The planar nature of microwave sensors leaves them vulnerable to ambient temperature changes with potential impact on the perception of the material under test. A temperature compensation technique is required to consider its direct effect on the dielectric property of materials. In this article, machine learning algorithms are employed in two configurations of classifier and regressor on frequency response of a split-ring resonator operating at 1.19 GHz. A wide range of dielectric constant is covered with concentrations of [0:20%:100%]-methanol/acetone in water with a temperature cycle of 25 °C-50 °C. This broad variety of cases captures the complicacy of entangled trends that are recognized using classifiers regardless of the measurement temperature. In the next step, the ambient temperature is extracted from the same measured data. This is accomplished by cascading the classifier with a regressor pool that contains trained parameters for individual classes. Highly accurate classification of material types followed by their corresponding temperature (using linear regression with R²= 97% averaged over tenfold cross validation and a mean absolute error of 0.58 °C) leads to investigating limit of detection in the proposed scheme. This step, through testing of [0:1%:5%] methanol in water, identified multilayer perceptron (MLP) and support vector machine (SVM) as the best performing algorithms. Final hyperparameter optimization yields parameters for these two models that provide accuracy of 0.97 and 0.99, respectively.

This research explores the application of an artificial intelligence (AI)-assisted approach to enhance the selectivity of microwave sensors used for liquid mixture sensing. We utilized a planar microwave sensor comprising two coupled rectangular complementary split-ring resonators operating at 2.45 GHz to establish a highly sensitive capacitive region. The sensor’s quality factor was markedly improved from 70 to approximately 2700 through the incorporation of a regenerative amplifier to compensate for losses. A deep neural network (DNN) technique is employed to characterize mixtures of methanol, ethanol, and water, using the frequency, amplitude, and quality factor as inputs. However, the DNN approach is found to be effective solely for binary mixtures, with a maximum concentration error of 4.3%. To improve selectivity for ternary mixtures, we employed a more sophisticated machine learning algorithm, the convolutional neural network (CNN), using the entire transmission response as the 1-D input. This resulted in a significant improvement in selectivity, limiting the maximum percentage error to just 0.7% (≈6-fold accuracy enhancement).

In this study, a loss-compensated microwave (MW) planar sensor is used to characterize fluids at ~1 GHz. The environmental temperature is shown to adversely impact the recorded resonance frequency of the MW sensor, leading to data mixing. This issue is resolved using a feedforward artificial neural network with two hidden layers. Various concentrations of methanol in water (0%-100% with 10% increments) are measured at temperatures ranging between 22 °C and 60 °C. This smart sensor system exhibits a strong ability to discriminate the correct data regardless of erroneous interfering factors up to 92%.

Distribution network reconfiguration (DNR) is one of the most important methods to cope with the increasing electricity demand due to the massive integration of electric vehicles. Most existing DNR methods rely on accurate network parameters and lack scalability and optimality. This study uses model-free reinforcement learning algorithms for training agents to take the best DNR actions in a given distribution system. Five reinforcement algorithms are applied to the DNR problem in 33- and 136-node test systems and their performances are compared: deep Q-learning, dueling deep Q-learning, deep Q-learning with prioritized experience replay, soft actor-critic, and proximal policy optimization. In addition, a new deep Q-learning-based action sampling method is developed to reduce the size of the action space and optimize the loss reduction in the system. Finally, the developed algorithms are compared against the existing methods in literature.

Microwave planar sensors employ conventional passive complementary split ring resonators (CSRR) as their sensitive region. In this work, a novel planar reflective sensor is introduced that deploys CSRRs as the front-end sensing element at $f_{\mathrm{res}}=6$ GHz with an extra loss-compensating negative resistance that restores the dissipated power in the sensor that is used in dielectric material characterization. It is shown that the $S_{11}$ notch of −15 dB can be improved down to −40 dB without loss of sensitivity. An application of this design is shown in discriminating different states of vanadium redox solutions with highly lossy conditions of fully charged ${\mathrm{V}}^{5+}$ and fully discharged ${\mathrm{V}}^{4+}$ electrolytes.