Predictive control of drying process using an adaptive neuro-fuzzy and partial least squares approach

In this paper, adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and partial least squares (PLS) approaches are applied to predictive control of a drying process. In the proposed approaches, the PLS analysis is used to pre-process actual data and to provide the necessary background to apply ANN and ANFIS approaches. A reasonable section of this study is assigned to the modeling with the aim at predicting the granule particle size and executing by ANFIS and ANN. ANN holds the promise of being capable of producing non-linear models, being able to work under noise conditions, and being fault tolerant to the loss of neurons or connections. Also, the ANFIS approach combines the advantages of fuzzy system and artificial neural network to design architecture and is capable of dealing with both limitation and complexity in the data set. The efficiencies of ANFIS and ANN approaches in prediction are compared and the superior approach is selected. Finally, by deploying the preferred approach, several scenarios are presented to be used in predictive control of spray drying as an accurate, fast running, and inexpensive tool. This is the first study that presents a flexible intelligent approach for predictive control of drying process by ANN, ANFIS, and PLS. The approach of this study may be easily applied to other production process.     

基于改进自适应模糊推理系统的YG3硬质合金精密外圆磨削表面质量预测

为提高硬质合金材料精密外圆磨削的表面完整性和加工质量,研究其表面质量的预测技术,建立了基于自适应模糊推理系统(ANFIS)的YG3硬质合金精密外圆磨削表面粗糙度预测模型,并引入混合田口遗传算法(HTGA)对预测模型进行了改进。采用工艺试验中所用的磨削参数及相应条件下测得的表面粗糙度数据作为训练样本和测试样本,通过对BP神经网络模型、传统ANFIS预测模型及改进ANFIS预测模型的预测结果进行对比分析,对三种模型的有效性和预测精度进行了验证。结果表明,所提出的改进ANFIS预测模型从预测值相对误差Er的分布及均方根相对误差EMSRE的大小来看,均优于其他两种预测模型,预测精度较高,是一种有效的表面质量预测方法。      

Prediction of quality responses in micro-EDM process using an adaptive neuro-fuzzy inference system (ANFIS) model

In the present trend of technological development, micro-machining is gaining popularity in the miniaturization of industrial products. In this work, a hybrid process of micro-wire electrical discharge grinding and micro-electrical discharge machining (EDM) is used in order to minimize inaccuracies due to clamping and damage during transfer of electrodes. The adaptive neuro-fuzzy inference system (ANFIS) and back propagation (BP)-based artificial neural network (ANN) models have been developed for the prediction of multiple quality responses in micro-EDM operations. Feed rate, capacitance, gap voltage, and threshold values were taken as the input parameters and metal removal rate, surface roughness and tool wear ratio as the output parameters. The results obtained from the ANFIS and the BP-based ANN models were compared with observed values. It is found that the predicted values of the responses are in good agreement with the experimental values and it is also observed that the ANFIS model outperforms BP-based ANN.     

Prediction of tool wear using regression and ANN models in end-milling operation

Tool wear prediction plays an important role in industry for higher productivity and product quality. Flank wear of cutting tools is often selected as the tool life criterion as it determines the diametric accuracy of machining, its stability and reliability. This paper focuses on two different models, namely, regression mathematical and artificial neural network (ANN) models for predicting tool wear. In the present work, flank wear is taken as the response (output) variable measured during milling, while cutting speed, feed and depth of cut are taken as input parameters. The Design of Experiments (DOE) technique is developed for three factors at five levels to conduct experiments. Experiments have been conducted for measuring tool wear based on the DOE technique in a universal milling machine on AISI 1020 steel using a carbide cutter. The experimental values are used in Six Sigma software for finding the coefficients to develop the regression model. The experimentally measured values are also used to train the feed forward back propagation artificial neural network (ANN) for prediction of tool wear. Predicted values of response by both models, i.e. regression and ANN are compared with the experimental values. The predictive neural network model was found to be capable of better predictions of tool flank wear within the trained range.     

Application of adaptive neuro-fuzzy inference system and cuckoo optimization algorithm for analyzing electro chemical machining process

Electrochemical machining process (ECM) is increasing its importance due to some of the specific advantages which can be exploited during machining operation. The process offers several special privileges such as higher machining rate, better accuracy and control, and wider range of materials that can be machined. Contribution of too many predominate parameters in the process, makes its prediction and selection of optimal values really complex, especially while the process is programmized for machining of hard materials. In the present work in order to investigate effects of electrolyte concentration, electrolyte flow rate, applied voltage and feed rate on material removal rate (MRR) and surface roughness (SR) the adaptive neuro-fuzzy inference systems (ANFIS) have been used for creation predictive models based on experimental observations. Then the ANFIS 3D surfaces have been plotted for analyzing effects of process parameters on MRR and SR. Finally, the cuckoo optimization algorithm (COA) was used for selection solutions in which the process reaches maximum material removal rate and minimum surface roughness simultaneously. Results indicated that the ANFIS technique has superiority in modeling of MRR and SR with high prediction accuracy. Also, results obtained while applying of COA have been compared with those derived from confirmatory experiments which validate the applicability and suitability of the proposed techniques in enhancing the performance of ECM process.     

