Multi-Output Classification Based on Convolutional Neural Network Model for Untrained Compound Fault Diagnosis of Rotor Systems with Non-Contact Sensors.

Fault diagnosis is important in rotor systems because severe damage can occur during the operation of systems under harsh conditions. The advancements in machine learning and deep learning have led to enhanced performance of classification. Two important elements of fault diagnosis using machine learning are data preprocessing and model structure. Multi-class classification is used to classify faults into different single types, whereas multi-label classification classifies faults into compound types. It is valuable to focus on the capability of detecting compound faults because multiple faults can exist simultaneously. Diagnosis of untrained compound faults is also a merit. In this study, input data were first preprocessed with short-time Fourier transform. Then, a model was built for classification of the state of the system based on multi-output classification. Finally, the proposed model was evaluated based on its performance and robustness for classification of compound faults. This study proposes an effective model based on multi-output classification, which can be trained using only single fault data for the classification of compound faults and confirms the robustness of the model to changes in unbalance.

Lightweight Semantic-Guided Neural Networks Based on Single Head Attention for Action Recognition.

Skeleton-based action recognition can achieve a relatively high performance by transforming the human skeleton structure in an image into a graph and applying action recognition based on structural changes in the body. Among the many graph convolutional network (GCN) approaches used in skeleton-based action recognition, semantic-guided neural networks (SGNs) are fast action recognition algorithms that hierarchically learn spatial and temporal features by applying a GCN. However, because an SGN focuses on global feature learning rather than local feature learning owing to the structural characteristics, there is a limit to an action recognition in which the dependency between neighbouring nodes is important. To solve these problems and simultaneously achieve a real-time action recognition in low-end devices, in this study, a single head attention (SHA) that can overcome the limitations of an SGN is proposed, and a new SGN-SHA model that combines SHA with an SGN is presented. In experiments on various action recognition benchmark datasets, the proposed SGN-SHA model significantly reduced the computational complexity while exhibiting a performance similar to that of an existing SGN and other state-of-the-art methods.

Design optimization of buttress type premium casing connection by modifying lower corner radius of stab flank.

Full-scale drilling for shale gas has been deepening, and the horizontal definitions have been increasing for drilling efficiency. Pressures and bending stresses are generated in the joints of gas-cored pipes, which seriously affect their durability. Premium casing connections are primarily forced at the interfaces of two parts, so the design of the threads is crucial, and the choice of optimal parameters is precisely related to their resistance to stresses. This article proposes a novel premium connection design, and its performance is validated through simulations to demonstrate good noise, vibration, and harshness (NVH) and durability performance. A parametric study is especially performed with the change of lower corner radius to observe maximum stress changes of the system and it is advised that a parameter be optimized. This study demonstrates that it is possible to design a premium connection capable of reducing the stress concentrated on the stab flank contact portion when drilling deep gas wells in response to parameter changes.

Effects of Home-Based Computerized Cognitive Training in Community-Dwelling Adults With Mild Cognitive Impairment.

OBJECTIVE: There is a growing importance for the home-based (HB) support services, and computerized cognitive training (CCT) has been reported as an effective intervention for cognitive impairment. However, there is still a need for further verification of the effect of HB-CCT. This study aimed to determine the effectiveness of HB-CCT on the cognitive function of community-dwelling adults with mild cognitive impairment (MCI) as well as safety in its use. METHODS: Fifty community-dwelling adults with MCI were included, of which 25 each were randomized to either HB-CCT or control groups. Evaluations of comprehensive cognition, memory, attention, language, executive function, and depression were performed before and after the intervention, including three times a week for eight weeks in the intervention group and eight weeks apart with no intervention in the control group. RESULTS: In baseline and post-evaluation comparisons, the HB-CCT group showed significant improvements, while the control group did not show significant changes. Statistically significant variations were noted between the HB-CCT and control groups in all post-intervention evaluations relative to baseline. Additionally, no side effects were observed. CONCLUSION: Beneficial effects on cognition and depression were noted in the intervention group compared with the control group, suggesting that HB-CCT may be a positive tool for cognitive improvement in adults with MCI.

