Product Quality Estimation Research Articles

Implementing multiblock techniques in a full-scale plant scenario: On-line prediction of quality parameters in a continuous process for different acrylonitrile butadiene styrene (ABS) products

BackgroundThe study explores the challenges of handling multiblock data of different natures (process and NIR sensors) for on-line quality prediction in a full-scale plant scenario, namely a plant operating in continuous on an industrial scale and producing different grade Acrylonitrile Butadiene Styrene (ABS) products. This environment is an ideal scenario to evaluate the use of multiblock data analysis methods, which can enhance data interpretation, visualization, and predictive performances. In particular, a novel multiblock extension of Locally Weighted PLS has been proposed by the authors, namely Locally Weighted Multiblock Partial Least Squares (LW-MB-PLS). Response-Oriented Sequential Alternation (ROSA) has also been employed to evaluate the diverse block relevance for the prediction of two quality parameters associated with the polymer. Data are split in blocks both according to sensor type and different plant sections, and different models have been built by incremental addition of data blocks to evaluate if early estimation of product quality is feasible. ResultsROSA method showed promising predictive performance for both quality parameters, highlighting the most influential plant sections through the selection of data blocks. The results suggested that both early and late-stage sensors play crucial roles in predicting product quality. A reasonable estimation of quality parameters before production completion has been achieved. On the other hand, the proposed LW-MB-PLS, while comparable in predictive performances, allowed reducing systematic prediction errors for specific products. SignificanceThis study contributes valuable insights for continuous production processes, aiding plant operators and paving the way for advancements in online quality prediction and control. Furthermore, it is implemented as a locally weighted extension of MB-PLS.

Prediction surface roughness of 3D printed parts using genetic algorithm optimized hybrid learning model

The final product of additive manufacturing (AM) or 3D printing critically depends on the surface quality. An experimental study on the 3D printed intake manifold flange using acrylonitrile butadiene styrene (ABS) material was executed by varying the four process parameters. A fused deposition modeling (FDM) based 3D printer was used to fabricate the flanges. The association between the parameters and the surface roughness of printed ABS flanges was investigated. A feed forward neural network (FFNN) model trained on particle swarm optimization (PSO) optimized with a genetic algorithm (GA) was used to estimate the surface roughness. A Box-Behnken design (BBD) with printing parameters at three levels was used, and 25 parts were fabricated. The suggested model demonstrated a coefficient of determination (R2) of 0.9865 on test values, mean of root-mean-square-error (RMSE) of 0.1231 after 500 times training for generalization. And also mean of overfitting factor is 0.7110. This means that the suggested system could generalize. Comparing the results from the suggested model and ANN, the suggested hybrid model outperformed ANN in predicting the surface roughness values with no overfitting. This suggests that GA optimized PSO based FFNN may be a more suitable method for estimating product quality in terms of surface roughness.

Dual-Mode Multispectral Imaging System for Food and Agricultural Product Quality Estimation

Dual-Mode Multispectral Imaging System for Food and Agricultural Product Quality Estimation

A novel sampled-data asynchronous CatBoost model with knowledge-based guidance for product quality estimation in the industrial processes

For process industry with asynchronous sampling, delayed laboratory analysis of the product quality restricts operation control and optimization. However, it is challenging to ensure the estimation accuracy due to the fact that online estimation model is disturbed by the dynamic change of production conditions. Therefore, a product quality estimation strategy for asynchronous sampling industrial processes under data-driven and knowledge-based guidance is proposed. First, domain knowledge and process mechanism are used to establish the mechanics models and identify the critical variables. Then, the dimensionality of the samples is reduced to extract effective information which is used to partition data samples. Besides, the data sample is balanced by the adaptive synthetic sampling technique under different production conditions. Finally, a CATBoost estimation model is built for product quality online acquisition to improve interpretability and adaptability. The reliability of the proposed estimation approach is verified by a sodium aluminate solution evaporation application case.

