Strain rate analyses during elliptical vibration cutting of Inconel 718 using finite element analysis,Taguchi method,and ANOVA

The high strain rate in metal cutting significantly affects the mechanical properties of the work piece by altering its properties. This study outlines the material strain rates during elliptical vibration cutting. The finite element analysis, Taguchi method, and analysis of variance (ANOVA) were employed to analyze the effects and contributions of cutting and vibration process parameters (feed rate, rake angle, tangential amplitude, and frequency of vibration) on the variation of strain rates during machining of Inconel 718. Taguchi signal-to-noise analysis on an L₁₈ (2¹×3³) orthogonal array was used to determine the optimum parametric combination for the maximum strain rate, and ANOVA was applied to evaluate the significance of control parameter factors on the strain rate. The results of the finite element analysis under different conditions illustrated that the feed rate and rake angle were negatively related to the strain rate, whereas the tangential amplitude and frequency had a positive response. Furthermore, ANOVA results indicated that the effect of the feed rate, tool rake angle, vibration frequency, and tangential amplitude on the strain rate were all statistically significant, with a reliability level of 95%. Of these, the dominant parameter affecting the strain rate was the feed rate, with a percentage contribution of 40.36%. The estimation of the optimum strain rate and confirmation tests proved that the Taguchi method could successfully optimize the working conditions to obtain the desired maximum strain rate.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-020-00315-0     

Warpage and Shrinkage Optimization of Injection-Molded Plastic Spoon Parts for Biodegradable Polymers Using Taguchi,ANOVA and Artificial Neural Network Methods

In this study, it is attempted to give an insight into the injection processability of three self-prepared polymers from A to Z. This work presents material analysis, injection molding simulation, design of experiments alongside considering all interaction effects of controlling parameters carefully for green biodegradable polymeric systems, including polylactic acid(PLA), polylactic acid-thermoplastic polyurethane(PLA-TPU) and polylactic acid-thermoplastic starch(PLA-TPS). The experiments were carried out using injection molding simulation software Autodesk Moldflow?in order to minimize warpage and volumetric shrinkage for each of the mentioned systems. The analysis was conducted by changing five significant processing parameters, including coolant temperature, packing time, packing pressure, mold temperature and melt temperature. Taguchi's L27(35) orthogonal array was selected as an efficient method for design of simulations in order to consider the interaction effects of the parameters and reduce spurious simulations. Meanwhile, artificial neural network(ANN) was also used for pattern recognition and optimization through modifying the processing conditions. The Taguchi coupled analysis of variance(ANOVA) and ANN analysis resulted in definition of optimum levels for each factor by two completely different methods. According to the results, melting temperature, coolant temperature and packing time had significant influence on the shrinkage and warpage. The ANN optimal level selection for minimization of shrinkage and/or warpage is in good agreement with ANOVA optimal level selection results. This investigation indicates that PLA-TPU compound exhibits the highest resistance to warpage and shrinkage defects compared to the other studied compounds.     

Remaining useful life prediction via a variational autoencoder and a time-window-based sequence neural network

The prediction of remaining useful life (RUL) has attracted much attention, and it is also a key section for predictive maintenance. In this study, a novel hybrid deep learning framework is proposed for RUL prediction, where a variational autoencoder (VAE) and time-window-based sequence neural network (twSNN) are integrated. Among it, VAE is used to extract the hidden and low-dimensional features from the raw sensor data, and a loss function is designed to extract useful data features; by using a sliding time window, twSNN can predict RUL dynamically; meanwhile, it can simplify the network architecture in the time dimension. Furthermore, to achieve higher performance on various failure conditions, long short-term memory (LSTM) cell and convolutional LSTM (ConvLSTM) cell are designed for twSNN respectively. A case study is completed with a dataset of aircraft turbine engines. It is found that the proposed frameworks with LSTM cell and ConvLSTM cell have better performance on both single failure mode and multiple failure modes. The results also show that the prediction accuracy is averagely improved by 6.65% for single failure mode and 15.05% for multiple failure modes respectively.     