Optimal placement criteria of hybrid mounting system for chassis in future mobility based on beam-type continuous smart structures.

Recently, research into the development of hybrid and electric vehicles has been vigorously undertaken, indicating a trend toward the replacement of internal combustion engine vehicles. However, while high efficiency and light weight are crucial in the development of vehicles, they increase the excitation force of the engine. In addition, sensor placement in future mobility is very important since it causes malfunctioning of autonomous driving systems when the location and orientation of sensors are changed due to excessive vehicle vibration. To reduce the structure-borne noise and vibration caused by engine excitation, an active engine mounting system must be installed in an optimal location. Thus, in this study, to determine the optimal location for an active engine mounting system applied to a beam structure, a series of simulations with two different methodologies are performed. The overall beam structure with two active mounting systems is modeled based on the lumped parameter model. To determine the optimal position of the active mounting system, it is moved to equal intervals, and the force and phase of the active mounts at each location combination are calculated based on static and dynamic methods. The optimal position is suggested such that the vibration reduction is maximized, while the applied force is minimized. Additionally, a feasibility experiment is conducted to validate the proposed criteria and confirm the simulation results. The results demonstrate that the optimal location of the active engine mounting system with a minimized force requirement and maximized vibration reduction can be identified.

Optimal placement criteria of actuators for hybrid mounting system on a non-aligned plate structure.

Electric motors in electric and hybrid vehicles generate mid-frequency noise and vibration. These factors cause drivers to experience discomfort while traveling. Active mounting techniques have been extensively researched and developed to effectively address this issue. The optimal placement of an active mounting system is essential for enhancing NVH performance when an active mounting system is utilized. In order to propose optimal location criteria for active paths, this paper concentrates on developing an analytical model based on both dynamic and static analysis. The secondary forces along active trajectories are mathematically determined when a structure is subjected to an excitation force. These locations are considered optimal for the active mounting system if the secondary forces are comparatively minimal. Simulations and feasibility experiments are also conducted in order to validate the proposed method. In addition, the results are compared with the case of beam structure. It has been determined through this procedure that the active path's control performance will be enhanced if it is positioned in the optimal location and less control force is required than in the case of beam.

Vibration characteristics of an active mounting system for motion control of a plate-like structure in future mobilities.

The vibration and noise caused by electric motors in hybrid and electric vehicles (EVs) generate complex signals with a mid-frequency band, which causes uncomfortable vibration and noise. In order to isolate the vibration and noise, active engine mounting systems based on smart structures have attracted attention. Thus, in this study, the vibration attenuation performance was validated through simulation and feasibility experiments by applying an active mounting system using a piezoelectric stack actuator. A plate structure with three paths, consisting of two passive paths and one active path, was modeled using the lumped parameter method. The source part was excited by a sinusoidal and modulated signal with a mid-frequency band to validate the vibration attenuation performance. Furthermore, (1) mathematical modeling with a source-path-receiver structure was proposed based on lumped parameter modeling, (2) normalized least mean square (NLMS) and multi-NLMS algorithms were applied to implement motion control, and (3) a principal experimental setup was designed to validate the simulation results. Through this process, the vibration attenuation performance of the proposed active mount structure was validated.

Quantification of active bearing input force for vibration reduction performance of unbalanced rotor systems.

Recently, rotating machinery has been widely applied in various mechanical systems such as hydroelectric and nuclear power plants. When mechanical systems are operated, the main rotor is rotated to manufacture the product. If a fault occurs in the rotor, then the system is damaged. Thus, to avoid malfunction of the system and rotor damage, vibration issues because of bending, misalignment, and imbalance should be considered. In this regard, a smart structure-based active bearing system is extensively researched and developed to control rotor vibration. This system can continuously improve the noise, vibration, and harshness performance under various operating conditions by controlling the dynamic characteristics of the active bearing. This study focused on the effect of rotor motion control by quantifying the active bearing force and phase when an active bearing was applied in a simple rotor model. A simple rotor with two active bearing systems was modeled based on lumped-parameter modeling. In the rotor model, the active bearing, which had two piezoelectric actuators and rubber grommets placed in both the x- and y-directions, was located on both sides to control the vibration. The interaction between the rotor and the active bearing system was considered to quantify the force and phase of this system. Furthermore, through simulation, the motion control effect was validated when an active bearing was applied in the rotor model.

