Model-based Procedure Research Articles

Coping with the uncertainties of make-to-order production: a new approach for determining reliable delivery times with the throughput diagram

Make-to-order companies have to deal with particular uncertainties in their offer processing. At the early stage of planning offers, it is particularly uncertain 1) which open offers will be accepted by customers and 2) what capacity these will require. Therefore, it is particularly challenging for make-to-order companies to determine and keep to binding delivery times, so that many companies have problems achieving a high delivery reliability. In this paper, we show a simple model-based procedure to determine delivery times using the throughput diagram with early available information such as the offer requests in the planning process. Simulation studies show that the procedure, especially in combination with a CONWIP order release and an EODD sequencing rule, achieves a high delivery reliability without sacrificing other logistic objectives such as utilisation. Furthermore, the procedure proves to be very robust against random deviations of the planning parameters.

On the Verification of Distributed Control for Multi Job Shop Assignment Problem in Smart Manufacturing System

The increasing need of product individualization and rapid demand fluctuation leads industrial manufacturers to leveraging new control solutions for production planning and control. Among these, distributed control approaches for the multi job shop scheduling problem could be a promising solution to make smart manufacturing systems more responsive to the market. In this context, this paper aims at investigating the effectiveness and the benefits of distributed control approaches for solving the multi job shop assignment problem on a real-world smart manufacturing process involving the production of high-vacuum solar panels. The validation is carried out by leveraging Cyber-Physical Systems modelling and a digital model-based procedure which, interacting with the physical plant, provides the proper job assignment in order to optimize the overall makespan and work-in-progress in a fully-distributed fashion.

Sparse and smooth functional data clustering

A new model-based procedure is developed for sparse clustering of functional data that aims to classify a sample of curves into homogeneous groups while jointly detecting the most informative portions of the domain. The proposed method is referred to as sparse and smooth functional clustering (SaS-Funclust) and relies on a general functional Gaussian mixture model whose parameters are estimated by maximizing a log-likelihood function penalized with a functional adaptive pairwise fusion penalty and a roughness penalty. The former allows identifying the noninformative portion of the domain by shrinking the means of separated clusters to some common values, whereas the latter improves the interpretability by imposing some degree of smoothing to the estimated cluster means. The model is estimated via an expectation-conditional maximization algorithm paired with a cross-validation procedure. Through a Monte Carlo simulation study, the SaS-Funclust method is shown to outperform other methods that already appeared in the literature, both in terms of clustering performance and interpretability. Finally, three real-data examples are presented to demonstrate the favourable performance of the proposed method. The SaS-Funclust method is implemented in the R package sasfunclust, available on CRAN.

Valid Model-Free Spatial Prediction

Predicting the response at an unobserved location is a fundamental problem in spatial statistics. Given the difficulty in modeling spatial dependence, especially in nonstationary cases, model-based prediction intervals are at risk of misspecification bias that can negatively affect their validity. Here we present a new approach for model-free nonparametric spatial prediction based on the conformal prediction machinery. Our key observation is that spatial data can be treated as exactly or approximately exchangeable in a wide range of settings. In particular, under an infill asymptotic regime, we prove that the response values are, in a certain sense, locally approximately exchangeable for a broad class of spatial processes, and we develop a local spatial conformal prediction algorithm that yields valid prediction intervals without strong model assumptions like stationarity. Numerical examples with both real and simulated data confirm that the proposed conformal prediction intervals are valid and generally more efficient than existing model-based procedures for large datasets across a range of nonstationary and non-Gaussian settings.

Analysis of the axial and transversal stiffness of an air spring suspension of a railway vehicle: mathematical modelling and experiments

ABSTRACT The secondary suspension of railway vehicles is fundamental for their dynamic behaviour. This paper outlines a model-based procedure for predicting and evaluating the influence of different parameters in the static stiffness and vibration transmission of an air spring employed in the secondary suspension system of a railway vehicle. For that aim, a detailed and experimentally validated finite element model of the air spring is defined. It includes the behaviour of the reinforced elastomer, the inner pressure-deformation coupling and the thermodynamic interactions taking place inside the bellow. A Computer Aided Design of Experiments is employed to evaluate the influence of seven construction parameters of the bellow. Experimental tests and simulation results show that the air spring has natural frequencies below 100 Hz, in the frequency range where structure-borne vibration transmission occurs. The cord angle modifies the axial-transversal stiffness relation and a larger separation between adjacent layers and fibres delay the vibration transmissibility.

