Artificial neural networks modelling of the performance parameters of the Stirling engine

The Stirling engine can theoretically be very efficient to convert heat into mechanical work at Carnot efficiency. Various parameters could affect the performance of the addressed Stirling engine which is considered in optimisation of the Stirling engine for designing purpose. Through addressed factors, torque has the highest effect on the robustness of the Stirling engines. Due to this fact, determination of the referred parameters with low uncertainty and high precision is needed. To solve the mentioned obstacle, throughout this paper, a generation of intelligent model called ‘artificial neural network’ (ANN) was implemented to estimate the torque of the Stirling heat engine. In addition, highly accurate actual values of the required parameters which were gained from open literature surveys from previous studies were implemented to develop a robust intelligent model. Based on the outcomes of the ANN approach, the output results of an ANN model were close to relevant actual values with a high degree of performance.     

Enhancing and multi-objective optimising of the performance of Stirling engine using third-order thermodynamic analysis

Stirling engine is an external combustion engine which uses eternal heat sources like solar radiation for heating a compressible fluid inside cylinders. In the recent years, significant attention is drawn to Stirling engines due to the clear advantages, high efficiency potential, flexible fuel, lower nitrogen oxides, quiet and minimal vibration, high reliability and highest specific output work for any closed regenerative cycle. The third order thermal analysis is one of the analyses which has been applied in several studies which have been carried out on Stirling engines. NSGA-II algorithm is applied to optimise the differential regenerator pressure (bar) and the power output (kW) for a Stirling engine system. In this study, three decision-making techniques are utilised to optimise the solutions, obtained of the results. At last, the employed techniques are compared with the data of an experimental research work.     

A neural network model for the prediction of compression ignition engine performance at different injection timings

Rapid depletion of fossil fuel and continuous increase in gasoline prices have stimulated the search of alternative fuels. This paper deals with the prediction of engine performance, emission and combustion characteristics of compression ignition engine fuelled with fish oil biodiesel using artificial neural network (ANN). Experimental investigations are carried out in a single cylinder constant speed direct injection diesel engine under variable load conditions at different injection timings?21⁰, 24⁰ and 27⁰ bTDC. The performance, combustion and emission characteristics are measured using an exhaust gas analyser, smoke meter, piezoelectric pressure transducer and crank angle encoder for different fuel blends and engine load conditions. For training the neural network, feed-forward back propagation algorithm is used. The developed ANN model predicts the performance, combustions and exhaust emissions with a correlation coefficients (R) of 0.97–0.99 and a mean relative error of 0.62–4.826%. The root mean square errors are found to be low. The developed model has found to predict accurately the engine performance, combustion and emission parameters at different injection timings.     

Prediction of engine performance and exhaust emissions with different proportions of ethanol–gasoline blends using artificial neural networks

The main purpose of this study is to experimentally investigate the use of ANNs (artificial neural networks) modelling to predict engine power, torque and exhaust emissions of a spark ignition engine which operates with gasoline and methanol blends. For the ANN modelling, the standard back-propagation algorithm was found to be the optimal choice for training the model. Afterwards, the performance of the ANN predictions was evaluated with the experimental results by comparing the predictions. Fuel type and engine speed have been used as the input layer, while engine torque, power, exhaust emissions, Tex and BSFC have also been used separately as the output layer. It was found that the ANN model is able to predict the engine performance, exhaust emissions, Tex and BSFC with a correlation coefficient of 0.9991887425, 0.9990868573, 0.9986749623, 0.9988624137, 0.9976761492, 0.9992943894 and 0.9978899033 for the Power, Torque, CO, CO₂, HC, Tex and BSFC for testing data, respectively.     

The effect of regenerative losses on the efficiency of a Stirling heat engine at maximum power output

A more realistic cycle model is established for discussing the performance of the Stirling heat engine with regenerative losses. The power output is adopted as an objective function for optimisation. The maximum power output and the corresponding efficiency of the Stirling heat engine are derived. The effect of regenerative losses on the efficiency at maximum power output is expounded. The times of four processes in the Stirling cycle are allotted optimally. Some new conclusions are obtained.     

Numerical investigations on the Dish–Stirling engine system

The Stirling engine is an environmentally friendly external combustion heat engine and reduces the complexities of the combustion process, and indirectly helps in reduction of CO₂ emission. Modelling based on cyclic analysis is performed for a Beta configuration Stirling engine of 1.5?kW_e capacity using a rhombic drive for the solar-dish-supported Stirling engine. The analysis helps in estimating the overall efficiency of the system using the experimental correlation of the solar concentrator ARUN160 at the engine operating temperature. The analysis shows that the system will have overall efficiency around 25% in the range of 750–1050?K at the expansion space. The degradation of performance compared to that at an operating temperature of 1025?K is only marginal and makes 750?K a more preferred temperature. The present study evaluates a range of possible design goals and provides suitable alternatives and thus provides a clear understanding of the system design considerations.     