Analysis of warpage and shrinkage properties of injection-molded micro gears polymer composites using numerical simulations assisted by the Taguchi method

Microgears containing four cavities and consisting of three different types of thermoplastic materials, namely, the amorphous polycarbonate/acrylonitrile–butadiene–styrene blend (PC/ABS), amorphous polyphenylene–ether/polystyrene (PPE/PS), and crystalline polyoxymethylene (POM) filled with glass fibers were analyzed. Molding parameters such as packing time, cooling temperature, molding and melting temperatures, packing and injection pressures, and fiberglass percentages are the most important factors affecting warpage and shrinkage. Three factors and their interactions were investigated in this case study. The effects of the injection parameters on warpage and shrinkage at different fiberglass percentages and cooling temperatures were analyzed according to the Taguchi method. The minimum values for warpage (0.0051 mm) and shrinkage (2.2886%) were derived from the PC/ABS and PPE/PS composites, respectively. Process efficiency predictions and conformational analyses of the optimal levels for each injection molding parameter were conducted to demonstrate the advantages of the Taguchi analytical method. The highest improvement percentages in the shrinkage and warpage analyses were obtained from the PPE/PS and the PC/ABS, respectively. PPE/PS was the best polymer composite by shrinkage analysis because of its molecular structure and minimum temperature at the flow front range, while the PC/ABS behaved the best in the warpage analysis.     

Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding

Warpage of plastic products is an important evaluation index for Plastic Injection Molding (PIM). A Back Propagation (BP) neural-network model for warpage prediction and optimization of injected plastic parts has been developed based on key process variables including mold temperature, melt temperature, packing pressure, packing time and cooling time during PIM. The approach uses a BP neural network trained by the input and output data obtained from the Finite Element (FE) simulations which are performed on Moldflow software platform. In addition, a kind of automobile glove compartment cap was utilized in this study. Trained by the results of FE simulations conducted by orthogonal experimental design method, the prediction system got a mathematical equation mapping the relationship between the process parameter values and warpage value of the plastic. It has been proved that the prediction system has the ability to predict the warpage of the plastic within an error range of 2%. Process parameters have been optimized with the help of the prediction system. Meanwhile energy consumption and production cycle were also taken into consideration. The optimized warpage value is 1.58 mm, which is shortened by 32.99% comparing to the initial warpage result 2.358 mm. And the cooling time has been decreased from 20 s to 10 s, which will greatly shorten the production cycle. The final product can satisfy with the matching requirements and fit the automobile glove compartment well.     

The incorporation of the Taguchi and the VIKOR methods to optimize multi-response problems in intuitionistic fuzzy environments

The Taguchi method is a powerful method of solving quality problems in various fields of engineering. However, this method was developed to optimize single-response processes. In many multi-response optimization problems, the important response is determined subjectively, based on knowledge or experience. However, using only exact numbers to represent this importance is problematic, because there is uncertainty and vagueness. The concept of intuitionistic fuzzy sets (IFSs) is a powerful method for characterization, using a membership function and a non-membership function. This paper proposes an efficient VIKOR method that optimizes multi-response problems in intuitionistic fuzzy environments. The importance weights of various responses are evaluated in terms of IFSs. In the proposed method, the similarity measure between IFSs is used to determine the crisp weights of the responses. This scheme eliminates the need for complicated intuitionistic fuzzy arithmetic operations and increases efficiency in solving multi-response optimization problems in intuitionistic fuzzy environments. Two case studies: plasma-enhanced chemical vapor deposition and a double-sided surface mount technology electronic assembly operation are used to demonstrate the effectiveness of the proposed method.     

A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters

This paper presents a hybrid optimization method for optimizing the process parameters during plastic injection molding (PIM). This proposed method combines a back propagation (BP) neural network method with an intelligence global optimization algorithm, i.e. genetic algorithm (GA). A multi-objective optimization model is established to optimize the process parameters during PIM on the basis of the finite element simulation software Moldflow, Orthogonal experiment method, BP neural network as well as Genetic algorithm. Optimization goals and design variables (process parameters during PIM) are specified by the requirement of manufacture. A BP artificial neural network model is developed to obtain the mathematical relationship between the optimization goals and process parameters. Genetic algorithm is applied to optimize the process parameters that would result in optimal solution of the optimization goals. A case study of a plastic article is presented. Warpage as well as clamp force during PIM are investigated as the optimization objectives. Mold temperature, melt temperature, packing pressure, packing time and cooling time are considered to be the design variables. The case study demonstrates that the proposed optimization method can adjust the process parameters accurately and effectively to satisfy the demand of real manufacture.     

