Application of Regression and ANN Models for Heat Pumps with Field Measurements

Developing accurate models is necessary to optimize the operation of heating systems. A large number of field measurements from monitored heat pumps have made it possible to evaluate different heat pump models and improve their accuracy. This study used measured data from a heating system consisting of three heat pumps to compare five regression and two artificial neural network (ANN) models. The models’ performance was compared to determine which model was suitable during the design and operation stage by calibrating them using data provided by the manufacturer and the measured data. A method to refine the ANN model was also presented. The results indicate that simple regression models are more suitable when only manufacturers’ data are available, while ANN models are more suited to utilize a large amount of measured data. The method to refine the ANN model is effective at increasing the accuracy of the model. The refined models have a relative root mean square error (RMSE) of less than 5%.

Download Full-text

Prediction of Slipper Pressure Distribution and Leakage Behaviour in Axial Piston Pumps Using ANN and MGGP

Mathematical Problems in Engineering ◽

10.1155/2019/7317520 ◽

2019 ◽

Vol 2019 ◽

pp. 1-13 ◽

Cited By ~ 3

Author(s):

Özkan Özmen ◽

Cem Sınanoğlu ◽

Turgay Batbat ◽

Ayşegül Güven

Keyword(s):

Pressure Distribution ◽

Predictive Modelling ◽

Measured Data ◽

Pump Efficiency ◽

Ann Model ◽

Novel Approach ◽

Multigene Genetic Programming ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Axial Piston

The pressure distribution (PD) and leakage between the slipper and swash plate in an axial piston pump (APP) have a considerable impact on the pump efficiency, affecting aspects such as the load bearing and wear performance of the slipper. Herein, multigene genetic programming (MGGP) and artificial neural network (ANN) machine learning methods (MLMs) are incorporated into a novel approach towards predictive modelling of the PD and leakage on the slipper, which can function hydrostatically/hydrodynamically. Experimentally measured data are used as input for the MGGP and ANN models. The validity of the MGGP and ANN models is verified using test data excluded from the analyses. In addition, the model results are compared with analytic equations (AEs). Both MLMs are found to exhibit strong agreement with the measured data. In particular, the ANN model exhibits superior prediction performance to the MGGP model and AEs.

Download Full-text

Modeling Fused Filament Fabrication using Artificial Neural Networks

Production Engineering ◽

10.1007/s11740-021-01020-y ◽

2021 ◽

Author(s):

Paul Oehlmann ◽

Paul Osswald ◽

Juan Camilo Blanco ◽

Martin Friedrich ◽

Dominik Rietzel ◽

...

Keyword(s):

Real Time ◽

Large Scale ◽

Cost Effective ◽

Print Quality ◽

Ann Model ◽

Production Environment ◽

Fused Filament Fabrication ◽

Artificial Neural ◽

Using Data ◽

Artificial Neural Network Ann

AbstractWith industries pushing towards digitalized production, adaption to expectations and increasing requirements for modern applications, has brought additive manufacturing (AM) to the forefront of Industry 4.0. In fact, AM is a main accelerator for digital production with its possibilities in structural design, such as topology optimization, production flexibility, customization, product development, to name a few. Fused Filament Fabrication (FFF) is a widespread and practical tool for rapid prototyping that also demonstrates the importance of AM technologies through its accessibility to the general public by creating cost effective desktop solutions. An increasing integration of systems in an intelligent production environment also enables the generation of large-scale data to be used for process monitoring and process control. Deep learning as a form of artificial intelligence (AI) and more specifically, a method of machine learning (ML) is ideal for handling big data. This study uses a trained artificial neural network (ANN) model as a digital shadow to predict the force within the nozzle of an FFF printer using filament speed and nozzle temperatures as input data. After the ANN model was tested using data from a theoretical model it was implemented to predict the behavior using real-time printer data. For this purpose, an FFF printer was equipped with sensors that collect real time printer data during the printing process. The ANN model reflected the kinematics of melting and flow predicted by models currently available for various speeds of printing. The model allows for a deeper understanding of the influencing process parameters which ultimately results in the determination of the optimum combination of process speed and print quality.

Download Full-text

How to Improve Effectiveness of Renewable Space Heating Programs by Better Understanding Homeowner—Installer Interactions

Energies ◽

10.3390/en14154625 ◽

2021 ◽

Vol 14 (15) ◽

pp. 4625

Author(s):

Alisa Freyre ◽

Stefano Cozza ◽

Matthias Rüetschi ◽

Meinrad Bürer ◽

Marlyne Sahakian ◽

...