Characteristics Prediction Method of Electro-hydraulic Servo Valve Based on Rough Set and Adaptive Neuro-fuzzy Inference System

Synthesis characteristics of the electro-hydraulic servo valve are key factors to determine eligibility of the hydraulicproduction. Testing all synthesis characteristics of the electro-hydranlic servo valve after assembling leads to high repair rate and reject rate, so accurate prediction for the synthesis characteristics in the industrial production is particular important in decreasing the repair rate and the reject rate of the product. However, the research in forecasting synthesis characteristics of the electro-hydraulic servo valve is rare. In this work, a hybrid prediction method was proposed based on rough set(RS) and adaptive neuro-fuzzy inference system(ANFIS) in order to predict synthesis characteristics of electro-hydraulic servo valve. Since the geometric factors affecting the synthesis characteristics of the electro-hydraulic servo valve are from workers' experience, the inputs of the prediction method are uncertain. RS-based attributes reduction was used as the preprocessor, and then the exact geometric factors affecting the synthesis characteristics of the electro-hydraulic servo valve were obtained. On the basis of the exact geometric factors, ANFIS was used to build the final prediction model. A typical electro-hydranlic servo valve production was used to demonstrate the proposed prediction method.The prediction results showed that the proposed prediction method was more applicable than the artificial neural networks(ANN) in predicting the synthesis characteristics of electro-hydraulic servo valve, and the proposed prediction method was a powerful tool to predict synthesis characteristics of the electro-hydraulic servo valve. Moreover, with the use of the advantages of RS and ANFIS, the highly effective forecasting framework in this study can also be applied to other problems involving synthesis characteristics forecasting.     

Prediction of wear behaviour of A356/SiCp MMCs using neural networks

In the present investigation, artificial neural network (ANN) approach was used to predict the wear behaviour of A356/SiC metal matrix composites (MMCs) prepared using rheocasting route. The ANN model was obtained to aid in prediction and optimization of the wear rates of the composites. The effect of the SiC particles size, SiC weight percent, applied pressure and test temperature on the wear resistance was evaluated using the ANN model. The results have shown that ANN is an effective tool in the prediction of the properties of MMCs, and quite useful instead of time-consuming experimental processes.     

Practical applications of artificial neural networks in chemical process development

Artificial neural networks (ANN) have the ability to map non-linear relationships without a-priori information about process or system models. This significant feature allows the network to “learn” the behavior of a system by example when it may be difficult or impractical to complete a rigorous mathematical solution. Recently ANN technology has been leaving the academic arena and placed in user-friendly software packages. This paper will offer an introduction to artificial neural networks and present a case history of two problems in chemical process development that were approached with ANN. Both optimal PID control tuning parameters and product particle size predictions were constructed from process information using neural networks. The ANN provides a rapid solution to many applications with little physical insight into the underlying system function. The amount of data preparation and performance limitations using a neural network will be discussed. However, the properly applied ANN will generally provide insight to which variables are most influential to the model and evolve dynamically to the minimum performance surface squared error. Neural networks have been used successfully with non-linear dynamic systems and can be applied to chemical process development for system identification and multivariate optimization problems.     

Tribological properties of ZrO2 (Y2O3)-Mo-BaF2/CaF2 composites at high temperatures

ZrO₂ (Y₂O₃) with different contents of BaF₂/CaF₂ and Mo were fabricated by hot pressed sintering, and the tribological behavior of the composites against SiC ceramic was investigated from room temperature to 1000 °C. It was found that the ZrO₂ (Y₂O₃)-5BaF₂/CaF₂-10Mo composite possessed excellent self-lubricating and anti-wear properties. The low friction and wear were attributed to enhanced matrix and BaMoO₄ formed on the worn surfaces.     

