Variable Speed Research Articles

Data imbalanced fault diagnosis of gearbox transmission system under various speeds based on dynamic dual-scale normalized fusion network

Abstract Gearboxes play a pivotal role in industrial production, and their reliability and safety are essential for production safety and efficiency. However, gearboxes frequently encounter challenges such as variable rotational speeds and unknown operating conditions. Unfortunately, most existing traditional fault diagnosis methods face the following issues: (1) They heavily rely on expert experience and pre-existing knowledge bases, making them unable to tackle fault diagnosis in unknown working conditions. (2) While addressing various speed issues, they seldom consider the problem of data imbalance in real-world industrial environments. (3) Many transfer learning methods primarily focus on global distribution alignment and knowledge transfer between source and target domains, neglecting the importance of fine-grained distribution alignment between subdomains. To address these issues, a dynamic dual-scale normalization fusion network (DSNFNet) is proposed for cross-domain fault diagnosis under variable speed and data imbalance. Firstly, the two parallel graph convolution frameworks constructed are used to extract multi-scale fault features. Subsequently, a dual-scale normalization fusion module is adopted to integrate the global and local fault feature information within the subdomains of both the source and target domains, thereby aligning their fine-grained distributions to obtain domain-invariant features. Finally, a dynamic soft threshold feedback strategy is introduced, which assigns pseudo labels to the target domain data, enabling the model to give equal attention to each class of data samples, even under data imbalance conditions, thereby improving the recognition accuracy of minority fault classes. Validating the proposed method on two real cases, our method achieved the highest accuracy compared to other advanced approaches.

Damage assessments of designed sandwich cores against an idealized impact loading of ship accidents: experiment-based validated nonlinear finite element approach

PurposeThe high rate of ship casualties demands serious attention. Earlier studies have yet to integrate several scenarios in an experiment. This research aims to determine damage to a ship's hull that is assumed to have been stranded due to being hit by a rock under the sea.Design/methodology/approachThis scenario was analyzed by conducting a penetration test simulation using the ANSYS LS DYNA. Modeling was carried out with core, speed, indenter shape and indenter angle variations. The test is carried out by moving the indenter against the plate until the plate is damaged.FindingsThe results of this research show that the round indenter gave the best results in testing, while changes in speed below 1.5 m/s did not significantly affect the results. The contact angle of the indenter to the panel is directly proportional to the damage to the panel, and core X has the best results in the test.Originality/valueThis work presented several proposed eccentric sandwich panels to calculate their performance against impact loading. The detailed geometry for future reference is presented, while the indenter-panel interactions are validated based on experimental work.

Estimating the Electric Fields Driving Lightning Dart Leader Development With BIMAP‐3D Observations

AbstractIn this paper, a numerical dart leader model has been implemented to understand the leader's development and the corresponding electric field changes observed by the 3D broadband mapping and polarization (BIMAP‐3D) system. The model assumes the extending leader channel is equipotential and has a linear charge distribution induced by an ambient electric field. The charge distribution induced by the ambient field can be used to model the electric field change at the ground. We then find the ambient electric field which best fits the field change measurements at the two BIMAP stations. The estimated ambient electric field decreases in the direction of dart leader propagation. Our observations and modeling results are consistent with our earlier hypothesis that dart leader speed is proportional to the electric field at the leader tip. The model also supports our earlier analysis that leader speed variations near branch junctions were due to previous charge deposits near the junctions. The modeled tip electric field is generally lower than the breakdown field unless the pre‐dart‐leader channel has a significant temperature of 3,000 K. This is consistent with the fact that dart leaders typically do not form new branches into the virgin air. Furthermore, the tip field is generally close to the negative streamer stability field at ambient temperatures, explaining the nature of the narrow and well‐defined channel structure. In addition to the charge distribution and the ambient and tip electric field, the development of the channel potential and current distribution are also presented.

