取相应的控制算法,使系统得到了较好的控制。MATLAB仿真和现场实验结果均表明该方法具有较高的动态性能和控制精度,以及较强的鲁棒性。该控制系统已成功投入现场运行。     

基于标准化变换的质量控制图研究

基于标准化变换的质量控制图一般应用在小批量环境下,对生产过程进行控制。分析标准化变换的准则,指出工序分析起到关键作用及能否对工序进行控制,不在于统计,而在于管理;通过对不同数据变换方式有效性的研究表明,各种标准化变换控制图的复杂性及灵敏性是不同的,因此要依工序分析的结果灵活采用各种标准化控制图。     

用模式识别轧机尾部跑偏的自适应控制

针对铝带热连轧轧制过程中影响跑偏的非线性因素众多,很难建立相应的跑偏控制模型的特点,基于现场测试数据进行分析,通过分析跑偏信号的数据特征,建立轧制过程跑偏量值神经网络辨识模型,找出了尾部跑偏模式与F_4机架敏感轧制参数的非线性关系,给出可应用于实际轧制生产的自适应纠偏控制模型,并以一组实测数据进行分析,纠偏效果良好.     

A novel approach for recognition of control chart patterns: Type-2 fuzzy clustering optimized support vector machine

Unnatural patterns in the control charts can be associated with a specific set of assignable causes for process variation. Hence, pattern recognition is very useful in identifying the process problems. In this study, a multiclass SVM (SVM) based classifier is proposed because of the promising generalization capability of support vector machines. In the proposed method type-2 fuzzy c-means (T2FCM) clustering algorithm is used to make a SVM system more effective. The fuzzy support vector machine classifier suggested in this paper is composed of three main sub-networks: fuzzy classifier sub-network, SVM sub-network and optimization sub-network. In SVM training, the hyper-parameters plays a very important role in its recognition accuracy. Therefore, cuckoo optimization algorithm (COA) is proposed for selecting appropriate parameters of the classifier. Simulation results showed that the proposed system has very high recognition accuracy.     

Identifying change point of a non-random pattern on control chart using artificial neural networks

An important step in root cause analysis is the identification of the time when process first changed. The time when a disturbance first manifested itself into the process is referred to as change point. Identification of the change point could help process engineer to perform root cause analysis effectively. In this paper, an estimator for the change point of a normal process mean using artificial neural network (ANN) is proposed. Five patterns of change namely single step, linear trend, systematic, cyclic, and mixture are studied. Whenever possible, results are compared numerically to the results obtained by other methods proposed by different researchers. First the type of change to be recognized by an ANN-based pattern recognizer is identified and then the change point in the process mean is estimated. Results indicate satisfactory performance for the proposed method that could be used as an effective method for root cause analysis by process engineer.     

一种应用于光缆外破在线监控的模式识别方案

电力通信网络线路常因沿途的工程机械施工,人为外力破坏等行为造成毫无预警的危害和损坏。为了实现对线路外破隐患高效预警,需要在现有预警定位的基础上,加上对碰撞敲击、管孔侵入、机械施工和开盖报警等行为的识别。将分布式光纤传感技术、梅尔频率倒谱系数和径向基神经网络相结合,提出一种可应用于光缆外破在线监控的模式识别方案。测试的总体识别率达97.78%,现场模拟的事件报警准确率高。该方案可广泛应用于长距离管线检测领域。     

小批量过程多变异控制图技术研究

针对小批量过程的主要控制图技术中目标图、比例图和标准变换图,归纳出小批量过程控制的同分布原理。考虑到不同小批量之间的差异,以目标均值控制图为例,对控制图进行改进,给出多变异目标均值控制图的建立步骤。通过一个例子发现,该方法既实现了小批量过程多变异的控制,又降低了控制图虚发警报的概率。     

A new adaptive control chart for monitoring process mean and variability

Traditionally, an $\bar{X}$ chart is used to control the process mean, and an R chart is used to control the variance. However, these charts are not sensitive to the small shifts in the processes. The adaptive charts might be considered if the aim is to detect process changes quickly. In this paper, we propose a new adaptive single control chart which integrates the exponentially weighted moving average procedure with the generalized likelihood ratio test statistics for jointly monitoring both the process mean and variability. This new chart is effective in detecting the disturbances that shift the process mean, increase or decrease the process variance, or lead to a combination of both effects.     

A synthetic control chart for monitoring process dispersion with sample range

A synthetic control chart for monitoring the changes in the standard deviation of a normally distributed process is proposed in this paper. The synthetic chart consists of the sample range (R) chart and the conforming run-length (CRL) chart. The R chart can be viewed as a special case of the synthetic chart. The operation, design and performance of this chart are described. Average run- length comparisons between other procedures and the synthetic chart are presented. It indicates that the synthetic chart is a good alternative for monitoring process dispersion. The variable sampling interval (VSI) schemes, as an enhancement to the synthetic chart, are discussed to further improve the chart performance. An example is presented to illustrate the application of synthetic chart and its VSI scheme.     

面向汽车造型的用户视觉模式识别比较

为使汽车造型设计更好地符合目标用户的审美心理,以跨文化视角对用户视觉模式识别进行了比较研究。基于Treisman的特征整合理论,提出汽车造型视觉识别一般模型。以汽车前视正面造型为样本,选取中德两国用户作为被试者,以品牌识别为任务,首先使用Dikablis眼动仪进行眼动跟踪实验,再结合Likert量表进行识别度的问卷调查。利用灰度直方图对眼动热点图进行特征提取,并对用户感兴趣区域的各项指标进行了对比分析,所得结论为面向中国市场的车型开发提供了借鉴和参考。     

Interpreting the out-of-control signal in multivariate control chart — a comparative study

Interpretation of the out-of-control signal poses a persistent problem in multivariate control chart owing to the limitations of available general methods like Hotelling T². Many research papers address these problems and present alternative approaches to diagnose faults in out-of-control conditions and to help identify aberrant variables. This work reviews the different methods and attempts to make a comparative study of some of these methods viz. Mason, Tracy and Young method (Journal of Quality Technology 27:99–108, 1995), Murphy method (The Statistician 36:571–583, 1987), Hawkins method (Technometrics 33:61–75, 1991) and Doganaksoy, Faltin and Tucker method (Communications in Statistics — Theory and Methods 20:2775–2790, 1991). A simulation approach was taken to generate data on various out of control situation and to compare the powers of different targeted methods. In control sate was characterised by a multi-variate normal with standardised mean and variance assuming intra-class correlation structure. Data were generated for different values of correlation and various out of control situation with respect to the shift of mean in one, two or more variables. Due to the limitations of using average run length as a performance criterion especially in case of skewed distribution of run length it was decided to use power as a measure of comparison. Situations in which the particular method works satisfactorily were identified with respect to correlation structure and pattern of shift of mean.