Current Issue : October-December Volume : 2022 Issue Number : 4 Articles : 5 Articles
Ultrasonic guided wave testing (UGWT) is a non-destructive testing (NDT) technique commonly used in structural health monitoring to perform wide-range inspection from a single point, thus reducing the time and effort required for NDT. However, the multi-modal and dispersive nature of guided waves makes the extraction of essential information that leads to defect detection an extremely challenging task. The purpose of this article is to give an overview of signal processing techniques used for filtering signals, isolating modes and identifying and localising defects in UGWT. The techniques are summarised and grouped according to the geometry of the studied structures. Although the reviewed techniques have led to satisfactory results, the identification of defects through signal processing remains challenging with space for improvement, particularly by combining signal processing techniques and integrating machine learning algorithms....
When using DSP technology, technicians can easily and conveniently replace DSP audio processors, make second-party equipment, improve processor performance, reduce application costs, and receive and make music to meet the needs of different signals. Introduces knowledge of speech comprehension, which includes theoretical and cognitive processes, such as pre-speech characterization, final discovery, behavior, structure, and knowledge. By analyzing and comparing various common features, Mel frequency cepstrum coefficient is used to determine the physical features, and the results of traditional algorithms are studied, compared, and evaluated. Research, compare, and evaluate numbers in traditional algorithms. The simulation is based on the algorithms of all the connections used in the system and checks that the algorithm is correct. Design an experimental model, compare the advantages and disadvantages of algorithms and algorithms, consider the process requirements and changes of the whole algorithm, and select the algorithm accordingly algorithm. The experimental results show that the speed recognition of the TW algorithm is not much different from that of the HMM algorithm, and the efficiency of the DTW algorithm in the training models is lower than that of the HMM algorithm. Given the limited resources of the DSP platform in this system, we have chosen the DTW algorithm as the self-reporting system for this system. Finally, the performance of the system is checked and the test results are released. Observations of the experimental instrument showed that the system was effective in being able to recognize small words and discrepancies in speech....
Computer network, as the basic course of teaching information majors in colleges and universities, in the process of teaching and learning, shows the characteristics of rich content, abstract theory, and difficulty understanding. This requires us not only to pay attention to theoretical teaching but also to pay attention to experimental teaching in the study of this subject. The current computer network experiment teaching mainly takes the form of computer room as the teaching location, which consumes a lot of manpower and material resources. That computer network experiment teaching based on simulation has lost the practical significance of network teaching. Through the analysis of the characteristics of the experimental teaching of computer network courses, this study studies and designs a set of computer network experimental platforms based on virtualization, aiming at the deficiencies in the existing experimental teaching of computer network courses. When the thread pool is 1, 2, 3, and 4, the average response time of the system is 324873 ms, 279309 ms, 227300 ms, and 221670 ms, respectively....
Electroencephalography (EEG) signal analysis is a fast, inexpensive, and accessible technique to detect the early stages of dementia, such as Mild Cognitive Impairment (MCI) and Alzheimer’s disease (AD). In the last years, EEG signal analysis has become an important topic of research to extract suitable biomarkers to determine the subject’s cognitive impairment. In this work, we propose a novel simple and efficient method able to extract features with a finite response filter (FIR) in the double time domain in order to discriminate among patients affected by AD, MCI, and healthy controls (HC). Notably, we compute the power intensity for each high- and low-frequency band, using their absolute differences to distinguish among the three classes of subjects by means of different supervised machine learning methods. We use EEG recordings from a cohort of 105 subjects (48 AD, 37 MCI, and 20 HC) referred for dementia to the IRCCS Centro Neurolesi “Bonino-Pulejo” of Messina, Italy. The findings show that this method reaches 97%, 95%, and 83% accuracy when considering binary classifications (HC vs. AD, HC vs. MCI, and MCI vs. AD) and an accuracy of 75% when dealing with the three classes (HC vs. AD vs. MCI). These results improve upon those obtained in previous studies and demonstrate the validity of our approach. Finally, the efficiency of the proposed method might allow its future development on embedded devices for low-cost real-time diagnosis....
At present, the degree of industrialization in China is deepening, and various types of production equipment appear. However, during the startup and operation of mechanical equipment, fracture and wear will occur due to various factors. Therefore, once the mechanical equipment fails, it must be diagnosed as soon as possible to avoid serious economic losses and casualties. Rotating machinery is an important power device, so it is necessary to regularly detect and monitor equipment signals to avoid the consequences of wrong control methods. In this study, the fault diagnosis of rotating machine based on adaptive vibration signal processing is studied under the safe environmental conditions. The fault diagnosis process of rotating machinery is to first collect vibration signals, then process signal noise reduction, and then extract fault characteristic signals to further identify and classify fault status and diagnose fault degree. This study briefly introduces several rotating machinery vibration signal processing methods and identifies the fault state of the rotating machine based on the high-order cumulant. By building a DDS fault diagnosis test bench, the chaotic particle swarm parameter optimization algorithm is used to calculate the accurate stochastic resonance parameters. After noise processing, the high-frequency part is significantly reduced. The results show that, after stochastic resonance wavelet decomposition and denoising processing, the number of intrinsic functions can be significantly reduced, the fault frequency can be increased, the high-frequency noise can be reduced, and the fault analysis accuracy can be improved. We identify the fault state of rotating machinery based on the high-order cumulant, train the four states of the bearing, and compare the four types of faults, no fault, inner ring fault, rolling element fault, and outer ring fault through the comparison of the actual test set and the predicted test set. It is concluded that the rotating machinery fault belongs to the rolling element fault and the identification accuracy rate is 95%. Finally, based on the LMD morphological filtering, the rotating machinery fault diagnosis is carried out, and the feature extraction is carried out based on the LMD algorithm to decompose the bearing fault signal. Finally, the result after the morphological filtering and LMD decomposition and extraction can avoid noise interference....
Loading....