人工神经网络及其在机械工程领域中的应用

在论述人工神经网络模型的特点和性质的基础上，综述国内机械工程领域研究与应用人工神经网络技术的现状与发展，介绍最常用的模型种类，举例说明这类模型在机械制造和机械设计各环节中的实际应用，并阐述了完善模型结构，改进建模方法方面的基础性研究工作，从内容，深度，实际效果和软硬件方面评述当前在人工神经网络模型研究与应用中的不足之处，指出今后努力的方向和潜在应用领域。     

Factors affecting algal blooms in a man-made lake and prediction using an artificial neural network

It is difficult to predict when, where, and how long algal blooms will occur in a water body. The objectives of this study were to determine the factors affecting algal bloom and predict chlorophyll-a (Chl-a) levels in the reservoir formed by damming a river using an artificial neural network (ANN). The automatic water quality monitoring data [water temperature, pH, dissolved oxygen (DO), electric conductivity, total organic carbon (TOC), Chl-a, total nitrogen (T-N), and total phosphorus (T-P)], weather data (precipitation, temperature, insolation, and duration of sunshine) and hydrologic data (water level, discharges, and inflows) in the man-made Lake Juam during 2008–2010 were used to develop a model to predict Chl-a as an indirect measure of the abundance of algae. The ANN was trained using the collected data during 2008–2010 and the accuracy of the model was verified using the data collected in 2011. It was found that Chl-a concentration, TOC, pH and atmospheric and water temperatures were the most important parameters in predicting Chl-a concentrations. The Chl-a prediction was most influenced by the parameters showing the algal activities such as Chl-a, TOC and pH. Due to the relatively long hydraulic retention time of ∼131 days, the inflow and outflow did not affect the prediction much. Likewise, atmospheric and water temperatures did not respond to the change of the Chl-a concentration due to the lake’s relatively slow response to the temperature. Most importantly, T-N and T-P were not the major factors in predicting Chl-a levels at Lake Juam. The ANN trained with the time series data successfully predicted the Chl-a concentration and provided information regarding the principal factors affecting algal bloom at Lake Juam.     

基于Fe3O4/SiO2/Au-MNPs磁性SERS基底的特布他林超灵敏检测

为了快速灵敏地检测特布他林(terbutaline,TB),制备核?卫星纳米结构的Fe3O4/SiO2/Au-MNPs磁性基底对其进行表面增强拉曼光谱(SERS)检测。通过磁性分离、调节体系pH的方法考察特布他林浓度与拉曼光谱强度之间的线性关系并绘制校准曲线。实验结果表明,该纳米卫星结构的磁性SERS基底对TB的检测限为3.77×10^?10 mol/L,同时在5×10?5~5×10^?9 mol/L范围内,TB的SERS信号与其浓度呈线性关系,利用最小二乘法拟合得到的线性相关系数R2为0.996。该复合材料制备方法简便易行,为合成其他纳米复合材料提供了参考。     

Comparison on abrasive wear of SiCrFe, CrFeC and Al2O3 reinforced Al2024 MMCs

The effects of volume fraction and size of SiCrFe, CrFeC, and Al₂O₃ particulates on the abrasive wear rate of compo-casted Al2024 metal matrix composites (MMCs) were studied. The process variables like the stirring speed, position and the diameter of the stirrer have affected the diffusion between particulates and matrix.The abrasive wear rate was decreased by the increase in particulate volume fraction of SiCrFe and CrFeC intermetallic reinforced composites over 80 grade SiC abrasive paper. The wear rates of the all composites decreased with aging treatment, and the best result was seen for the composite having a hybrite structure as SiCrFe and CrFeC particulates together. Nevertheless, the fabrication of composites containing soft particles as copper favors a reduction in the friction coefficient.     

Measurement failure robustness in H2/H∞ reliable controller synthesis

Attention has returned towards the design of closed loop control systems which remain stable under measurement (or actuator) failure. Engineers wish to introduce reliability into the closed loop system by including redundant measurements. These systems are designed to be robust to measurement failures in terms of retaining closed loop stability and desirable system performance. Two methods of denoting measurement failure within a system are introduced. The existing design procedures for designing reliable H_∞ controllers are considered before re-formulating the reliability issue in the H₂ framework. The system performance for different measurement failure structures can be measured in terms of the bound on the H_∞ norm or the H₂ cost.     

Mass modeling of Bam orange with ANFIS and SPSS methods for using in machine vision

Orange is a citrus fruit which is rich in vitamins and minerals and other nutrients. Getting the relationship between physical properties of orange and its mass can create tremendous change in the packaging industry. The Iranian orange fruits used in this study consisted of Bam cultivars that they got from Kermanshah–Iran (longitude: 7.03°E; latitude: 4.22°N). One hundred samples were randomly selected. All the measurements were carried out at the laboratory with temperature of 24 °C during 2 days. Fourteen parameters were got by image processing for each orange. ANFIS and SPSS models were employed to predict the mass based on perimeter and (width/length) value as inputs. The coefficient of determination (R²) for ANFIS and SPSS were 0.936999 and 0.919 respectively. To evaluate the ANFIS model, samples were divided into two sets, 70% of data was used for training the model and 30% of data was used to test the model. So, The ANFIS model with less error percentage can be used to design and develop sizing systems.     