A Study on a Geohash Cell-Based Spatial Analysis Using Individual Vehicle Data for Linear Information

Linear spatial data are primarily used in Geographic Information Systems (GISs) to represent spatial data in the form of roads, rivers, railways, and utility lines. Linear spatial data are mostly composed of one-dimensional linear elements, incorporating geometric attributes such as location, direction, and length, as well as the interconnections of these elements. In the case of roads, this information is used to map and analyze traffic data, such as vehicle movements, on the road network. This study aims to propose an area-based spatial analysis method that allows for the flexible application of analysis scales using individual vehicle data, as opposed to node and link generation for linear road networks. The analysis focused on nine expressways, conducting a microscopic analysis of speed-homogeneous sections. The final analysis showed that out of 375 cells, 91 cells in the final 12 division cells did not meet the homogeneity criteria. This discrepancy was ascertained to be due to vehicles decelerating or accelerating when entering or exiting highways at ramps or interchanges, not due to directional speed differences but lane-specific speed variations. The final cells with large speed deviations were found to be influenced by connections to highway on-ramps or off-ramps. In contrast, sections with small speed variations within a cell were influenced by traffic factors such as connection points and traffic volume, which hindered normal driving. As a result, this study validated that traffic information from highways, typically provided as linear data, could be divided into cells based on real-time GPS speed data and presented on an area-based scale. While dividing regions based on fixed intervals does not pinpoint exact speed change points, this study found that reasonable segmentation is possible based on spatial size and speed-homogeneous sections.

The Parameterization of the Sound Speed Profile in the Sea of Japan and Its Perturbation Caused by a Synoptic Eddy

This study presents the description of the parameterization of sound speed distribution in the Sea of Japan in the presence of a synoptic eddy. An analytical representation of the background sound speed profile (SSP) on its periphery is proposed. The perturbation of sound speed directly associated with the presence of an eddy is investigated. The proposed parameterization of the background SSP leads to a Sturm–Liouville problem for normal mode computation, which is equivalent to the eigenvalue problem for the Schrödinger equation with the Morse potential. This equivalence leads to simple analytical formulae for normal modes and their respective horizontal wavenumbers. It is shown that in the presence of an eddy causing moderate variations in sound speed, the standard perturbation theory for acoustic modes can be applied to describe the variability in horizontal wavenumbers across the area in which the eddy is localized. The proposed parameterization can be applied to the sound propagation modeling in the Sea of Japan.

Dynamical Response Comparison Between Variable Speed and Synchronous Speed Pumped-Storage Units in Turbine Mode

Dynamical Response Comparison Between Variable Speed and Synchronous Speed Pumped-Storage Units in Turbine Mode

Isokinetic Dynamometry for External and Internal Rotation Shoulder Strength in Youth Athletes: A Scoping Review.

Accurately measuring shoulder strength in overhead athletes is critical, as sufficient strength is essential for safe and sustained performance during repetitive athletic movements. Isokinetic dynamometry (ID) offers dynamic strength assessments that surpass the capabilities of static methods, such as manual muscle testing and handheld dynamometry. The dynamic assessment provided by ID may enhance upper extremity evaluation, aiding in the prediction of injury risk and the determination of return-to-sport criteria for overhead athletes. The purpose of this review was to examine the existing literature concerning the application of isokinetic shoulder strength testing in rehabilitation and clinical decision-making processes among youth athletes who perform repetitive overhead activities. Scoping review. A comprehensive literature search was conducted using PubMed and EBSCO Host databases, covering publications from 2000-2024. Search terms included "isokinetic dynamometry," "shoulder," and "youth athlete." Inclusion criteria focused on youth athletes (<18 years) engaged in overhead sports, excluding those with neurological conditions or those designated as college or professional athletes. The PRISMA-ScR guidelines were followed. A total of 23 articles met the inclusion criteria. Volleyball and swimming were the most studied sports, with the most common testing position being the seated 90/90 position. Variations in testing speeds and outcome measures, such as peak torque and external rotation (ER) ratios, were identified. Isokinetic dynamometry is a valuable tool for assessing shoulder strength in youth overhead athletes. It provides critical insights into muscle strength dynamics, aiding in injury prevention and rehabilitation. Further research is needed to optimize strength assessment protocols and enhance clinical decision-making for safe return-to-sport practices.

