Additive manufacturing (AM) has been playing a crucial role in the fourth industrial revolution. Sensor-based monitoring technologies are essential for detecting defects and providing feedback for process control. Acoustic emission (AE) sensors have been used for a long time in a wide range of processes and fields, but they are still a challenge in AM processes. This work presents a study on the AE signals in the time-domain—raw and root mean square (RMS) values—regarding their behavior during the manufacture of a single-layer part in the fused filament fabrication process for two infill patterns. The tests were conducted on a cartesian 3D printer using polylactic acid material. The AE sensor was attached to the printer table through a magnetic coupling, and the signal was collected by an oscilloscope at 1 MHz sampling frequency. It was found that the raw AE signals behaved quite differently not just for the two infill patterns, but within the same pattern. The raw and RMS AE signals contained many spikes along the whole process, but the higher ones were those generally occurring at the end and/or start of a fabrication line. The RMS values, however, were useful for finding the start and end times of each fabricated line for both patterns. The mean RMS values showed nearly constant but distinct averages for the extruder-only, table-only and extruder–table movements.

Industrial demand forecasting is crucial for managing stock levels, financial revenue projections, logistics, and efficient production operations. However, there are notable gaps in the literature, particularly in the research that explores the potential of intelligent monitoring systems using Internet of Things (IoT) devices in combination with industrial production forecasting algorithms. This gap is particularly evident in scenarios characterized by seasonal data and limited historical samples. This research work presents an affordable method for monitoring and forecasting industrial production demand, which involves developing an IoT device and applying deep learning algorithms to an industrial production line. In the proposed methodology, an edge device, known as a datalogger, collects and transmits production data to a cloud server obtained through photoelectric laser beam sensors and the PLC of a filling machine. The data is subsequently retrieved from the cloud database for analysis and production demand forecasting. This work compares the performance of three distinct neural networks–sxLSTM, GRU, and SCINet-in the context of time series forecasting. The evaluation employs metrics such as root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Through this framework, it was possible to achieve to forecast production demand with error rates of 9.08 (RMSE), 7.67 (MAE), and 1.86 (MAPE), due to the SCINet neural network, even in scenarios with seasonal samples and limited historical data from an industrial filling line.

The monitoring of manufacturing processes is essential to ensure the quality and structural integrity of the produced parts. However, several processes still require human intervention for defect detection, such as 3-D printing. This paper investigates the potential of a monitoring system based on the electromechanical impedance (EMI) technique to identify defects in 3-D printed parts. A piezoelectric diaphragm was affixed to the print bed, and different printing conditions were used to manufacture the parts. The experimental results demonstrated that the EMI technique can infer defect areas by calculating the root mean square deviation (RMSD) index from the imaginary part of the impedance at a frequency range of (123.5-124.0) kHz. Notably, the diaphragm used in this study was obtained at a cost of less than one US dollar, and its performance exhibited a strong correlation. These observations suggest that the proposed system possesses considerable potential for effective monitoring of the 3-D printing process.

The identification and severity of structural damages in carbon fiber reinforced polymer (CFRP), especially in the early stage, is critical in structural health monitoring (SHM) of composite materials. Among several approaches used to accomplish this goal, ultrasound inspection using Lamb waves has been taking place within non-destructive testing (NDT) methods. Likewise, the use of digital signal processing techniques for structural damage diagnosis has become popular due to the fact that it provides relevant information through feature extraction. In this context, this paper presents an alternative strategy based on the use of root mean square deviation (RMSD) and correlation coefficient deviation metric (CCDM) representative indices to extract the most sensitive information related to damage in CFRP plates through ultrasonic NDT signals in specific frequency ranges. In the experimental analysis, CFRP coupons were subjected to two types of damages: cracking and delamination. The signals, generated by piezoelectric transducers attached to the host structure using the pitch-catch method of Lamb waves, were subject to signal processing parameters based on the proposed approach. The results reveal that the proposed method was able to characterize the different types of damage in CFRP, as well as their severity in specific frequency bands. The results indicate the feasibility of the proposed method to detect and characterize damage in composite materials in a simple way, which is attractive for industrial applications.

The evaluation of the response of sensors fixed to the print bed in the fused filament fabrication (FFF) process has been the subject of recent studies due to the increasing use of the FFF process. Many of these studies focus on topics related to monitoring the FFF process through the signals collected by sensors. Recently, some works employing piezoelectric diaphragm and electret microphones can be found in the monitoring of the FFF process, but the influence of the transducer response due to the variation of temperature has not been addressed. Thus, this work presents a study of the response of a low-cost electret microphone attached to the print bed under different temperature values. A 3D printer with polylactic acid (PLA) filament was used in the tests, which consisted of applying the pencil lead break method (PLB on the heated print bed at temperature values ranging from 25 °C to 65 °C. The acoustic waves generated by the tests were captured by the electret microphone attached near the breakage point, and the signals were sampled using an oscilloscope at a frequency of 2 MHz. The signals were processed in the time and frequency domains, followed by comparative analyses between the signals obtained for different temperature values. The results showed that it was not possible to determine a single temperature value at which the response of the electret microphone starts to undergo significant changes, but rather there is inconsistent change in the transducer’s response across all frequency bands, indicating that the influence of temperature takes place in a complex way as frequency varies. This complexity is further evidenced by the non-linear behavior of RMSD values for the evaluated temperatures. Thus, the results can be helpful to those who use this type of transducer attached to the printing bed for monitoring purposes.

This work presents the study of a reproducible acoustic emission method based on the launching of a metallic sphere and low-cost piezoelectric diaphragm. For this purpose, tests were first conducted on a carbon fiber-reinforced polymer structure, and then on an aluminum structure for comparative analysis. The pencil-lead break (PLB) tests were also conducted for comparisons with the proposed method. Different launching heights and elastic deformations of the structures were investigated. The results show higher repeatability for the sphere impact method, as the PLB is more affected by human inaccuracy, and it was also effective in damage detection.