This paper presents an improved method for recognizing the drill state on the basis of hole images drilled in a laminated chipboard, using convolutional neural network (CNN) and data augmentation techniques. Three classes were used to describe the drill state: red -- for drill that is worn out and should be replaced, yellow -- for state in which the system should send a warning to the operator, indicating that this element should be checked manually, and green -- denoting the drill that is still in good condition, which allows for further use in the production process. The presented method combines the advantages of transfer learning and data augmentation methods to improve the accuracy of the received evaluations. In contrast to the classical deep learning methods, transfer learning requires much smaller training data sets to achieve acceptable results. At the same time, data augmentation customized for drill wear recognition makes it possible to expand the original dataset and to improve the overall accuracy. The experiments performed have confirmed the suitability of the presented approach to accurate class recognition in the given problem, even while using a small original dataset.

In this paper we introduce the enhanced drill wear recognition method, based on classifiers ensemble, obtained using transfer learning and data augmentation methods. Red, green and yellow classes are used to describe the current drill state. The first one corresponds to the case when drill should be immediately replaced. The second one denotes a tool that is still in a good condition. The final class refers to the case when a drill is suspected of being worn out, and a human expert evaluation would be required. The proposed algorithm uses three different, pretrained network models and adjusts them to the drill wear classification problem. To ensure satisfactory results, each of the methods used was required to achieve accuracy above 90\% for the given classification task. Final evaluation is achieved by voting of all three classifiers. Since the initial data set was small (242 instances), the data augmentation method was used to artificially increase the total number of drill hole images. The experiments performed confirmed that the presented approach can achieve high accuracy, even with such a limited set of training data.

No abstract

Further increases in the number of photovoltaic installations in industry and residential buildings will require technologically and economically flexible energy storage solutions. Some countries utilize net-metering strategies, which use national networks as “virtual batteries.” Despite the financial attractiveness, net-metering faces many technological and economical challenges. It could also lead to the negative tendencies in prosumer behavior, such as a decrease in motivation for the self-consumption of photovoltaic (PV)-generated electricity. Batteries, which are installed on the prosumer’s premises, could be a solution in a particular case. However, the price for battery-based storage solutions is currently sufficiently unattractive for the average prosumer. This paper aimed to present a comparison of the economic and energy related aspects between net-metering and batteries for a single case study by considering the Lithuanian context. The net present value, degree of self-sufficiency, internal rate of return, payback time, and quantified reduction of carbon emission were calculated using a specially developed Prosumer solution simulation tool (Version 1.1, Delloite, Madrid, Spain) for both the PV and net-metering and PV and batteries cases. The received results highlight that the battery-based energy storage systems are currently not an attractive alternative in terms of price where net-metering is available; a rather radical decrease in the installation price for batteries is required.

Flat plate solar collector has been presented as an example of a heat-exchanger with two input signals, solar radiation intensity and temperature of working medium on the input, and one output signal, the temperature of a working medium on the output. The dynamics of heat exchange were analyzed for two models of a solar collector—an analog one using a thermoelectric analogy, and a digital one—determined experimentally in on-line mode using the parametric identification method. The characteristics of both models were compared in terms of their step and frequency response for selected construction and operational parameters. Tests of step responses determined for the analog model indicate that the dynamics of heat exchange in the solar collector depending on two input signals is varied. For step-forcing of input signals of the analog model, in both cases, a stable steady state is achieved, but while the first of the signals is inertial, the second one is oscillatory. The phenomenon of temperature oscillation at the collector outlet suggests the need to introduce a new physical quantity in the thermoelectric analogy-thermal inductance. Such an assessment of the dynamics of the solar collector can be useful for proper designing (construction parameters simulation) and diagnostics (operational parameters simulation) of the device.