Empirical Best Prediction of Small Area Means Based on a Unit-Level Gamma-Poisson Model

Abstract Existing small area estimation procedures for count data have important limitations. For instance, an M-quantile-based method is known to be less efficient than model-based procedures if the assumptions of the model hold. Also, frequentist inference procedures for Poisson generalized linear mixed models can be computationally intensive or require approximations. Furthermore, area-level models are incapable of incorporating unit-level covariates. We overcome these limitations by developing a small area estimation procedure for a unit-level gamma-Poisson model. The conjugate form of the model permits computationally simple estimation and prediction procedures. We obtain a closed-form expression for the empirical best predictor of the mean as well as a closed-form mean square error estimator. We validate the procedure through simulations. We illustrate the proposed method using a subset of data from the Iowa Seat-Belt Use survey.

Model Based Design, Prototyping and Testing of a Small Size High Speed Electrically Driven Centrifugal Pump

<div class="section abstract"><div class="htmlview paragraph">Within automotive sector, there are several high-performance applications, like, for instance, those referred to racing and motorsport, where cooling needs are usually fulfilled by simple circuits with conventional low-efficiency pumps. The cooling needs in these applications are represented by low flow rates delivered (in the range of 10 - 50 L/min). The operating conditions of these small pumps are usually characterized by very high revolution speeds, which intrinsically cause low efficiency and critical intake phenomena (cavitation) if the design is not specifically optimized to address these concerns.</div><div class="htmlview paragraph">Hence, in this paper a small-size pump operating in the racing sector has been designed using a model-based approach, built and tested having reached both high efficiency (aimed to 50%) and absence of intake operational problems (cavitation). Starting from the specific cooling request (design flow rate equal to 14.0 L/min and pressure rise equal to 2.5 bar), the very limited space available on board oriented the design to an operational revolution speed of 12000 RPM. The interest of this study was to introduce a so high revolution speed in more conventional automotive cooling pumps electrically assisted, keeping high efficiency. In fact, the strong reduction of the size of the pump allows an easy and correct positioning on board.</div><div class="htmlview paragraph">The model-based design was done by a two-steps procedure. The first made use of a 0D model which, catching main physical phenomena of the flow even in simplified form, leads to an optimum geometrical design for the impeller and the volute. A final refinement has been done with a CFD code predicting the off-design performance and limiting cavitation zones. Cavitation, which is one of the most critical issues of high-speed pumps, was completely investigated through a CFD numerical analysis.</div><div class="htmlview paragraph">The pump has been prototyped and tested on a dynamic test bench for pumps, which reproduces homologation cycles and real driving. A good agreement has been reached between theoretical and experimental results, being the mean relative error on pressure rise for all operating point close to 4 %. This model-based procedure opens the way to support the development of electric water pumps for more conventional applications (automotive, light duty engines) in which a redesign will be focused to manage the thermal state of the engine and reduce the energy absorbed during the homologation cycle.</div></div>

Artificial neural network based photovoltaic module diagnosis by current–voltage curve classification

In this paper a model-based procedure for fault detection and diagnosis of photovoltaic modules is presented. A four-layered feedforward artificial neural network learns the correlation between the features of the current vs. voltage curve and the environmental variables, which are the irradiance and the temperature. This correlation describes the behavior of the module at normal conditions. Moreover, the effect of anomalous variation of some parameters is learnt and correlated to the shape of the same curve, thus associated to a specific failure mechanism and to some assigned ranges quantifying the fault severity. The neural network is trained by using synthetic curves simulated by employing the single diode model and some well assessed and validated translation formulae. The obtained results over the simulated set of curves with different failures allow to achieve a classification error lower than 1.5%. The proposed approach has been also validated for detecting anomalous increases of the series resistance in a large experimental set of curves; in this case, a classification error of 2.7% has been achieved.

Clinical outcome of single posterior implant-supported monolithic zirconia crowns fabricated using full digital workflow and conventional workflow: a 3-year follow-up