Remote Assessment of ADHD Symptoms Based on Mobile Game Performance in Children with ADHD: A Proof of Concept.

The use of game-based digital medicine is gaining increasing interest in helping children with ADHD to improve their attention outside the clinical setting. In this process, it is important to continue monitoring children's responses to the use of digital medicine. In this work, we introduce novel digital markers and an analytic pipeline to estimate ADHD-related symptomatic levels during the self-administration of attention games. The digital markers, capturing the children's characteristics of attention and inattention spans, were extracted and translated into clinically-accepted measures of ADHD symptoms, specifically the ADHD-Rating Scale (ADHD-RS) and Child Behavior Checklist (CBCL). To validate the feasibility of our approach, we collected game-specific performance data from 15 children with ADHD, which was used to train machine learning-based regression models to estimate their corresponding ADHD-RS and CBCL scores. Our experiment results showed mean absolute errors of 5.14 and 4.05 points between the actual and estimated ADHD-RS and CBCL scores respectively. This study enables new clinical and research opportunities for accurate longitudinal assessment of symptomatic levels of ADHD via an interactive means of playing mobile games.

Investigating the Impact of Control Modes to Competency and Engagement in Serious Game Play for Children with ADHD.

Serious games are designed to reduce symptoms of attention deficit among children with Attention Deficit/Hyperactivity Disorder (ADHD). These games predominantly use touchscreen interfaces that children with ADHD play in a sitting position, which contributes to already-problematic sedentary behaviors. In an effort to mitigate negative impacts of sedentary behavior, we set out to investigate the use of Dance Dance Revolution (DDR) mats with serious games to induce gross movements. To that end, we designed and implemented Breathtaking Glass Bridge to investigate the impact of interface (DDR vs. touchscreen) on competency and engagement in children with ADHD. Our investigation with 30 children with ADHD reveal that the DDR mat was as engaging as the conventional touchscreen interface despite relatively lower competence shown by our participants. Our study opens new research opportunities for developing and strategically using movement-based control interfaces to encourage gross movements while reducing attention deficit symptoms among children with ADHD.

Examination of sub-harmonic responses along with various initial conditions induced by multi-staged clutch damper system.

Using the harmonic balance method to investigate the nonlinear dynamic behaviors pertaining to sub-harmonic responses is difficult compared with that of super-harmonic cases because of the limitations of the HBM. Since sub-harmonic motions differ under various initial conditions, difficulties can arise when this method is used to calculate all possible solutions within sub-harmonic resonances. To explore complex dynamic behaviors in sub-harmonic resonant areas, this study suggests mathematical and numerical techniques to estimate sub-harmonic responses depending on various initial conditions. First, sub-harmonic responses are calculated under various excitation conditions relevant to the sub-harmonic input locations of the HBM formula. Second, the HBM results are verified by comparing them with the results of the numerical simulation (NS) under various initial conditions with respect to different frequency up-sweeping paths. Finally, the positive real part of the eigenvalues is examined to anticipate bifurcation characteristics, which reflect the relevance of the complex dynamic behaviors in the eigenvalues' unstable solutions. Overall, this study successfully proves that the techniques and methods described are suitable for examining complex sub-harmonic responses, and suggests basic ideas for analyzing nonlinear dynamic behaviors in sub-harmonic resonances using the HBM.

Investigation of complex nonlinear dynamic behaviors observed in a simplified driveline system with multistage clutch dampers.