外燃机热电联产与地下工程能源系统的优化配置

根据在我国地下工程中惟独选用柴油发电机作为备用电源的现状和由此产生的主要问题，指出采用外燃机热电联产技术不仅可以有效地提高现有工程的伪装性能、能源利用效率，而且通过与空调除湿系统的有机结合还可以解决工程对采暖、除湿和制冷的综合需求。最后，对外燃机热电联产技术在地下工程中的应用可行性和系统配置方案进行了探讨。     

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore mine,Iran简

Blast-induced ground vibration is one of the inevitable outcomes of blasting in mining projects and may cause substantial damage to rock mass as well as nearby structures and human beings. In this paper, an attempt has been made to present an application of artificial neural network (ANN) to predict the blast-induced ground vibration of the Gol-E-Gohar (GEG) iron mine, Iran. A four-layer feed-forward back propagation multi-layer perceptron (MLP) was used and trained with Levenberg–Marquardt algorithm. To construct ANN models, the maximum charge per delay, distance from blasting face to monitoring point, stemming and hole depth were taken as inputs, whereas peak particle velocity (PPV) was considered as an output parameter. A database consisting of 69 data sets recorded at strategic and vulnerable locations of GEG iron mine was used to train and test the generalization capability of ANN models. Coefficient of determination (R²) and mean square error (MSE) were chosen as the indicators of the performance of the networks. A network with architecture 4-11-5-1 and R² of 0.957 and MSE of 0.000722 was found to be optimum. To demonstrate the supremacy of ANN approach, the same 69 data sets were used for the prediction of PPV with four common empirical models as well as multiple linear regression (MLR) analysis. The results revealed that the proposed ANN approach performs better than empirical and MLR models.     

Artificial neural network-based prediction of performance and emission characteristics of CI engine using polanga as a biodiesel

The present work predicts the performance parameters, namely brake specific fuel consumption (BSFC), brake thermal efficiency (BTE), peak pressure, exhaust gas temperature and exhaust emissions of a single cylinder four-stroke diesel engine at different injection timings and engine load using blended mixture of polanga biodiesel by artificial neural network (ANN). The properties of biodiesel produced from polanga were measured based on ASTM standards. Using some of the experimental data for training, an ANN model was developed based on standard back-propagation algorithm for the engine. Multi-layer perception network was used for non-linear mapping between input and output parameters. Different activation functions and several rules were used to assess the percentage error between the desired and the predicted values. It was observed that the developed ANN model can predict the engine performance and exhaust emissions quite well with correlation coefficient (R) 0.99946, 0.99968, 0.99988, 0.99967, 0.99899, 0.99941 and 0.99991 for the BSFC, BTE, peak pressure, exhaust gas temperature, NO_x, smoke and unburned hydrocarbon emissions, respectively. The experimental results revealed that the blended fuel provides better engine performance and improved emission characteristics.     

A parametric study on the effects of displacer-cylinder-circumferential-wall thermal conditions on the performance of a γ-type LTD Stirling engine

ABSTRACT

Regarding a Stirling engine’s heat source and heat sink, most of the studies in the literature focus only on the magnitude of temperature difference between them. However, different Stirling engines adopt very different heat-source and heat-sink configurations. This study is aimed at understanding the effects of different displacer-cylinder-wall thermal conditions on engine performance using computational fluid dynamics (CFD). Results include p–V diagrams, heat flux distributions, temperature variations, and effects of three displacer-cylinder-wall parameters on indicated power and efficiency. It is found that the thermal conditions on the displacer-cylinder-circumferential wall (DCCW) impose significant effects on engine performance. Within the ranges of parameters investigated in this study, extending the coverage of heat source and heat sink on this wall improves up to 28% in indicated power at the cost of losing about 10% in efficiency, proving the significance of DCCW conditions on engine performance.     

Performance studies of R433A in a direct expansion solar-assisted heat pump

ABSTRACT

Energy assessment of a simple direct expansion solar-assisted heat pump system has been experimentally assessed with R433A as a possible alternative to R22. An artificial neural network integrated genetic algorithm model was developed to assess the performance system. The data obtained from the experimentation at different ambient conditions are used as the training data for the ANN network. The back propagation learning mechanism with variants Lavenberg-Maguardt with 20 neurons in the hidden layer were used in modelling of ANN. The values obtained from the analysis using ANN are optimised further by integrating the ANN procedure with GA. The results indicated that R433A has 6.4% and 1% lower instantaneous compressor power consumption and heating capacity compared to R22. Energy performance ratio of R433A was found to be about 5.67% higher compared to R22. The results confirmed that R433A can be used as a possible alternative to R22 DX-SAHP systems.     

Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network

An accurate prediction of earth pressure balance (EPB) shield moving performance is important to ensure the safety tunnel excavation. A hybrid model is developed based on the particle swarm optimization (PSO) and gated recurrent unit (GRU) neural network. PSO is utilized to assign the optimal hyperparameters of GRU neural network. There are mainly four steps: data collection and processing, hybrid model establishment, model performance evaluation and correlation analysis. The developed model provides an alternative to tackle with time-series data of tunnel project. Apart from that, a novel framework about model application is performed to provide guidelines in practice. A tunnel project is utilized to evaluate the performance of proposed hybrid model. Results indicate that geological and construction variables are significant to the model performance. Correlation analysis shows that construction variables (main thrust and foam liquid volume) display the highest correlation with the cutterhead torque (CHT). This work provides a feasible and applicable alternative way to estimate the performance of shield tunneling.     

Optimisation of the thermodynamic performance of the Stirling engine

In this communication, the thermodynamic performance of an ideal Stirling cycle engine has been investigated. In this regard, the first law of thermodynamics has been employed to determine state of total heat addition, network output, and thermal efficiency with changes in dead volume percentage and regenerator effectiveness. Second law analysis is applied to obtain the trends for the total entropy generation of the cycle. Moreover, the entropy generation of each element involving the Stirling cycle processes is measured. Three objective functions including the output power per rate of mass of the ideal gas working fluid (w_net) and the thermal efficiency (η_t) have been considered simultaneously for maximisation, and the ratio of total entropy generation to rate of mass of the ideal gas working fluid of the Stirling engine is minimised at the same time. Multi-objective evolutionary algorithms based on the NSGA-II algorithm have been employed, while effectiveness of the regenerator, effectiveness of low- and high-temperature heat exchangers, effectiveness of high-temperature heat exchanger, temperatures of the hot side and cold side, and dead volume ratio are considered as decision variables. After the definition of the Pareto optimal frontier, the final optimal solution has been selected using different decision-making methods such as the fuzzy Bellman–Zadeh, LINMAP and TOPSIS.     

基于热气机分布式冷热电三联供效益分析

以上海地区一幢典型五层住宅建筑热、电、冷负荷需求为计算基础,分别计算了基于热气机的冷热电三联供系统和传统冷热电分供系统的一次能耗率、全年净收益以及投资回收期,验证了三联供系统的节能性和经济性。分析表明热气机余热利用率和能源价格是影响该三联供系统节能效益和经济效益的主要因素。     

A new method to optimise finite dimensions thermodynamic models: application to an irreversible Stirling engine

Different economical configurations, due for instance to the relative cost of the fuel they consume, can push a heat engine into operating whether at maximum efficiency or at maximum power produced. Any relevant design of such a system hence needs to be based, at least partly, on the knowledge of its specific ‘power vs. efficiency’ characteristic curve. However, even when a simple model is used to describe the engine, obtained, for example, thanks to finite dimensions thermodynamics, such a characteristic curve is often difficult to obtain and takes an explicit form only for the simplest of these models. When more realistic models are considered, including complex internal subsystems or processes, an explicit expression for this curve is practically impossible to obtain. In this paper, we propose to use Graham's scan algorithm in order to directly obtain the power vs. efficiency curve of a realistic Stirling engine model, which includes heat leakage, regenerator effectiveness, as well as internal and external irreversibilities. Coupled with an adapted optimisation routine, this approach allows to design and optimise simple or complex heat engine models. Such a method can then be useful during the practical design task of any thermal power converter, almost regardless of its own internal complexity.     

Application of artificial neural network for performance evaluation of vertical axis wind turbine rotor

In the present paper, artificial neural network (ANN) modelling has been performed for evaluating power coefficient (C_p) and torque coefficient (C_t) of a combined three-bucket-Savonius and three-bladed-Darrieus vertical axis wind turbine rotor, which has got potential for power generation in a small-scale manner, especially in low wind speed conditions. However, detailed experimental work on the rotor for evaluating its performance parameters is either scarce or too costly and time consuming to carry out. In this work, a new ANN modelling method is adopted to map the input–output parameters using very small training data sets, selected from past experimental results of the rotor. The trained ANN models are used to predict the performance data, which are obtained within acceptable error limits. Furthermore, to evaluate the fit values and estimate the variance of the predicted data by the ANN models, linear regression equations are fitted to the experimental and predicted results, which shows that R-squared (R²) values are obtained close to unity meaning good fitting of the data. Moreover, the results of ANN modelling are also compared with that of radial basis function (RBF) networks, which also show a good agreement between ANN predicted data and RBF network data. The present ANN models can be exploited to extract more performance data within a given range of input data.     