Objective: To compare the clinical performance of posterior single implant-supported monolithic zirconia crowns fabricated by full digital workflow and that of those fabricated by conventional workflow. Methods: This is prospective clinical research. Thirty-five patients who participated in a previous study during August 2017 to October 2018 at Department of Prosthodontics, Peking University School and Hospital of Stomatology were included in this 3-year follow-up study. The 35 patients, 17 females and 18 males, aged (49.0±15.4) years (24-86 years old), was allocated into two groups. In the full digital workflow group, intraoral scanning was taken immediately after implant placement, and a full zirconia implant crown was fabricated using model-free computer aided design/computer aided manufacturing (CAD/CAM) procedure (n=14). In the conventional group, a conventional impression was taken 3 months after implant placement and the stone model was produced. A full zirconia implant crown was fabricated using conventional model-based procedure (n=21). Three years following crown delivery, all the prostheses were evaluated in the aspect of color, surface roughness, contour and marginal integrity using modified US Public Health Service criteria (MUSPHS criteria). The soft and hard tissue around implant was evaluated using modified plaque index, probing depth (PD), number of implants with bleeding on probing, marginal bone loss (MBL). The biological and mechanical complication were also recorded. Statistical analysis was performed using independent samples t test, Mann-Whitney U test and Fisher's exact test. Results: The total survival rate of prosthesis and implant was 100% (35/35). No significant difference in MUSPHS criteria ratings on color, surface roughness, contour and marginal integrity of these crowns were found between the full digital workflow group and the conventional group (P>0.05). Sixteen out of the 35 crowns had a contour score of B due to loss of interproximal contact. Ten out of the 35 crowns had the screw hole sealing resin sinking or falling off, four in the full digital workflow group and six in the conventional group. There was no significant difference in the rate of prostheses mechanical complications between the two groups (P=1.000). For all the implants, there was no significant difference in MBL, PD, the modified plaque index, and number of implants with bleeding on probing between the two groups (U=119.50,133.00,142.50, t=-0.53, P>0.05). Conclusions: The clinical performance of implant-supported posterior single monolithic zirconia crowns fabricated by full digital workflow was stable. There was no significant difference in the clinical performance of the single implant crowns between the full digital workflow group and the conventional group.

A Response-Time-Based Latent Response Mixture Model for Identifying and Modeling Careless and Insufficient Effort Responding in Survey Data

Careless and insufficient effort responding (C/IER) can pose a major threat to data quality and, as such, to validity of inferences drawn from questionnaire data. A rich body of methods aiming at its detection has been developed. Most of these methods can detect only specific types of C/IER patterns. However, typically different types of C/IER patterns occur within one data set and need to be accounted for. We present a model-based approach for detecting manifold manifestations of C/IER at once. This is achieved by leveraging response time (RT) information available from computer-administered questionnaires and integrating theoretical considerations on C/IER with recent psychometric modeling approaches. The approach a) takes the specifics of attentive response behavior on questionnaires into account by incorporating the distance–difficulty hypothesis, b) allows for attentiveness to vary on the screen-by-respondent level, c) allows for respondents with different trait and speed levels to differ in their attentiveness, and d) at once deals with various response patterns arising from C/IER. The approach makes use of item-level RTs. An adapted version for aggregated RTs is presented that supports screening for C/IER behavior on the respondent level. Parameter recovery is investigated in a simulation study. The approach is illustrated in an empirical example, comparing different RT measures and contrasting the proposed model-based procedure against indicator-based multiple-hurdle approaches.

Model-based single-month unemployment rate estimates for the Brazilian Labour Force Survey1

The Brazilian Labour Force Survey (BLFS) is a quarterly rotating panel survey with 80% sample overlap between two successive quarters. Monthly unemployment rate estimates are regularly produced based on a three-month average of direct estimates. Due to the unforeseen situation of COVID19 pandemic and its effects in the economy and labour market, there was a need to investigate model-based estimation procedures to obtain unemployment rate single-month estimates. We present structural time series models developed to produce model-based single month estimates at national level as well as small area (state-level) estimates at a higher frequency than those currently being published. Using the state-space framework, the models account for the autocorrelation due to sample overlap and the increased dynamics in the labour force series in 2020. In addition, bivariate models that combine claimant count and survey data are investigated. The models not only yield estimates with better precision than direct estimates, since the latter were affected by a rise in non-response, but they can deliver reliable state-level official statistics at a monthly frequency that are presently required. The new improved model-based estimates were proposed as experimental statistics for the Brazilian national statistical office (IBGE).

DECISION SUPPORT SYSTEM TO DETERMINE THE FEASIBILITY OF APPLYING TEACHER CERTIFICATION WITH SIMPLE ADDITIVE WEIGHTING METHOD (CASE STUDI : MA AL MUHAJIRIN JANTI JOGOROTO JOMBANG)

Formal educational institutions have an important task to prepare quality Indonesian human resources (HR) in the future. In this school education environment, professional teachers hold the main key for improving the quality of future human resources (HR) and teachers are professionals who carry out the main tasks and functions of improving the knowledge, skills, and attitudes of students as Indonesian human assets for the future. In the process of quality education, it is an obligation and obligation that is required for every school, to have certified teachers so that education can increase and can affect student achievement. Decision-making system as a set of model-based procedures for data processing and assessment. to assist schools in determining teachers who are eligible to receive certification with criteria namely pedagogic, personality, social, professional. The purpose of this research is to help decision makers in the selection process easily and quickly. The simple additive weighing (SAW) method to provide decisions on the selection process for submitting teacher certification. The system developer method uses the waterfall method. An educator certificate is a requirement for proof that teachers meet educational professional standards.

