Neural network-based real-time malfunction diagnosis of reactive ion etching using in situ metrology data

To mitigate capital equipment investments and enhance product quality, semiconductor manufactures are turning to advanced process control (APC) methods. With the objective of facilitating APC, this paper investigates a methodology for real-time malfunction diagnosis of reactive ion etching (RIE) employing two types of in situ metrology: optical emission spectroscopy (OES) and residual gas analysis (RGA). Based on metrology data, time series neural networks (TSNNs) are trained to generate evidential belief for potential malfunctions in real time, and Dempster-Shafer (D-S) theory is adopted for evidential reasoning. Successful malfunction diagnosis is achieved, with only a single missed alarm and a single false alarm occurring out of 21 test runs when both sensors are used in tandem. From the results, we conclude that the OES and RGA sensors, in conjunction with the TSNN models, can be effectively used for RIE monitoring and diagnosis. Furthermore, D-S theory is shown to be an appropriate inference methodology.     

等离子体刻蚀工艺中的OES监控技术

采用光学发射光谱(OES)原位检测技术,对等离子体刻蚀机中的等离子体状态进行实时监控,讨论了其在故障诊断、分类、刻蚀终点的判断及控制方面的应用。实验平台为在新研发的高密度等离子体刻蚀机,采用化学气体HBr/Cl₂为刻蚀气体进行多晶硅刻蚀工艺实验,实验过程中所采集的OES数据通过PCA法进行分析,得到与刻蚀过程相关的特征谱线。实验结果表明：OES技术适合于深亚微米等离子体刻蚀工艺过程的终点检测及故障诊断。最后就OES技术未来发展面临的挑战进行了讨论。     

Neural network modeling of reactive ion etching using optical emission spectroscopy data

Neural networks are employed to model reactive ion etching (RIE) using optical emission spectroscopy (OES) data. While OES is an excellent tool for monitoring plasma emission intensity, a primary issue with its use is the large dimensionality of the spectroscopic data. To alleviate this concern, principal component analysis (PCA) and autoencoder neural networks (AENNs) are implemented as mechanisms for feature extraction to reduce the dimensionality of the OES data. OES data are generated from a 2/sup 4/ factorial experiment designed to characterize RIE process variation during the etching of benzocyclobutene (BCB) in a SF/sub 6//O/sub 2/ plasma, with controllable input factors consisting of the two gas flows, RF power, and chamber pressure. The OES data, consisting of 226 wavelengths sampled every 20 s, are compressed into five principal components using PCA and seven features using AENNs. Each method is subsequently used to establish multilayer perceptron neural networks trained using error back-propagation to model etch rate, uniformity, selectivity, and anisotropy. The neural network models of the etch responses using both methods show excellent agreement, with root-mean-squared errors as low as 0.215% between model predictions and measured data.     

Spatial characterization of wafer state using principal componentanalysis of optical emission spectra in plasma etch

Optical emission spectroscopy (OES) is often used to obtain in-situ estimates of process parameters and conditions in plasma etch processes. Two barriers must be overcome to enable the use of such information for real-time process diagnosis and control. The first barrier is the large number of measurements in wide-spectrum scans, which hinders real-time processing. The second barrier is the need to understand and estimate not only process conditions, but also what is happening on the surface of wafer, particularly the spatial uniformity of the etch. This paper presents a diagnostic method that utilizes multivariable OES data collected during plasma etch to estimate spatial asymmetries in commercially available reactor technology. Key elements of this method are: first, the use of principal component analysis (PCA) for dimensionality reduction, and second, regression and function approximation to correlate observed spatial wafer information (i.e., line width reduction) with these reduced measurements. Here we compare principal component regression (PCR), partial least squares (PLS), and principal components combined with multilayer perceptron neural networks (PCA/MLP) for this in-situ estimation of spatial uniformity. This approach has been verified for a 0.35-μm aluminum etch process using a Lam 9600 TCP etcher. Models of metal line width reduction across the wafer are constructed and compared: the root mean square prediction errors on a test set withheld from training are 0.0134 μm for PCR, 0.014 μm for PLS, and 0.016 μm for PCA/MLP. These results demonstrate that in-situ spatially resolved OES in conjunction with principal component analysis and linear or nonlinear function approximation can be effective in predicting important product characteristics across the wafer     

