Artificial Neural Network Inversion Research Articles

A once-through artificial neural network approach for used nuclear fuel inverse depletion analysis: A comparative study

This work addresses the challenge of identifying the origins and burnup history of used nuclear fuel, which is crucial for safeguarding and non-proliferation analysis. It presents a comparative evaluation of two distinct computational approaches to bundles at the same in-core position: the first entails building a forward Artificial Neural Networks (ANN) surrogate model for fuel inventory prediction followed by solving the inverse depletion problem using an optimization solver. The second approach is to build an inverse ANN model that relates the used nuclear fuel inventory to its initial and burnup conditions (a once-through approach), eliminating the need for the inverse optimization solver step which results in better accuracy, less computational costs, and renders the application of such approach practical. KENO VI depletion model is utilized to deplete a VVER assembly model generating the necessary datasets for the ANN inverse model training and validation. The inverse model is then employed to estimate the initial composition and the burnup for several test cases. The results are then compared to the known initial and burnup conditions as well as to the estimations made by benchmark results from an existing ANN forward surrogate model combined with the Particle Swarm Optimization (PSO) solver. Comparative analyses across eight scenarios consistently reveal that the once-through ANN inverse model has superior accuracy and consistency in terms of estimating the actual burnup and initial fuel enrichment with a relative root mean squared error (RMSE) of 1.20×10-2 compared to the benchmark approach (ANN-PSO) which yielded a relative RMSE of 2.18×10-2. Moreover, the once-through inverse approach has a significantly lower computational cost as it requires 1 inverse model run compared to the 9,450,000 model runs required by the benchmark approach (ANN-PSO). Overall, the results demonstrate that the proposed once-through approach simplifies and enhances the efficiency of solving the inverse fuel depletion problem while outperforming the benchmark approach in terms of predictive accuracy computational cost.

Simultaneous increase of parameters of an experimental absorption system: Neural network inverse optimization methodology with multi-inputs

The Absorption Heat Transformer (AHT) has become an alternative proposal to weaken the trend of thermal pollution because it contributes to the recovery of residual heat and the use of solar thermal energy for its activation. Recently, compact designs have been developed that share two heat exchangers in one shell to reduce heat losses and save maintenance costs. The evaluation of the performance of AHTs depends on multiple parameters, which have been optimized using models based on ideal conditions. Multivariable optimization with artificial intelligence has considered experimental data to obtain feasible conditions related to the operation of the AHT. However, these models have focused only on determining one parameter at a time, reflecting a limitation. This study aims to develop a new optimization strategy to simultaneously maximize two relevant parameters associated with the efficiency of a compact experimental AHT. The optimization methodology is applied to increment the values of the heat generated in the absorber (QAB) and the Exergy Coefficient of Performance (ECOP) using the same objective function. This objective function is resolved when reaching the desired output parameters by determining multiple optimal conditions of the AHT. Initially, the modeling of the experimental data was carried out using an artificial neural network (ANN) for the diagnosis and prediction of the QAB and the ECOP. The model was validated by comparing the experimental values of QAB and ECOP against predicted values through a linear regression model, with a satisfactory result of R2>0.98. Subsequently, the multivariable inverse artificial neural network methodology for multiple output parameters (ANNim-m) was used and coupled with the Particle Swarm Optimization algorithm (ANNim-m-PSO) to generate the new multivariate optimization strategy and improve QAB and ECOP parameters simultaneously. Finally, 4 random tests with different initial operating conditions were optimized. Based on the optimization of the 4 tests, the QAB heat load was increased by 87.7 %, 54.2 %, 30.79 %, and 22.66 % from initial experimental conditions of 2.7, 9.0, 14.23 and 23.29 kW, respectively. In the case of ECOP, elevations of 28.5 %, 23.4 %, 15.4 %, and 16.18 % were obtained for initial values of 0.3801, 0.455, 0.5180, and 0.5729, respectively. It is determined that the parameters QAB and ECOP have a high sensitivity when the inlet temperature of the absorber of the external circuit (TAB) decreases. The results reveal that it is feasible to use the ANNim-m-PSO model, because the optimization was able to significantly maximize both QAB and ECOP parameters of the 40 kW experimental AHT.