Keyword(s):

Literature Review ◽

Financial Incentives ◽

Heating System ◽

Heat Pumps ◽

Single Family ◽

Heating Systems ◽

Current State ◽

Ex Post ◽

Improved Technology

In this paper, we perform a literature review on the current state of knowledge about homeowners in the context of the adoption of renewable heating systems. Despite a considerable number of studies about homeowners, homeowner–installer interactions, and ways to improve the effectiveness of renewable heating programs, based on homeowner knowledge, have not yet been studied in much detail. To address these knowledge gaps, we conduct a qualitative study on single-family house owners who installed heat pumps and took part in a renewable heating program in Geneva, Switzerland. We cover homeowner practices in choosing installers and heating system types, homeowners’ feedback about heat pump installation and use, as well as their experience in participation in the renewable heating program. Based on the literature review and the findings from the interviews, we provide the following recommendations on how to increase the effectiveness of renewable heating programs: (a) support for homeowners should not be limited to financial incentives; (b) partnership programs with installers could help to increase the quality of installation services and enable homeowners to choose qualified installers; and (c) assisting homeowners in pre-qualification and ex-post analysis, in learning how to operate their renewable heating systems and in solving problems during the post-installation period, can contribute to improved technology reputation, which can, in turn, increase technology uptake by other homeowners.

Download Full-text

Development of Neural Network Models for a Crude Oil Distillation Column

Jurnal Teknologi ◽

10.11113/jt.v38.509 ◽

2012 ◽

Author(s):

Khairiyah Mohd. Yusof ◽

Fakhri Karray ◽

Peter L. Douglas

Keyword(s):

Neural Network ◽

Steady State ◽

Crude Oil ◽

Distillation Column ◽

Network Models ◽

Ann Model ◽

Neural Network Models ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Crude Oil Distillation

This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the model is developed for real time optimisation (RTO) applications they are steady state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO.

Download Full-text

Computational Performance Analysis of Neural Network and Regression Models in Forecasting the Societal Demand for Agricultural Food Harvests

10.4018/978-1-6684-2408-7.ch062 ◽

2022 ◽

pp. 1287-1300

Author(s):

Balaji Prabhu B. V. ◽

M. Dakshayini

Keyword(s):

Neural Network ◽

Crop Production ◽

Demand Forecasting ◽

Forecasting Model ◽

Ann Model ◽

Demand Prediction ◽

Computational Performance ◽

Societal Needs ◽

Ann Models ◽

Artificial Neural Network Ann

Demand forecasting plays an important role in the field of agriculture, where a farmer can plan for the crop production according to the demand in future and make a profitable crop business. There exist a various statistical and machine learning methods for forecasting the demand, selecting the best forecasting model is desirable. In this work, a multiple linear regression (MLR) and an artificial neural network (ANN) model have been implemented for forecasting an optimum societal demand for various food crops that are commonly used in day to day life. The models are implemented using R toll, linear model and neuralnet packages for training and optimization of the MLR and ANN models. Then, the results obtained by the ANN were compared with the results obtained with MLR models. The results obtained indicated that the designed models are useful, reliable, and quite an effective tool for optimizing the effects of demand prediction in controlling the supply of food harvests to match the societal needs satisfactorily.

Download Full-text

Computational Performance Analysis of Neural Network and Regression Models in Forecasting the Societal Demand for Agricultural Food Harvests

International Journal of Grid and High Performance Computing ◽

10.4018/ijghpc.2020100103 ◽

2020 ◽

Vol 12 (4) ◽

pp. 35-47

Author(s):

Balaji Prabhu B. V. ◽

M. Dakshayini

Keyword(s):

Neural Network ◽

Crop Production ◽

Demand Forecasting ◽

Ann Model ◽

Demand Prediction ◽

Computational Performance ◽

Societal Needs ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Agricultural Food

Download Full-text

Evaluation and ANN-Based Prediction on Functional Parameters of Surface Roughness in Precision Grinding of Cast Iron

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1017.166 ◽

2014 ◽

Vol 1017 ◽

pp. 166-171

Author(s):

Bin Zhao ◽

Song Zhang ◽

Jian Feng Li

Keyword(s):

Surface Roughness ◽

Cast Iron ◽

Three Dimensional ◽

Ann Model ◽

Linear Speed ◽

Functional Parameters ◽

Grinding Parameters ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Dimensional Surface

Three-dimensional surface roughness parameters are widely applied to characterize frictional and lubricating properties, corrosion resistance, fatigue strength of surfaces. Among them, the functional parameters of surface roughness, such as Sbi, Sci, and Svi, are used to evaluate bearing and fluid retention properties of surfaces. In this study, the effects of grinding parameters, including wheel linear speed (Vs), workpiece linear speed (Vw), grinding depth (ap), longitudinal feed rate (fa), and dressing rate (F), on functional parameters were studied in grinding of cast iron. An artificial neural network (ANN) model was developed for predicting the functional parameters of three-dimensional surface roughness. The inputs of the ANN models were grinding parameters (Vs, Vw, ap, fa, F), and the output parameters of the models were functional parameters of surface roughness (Sbi, Sci, Svi). With small errors (e.g MSE = 0.09%, 0.61%, and 0.0014%. ), the ANN-based models are considered sufficiently accurate to predict functional parameters of surface roughness in grinding of cast iron.