A comparative study of B10 biodiesel blends and its performance and combustion characteristics

The current work is to investigate the diesel engine performance and combustion characteristics fuelled with Banalities aegyptiaca (BA) biodiesel and compare those with the performance and combustion characteristics of palm biodiesel, sesame biodiesel,rapeseed biodiesel, soybean biodiesel and diesel fuel. In this study, only 10% of each biodiesel (BA10, PALM10, SESAME10, RAPESEED10 and SOYBEAN10) was tested in a diesel engine. The physical properties of all the fuel samples are mentioned and compared with ASTM standards. The test rig consists of a single cylinder, auxiliary water-cooled and computer-based variable compression ratio diesel engine, which was used to evaluate their performance at a measured torque. All biodiesel fuel samples reduce brake power and brake thermal efficiency and increase brake-specific fuel consumption rate than diesel fuel. Combustion characteristics results indicated that the blended fuel samples performed with a significant reduction in terms of cylinder pressure and heat release rate compared with diesel fuel apart from diesel pressure. Among the biodiesel-blended fuel samples, BA10 showed better performance in terms of brake power, brake-specific fuel consumption and brake thermal efficiency and cylinder pressure and heat release rate in terms of combustion characteristics compared with D100.     

并联式混合动力燃气热泵充放电性能研究

本文基于混合动力燃气热泵系统,设计了该系统的并联式驱动形式.基于发动机燃气消耗率以及发动机与压缩机的速度匹配,对并联式驱动系统的传动装置进行了设计.对余热回收系统的管道布置方式进行了区分和研究,选择了旁通式的余热回收系统.将并联式驱动系统、余热回收系统以及热泵系统结合构建了并联式混合动力燃气热泵系统.在此基础上,对该热泵系统进行了电机恒定扭矩的充放电试验,研究了在不用运行模式下,整个系统的性能与各个参数的变化规律,包括：热泵性能系数（COP）、热泵制热量、发动机燃气流量、余热回收量.最后,基于对系统的试验性能研究,分析该系统的一次能源效率（PER）的变化规律,并与燃气热泵系统进行比较.结果发现,电机充电扭矩提高系统PER约14％效果明显,而电机扭矩提高系统PER为1.1％左右.     

Artificial neural network optimized by differential evolution for predicting diameters of jet grouted columns

A novel and effective artificial neural network (ANN) optimized using differential evolution (DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters. The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters (i.e. the epoch size, the number of neurons in a hidden layer, the number of hidden layers, and the regularization parameter) that govern the neural network efficacy. This approach is further enhanced by a stochastic gradient optimization algorithm to allow ‘expensive’ computation efforts. The ANN-DE is first trained using a prepared jet grouting dataset, then verified and compared with the prevalent machine learning tools, i.e. neural networks and support vector machine (SVM). The results show that, the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance. Specifically, the ANN-DE achieved root mean square error (RMSE) values of 0.90603 and 0.92813 for the training and testing phases, respectively. The corresponding values were 0.8905 and 0.9006 for the optimized ANN, then, 0.87569 and 0.89968 for the optimized SVM, respectively. The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.     

Artificial neural network approach to predict the engine performance of fish oil biodiesel with diethyl ether using back propagation algorithm

An artificial neural network (ANN) model is developed to predict the engine performance of fish oil biodiesel blended with diethyl ether. Engine performance and emission characteristics such as brake thermal efficiency, hydrocarbon, exhaust gas temperature, oxides of nitrogen (NO_x), carbon monoxide (CO), smoke and carbon dioxide (CO₂) were considered. Experimental investigations on single-cylinder, constant speed, direct injection diesel engine are carried out under variable load conditions. The performance and emission characteristics are measured using an exhaust gas analyser, smoke metre, piezoelectric pressure transducer and crank angle encoder for different fuel blends and engine load conditions. In this model, a back propagation algorithm is used to predict the performance. Computational results clearly demonstrated that the developed ANN models produced less deviations and exhibited higher predictive accuracy with acceptable determination correlation coefficients of 0.97–1 and mean relative error of 0–3.061% with experimental values. The root mean square errors were found to be low. The developed model produces the idealised results and it has been found to be useful for predicting the engine performance and emission characteristics with limited number of available data.