Investigation of measurement invariance in longitudinal health-related quality of life in preemptive or previously dialyzed kidney transplant recipients.

Kidney transplantation (KT) can impact patients' evaluation of health-related quality of life (HRQoL) as they adapt to their new life with a graft and its changes. Patients may adapt to KT in a different way, depending on whether they were on dialysis prior to transplantation or not (i.e. preemptive group). This may result in lack of measurement invariance between these patients' groups and/or over time (i.e. response shift, RS) which may invalidate the between-group comparison of HRQoL change scores. The aim of this study was to investigate and compare RS before and after KT between these two patients' groups. Measurement invariance was investigated between groups and over time with three measurement occasions. Adult patients completed the SF-36 at the last visit before KT, and 3, 6months after. A structural equation model-based procedure was used to (i) detect and take into account measurement non-invariance between groups and RS, if appropriate, (ii) identify the period of occurrence of RS, (iii) study the heterogeneity of RS between the two groups. Before KT (i.e. baseline), measurement invariance was not rejected between dialyzed (n = 196) and preemptive (n = 178) patients' groups. Between baseline and 3 months after KT, similar uniform recalibration was detected on the general health domain in both groups. Uniform recalibration was found between 3- and 6 months after KT on the vitality domain for preemptive patients only. HRQoL, adjusted for RS, increased overall for preemptive and dialyzed kidney transplant patients after transplantation. RS may reflect differing adaptation processes following KT.

Structural identification of the dynamic behavior of floor diaphragms in existing buildings

The deformability of floor diaphragms plays a primary role in the structural behavior of existing buildings. Nonetheless, few structural identification procedures are available to investigate this matter from in-situ experimental measurements. Ambient vibration tests can be very useful to the purpose, allowing to assess the importance of the floor deformability in operational modal analyses through model-driven approaches. This information is particularly valuable for unreinforced masonry buildings, often characterized by deformable diaphragms whose effective stiffness is commonly unknown and hard to be evaluated. Based on these motivations, in this paper, a discrete linear model of deformable diaphragm is formulated in a novel fashion. The modal properties governing the free undamped dynamics are analytically determined through a fully general perturbation technique (direct problem). Therefore, a model-based structural identification procedure is proposed to analytically assess the inertial and elastic properties of the deformable diaphragm (inverse problem), assuming the outcomes of experimental modal analyses as known input. Consistently with the perturbation approach, explicit formulas are determined for low-order minimal models and higher-order model updating, accounting for mass and inertial eccentricities. Among the other identifiable mechanical parameters, the focus is put on the first and second-order identification of the in-plane shear stiffness of the diaphragm. The theoretical developments are successfully verified on pseudo-experimental and experimental bases, by applying the identification procedure to (i) the computational model of a prototypical steel frame structure, (ii) the large scale laboratory model of a two-story composite structure with mass eccentricities, (iii) a permanently monitored masonry building recently struck by the 2016-2017 Central Italy earthquake sequence.

Phospho-islands and the evolution of phosphorylated amino acids in mammals.

BackgroundProtein phosphorylation is the best studied post-translational modification strongly influencing protein function. Phosphorylated amino acids not only differ in physico-chemical properties from non-phosphorylated counterparts, but also exhibit different evolutionary patterns, tending to mutate to and originate from negatively charged amino acids (NCAs). The distribution of phosphosites along protein sequences is non-uniform, as phosphosites tend to cluster, forming so-called phospho-islands.MethodsHere, we have developed a hidden Markov model-based procedure for the identification of phospho-islands and studied the properties of the obtained phosphorylation clusters. To check robustness of evolutionary analysis, we consider different models for the reconstructions of ancestral phosphorylation states.ResultsClustered phosphosites differ from individual phosphosites in several functional and evolutionary aspects including underrepresentation of phosphotyrosines, higher conservation, more frequent mutations to NCAs. The spectrum of tissues, frequencies of specific phosphorylation contexts, and mutational patterns observed near clustered sites also are different.