Download Full-text

Neural Network MIMO Model for Production of Isopropyl Myristate in a Semibatch Reactive Distillation Column

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.284-287.403 ◽

2013 ◽

Vol 284-287 ◽

pp. 403-408

Author(s):

Nur Alwani Ali Bashah ◽

Mohd Roslee Othman ◽

Norashid Aziz

Keyword(s):

Neural Network ◽

Reactive Distillation ◽

Batch Reactor ◽

Isopropyl Myristate ◽

Ann Model ◽

Validation Data ◽

Testing Data ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Mimo Model

Batch reactive distillation is an integrated unit of batch reactor and distillation. It provides benefits of having higher conversion and yield by continuous removal of side product. The aim of this paper is to develop an artificial neural network (ANN) based model for production of isopropyl myristate in an industrial scaled semibatch reactive distillation. Two cases of the MIMO model were developed. Case 1 does not consider historical data as inputs while case 2 does. The trained ANN for both cases was validated with independent validation data and the best architecture was optimized. Case 1 resulted to 8 inputs, 14 hidden nodes and 2 outputs [8-14-2] ANN while Case 2 resulted to [12-13-2] ANN. The results show that both ANN models have ability to predict the unknown validation and testing data very well. However, the [8-14-2] ANN model produce higher accuracy than [12-13-2] ANN model with MSE of 0.00094 and 0.0013, respectively.

Download Full-text

Modeling of hourly river water temperatures using artificial neural networks

Water Quality Research Journal ◽

10.2166/wqrjc.2014.007 ◽

2014 ◽

Vol 49 (2) ◽

pp. 144-162 ◽

Cited By ~ 1

Author(s):

Cindie Hebert ◽

Daniel Caissie ◽

Mysore G. Satish ◽

Nassir El-Jabi

Keyword(s):

Water Temperature ◽

Coefficient Of Determination ◽

Ann Model ◽

Air Temperatures ◽

Level Data ◽

Water Level Data ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

The Many

Water temperature is an important component for water quality and biotic conditions in rivers. A good knowledge of river thermal regime is critical for the management of aquatic resources and environmental impact studies. The objective of the present study was to develop a water temperature model as a function of air temperatures, water temperatures and water level data using artificial neural network (ANN) techniques for two thermally different streams. This model was applied on an hourly basis. The results showed that ANN models are an effective modeling tool with overall root-mean-square-error of 0.94 and 1.23 °C, coefficient of determination (R2) of 0.967 and 0.962 and bias of −0.13 and 0.02 °C, for Catamaran Brook and the Little Southwest Miramichi River, respectively. The ANN model performed best in summer and autumn and showed a poorer performance in spring. Results of the present study showed similar or better results to those of deterministic and stochastic models. The present study shows that the predicted hourly water temperatures can also be used to estimate the mean and maximum daily water temperatures. The many advantages of ANN models are their simplicity, low data requirements, their capability of modeling long-term time series as well as having an overall good performance.

Download Full-text

Prediction of Locations in Medical Images Using Orthogonal Neural Networks

10.21203/rs.3.rs-649890/v1 ◽

2021 ◽

Author(s):

Jong Soo Kim ◽

Yongil Cho ◽

Tae Ho Lim

Keyword(s):

Neural Network ◽

Diagnostic Performance ◽

Medical Images ◽

Selection Criterion ◽

Activation Function ◽

X Rays ◽

Ann Model ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Image Localization

Abstract An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). The diagnostic performance of ONN for detecting the location of pneumothorax in chest X-rays was assessed and compared to that of CNN. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.870, an accuracy of 85.3%, a sensitivity of 75.0%, and a specificity of 86.5% were achieved; the ONN outperformed the CNN. The diagnostic performance of the ONN with a sigmoid activation function for all the nodes obviously outperformed the ONN with the rectified linear unit (RELU) activation function for all the nodes other than the output nodes. In addition, by applying ONN and CNN to predict the location of the glottis in laryngeal images, we achieved accurate and adjacent prediction rates of 70.5% and 20.5%, respectively, with the ONN. The prediction accuracy of the ONN was compared favorably with that of the CNN. Compared to a CNN, an ONN required only approximately 10% of the computations using a CNN trained on images with an input resolution of 256 × 256 pixels. A fully-connected small artificial neural network (ANN), selected by comparing the test results of several dozens of small ANN models, achieved the best location prediction performance on medical images. This study demonstrated that an ONN can be used as a quick selection criterion to compare ANN models for image localization since an ONN performed well compared decently with the selected ANN model.

Download Full-text