This paper presents a monitoring method for on-line detection and indication of the occurrence of a cutting tool failure during high-speed face milling. The method consists of processing of the vibration signal using a reconfigurable infinite impulse response (IIR) bandpass digital filter and statistical techniques. The healthy tool threshold and the filter passband are adjusted and configured based on the cutting parameters that were set up during the machining process. For this process, sets of filter coefficients are pre-calculated for a number of defined insert passing frequencies ranges. The method is verified on-line during machining tests that are carried out at different tool failure levels and using various cutting parameters. In all experimental tests, the method allows the tool condition to be detected and indicated correctly. The proposed method is therefore shown to be simple, fast, computationally efficient, and reliable for the detection and indication of the presence of several types of tool failures for various cutting parameters, and the use of this method does not require any modification of the machine tool structure.

The existence of failures in photovoltaic systems causes energy losses, security problems, and damage to its components. Therefore, it is necessary to develop monitoring systems to improve their productivity, reliability, efficiency, and safety. This work proposes a method for detecting and indicating short-circuit failure and partial shading present in grid-connected photovoltaic modules. The novelty of this proposal is the processing of voltage and current signals generated (ripple signals) by the electrical interaction between the photovoltaic string, the photovoltaic inverter, the condition of the modules, temperature, and irradiance. The magnitudes of specific frequency components are obtained from these electrical signals using DFT, and Cartesian coordinates are formed in a three-dimensional plane. Coordinates belonging to each of the string conditions are mostly located in different octants from this plane. This distribution allows an assessment of the modules state. Certain scattering is solved with a K-nearest neighbors algorithm. The effectiveness of the methodology was experimentally validated in two PVG with different characteristics. In each test case, the method was adaptable to the real conditions of the photovoltaic system. The results show effectiveness greater than 90% in the first evaluation levels, there is a slightly lower detection certainty in anomalous conditions with coordinates that are very close to each other. However, the system has 100% certainty detecting the presence of an abnormal condition. The method allows adaptation to different conditions, and takes advantage of the electrical signals derived from the actual performance of the used devices.

Accurate classification of electromyographic (EMG) signals is vital in biomedical applications. This study evaluates different architectures of recurrent neural networks for the classification of EMG signals associated with five movements of the right upper extremity. A Butterworth filter was implemented for signal preprocessing, followed by segmentation into 250 ms windows, with an overlap of 190 ms. The resulting dataset was divided into training, validation, and testing subsets. The Grey Wolf Optimization algorithm was applied to the gated recurrent unit (GRU), long short-term memory (LSTM) architectures, and bidirectional recurrent neural networks. In parallel, a performance comparison with support vector machines (SVMs) was performed. The results obtained in the first experimental phase revealed that all the RNN networks evaluated reached a 100% accuracy, standing above the 93% achieved by the SVM. Regarding classification speed, LSTM ranked as the fastest architecture, recording a time of 0.12 ms, followed by GRU with 0.134 ms. Bidirectional recurrent neural networks showed a response time of 0.2 ms, while SVM had the longest time at 2.7 ms. In the second experimental phase, a slight decrease in the accuracy of the RNN models was observed, standing at 98.46% for LSTM, 96.38% for GRU, and 97.63% for the bidirectional network. The findings of this study highlight the effectiveness and speed of recurrent neural networks in the EMG signal classification task.

Post-consumer polymers require viable actions to transfer value to the final consumer to reduce environmental impact. Worldwide, initiatives are being developed to promote the culture of recycling and thus reduce waste generation. These initiatives seek to make the work of thousands of people visible, encourage job creation, and promote businesses through incentive schemes for effective separation, collection, classification, reuse, and recycling, in the hands of consumers, collectors, and scavenges. It is necessary to emphasize that Mexico needs to develop techniques to increase the productivity of collection centers for recyclable materials and to face the challenges that recycling implies. For these reasons, the Mexican government has spoken of waste management as a national priority due to the COVID-19 pandemic, which increased urban solid waste between 3.3 % and 16.5 % in addition to what was generated under normal conditions. Also, the recycling chain provides economic income to more than 35 thousand Mexicans. Polyethylene terephthalate (PET) is an example of the most notable circular economy in Mexico because 60 % of PET bottles are recycled. Therefore, this article addresses the methods and systems in the management of urban solid waste. It focuses on post-consumer recycled plastic bottles to provide an overview of cost-effective strategies for designing and developing an affordable sorting system in Mexico from the academic field. In addition, to simplify the solution that we propose, it is recommended to combine optical techniques such as infrared spectroscopy and Raman spectroscopy with others methods that work together, such as computer vision, to develop affordable systems that address the limitations of mechanical systems.