Statistical feedback control of a plasma etch process

This paper presents the methodology developed for the automatic feedback control of a silicon nitride plasma etch process. The methodology provides an augmented level of control for semiconductor manufacturing processes, to the level that the operator inputs the required process quality characteristics (e.g. etch rate and uniformity values) instead of the desired process conditions (e.g., specific RF power, pressure, gas flows). The optimal equipment settings are determined from previously generated process/equipment models. The control algorithm is driven by the in-situ measurements, using in-line sensors monitoring each wafer. The sensor data is subjected to Statistical Quality Control (SQC) to determine if deviations from the required process observable values can be attributed to noise in the system or are due to a sustained anomalous behavior of the equipment. Once a change in equipment behavior is detected, the process/equipment models are adjusted to match the new state of the equipment. The updated models are used to run subsequent wafers until a new SQC failure is observed. The algorithms developed have been implemented and tested, and are currently being used to control the etching of wafers under standard manufacturing conditions     

Network traffic prediction based on INGARCH model

In this paper, we introduce the integer-valued generalized autoregressive conditional heteroscedasticity (INGARCH) as a network traffic prediction model. As the INGARCH is known as a non-linear analytical model that could capture the characteristics of network traffic such as Poisson packet arrival and long-range dependence property, INGARCH seems to be an adequate model for network traffic prediction. Based on the investigation for the traffic arrival process in various network topologies including IoT and VANET, we could confirm that assuming the Poisson process as packet arrival works for some networks and environments of networks. The prediction model is generated by estimating parameters of the INGARCH process and predicting the Poisson parameters of future-steps ahead process using the conditional maximum likelihood estimation method and prediction procedure, respectively. Its performance is compared with those of three different models; autoregressive integrated moving average, GARCH, and long short-term memory recurrent neural network. Anonymized passive traffic traces provided by the Center for Applied Internet Data Analysis are used in the experiment. Numerical results show that the proposed model predicts better than the three models in terms of measurements used in prediction models. Based on the study, we can conclude the followings: INGARCH can capture the characteristics of network traffic better than other statistic models, it is more tractable than neural networks (NNs) overcoming the black-box nature of NNs, and the performances of some statistical models are comparable or even superior to those of NNs, especially when the data is insufficient to apply deep NNs.

     

多传感器信息融合技术应用研究

近年来,情报、监视和侦察领域的多传感器信息融合技术研究飞速发展,应用领域不断扩展,显示出巨大的优越性,发挥了重要作用。战场的数字化对战场侦察监视领域的多传感器信息融合的质量和效率都提出了更高的要求。根据多传感器信息融合技术的研究现状,从运用的角度出发,结合当前建设中存在的一系列问题,对战场侦察监视领域多传感器信息融合技术的主要作用和工作特点进行了比较深入的研究,分析了多传感器信息融合技术在战略预警探测、地面传感侦察、雷达组网监视、图像情报处理和机载多传感器集成等ISR领域的应用特点和前景。     

一种红外/雷达双传感器融合目标跟踪算法

分析了一种集中式单目标雷达／红外双传感器融合跟踪算法的基本流程，针对两种传感器间测量信息不同步的问题，采用了一种基于最小二乘法的时空配准方法。给出了一种基于拉格朗日乘数法的最优加权平均融合算法，并设计了跟踪滤波器进行仿真实验。     

熔石英亚表面微缺陷原位表征及损伤阈值研究

通过对熔石英表面和亚表面划痕的原位测量,研究划痕的表面均方根(RMS)粗糙度、宽度和深度在HF溶液中刻蚀不同时间后的变化规律,测试了不同刻蚀时间下熔石英的损伤阈值。实验结果表明:随刻蚀时间的增加,表面RMS、划痕深度及宽度的总体变化趋势是增加的;熔石英的损伤阈值随刻蚀时间的增加,在1～10min时间段呈增加趋势,在20～40 min时间段呈下降趋势,而在60～120 min时间段先增加后降低。综合熔石英划痕的微观形貌损伤阈值的测量结果认为,刻蚀10 min时效果最佳。     

高密度等离子体刻蚀机中的终点检测技术

高密度等离子体刻蚀是当今超大规模集成电路制造过程中的关键步骤.目前已经开发出许多终点检测技术.文章讨论了终点检测技术的原理,综述了目前主流刻蚀机使用的两种终点检测技术-OES和IEP-的最新进展,讨论了终点检测技术在深亚微米等离子体刻蚀工艺中的应用,以及所面临的挑战.     