Inverse artificial neural network assisted rapid multiband antenna design for multiple custom requirements

Inverse artificial neural network assisted rapid multiband antenna design for multiple custom requirements

Deep-Learning-Based Simulation and Inversion of Transient Electromagnetic Sounding Signals in Permafrost Monitoring Problem

Abstract —This article presents a novel approach to addressing the challenges in permafrost monitoring through the integration of deep-learning techniques with conventional electromagnetic sounding methods. Our methodology comprises a forward finite element method (FEM) solver, augmented with the Sumudu transform, and an artificial neural network (ANN) solver trained on FEM-generated data. Remarkably, the ANN solver demonstrates similar accuracy to the FEM solver but operates at a superior speed that is nearly 10,000 times faster. Furthermore, we introduce an inverse problem solution drawing on the PARS algorithm. In addition, we present an ANN-based inverse solver, where the input and output roles are inverted. The ANN inverse solver is trained on the same data, thereby offering an alternative approach to solving the inverse problem. In a computational experiment, we compare the numerical inversion results using the PARS algorithm with those obtained from the ANN forward solver, ANN inversion, and a linear combination of these solutions. This comprehensive analysis sheds light on the effectiveness of our deep-learning-based approach in permafrost monitoring, providing insights for future applications in geophysics and environmental science.

A Radial Basis Function Neural Network Algorithm for the Simultaneous Retrieval of Two Meteorological Parameters from Solar Radiation

Local meteorological parameters are key in understanding the frequency of occurrence of extreme weather conditions such as floods, and droughts, among others. In this study, we present a method for simultaneous retrieval of two weather parameters. The method is based on already measured monthly average values of weather parameters from 2011 to 2016, which were used to train a Feed-forward radial basis function neural network (RBFNN) to obtain a fast and accurate method to compute global solar radiation for specified weather parameters pair. In inverse modelling, a multidimensional unconstrained non-linear optimization was employed to retrieve the weather parameters pair. The new approach was validated using weather parameter data measured at the Department of Physics, Makerere University (0.31° N, 32.58° E, 1200 m). Statistical tools were used to evaluate the method's performance. In the Feed-forward artificial neural network (ANN), the correlation coefficient (R), mean bias error (MnB), root mean square error (RMSE), and mean percentage error (MAPE) were in the ranges 0.80-0.95, -0.0011-0.0077, 0.55-1.04 and 2.49%-5.82%, respectively. The pairs (sunshine hours, relative humidity) and (sunshine hours, minimum temperature) had the highest correlation coefficient of 0.95. In the inverse artificial neural network (ANNi), the R, MnB, RMSE and MAPE were in the ranges 0.3-0.9, 0.01-0.08, 0.51-11.14 and 2.1%-14.5%, respectively. The pair (sunshine hours, relative humidity) had the highest correlation coefficients of 0.92 and 0.62, respectively. The method helps in obtaining weather parameter data sets in places where measuring equipment is lacking or during days when measuring equipment malfunctions.

Estimating Forest Aboveground Biomass Combining Pléiades Satellite Imagery and Field Inventory Data in the Peak–Cluster Karst Region of Southwestern China

The mountainous region of southwest China has the largest karst geomorphology in China and in the world. Quantifying the forest aboveground biomass in this karst region is of great significance for the investigation of carbon storage and carbon cycling in terrestrial ecosystems. In this study, the actual measured aboveground biomass was calculated based on the allometric functions of 106 quadrats from 2012 to 2015. A backpropagation artificial neural network (BPANN) inversion model was constructed by combining very high-resolution satellite imagery, field inventory data, and land use/land cover data to estimate the forest aboveground biomass in the Banzhai watershed, a typical peak–cluster karst basin in southern Guizhou Province. We used 70% of the actual measured aboveground biomass for training the BPANN model, 20% for accuracy verification, and 10% to prevent overtraining. The results show that the absolute root mean square error of the BPANN model was 11.80 t/ha, which accounted for 9.92% of the mean value of aboveground biomass. Based on the BPANN inversion model, the average value of the forests’ aboveground biomass was 135.63 t/ha. The results showed that our study presented a quick, easy, and relatively high-precision method for estimating forest aboveground biomass in the Banzhai watershed. This indicates that the Pléiades image-based BPANN model displayed satisfactory results for estimating the forests’ aboveground biomass in a typical peak–cluster karst basin. This method can be applied to the estimation of forest AGB in the karst mountainous areas of southwest China.