Development of Mathematical Models for Industrial Processes Using Dynamic Neural Networks

Dynamic neural networks (DNNs) are a type of artificial neural network (ANN) designed to work with sequential data where context in time is important. Unlike traditional static neural networks that process data in a fixed order, dynamic neural networks use information about past inputs, which is important if the dynamic of a certain process is emphasized. They are commonly used in natural language processing, speech recognition, and time series prediction. In industrial processes, their use is interesting for the prediction of difficult-to-measure process variables. In an industrial isomerization process, it is crucial to measure the quality attributes that affect the octane number of gasoline. Process analyzers commonly used for this purpose are expensive and subject to failure. Therefore, to achieve continuous production in the event of a malfunction, mathematical models for estimating product quality attributes are imposed as a solution. In this paper, mathematical models were developed using dynamic recurrent neural networks (RNNs), i.e., their subtype of a long short-term memory (LSTM) architecture. The results of the developed models were compared with the results of several types of other data-driven models developed for an isomerization process, such as multilayer perceptron (MLP) artificial neural networks, support vector machines (SVM), and dynamic polynomial models. The obtained results are satisfactory, suggesting a good possibility of application.

Development of the automatic method of detection and grouping of external welding imperfections

The non-destructive testing of welded joints is a key issue in welding technology and processes. It is especially crucial for estimation of product quality. Among others methods, visual testing is the most fundamental. In most cases, it is made manually, which can introduce some problems resulting from the lack of objectivity and fatigue of the controlling person. This paper is an attempt of changing a mode of visual inspection. The proposed system is based on image analysis of welded joints. The welding imperfections were correlated with quality levels according to the ISO 5817 standard. For the original inspection system, six the most fundamental imperfections have been selected. The main idea of this system is a detection of selected welding imperfections and, based on acceptance criteria, assigning welded joints for the appropriate quality level. In order to validate the correct operation of the proposed system, the same welded joints have been subjected to conventional manual visual inspection. The compliance of the results was more than 90%, and the speed of visual examinations was more than 10 times higher than in the manual method.

Research on adaptive soft sensing modeling method of photovoltaic power generation process based on online semi-supervised selective ensemble learning

Soft sensors often estimate product quality variables that are difficult to measure in real time. However, strong nonlinearity and dynamic and time-varying characteristics lead to poor prediction performance of soft sensors for the photovoltaic power generation process. This paper proposes an adaptive soft sensor model construction strategy based on extreme learning machine online semi-supervised selective ensemble learning (SEMI-SEL-ELM). Firstly, a local learning strategy based on the Spatio-temporal criterion is proposed to limit the impact of nonlinear dynamic characteristics. The unlabeled samples are then examined to provide a semi-supervised sample set reconstruction. After that, using the extreme learning machine method, a local soft sensor model is created. Furthermore, the statistical hypothesis test is used to create the statistical information of the test samples, and the t-test is utilized to acquire the quantitative local model satisfaction. Additionally, the adaptive computation of mixed weights of distinct sub-models is performed using the improved information entropy. The black hole algorithm determines the parameters of this approach automatically. Finally, the method is applied to the historical data set of a photovoltaic power station in Australia. The results show that the method effectively deals with nonlinear, dynamic, and time-varying regression problems in PV power prediction.

A multimode mechanism-guided product quality estimation approach for multi-rate industrial processes

Discrete and delayed laboratory analyses of product quality restrict the operational optimization of industrial processes. However, it is challenging to build an accurate online estimation model for product quality because of complex process dynamics, multiple working conditions, and multi-rate characteristics. Therefore, a multimode mechanism-guided product quality variable estimation model is proposed in this study. First, representative features are extracted from high-dimensional and redundant process variables via both feature engineering and deep learning to describe the internal reaction state. Then, the representative features are used to partition the data samples which are used to train the multi-mode long short-term memory (LSTM) network to increase the adaptability of the estimation model. Finally, the LSTM units are cascaded to learn the variation in the quality variable against time to handle the multi-rate problem. The mechanism models are placed in parallel with the LSTM units to guide the learning process. The estimation model utilizes production data, mechanism knowledge and working condition information, which increases model interpretability and adaptability. A zinc fluidized bed roaster is used to illustrate the proposed estimation approach. The simulation results demonstrate the feasibility and effectiveness of the proposed multi-rate estimation approach.