The spatial statistic trinity: A generic framework for spatial sampling and inference

Geospatial referenced environmental data are extensively used in environmental assessment, prediction, and management. Data are commonly obtained by nonrandom surveys or monitoring networks, whereas spatial sampling and inference affect the accuracy of subsequent applications. Design-based and model-based procedures (DB and MB for short) both allow one to address the gap between statistical inference and spatial data. Creating independence by sampling implies that DB may neglect spatial autocorrelation (SAC) if the sampling interval is beyond the SAC range. In MB, however, a particular sampling design can be irrelevant for inferential results. Empirical studies further showed that MSE (mean squared error) values for both DB and MB are affected by SAC and spatial stratified heterogeneity (SSH). We propose a novel framework for integrating SAC and SSH into DB and MB. We do so by distinguishing the spatial population from the spatial sample. We show that spatial independence in a spatial population results in independence in a spatial sample, whereas SAC in a spatial population is reflected in a spatial sample if sampling distances are within the range of dependence; otherwise, SAC is absent in the spatial sample. Similarly, SSH in a population may or may not be inherited in data, and this depends on the sampling method. Thus, the population, sample, and inference constitute a so-called spatial statistic trinity (SST), providing a new framework for spatial statistics, including sampling and inference. This paper shows that it greatly simplifies the choice of method in spatial sampling and inferences. Two empirical examples and various citations illustrate the theory.

Optimal Retrofit of a Multiplant Heat Exchanger Network with a Fair Benefit Allocation Plan

A model-based procedure has recently been developed to address the benefit allocation issue among members of an interplant heat integration scheme in the spirit of co-operative game. Although satisfactory results were reported, their approach is only applicable to grass-root designs. In practical applications, the existing plants on an industrial park were usually built to meet the targeted market demands, which arose during different periods in the past and each must have already been equipped with a heat exchanger network (HEN) by the time when its construction was completed. Therefore, the aforementioned allocation problem is more likely to take place when a multiplant HEN retrofit project is called for to facilitate a further reduction in utility consumption. This paper presents three viable strategies to solve the more realistic revamp problems. Depending upon other requirements in practical applications, for example, safety concerns, spatial limits, operability, and so forth, these strategies are devised by introducing different levels of restrictions on the new and original matches, on repiping and reusing of existing units in the multiplant HEN, and on the installation of purchased new heat exchangers, coolers, and heaters. The actual financial benefits allocated to the participating members of the interplant heat integration scheme are then determined according to the corresponding Shapley values. A simple example is presented in this paper to illustrate the aforementioned HEN retrofit and saving distribution procedures.

Implementation of Optimized Artificial Neural Networks for Real-Time Estimation of Low Pressure Cooled Exhaust Gas Recirculation in a Turbocharged Gasoline Direct Injection Engine Using a Model-Based Design Approach

Abstract Low pressure cooled exhaust gas recirculation (LP-EGR) system has been widely adopted to improve energy efficiency in turbocharged gasoline direct injection (GDI) engines. In order to utilize complete beneficial effects of the LP-EGR, a technique capable of accurately observing the LP-EGR flow into the cylinder in real-time is a prerequisite. To precisely estimate the LP-EGR rate in real-time, this paper proposes artificial neural network (ANN) models and its implementation on a real-time embedded system. As inputs for the ANN models, 12 combustion parameters physically correlated with the LP-EGR in the combustion process are selected and calculated from the in-cylinder pressure. The ANN models for the real-time LP-EGR estimation were trained with the steady-state data of 30,000 cycles and their hyper-parameters were searched by a hyper-parameter optimization method. Moreover, a model-based design procedure is introduced to implement the optimized ANN models on the real-time embedded system. Since the proposed implementation performs the validation procedure for each process, it provides a systematic and seamless process for creating ANN models for real-time embedded systems. In real-time experiments under eight steady-state engine operating points, the embedded ANN models show the estimation performance with R2 of above 0.9716. The operation time of each ANN was less than 1.285 ms meaning that the target system can operate in real-time sufficiently with a mass-produced 32 bit microprocessor up to 256 MHz.

Data generation for composite-based structural equation modeling methods

Examining the efficacy of composite-based structural equation modeling (SEM) features prominently in research. However, studies analyzing the efficacy of corresponding estimators usually rely on factor model data. Thereby, they assess and analyze their performance on erroneous grounds (i.e., factor model data instead of composite model data). A potential reason for this malpractice lies in the lack of available composite model-based data generation procedures for prespecified model parameters in the structural model and the measurements models. Addressing this gap in research, we derive model formulations and present a composite model-based data generation approach. The findings will assist researchers in their composite-based SEM simulation studies.

Supplemental Material for Improved Inference in Mediation Analysis: Introducing the Model-Based Constrained Optimization Procedure

Supplemental Material for Improved Inference in Mediation Analysis: Introducing the Model-Based Constrained Optimization Procedure