Mutual Coupling Reduction in Antenna Arrays Using Artificial Intelligence Approach and Inverse Neural Network Surrogates.

This paper presents a novel approach to reducing undesirable coupling in antenna arrays using custom-designed resonators and inverse surrogate modeling. To illustrate the concept, two standard patch antenna cells with 0.07λ edge-to-edge distance were designed and fabricated to operate at 2.45 GHz. A stepped-impedance resonator was applied between the antennas to suppress their mutual coupling. For the first time, the optimum values of the resonator geometry parameters were obtained using the proposed inverse artificial neural network (ANN) model, constructed from the sampled EM-simulation data of the system, and trained using the particle swarm optimization (PSO) algorithm. The inverse ANN surrogate directly yields the optimum resonator dimensions based on the target values of its S-parameters being the input parameters of the model. The involvement of surrogate modeling also contributes to the acceleration of the design process, as the array does not need to undergo direct EM-driven optimization. The obtained results indicate a remarkable cancellation of the surface currents between two antennas at their operating frequency, which translates into isolation as high as -46.2 dB at 2.45 GHz, corresponding to over 37 dB improvement as compared to the conventional setup.

A Bidirectional Deep Learning Approach for Designing MEMS Sensors

To achieve the desired characteristics for MEMS sensors, traditional design process obtains the geometrical parameters based on complex theoretical calculations and interactive finite element (FE) simulations, which are time-consuming and data-consuming. To solve the above problems, a data-driven bidirectional design approach based on deep learning (DL) method is introduced to improve the design efficiency of MEMS sensors in this work. By using the piezoresistive acceleration sensor as a design example, the forward artificial neural network (ANN) with the sensor geometrical parameters as the input and the sensor performance as the output is trained and realized by using 1000 groups of data collected through FE simulation. This forward ANN can accurately predict the sensor performance including the measurement range, sensitivity, and resonant frequency. In addition, the inverse ANN with the sensor performance as the input and the sensor geometrical parameters as the output is also achieved by using a tandem network. This inverse ANN can provide the geometrical parameters directly and instantly according to the target performance. Both the forward and inverse networks cost only about 6 ms for each task and the mean relative errors are less than 3%. The high efficiency and low relative error indicate that DL is a promising approach to improve the design efficiency for MEMS sensors.

A multivariable output neural network approach for simulation of plug-in hybrid electric vehicle fuel consumption

This study is laser focused on the simulation of fuel consumption and fuel economy label parameters of plug-in hybrid electric vehicles. While fuel economy is a key factor in the design of plug-in hybrid electric vehicles, a fuel economy label can educate customers about the economic advantage of purchasing a particular car. The fuel economy label of a PHEV consists of parameters like driving range, electrical energy consumption, fuel economy for city, highway, and combined use, battery recharge time, and fuel consumption rates. The study used an inverse function model of an artificial neural network to simulate and calculate the parameters of the fuel economy labels of PHEVs. Firstly, the selected parameters of the fuel economy label of plug-in hybrid electric vehicles were used to develop a single output model. The output variable of the single output model was then merged with dummy functions to form input variables for the inverse function model. The output variables simulated were engine size in litres; estimated driving range when the battery is fully charged in km, battery recharged time in hours, city fuel consumption (L/100 ​km), highway fuel consumption (L/100 ​km), combined fuel consumption (L/100 ​km), estimated driving range when the tank is full, carbon dioxide (CO2) emission in grams/km, electric motor power in kW, number of cylinders, and electrical charges consumed in kWh/100 ​km. Different cases of input variables were considered for the inverse function model. The accuracy of the model was 29.1 times greater than that of the conventional inverse artificial neural network model.