A Bayesian information fusion approach for end product quality estimation using machine learning and on-machine probing

There is an increasing demand for manufacturing processes to improve product quality and production rates while minimising the costs. The quality of the products is influenced by several sources of errors introduced during the series of manufacturing operations. These errors accumulate over these multiple stages of manufacturing. Therefore, monitoring systems for product health utilising data and information from different sources and manufacturing stages is a key factor to meet these growing demands. This paper addresses the process of combining new measurement data or information with machine learning-based prediction information obtained as each product goes through a series of manufacturing steps to update the conditional probability distribution of the end product quality during manufacturing. A Bayesian approach is adopted in obtaining an updated posterior distribution of the end product quality given new information from subsequent measurements, and, in particular, On-Machine Probing (OMP). Following the steps of heat treatment, machining, and OMP, the posterior distribution of the previous step can be considered as the new prior distribution to obtain an updated posterior distribution of the product condition as new metrological information becomes available. It is demonstrated that the resulting posterior estimates can lead to more efficient product condition monitoring in multistage manufacturing.

A PERCEPTION CLASSIFICATION USING HYBRID FEATURE EXTRACTION

The estimation of product quality is more signicant during the purchasing of online products. Therefore, many opinion mining and sentiment classication methods were introduced to purchase the best products through online shopping. But, these classication methods haven't attained the effective product classication with best reviews and ratings. Several popular classication algorithms estimated along with three ltering Methods. Presented a hybrid technique to extract the product features. In this method, association rules and point-wise mutual information is combine. Large amount of features of products, not only to increase the time of computation but also to increase accuracy of classication. Optimize the amount of marketing funds spent on each customer, and just making a binary decision on whether to market to him. General Purpose Emotion Lexicons (GPELs) that associate with emotion categories remain a valuable resource for emotion analysis. Proposed a hybrid feature extraction method PCA (Principle Component Analysis) using lexicon-based method to classify and separate the products from the large set of different products depending on their features, best product ratings and positive reviews.

Quality designing and food safety provisioning based on qualimetric forecasting

Two interrelated systemic challenges need to be successfully addressed to achieve sustainable, progressive development of processing plants: designing and consistently producing products in demand by customers and ensuring their safety. The solution to this systemic task requires a systemic approach. As such a solution, the author's approach to quality design and food safety based on the qualimetric forecasting and risk qualimetry methodology is proposed in the paper. The key elements of the proposed approach and risk qualimetry are presented. The proposed approach to designing competitive products and ensuring their safety was tested using structured dairy products, particularly milk puddings. The indicators of consumer preferences were revealed; the formula for complex estimation of milk puddings quality was presented; the matrix of consumer preferences with the indication of target indicators values was developed; the regression equations for structural-mechanical indices of milk base quality depending on the mass part of structurizer Tirgo 601 and temperature of model medium heat treatment were obtained. The milk pudding recipe variants were also suggested; the results of consumers' estimation of new product quality and products sold on the market were presented: 94.8% and 89.2%, 82.6%, 88.0%, 88.5%, respectively.

Estimation of product quality in China's food processing and manufacturing industries

Using a product variety model, where higher-quality products increase consumer utility and quality products are more costly to produce, we show that optimal product quality depends on a parameter of the consumer utility function and the firm's cost of production. Our theoretical analysis shows that a firm's unobserved product quality is structurally linked to its observed sales revenue; the structural relationship allows estimation of the product quality within an industry. We then utilize firm-level data from China from 2005 to 2007 to estimate product quality in China's (i) food processing and (ii) food manufacturing industries. By comparing the distributions of product quality (and product quality growth rates) over time, we argue that product quality in both industries is improving.

Virtual metrology as an approach for product quality estimation in Industry 4.0: a systematic review and integrative conceptual framework

Virtual metrology (VM) involves estimating a product’s quality directly from production process data without physically measuring it. This enables the product quality of each unit of production to be monitored in real time, while preserving the process efficiency. Initially developed for the semiconductor industry, VM has recently been examined for use in other industrial fields. VM is enabled by components such as quality estimators and drift detectors. It enhances various industrial applications such as machine control and sampling decision systems. The literature lacks a comprehensive summary and a systematic review of the state of the art in VM. To fill this gap, this study followed a systematic methodology to conduct a complete and structured literature review of VM. This paper presents a detailed analysis of the 199 papers that we identified based on our search and selection criteria. Following our methodological framework, we assigned these papers to categories and highlighted shortcomings. Finally, we discussed VM’s use in various industrial fields, underlining its potential for every manufacturing industry. This study and the proposed framework are useful for both practitioners and academicians since they raise crucial theoretical and managerial questions as well as provide suggestions for further research on this critical topic.