Low open-area endpoint detection using a PCA-based T2statistic and Q statistic on optical emission spectroscopy measurements

Examines an approach for automatically identifying endpoint (the completion in etch of a thin film) during plasma etching of low open area wafers. Because many end-pointing techniques use a few manually selected wavelengths or simply time the etch, the resulting endpoint detection determination may only be valid for a very short number of runs before process drift and noise render them ineffective. Only recently have researchers begun to examine methods to automatically select and weight spectral channels for estimation and diagnosis of process behavior. This paper will explore the use of principal component analysis (PCA)-based T² formulation to filter out noisy spectral channels and characterize spectral variation of optical emission spectroscopy (OES) correlated with endpoint. This approach is applied and demonstrated for patterned contact and via etching using digital semiconductor's CMOS6 (0.35-μm) production process     

Modeling and algorithm development for automated optical endpointing of an HBT emitter etch

This paper discusses the development of a high-accuracy endpointing algorithm for the emitter etch of a heterojunction bipolar transistor (HBT). Fabrication of high-performance HBTs using self-aligned base-emitter processes requires etching through the emitter layer and stopping with very high accuracy on the base layer. The lack of selectivity in dry etching coupled with the high etch rates possible in high density plasmas render the use of a standard timed overetch impractical, especially as device layers continue to become thinner. The etch process under study requires the complete removal of an AlInAs emitter while etching no more than 5 nm of the underlying GaInAs base layer. Etch products are monitored using optical emission spectroscopy (OES) to determine etch endpoint. The process under study relies on the intensity of the 417.2 nm Ga emission line. The detection of the Ga line indicates that the etch has reached the GaInAs layer. However, the presence of a time-varying Ga baseline signal before endpoint and significant noise in the OES signal necessitate more than a simple threshold scheme for critical endpoint detection. The algorithm presented here is based on a generalized likelihood ratio with a signature function. This algorithm is robust to variance in the optical gains of the measurement equipment and is applicable to other etch processes. Experimental results of automated endpointing using this algorithm are presented in the form of pre- and post-etch ex situ film thickness measurements.     

A neural network approach to estimating rainfall from spacebornemicrowave data

Various techniques use microwave (MW) brightness temperature (BT) data, obtained from remote sensing orbiting platforms, to calculate rain rates. The most commonly used techniques are based on regressions or other statistical methods. An emerging tool in rainfall estimation using satellite data is artificial neural networks (NNs), NNs are mathematical models that are capable of learning complex relationships. They consist of highly interconnected, interactive data processing units. NNs are implemented in this study to estimate rainfall, and backpropagation is used as a learning scheme. The inputs for the training phase are BTs and the outputs are rainfall rates, all generated by three-dimensional (3D) simulations based on a 3D stochastic, space-time rainfall model, and a 3D radiative transfer model. Once training is complete the NNs are presented with multi-frequency and polarized (horizontal and vertical) BT data, obtained from the Special Sensor Microwave/Imager (SSM/I) instrument onboard the F10 and F11 polar-orbiting meteorological satellites. Hence, rainrates corresponding to real BT measurements are generated. The rainfall rates are also estimated using a log-linear regression model. Comparison of the two approaches, using simulated data, shows that the NN can represent more accurately the underlying relationship between BT and rainrate than the regression model, Comparison of the rates, estimated by both methods, with radar-estimated rainrates shows that NNs outperform the regression model. This study demonstrates the great potential of NNs in estimating rainfall from remotely sensed data     

高密度等离子刻蚀机中的等离子体诊断技术

等离子体诊断技术对于高密度等离子刻蚀过程的监控显得非常重要.讨论了几种主要的等离子体诊断技术:langmuir探针,发射光谱法(OES),激光诱导荧光法(LIF),光谱椭偏法,质谱法,并就其技术特点及在实际运用时面临的问题进行了详细的讨论.     