Inverse identification of pipeline steel mechanical state by means of coupled magnetic measurements and artificial neural networks

Artificial neural networks are widely used to develop models able to predict properties of interest by learning and establishing relationships between inputs and outputs of a system. It is particularly relevant for the inversion process in the framework of Non-Destructive Testing (NDT) involving strongly non-linear and non-monotonic behavior and/or saturations. The case-study considered in this work is a magnetic material subjected to uniaxial mechanical stress, plastic strain and magnetic field. An Artificial Neural Networks (ANN) model is proposed to predict the corresponding remanent magnetization, coercive field and the maximum magnetization as target properties. A series of experimental data made of various magneto-mechanical measurements are used to train, evaluate and validate the ANN model. The proposed model suitably predicts the magnetic properties of a second specimen of the material in the same magnetic field, plastic strain and stress ranges as the first specimen. An inverse ANN is then proposed to evaluate the mechanical loading and the plastic strain from the magnetic signature. Unique and accurate solutions are found that proves the relevance of machine learning approach in such NDT application.

Versatile focal field design using cascaded artificial neural network

Both forward and inverse design methods have been developed for focal field engineering, which has applications in many areas including super-resolution imaging and optical lithography, high-density optical storage, and particle manipulation. However, a certain method is normally targeted at a unique focal field distribution. Here, we report on a versatile focal field design method based on a cascaded artificial neural network (CANN) for the inverse design of focal field distributions in a high numerical aperture focusing system. The CANN consists of a forward and an inverse artificial neural network. Once trained properly, the CANN can predict modulation phase patterns for multiple focal field distributions. We demonstrate the effectiveness of the CANN by the design of focal field distributions along the optical axis including a uniform optical needle and an anti-point spread function with lengths up to 14 wavelengths and multiple focal spots with controllable intensities as well as those in the focal plane including flat-top and sub-diffraction focal spots.

An Artificial Neural Network Method for High-Accurate and High-Efficient MEMS Pressure Sensor Design

Microelectromechanical system (MEMS) devices have numerous advantages including small sizes, high performance, and easy integration capability and thus have been widely used in the Internet of Things (IoT). A typical MEMS device usually includes a set of performance parameters, and each parameter is sensitive to the device geometries but with different regularities and weights, thus resulting in the complexity of MEMS device design. The conventional design method is mainly based on iterative finite-element (FE) simulation and optimization, which is time-consuming and inefficient. To address the above issues, a bidirectional artificial neural network (ANN)-based method is explored and used as the design method by using an MEMS pressure sensor as a design example. First, a forward ANN with the geometries and performance as the input and output, respectively, is trained and constructed, which can accurately predict the performance. Then, an inverse ANN with the performance and geometries as the input and output, respectively, is also investigated. By means of a tandem network, the nonuniqueness issue of the inverse ANN caused by a one-to-many response from the input to the output can be well addressed. This tandem network can output the corresponding geometries instantly according to the target performance. This work demonstrates the great potential of the ANN as a new and facile strategy in MEMS device design.

Design of All-Dielectric Metasurface-Based Subtractive Color Filter by Artificial Neural Network.

Structural colors produced by light manipulating at subwavelength dimensions have been widely studied. In this work, a metasurface-based subtractive color filter (SCF) is demonstrated. The color display of the SCF is confirmed by finding the complementary color of colors filtered by SCF within the color wheel. In addition, two artificial neural network (ANN) models are utilized to accelerate the metasurface forward prediction, and the long short-term memory (LSTM) shows much better performance than traditional multilayer perceptron (MLP). Meanwhile, we train an inverse ANN model established with LSTM to recover the optimal geometric parameter combinations of the meta-atoms. With the variation of the geometric parameters of meta-atoms, versatile color displays of structural colors are realized. The metasurface we propose exhibits good performance of transmissive-type structural color in visible range. The work provides a method for high-efficiency geometric parameter prediction, and paves the way to nanostructure-based color design for display and anticounterfeiting applications.