Determination of banana quality indices during the ripening process at different temperatures using smartphone images and an artificial neural network

Banana quality and ripening stages were studied at four different temperatures (20, 25, 27.5, and 30 °C) using a smartphone camera and an artificial neural network (ANN). Changes in chemical and physical properties such as firmness, total soluble solids (TSS), pH, and ratio of pulp to peel, were determined and the relationship with color features (L*a*b*, hue, saturation, value [HSV], and luminance and chrominance [YUV]) were extracted from red, green, blue (RGB) images. ANN models based on color features were used to predict the quality indices of bananas during the ripening process. In addition, the developed models were verified by the coefficient of determination (R2), root mean squared error (RMSE), and the ratio of performance to deviation (RPD). The ANN model predicted the firmness and TSS of banana efficiently, with R2 values higher than 0.96 and RMSE values less than 72.32 and 1.40 for firmness and TSS, respectively. However, the ANN model was not suitable for predicting the pH value and ratio of pulp to peel with R2 values less than 0.60 and RMSE values of over 0.20 and 0.23 for pH and the ratio of pulp to peel, respectively. Thus, we demonstrated a post-harvest methodology to determine the ripening status of bananas by predicting their quality indices during the ripening process on a smartphone camera using ANN, and suggest smartphone camera as a potential tool to estimate product quality.

The influence of online review adoption on the profitability of capacitated supply chains

The paper explores the influence of online review adoption on supply chain profitability under the presence of a capacity constraint. Nowadays, customers increasingly rely on online reviews for decision making, and online retailers regard reviews as a norm. Although online reviews have been extensively examined in marketing disciplines, little research has been conducted to investigate their influence from a supply chain perspective. In addition, previous research has largely focused on how online review information can influence customer purchase behaviours, but ignores the more basic decision: whether and when companies should adopt reviews. This paper examines the online review adoption decision from a capacitated supply chain perspective through mathematical modelling and simulation. The simulation considers the influence of variables including online review adoption decision, capacity constraint level, lost sales penalty level, and product quality estimation on supply chain profitability. Generally, we find that online reviews can bring more profit to the supply chain than without online reviews, although such influence is moderated by the other three variables. The findings reveal the complexity of the contextual variable impacts on online review adoption, and demonstrate that decisions concerning the adoption of online reviews should take all supply-chain-related variables into consideration rather than only aiming for increasing customer orders.

Understanding Persuasion Cascades in Online Product Rating Systems: Modeling, Analysis, and Inference

Online product rating systems have become an indispensable component for numerous web services such as Amazon, eBay, Google Play Store, and TripAdvisor. One functionality of such systems is to uncover the product quality via product ratings (or reviews) contributed by consumers. However, a well-known psychological phenomenon called “ message-based persuasion ” lead to “ biased ” product ratings in a cascading manner (we call this the persuasion cascade ). This article investigates: (1) How does the persuasion cascade influence the product quality estimation accuracy? (2) Given a real-world product rating dataset, how to infer the persuasion cascade and analyze it to draw practical insights? We first develop a mathematical model to capture key factors of a persuasion cascade. We formulate a high-order Markov chain to characterize the opinion dynamics of a persuasion cascade and prove the convergence of opinions. We further bound the product quality estimation error for a class of rating aggregation rules including the averaging scoring rule, via the matrix perturbation theory and the Chernoff bound. We also design a maximum likelihood algorithm to infer parameters of the persuasion cascade. We conduct experiments on both synthetic data and real-world data from Amazon and TripAdvisor. Experiment results show that our inference algorithm has a high accuracy. Furthermore, persuasion cascades notably exist, but the average scoring rule has a small product quality estimation error under practical scenarios.