超高效合相色谱-串联质谱法测定口含烟中对羟基苯甲酸酯

建立了QuEChERS-超高效合相色谱-串联质谱法（UPC²-MS/MS）测定口含烟中对羟基苯甲酸酯类防腐剂。采用乙腈提取,基质分散固相萃取净化,UPC^{2 TM} HSS C18 SB色谱柱（3.0 mm×100 mm×1.8 μm）分离,内标法定量。优化后的对羟基苯甲酸酯的合相色谱分离条件为：主要流动相为CO₂,改性剂为甲醇-异丙醇混合溶液（V/V,1∶1）,系统流速1.5 mL/min,离子化辅助溶剂（补偿溶剂）为0.1%甲酸-甲醇溶液,动态备压1.03×10⁷ Pa,柱温55 ℃,可在3 min内完成单个样品分析。4种成分的线性范围均为0.5~5.0 mg/kg;在低、中、高加标水平下,方法的平均回收率为94.6%~105.6%,相对标准偏差小于5%。实际样品测定结果表明,单个成分的含量和多种成分的总含量均小于10 mg/kg,低于GB 2760-2014对于此类防腐剂在食品中添加限量的要求。该方法环境友好、高效、准确,适用于口含烟中对羟基苯甲酸酯类物质的测定。     

Application of an Adaptive Neuro-Fuzzy Inference System for the Optimal Analysis of Chemical-Mechanical Polishing Process Parameters

This paper examines the machining parameters during the wafer flattening process by chemical–mechanical polishing (CMP). There are very few data available from CMP experiments for wafer flattening. This study adopted an adaptive neuro-fuzzy inference system (ANFIS) to predict the surface roughness in the absence of CMP experiments. An integrated concept like ANFIS combines the advantages of the two systems of fuzzy control and neuro networks. Next, the feasible directions algorithm and sequential approximation algorithm from the local search method are combined with ANFIS. During the process of combination, the value from the optimisation theory is replaced by that from the ANFIS, so that, the roughness value of the wafer surface can be predicted. Alternatively, the optimal values of various process parameters can also be predicted. To sum up, verification through experiments indicates that the optimal experimental values of process parameters are identical with those predicted by the optimisation theory and ANFIS. Thus, the optimal precise value can be simulated and predicted within the parameters of the experimental design. The predicted optimal result is compared with the optimal experimental result of Kung and Dai to show that the predicted optimal result is acceptable. As a result, the CMP process parameters investigated in this study can be controlled.     

Tribological behavior of plasma sprayed Cr2O3-3%TiO2 coatings

Tribological behaviors of plasma-sprayed conventional and nanostructured Cr₂O₃-3%TiO₂ ceramic coatings (i.e., CC3T and NC3T, respectively) using pin on disc type dry sliding and pot type slurry erosion test were investigated in the present work. The experimental results indicated that there were two main wear mechanisms, plastic smearing and adhesive tearing, in the worn coatings under dry sliding. Plastic smearing corresponded to a lower average friction coefficient and wear rate, while adhesive tearing corresponded to higher values. The erosive environment selected for the slurry erosion experiments include 10, 20 and 30% of SiO₂ slurry concentrations in water with particle size 75-106 μm. The main damage mechanism observed in all the coatings submitted to slurry erosion were the formation and propagation of brittle cracks resulting in the detachment of coating surface material. Microstructural investigation was also carried to investigate the wear and erosion mechanism of the coatings using FE-SEM and EDS analysis. Properties like microhardness and porosity were also investigated for these coatings. Tribological performance of NC3T was better as compared to CC3T as observed in the present work.     

Modelling particulate erosion–corrosion regime transitions for Al/Al2O3 and Cu/Al2O3 MMCs in aqueous conditions

Very little research effort has been directed at development of models of erosion–corrosion of composite materials. This is because, in part, the understanding of the erosion–corrosion mechanisms of such materials is poor. In addition, although there has been a significant degree of effort in the development of models for erosion of MMCs, there are still difficulties in applying such models to the laboratory trends on erosion rate.In this paper, the methodology for mapping erosion–corrosion processes in aqueous slurries was extended to particulate composites. An inverse rule of mixtures was used for the construction of the erosion model for the particulate MMCs. The corrosion rate calculation was evaluated with reference to the matrix material.The erosion–corrosion maps for composites showed significant dependency on pH and applied potential. In addition, the corrosion resistance of the matrix material was observed to affect the regime boundaries. Materials maps were generated based on the results to show the optimum composite composition for exposure to the environment.