An inverse artificial neural network algorithm for retrieval of sunshine hours from ground-based global solar irradiation measurements

Availability of meteorological parameter values is important in applications that require solar irradiation. Meteorological parameters such as sunshine hours are best provided by measuring equipment mainly stationed at weather stations. The cost of purchasing the measuring equipment, and setting up and maintaining weather stations is enormous and cannot be easily afforded by many developing countries like Uganda. Furthermore, in Uganda, we have some weather stations which have been measuring global horizontal solar irradiation for quite some time but lacked sunshine duration sensors, and at some others, the sunshine measuring equipment malfunctioned. In this work we present an inverse artificial neural network algorithm that predicts sunshine hours based on horizontal global solar irradiation, the algorithm caters to cases where global horizontal solar irradiation is present but sunshine hour measuring equipment is missing or malfunctioned. A radial basis function neural network (RBF-NN) was trained for forward computation of global horizontal solar irradiation from sunshine hour values. The inverse modelling algorithm employs multidimensional unconstrained non-linear optimization to retrieve sunshine hours. The correlation coefficient (r) between the measured sunshine hour values and those predicted by the inverse artificial neural network algorithm was found to be 0.924. The average value of the ratios of the inverse artificial neural network algorithm computed values to the sunshine duration sensor measurements was 1.043. The algorithm predicted sunshine hour values with a mean bias and relative root mean square error of 0.043 and 0.394, respectively. The algorithm developed provides an affordable, fast and reliable method for determining sunshine hour values based on global horizontal solar irradiation. However, sunshine hour values prediction for low values of global horizontal solar irradiation was less precise, and this could be attributed to high levels of cloudiness. It is recommended that an inverse algorithm that retrieves sunshine hours under cloudy conditions be constructed

Electrochemical evaluation of an Acanthocereus tetragonus aqueous extract on aluminum in NaCl (0.6 M) and HCl (1 M) and its modelling using forward and inverse artificial neural networks

• Acanthocereus tetragonus aqueous extract was evaluated in acidic and neutral media as a corrosion inhibitor. • Forward ANNs were trained with two Aluminum electrochemical evaluations databases. • Larger databases were calculated from Forward ANNs. • Inverse ANNs (IANNs) were trained with the large databases. • Time and concentration of the Acanthocereus tetragonus extract were found from optimal IANNs. An innovative numerical method based on a machine learning approach is presented in order to model the electrochemical behaviour of an Acanthocereus tetragonus aqueous extract on Aluminum in acidic and neutral media. Experimental data of an electrochemical evaluation of Aluminum in HCl (1 M) and NaCl (0.6 M) were used to generate the training set for forward Artificial Neural Networks (ANN). Later, this nonlinear relationship is inverted and refined with the purpose of design and train an inverse ANN that solves the following inverse problem: to find the concentration of a green corrosion inhibitor and the exposure time as a function of pH values, real and imaginary impedance values, and a frequency range of measure between 10,000 and 0.01 Hz.

Inverse artificial neural network control design for a double tube heat exchanger

This work focused on a new developed and experimentally tested non-linear control approach to control a double tube heat exchanger's output cold water temperature. The control approach uses an inverse artificial neural network (ANNi) and an integral control law. The ANNi objective is to obtain the cold water flow considering as a reference the desidered output cold water temperature. The ANNi was built from a feedforward ANN with four inputs (input cold water temperature, input hot water temperature, cold water flow, hot water flow), a hidden layer with a neuron, and two outputs (output cold water and output hot water temperature). The integral control law is implemented to reduce the error between the setpoint and the ANNi estimate. As a result, the output cold water temperature regulation is achieved through a simple controller that does not need a complex ANN model and does not depend on the process parameters' exact value. The proposed control scheme (Inverse Artificial Neural Network with Integral Control (ICANNi)) showed good reference tracking, obtaining a root mean square error (RMSE) of 0.2025, standard deviation (SD) of 0.0410, establishment time of 23 s, and overshoots less than 2.7 °C. In addition, the ICANNi control has a settling time that is 1.91 times faster than the PID control and 1.5 times faster than the ANNi control.