Near-Infrared Wavelength-Selection Method Based on Joint Mutual Information and Weighted Bootstrap Sampling

Near-infrared (NIR) spectroscopy is widely used to estimate product quality and other key variables. Eliminating redundant variables is very important in constructing a high-quality NIR model. This article proposes a new wavelength-selection method for NIR spectroscopy based on joint mutual information and weighted bootstrap sampling (WBS). The method considers the combination effect of variables and involves the dynamic selection of wavelength in each iteration to increase the model prediction accuracy. The index based on joint mutual information is used to determine the importance of variables and thus accurately reflects the variable-combination effect. WBS is further used to dynamically adjust the importance of candidate variables, i.e., to increase the weights of samples with poor prediction results and decrease those of samples with accurate prediction. This process ensures that the subsequently selected wavelength focuses on inaccurately estimated samples. The performance of this method is demonstrated through three NIR datasets of gasoline, shootout, and diesel fuels. The proposed method is found to have better accuracy than the traditional partial-least-squares method, variable iterative space shrinkage approach, and several other wavelength-selection methods.

RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes

Direct online measurement on product quality of industrial processes is difficult to be realized, which leads to a large number of unlabeled samples in modeling data. Therefore, it needs to employ semi-supervised learning (SSL) method to establish the soft sensor model of product quality. Considering the slow time-varying characteristic of industrial processes, the model parameters should be updated smoothly. According to this characteristic, this paper proposes an online adaptive semi-supervised learning algorithm based on random vector functional link network (RVFLN), denoted as OAS-RVFLN. By introducing a L2-fusion term that can be seen a weight deviation constraint, the proposed algorithm unifies the offline and online learning, and achieves smoothness of model parameter update. Empirical evaluations both on benchmark testing functions and datasets reveal that the proposed OAS-RVFLN can outperform the conventional methods in learning speed and accuracy. Finally, the OAS-RVFLN is applied to the coal dense medium separation process in coal industry to estimate the ash content of coal product, which further verifies its effectiveness and potential of industrial application.

E-Commerce Product Classification using Lexical Based Hybrid Feature Extraction and SVM

At present, online shopping has become a growing process, in which the profit statistics are posted by familiar e-commerce corporations like Amazon, Flipkart, Snapdeal, etc. However, this kind of online shopping unkindly omits the touch and feel of the products that can be used to estimate the product quality as the main factor while buying the commodities from the shops. The estimation of product quality is more significant during the purchasing of online products. Therefore, many opinion mining and sentiment classification methods were introduced to purchase the best products through online shopping. But, these classification methods haven’t attained the effective product classification with best reviews and ratings. In this paper, we propose a hybrid feature extraction method PCA (Principle Component Analysis) and t-SNE (t-Distributed Stochastic Neighbor Embedding ) with SVM (Support Vector Machine) using lexicon-based method to classify and separate the products from the large set of different products depending on their features, best product ratings and positive reviews. In this process, the online products will be isolated and listed according to their high positive reviews. The data preprocessing is applied to the dataset to get the data accuracy before the execution of feature extraction and classification. The dimensionality reduction and best visualization of large data set are executed by applying the PCA and t-SNE method. The sentiments are also been extracted by this hybrid feature extraction method to acquire the best neighboring product ratings. The polarity of words is discovered using a lexical based approach to extract positive reviews for obtaining the best products. Finally, the SVM is exploited to the classification of products. The performance of the proposed method is estimated with precision, recall, accuracy and complexity that can provide the entire accurateness of the system.

Optimization of time‐variable‐parameter model for data‐based soft sensor of industrial debutanizer

SummaryThe enhancement of modern process control methods has caused the popularity of soft sensors in online quality prediction. It is significant to consider the reduction of model complexity, the performance increment, and decrement of input variables in soft sensor design, simultaneously. The aim of this paper is designing and applying a new data‐based soft sensor with minimum input variables for the enhancement of product quality estimation. Time‐varying‐parameter model by employing the Kalman filter and fixed interval smoothing algorithms has been developed to determine the dynamic transfer function and parameters setting based on time. A novel hybrid method with a dynamic autoregressive exogenous variable model and genetic algorithm has been presented for both state identification and parameter prediction. The combinatorial optimization problem has constructed based on a selection of input variables and an evaluation of Akaike information criterion as a fitness function. An industrial debutanizer column has been used for soft sensor performance validation. The result has indicated that the final soft sensor model in comparison to other presented soft sensing methods for this case has less complexity, fewer input variables, more robust and higher predictive performance. Due to fewer input variables, rapid convergence, and low complexity of this model, it can be efficient in industrial processes control, time‐saving, and improvement of quality prediction.