Teeth category classification via seven-layer deep convolutional neural network with max pooling and global average pooling

Accurately classify teeth category is important in further dental diagnosis. Analyzing huge dental data, that is, identifying the teeth category, is often a hard task. Current automatic methods are based on computer vision and deep learning approaches. In this study, we aimed to classify the teeth category into four classes: incisor, canine, premolar, and molar. Cone beam computed tomography was used to collect the data. We proposed a seven-layer deep convolutional neural network with global average pooling to identify teeth category. Data augmentation method was used to enlarge the size of training dataset. The results showed the sensitivities of incisor, canine, premolar, and molar teeth are 88%, 86%, 84%, and 90%, respectively. The average sensitivity is 87.0%. We validated max pooling gives better results than average pooling. Our method is better than three state-of-the-art approaches.     

Performance comparison of feedforward neural network training algorithms in modeling for synthesis of polycaprolactone via biopolymerization

This paper reports the biopolymerization of ε-caprolactone, using lipase Novozyme 435 catalyst at varied impeller speeds and reactor temperatures. A multilayer feedforward neural network (FFNN) model with 11 different training algorithms is developed for the multivariable nonlinear biopolymerization of polycaprolactone (PCL). In previous works, biopolymerization carried out in scaled-up bioreactors is modeled through FFNN. No review discussed the role of different training algorithms in artificial neural network on the estimation of biopolymerization performance. This paper compares mean absolute error, mean square error, and mean absolute percentage error (MAPE) in the PCL biopolymerization process for 11 different training algorithms that belong to six classes, namely (1) additive momentum, (2) self-adaptive learning rate, (3) resilient backpropagation, (4) conjugate gradient backpropagation, (5) quasi-Newton, and (6) Bayesian regulation propagation. This paper aims to identify the most effective training method for biopolymerization. Results show that the quasi-Newton-based and Levenberg–Marquardt algorithms have the best performance with MAPE values of 4.512, 5.31, and 3.21% for the number of average molecular weight, weight average molecular weight, and polydispersity index, respectively.     

Fault detection,classification, and location for active distribution network based on neural network and phase angle analysis

The improved radial basis function (RBF) method utilizes an orthogonal regression matrix to produce an artificial neural network structure based on regularized least square. The phase angle and amplitude signal of fault voltage and current are extracted based on frequency domain analysis. The proposed method adopts the fault signal for fault diagnosis synchronously. The IEEE 13-bus active distribution network (ADN) simulation model is set up in Matlab. Test results demonstrate that accuracy of the fault diagnosis can reach 98.07% and the response time of the fault classification method is less than 0.04s. The wavelet neural network (WNN) model is developed to extract the maximum decomposition level and time series behavior. The WNN method can resist noise effects and improve the fault classification accuracy by 4.3%. The effect of fault type and fault resistance on the fault location method is researched. The fault simulation result shows that the proposed method can locate a fault precisely and synchronously. The improved RBF method can diagnose the fault section, classify the fault type and locate a fault accurately in ADN. The research is significant to maintain system stability against realistic fault and network restore.     

Plasticity including the Bauschinger effect,studied by a neural network approach

Summary The first known vibration analysis of composite cantilevered shallow shells having right triangular and trapezoidal planforms is conducted. Accurate frequencies are obtained using the Ritz method with algebraic polynomials. This is demonstrated by detailed convergence studies. The lowest six natural frequencies for these shallow shells with double curvature are listed. Effects of curvature, material orthotropy and lamination angle on the natural frequencies are investigated.     

基于神经网络的信息融合算法研究及其在入侵检测中的应用

目前，网络入侵技术越来越先进，许多黑客都具备反检测的能力，他们会有针对性地模仿被入侵系统的正常用户行为；或将自己的入侵时间拉长，使敏感操作分布于很长的时间周期中；还可能通过多台主机联手攻破被入侵系统．对于伪装性入侵行为与正常用户行为来说，仅靠一个传感器的报告提供的信息来识别已经相当困难，必须通过多传感器信息融合的方法来提高对入侵的识别率，降低误警率．应用基于神经网络的主观Bayes方法，经实验，效果良好．     

Prediction of shrinkage and warpage in consideration of residual stress in integrated simulation of injection molding

The accurate prediction of shrinkage and warpage of injection molded parts is important to achieve successful mold design with high precision. In this study, the numerical analysis of shrinkage and warpage of injection molded parts made of amorphous polymers was carried out in consideration of the residual stresses produced during the packing and cooling stages of injection molding. The temperature and pressure fields were obtained from the coupled analysis of the filling and post-filling stages. For residual stress analysis, a thermo-rheologically simple viscoelastic material model was introduced to consider the stress relaxation effect and to describe the mechanical behavior according to the temperature change. The effect of the additional material supply during the packing stage was modeled by assigning the reference strain. The deformation of injection molded parts after ejection induced by the residual stress and temperature change was analyzed using a linear elastic three-dimensional finite element approach. In order to verify the numerical predictions obtained from the developed program, the simulation results were compared with the available experimental data in the literature. In the case of residual stress, it was found that the present simulation results overpredicted the tensile residual stresses at the surface of injection molded parts. However, the predicted shrinkage was found to be reasonable to describe the effects of processing conditions well. Finally, an analysis of the shrinkage and warpage was successfully extended for a part with a more complex curved shape.     