The results of the harmonic balance method (HBM) for a nonlinear system generally show nonlinear response curves with primary, super-, and sub-harmonic resonances. In addition, the stability conditions can be examined by employing Hill's method. However, it is difficult to understand the practical dynamic behaviors with only their stability conditions, especially with respect to unstable regimes. Thus, the main goal of this study is to suggest mathematical and numerical approaches to determine the complex dynamic behaviors regarding the bifurcation characteristics. To analyze the bifurcation phenomena, the HBM is first implemented utilizing Hill's method where various local unstable areas are found. Second, the bifurcation points are determined by tracking the stability variational locations on the arc-length continuation scheme. Then, their points are defined for various bifurcation types. Finally, the real parts of the eigenvalues are analyzed to examine the practical dynamic behaviors, specifically in the unstable regimes, which reflect the relevance of various bifurcation types on the real part of eigenvalues. The methods employed in this study successfully explain the basic ways to examine the bifurcation phenomena when the HBM is implemented. Thus, this study suggests fundamental method to understand the bifurcation phenomena using only the HBM with Hill's method.

Stability and bifurcation analysis of super- and sub-harmonic responses in a torsional system with piecewise-type nonlinearities.

The nonlinear dynamic behaviors induced by piecewise-type nonlinearities generally reflect super- and sub-harmonic responses. Various inferences can be drawn from the stability conditions observed in nonlinear dynamic behaviors, especially when they are projected in physical motions. This study aimed to investigate nonlinear dynamic characteristics with respect to variational stability conditions. To this end, the harmonic balance method was first implemented by employing Hill's method, and the time histories under stable and unstable conditions were examined using a numerical simulation. Second, the super- and sub-harmonic responses were investigated according to frequency upsweeping based on the arc-length continuation method. While the stability conditions vary along the arc length, the bifurcation phenomena also show various characteristics depending on their stable or unstable status. Thus, the study findings indicate that, to determine the various stability conditions along the direction of the arc length, it is fairly reasonable to determine nonlinear dynamic behaviors such as period-doubling, period-doubling cascade, and quasi-periodic (or chaotic) responses. Overall, this study suggests analytical and numerical methods to understand the super- and sub-harmonic responses by comparing the arc length of solutions with the variational stability conditions.

Remote Assessment of Cognitive Impairment Level Based on Serious Mobile Game Performance: An Initial Proof of Concept.

Individuals with cognitive impairments are evaluated using clinically validated cognitive assessment tools, which need to be administered by trained therapists. This serves as a major barrier for frequent and longitudinal monitoring of patients' cognitive impairment level. We introduce Neuro-World, a set of six mobile games designed to challenge visuospatial short-term memory and selective attention, which allows one to self-administer the assessment of his/her cognitive impairment level. Game performance is analyzed to estimate a widely accepted clinical measure, the mini mental state examination (MMSE), which highlights the translational impact of the system in real-world settings. We collected game-specific performance data from 12 post-stroke patients at baseline and a three-month follow-up, which were used to train supervised machine learning models to estimate the corresponding MMSE scores. The results presented herein show that the proposed approach can estimate the MMSE scores with a normalized root mean square error of 5.75%. We also validate the system's responsiveness to longitudinal changes in cognitive impairment level and demonstrate the system's positive usability in cognitively impaired individuals and their willingness to adhere to the longitudinal use. This study demonstrates that Neuro-world has great potential to be used to evaluate the cognitive impairment level and monitor its long-term change. This study enables new clinical and research opportunities for accurate, longitudinal assessment of cognitive function via mobile games.

Estimating Mini Mental State Examination Scores using Game-Specific Performance Values: A Preliminary Study.

Individuals with permanent cognitive impairment need to be evaluated and monitored. There exists a number of clinically validated cognitive assessment tools, but they often need to be administered by trained therapists in clinical settings. This serves as a major barrier for frequent, longitudinal monitoring of cognitive function. In this work, we introduce Neuro-World, a collection of innovative 3D mobile games, that allows one to self-administer the assessment of his/her cognitive function. The game performance is analyzed and converted into a clinically-accepted measure of cognitive function, specifically the Mini Mental State Examination (MMSE) score, improving the translational impact of the system in real-world clinical settings. To validate the feasibility of our approach, we collected game-specific performance data from 12 post-stroke patients, which was used to train a supervised machine learning model to estimate the corresponding MMSE score. Our experiment results showed a normalized root mean square error of 5.3% between the actual and estimated MMSE scores. This study enables new clinical and research opportunities for accurate longitudinal assessment of cognitive function via an interactive means of playing mobile games.