Multivariate inverse artificial neural network to analyze and improve the mass transfer of ammonia in a Plate Heat Exchanger-Type Absorber with NH3/H2O for solar cooling applications

This work presents a numerical approach to compute optimal operating conditions that maximize the absorption flux into a heat exchanger designed for absorption refrigeration systems. Experimental data were obtained from a test circuit that operates in bubble absorption mode with an inner vapor distributor into a Plate Heat Exchanger-type (PHE-type) and interacts with ammonia vapor, NH3-H2O refrigerant, and cooling water. An artificial neural network (ANN) was trained to correlate the thermal properties of the solution and absorption flux in function of easily measurable parameters (concentrations, mass flows, and pressures of saturated and diluted solutions, flow and temperature of the ammonium vapor, environment temperature, and solution temperature). According to results, ANN is adequate to correlate the operational parameters and the transport phenomena inside the heat exchanger with a precision > 99%. ANN also quantitatively identified the ammonium vapor flow (43.1%), dilute solution flow (18.1%), and dilute solution concentration (13.1%) as the variables most importantly in influencing absorption flux optimization. Subsequently, a multivariable inverse artificial neural network was applied to improve the mass transfer into the PHE-type.It was identified that simultaneous optimization of the ammonia and dilute concentration flow rates improves the absorption flow performance by up to 96.3% under a worst-case scenario (ammonia flow rate<1.4 kg/min) and even 7.04% when even when operating near the amino vapor flow limit (ammonia flow rate>2.0 kg/min). Finally, it was confirmed that incorporating the diluted solution concentration into the optimization contributes to improving the performance of the absorption process 1%. Results obtained are relevant in the search to produce more competitive absorption cooling systems, demonstrating the feasibility of improving the performance of heat exchangers without structural modifications. The proposed methodology represents an interesting option to be implemented to improve performance in solar cooling systems.

Validation of a Stewart platform inspection system with an artificial neural network controller

The use of thermographic cameras attached to Stewart platforms may become a valuable approach to build non-destructive inspection systems. However, achieving successful inspections requires positioning the platform that holds the camera very accurately, especially when the camera lacks of autofocus capabilities. Thus, if the distance from the lenses to the inspection surface is in range, sharp quality images may be obtained, otherwise, images may suffer defocusing producing poor inspection results. This work presents a new Artificial Neural Network (ANN) control aimed at improving the accuracy of the Stewart platform that holds a camera, hence improving the quality of the inspection system. The proposed ANN architecture positions the platform more accurately than the vendor provided Proportional Integral (PI) control strategy. The system kinematics and dynamics are analyzed in order to design the ANN model for the system. The developed control scheme is based on the inverse ANN model with an additional integral control. The advantages of this novel approach are that (1) the controller considers the interactions among the actuators and (2) includes a training process that continuously fine-tunes the ANN weight matrix. The proposed control scheme was validated experimentally, and the performance compared with tuned PI control, taken as the reference, for two different inspection trajectories. The results show that the ANN control is much more accurate and efficient than the reference PI (above 40% error reduction in the actuator positioning with the same power consumption), hence performing the inspections successfully.

Electrochemical Evaluation of an Acanthocereus Tetragonus Aqueous Extract on Aluminum in Nacl (0.6m) and Hcl (1 M) and its Modelling Using Forward and Inverse Artificial Neural Networks

Electrochemical Evaluation of an Acanthocereus Tetragonus Aqueous Extract on Aluminum in Nacl (0.6m) and Hcl (1 M) and its Modelling Using Forward and Inverse Artificial Neural Networks

Optimization strategy to improve the removal efficiency of commercial herbicides using a multivariable inverse artificial neural network adapted with particle swarm optimization

Optimization strategy to improve the removal efficiency of commercial herbicides using a multivariable inverse artificial neural network adapted with particle swarm optimization