Fault detection of plasma etchers using optical emission spectra

The objective of this paper is to investigate the suitability of using optical emission spectroscopy (OES) for the fault detection and classification of plasma etchers. The OES sensor system used in this study can collect spectra at up to 512 different wavelengths. Multiple scans of the spectra are taken from a wafer, and the spectra data are available for multiple wafers. As a result, the amount of the OES data is typically large. This poses a difficulty in extracting relevant information for fault detection and classification. In this paper, we propose the use of multiway principal component analysis (PCA) to analyze the sensitivity of the multiple scans within a wafer with respect to typical faults such as etch stop, which is a fault that occurs when the polymer deposition rate is larger than the etch rate. Several PCA-based schemes are tested for the purpose of fault detection and wavelength selection. A sphere criterion is proposed for wavelength selection and compared with an existing method in the literature. To construct the final monitoring model, the OES data of selected wavelengths are properly scaled to calculate fault detection indices. Reduction in the number of wavelengths implies reduced cost for implementing the fault detection system. All experiments are conducted on an Applied Materials 5300 oxide etcher at Advanced Micro Devices (AMD) in Austin, TX     

Plasma impedance monitoring for real time endpoint detection of bulk materials etched in ICP tool

Plasma impedance monitoring (PIM) based on electrical measurements is successfully used as an alternative to determine real time detection endpoint during plasma etching of structured bulk materials. In this paper we present the results with this technique for the endpoint detection during the etching of various materials.The endpoint conditions are tested in the sixth harmonic components of the electrical plasma parameters with an RF sensor. The endpoint is determined when an electrical parameter transition is observed. This transition corresponds to the change of the total reactor impedance, and allows the etching of the doped layer to stop on the bulk substrate.Using a Smith chart we determine the best harmonics/electrical monitoring couple parameters for processes on various materials. Resistivity measurements are used before and after etching in order to confirm the usefulness of the PIM method.In this paper, we also demonstrate how to monitor a real time control of non-uniformity during the reactive ion etching (RIE) process in the case of gallium arsenide etching.     

Multisensor integration and fusion model that uses a fuzzyinference system

An intelligent multisensor integration and fusion model that uses fuzzy logic is developed. Measurement data from different types of sensors with different resolutions are integrated and fused based on the confidence in them derived from information not usually used in data fusion, such as operating temperature, frequency range, fatigue cycles, etc. These are fed as additional inputs to a fuzzy inference system (FIS) that has predefined membership functions for each of these variables. The output of the FIS are weights that are assigned to the different sensor measurement data that reflect the confidence in the sensor's behavior and performance. A modular approach is adopted. It allows adding or deleting a sensor, along with its fuzzy logic controller (FLC), anytime without affecting the entire data fusion system. This paper presents a preliminary model that fuses the data from three different types of sensors that monitor the strain at a single location in a cantilever beam. This will be later extended to sensors that will be fixed at different locations on the same beam. The results from the proposed work are a stepping stone toward the development of generic autonomous sensor models that are capable of data interpretation, self-calibration, data fusion from other sources, and even learning so as to improve their performance with time. This work is aimed at the development of smart structural health monitoring systems, but has applications in diverse fields such as robotics, controls, target tracking, and biomedical imaging     

背照式CMOS图像传感器的硅减薄湿法刻蚀工艺

针对背照式CMOS图像传感器制作工艺,提出了一种采用氢氧化四甲基铵液进行湿法刻蚀的背部硅片减薄工艺。分析了硅减薄工艺的整体流程,针对化学机械研磨后的湿法刻蚀工艺进行了实验。通过调整反应时间、硅片转速、喷嘴速度和摆幅,得到最优刻蚀参数,使厚度均值达到目标值,平整度控制在一定范围内。该湿法刻蚀工艺中,首先对硅片表面形貌进行修正,接着对硅片进行整体刻蚀,达到目标厚度,最后通过减薄得到BSI背部硅片。采用该硅片制作的图像传感器的成像质量得到提高。     

Etch characteristics of GaN and BN materials in chlorine-based plasmas

Reactive ion etching (RIE) was performed on GaN and BN thin films using chlorine-based plasmas. The optimum chemistry was found to be BCl₃/Cl₂/N₂/Ar and Cl₂/Ar at 30 and 40 mtorr for GaN and BN etching, respectively. X-ray photoelectron spectroscopy (XPS) and Auger electron spectroscopy (AES) analysis of the GaN and BN etched surfaces show a decrease in the surface nitrogen atomic composition and an increase in chlorine impurity incorporation with increasing self-dc bias. A photo-assisted RIE (PA-PIE) process using an IR filtered Xe lamp beam was then used and resulted in improved etch rates and surface composition. Optical emission spectroscopy (OES) measurements have also shown photoenhancement of the etch process.