Remaining useful life prediction via long-short time memory neural network with novel partial least squares and genetic algorithm

Advancements in information technology have made various industrial equipment increasingly sophisticated in recent years. The remaining useful life (RUL) of equipment plays a crucial important role in the industrial process. It is difficult to establish a functional RUL model as it requires the fusion of time-series data across different scales. This paper proposes a long-short term memory neural network, which integrates a novel partial least square based on a genetic algorithm (GAPLS-LSTM). The parameters are first analyzed by PLS to obtain the parameter fusion function of the health index (HI). The GA then searches the optimal coefficients of the function; the expected HI values can be calculated with the fusion function. Finally, the RUL of the equipment is predicted with the LSTM method. The proposed GAPLS-LSTM was applied to RUL prediction of a marine auxiliary engine to validate it by comparison against GAPLS-BP and GAPLS-RNN methods. The results show that the proposed method is capable of effective RUL prediction.     

Comparative analysis of requirements change prediction models: manual,linguistic, and neural network

Requirement change propagation, if not managed, may lead to monetary losses or project failure. The a posteriori tracking of requirement dependencies is a well-established practice in project and change management. The identification of these dependencies often requires manual input by one or more individuals with intimate knowledge of the project. Moreover, the definition of these dependencies that help to predict requirement change is not currently found in the literature. This paper presents two industry case studies of predicting system requirement change propagation through three approaches: manually, linguistically, and bag-of-words. Dependencies are manually and automatically developed between requirements from textual data and computationally processed to develop surrogate models to predict change. Two types of relationship generation, manual keyword selection and part-of-speech tagging, are compared. Artificial neural networks are used to create surrogate models to predict change. These approaches are evaluated on three connectedness metrics: shortest path, path count, and maximum flow rate. The results are given in terms of search depth needed within a requirements document to identify the subsequent changes. The semi-automated approach yielded the most accurate results, requiring a search depth of 11 %, but sacrifices on automation. The fully automated approach is able to predict requirement change within a search depth of 15 % and offers the benefits of full minimal human input.     

线性神经网络及模态声发射在时差定位中的应用

分析了影响时差定位法精度的主要因素,将线性神经网络方法和模态声发射理论应用于突发声发射定位中,并在板结构上进行实验验证。实验结果表明,达到了精确定位的预期要求,定位不确定度由1.89%降至0.45%,较好地满足了工程实际需要。该方法不仅适用于突发声发射时差定位,也为连续声发射时差定位奠定了基础。     

Pseudospectra,MUSIC, and dynamic wavelet neural network for damage detection of highrise buildings

A non-parametric system identification-based model is presented for damage detection of highrise building structures subjected to seismic excitations using the dynamic fuzzy wavelet neural network (WNN) model developed by the authors. The model does not require complete measurements of the dynamic responses of the whole structure. A large structure is divided into a series of sub-structures around a few pre-selected floors where sensors are placed and measurements are made. The new model balances the global and local influences of the training data and incorporates the imprecision existing in the sensor data effectively, thus resulting in fast training convergence and high accuracy. A new damage evaluation method is proposed based on a power density spectrum method, called pseudospectrum. The multiple signal classification (MUSIC) method is employed to compute the pseudospectrum from the structural response time series. The methodology is validated using the data obtained for a 38-storey concrete test model. The results demonstrate the effectiveness of the WNN model together with the pseudospectrum method for damage detection of highrise buildings based on a small amount of sensed data. Copyright © 2007 John Wiley & Sons, Ltd.     

Performance of an optoelectronic neural network in the presence of noise

Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed multi-quantum-well modulators was constructed. It employed a general method for optical representation of bipolar values, which required only a minimal increase in network dimensions and gave the network immunity to common-mode parameter variations. Different ways of partitioning pattern-recognition problems were compared, and the accuracy of one configuration was tested with the experimental network over a range of noise levels.