New Generation Site and Estimated Propagation of Nonlinear Internal Waves Under Varying Background Stratification in the Northeastern East China Sea

AbstractThis study investigates the generation and propagation of nonlinear internal waves (NLIWs) in the northeastern East China Sea (ECS), focusing on the impact of time‐varying background stratification. Using satellite imagery and tide‐generating body force, 327 groups of NLIWs were identified from 93 MODIS images collected between 2015 and 2019 and classified into three distinct types based on their propagation directions—Type‐A (∼42%), Type‐B (∼38%), and Type‐C (∼20%)—each originating from different generation sites. Type‐B NLIWs were found to originate from a newly identified site near southwestern Fukue Island reported here for the first time, whereas Type‐A and Type‐C originated from the northern Okinawa Trough and southwestern Jeju Island, respectively. Seasonal variations in NLIW propagation speed using historical CTD data revealed an increase in the speed from winter to spring and fall, peaking in summer due to strong stratification. Although spatial distribution varied by season, propagation was generally faster in the eastern region than in the western region attributed to deeper thermoclines and higher density gradients. During field observation in May 2015, the observed NLIWs had an amplitude of 5–6 m, a characteristic width of 380–450 m, southwestward propagating directions, and a speed of ∼0.54 m s−1. An empirical model, used to track and predict these waves, confirmed their generation locations from southwestern Fukue Island (Type‐B) and indicated fast arrival speeds, influenced by time‐varying stratification conditions during the stratification period. These findings highlight the impacts of varying background conditions on NLIW propagation and would facilitate their prediction.

Impact of natural fractures on hydraulic fracture propagation in Denver-Julesburg Basin: Insights from a decade of research

The Denver-Julesburg (DJ) Basin is a key region for unconventional oil and gas extraction, particularly from the Niobrara and Codell formations. This study synthesizes findings from a decade of research conducted in three different geographic areas of the basin as part of the industry consortium Reservoir Characterization Project at Colorado School of Mines. The research explores how natural fractures affect hydraulic fracture propagation, leveraging geophysical data sets including 3D seismic imaging, image logs, microseismic monitoring, and crosswell distributed strain sensing. Key observations reveal significant variations in hydraulic fracture orientations and propagation speeds between the Niobrara and Codell formations, which are the main targets for horizontal drilling and stimulation. High natural fracture densities and orientations notably influence the propagation of hydraulic fractures in the Niobrara Formation, deviating them from the regional maximum horizontal stress (SHmax) directions, while hydraulic fractures in Codell consistently align with SHmax where lower natural fracture densities are observed. The study also highlights the critical role of stress anisotropy and zipper fracturing sequences in dictating hydraulic fracture behavior. Additionally, a marked negative correlation between natural fracture density and hydraulic fracture propagation speed underlines the fracture network complexity added by natural fractures. These findings advocate for a comprehensive natural fracture characterization and tailored fracturing strategies to optimize well placement and completions. The implications for DJ Basin development from this study are profound, suggesting that understanding local geomechanics and fracture networks can significantly enhance hydrocarbon recovery. Future work should focus on more precise assessments of hydraulic fracture interactions with natural fracture systems to refine operational strategies further.

Experimental assessment of communication delay's impact on connected automated vehicle speed volatility and energy consumption

Communication delays within connected and autonomous vehicles (CAVs) pose significant risks. It is imperative to address these issues to ensure the safe and effective operation of CAVs. However, the exploration of communication delays on CAV operations and their energy use remains sparse in the literature. To fill the research gap, this study leverages the facilities at America Center of Mobility (ACM) Smart City Test Center to implement and evaluate a CAV merging control algorithm through vehicle-in-the-loop testing. This study aims at achieving three main objectives: (1) develop and implement a CAV merging control strategy in the experimental test bed through vehicle-in-the-loop testing, (2) propose analytical models to quantify the impacts of communication delay on the variability of CAV speed and energy consumption based on field experiment data, and (3) create a predictive model for energy usage considering various CAV attributes and dynamics, e.g., speed, acceleration, yaw rate, and communication delays. To our knowledge, this is one of the first attempts at evaluating the impacts of communication delays on CAV merging operational control with field data, making critical advancement in the field. The results suggest that communication delay has a more substantial effect on energy consumption under high-speed volatility compared to low-speed volatility. Among all factors examined, acceleration is the dominant characteristic that influences energy usage. It also revealed that even minor improvements in communication delay can yield tangible improvements in energy efficiency. The results provide guidance on CAV field experiments and the influence of communication delays on CAV operation and energy consumption.

Impact of boundary layer parameterizations on simulated seasonal meteorology over North-East India

This study evaluated the accuracy of six planetary boundary layer (PBL) parameterization schemes in simulating two different seasons of pre-monsoon and monsoon in India's North-East region through the Weather Research and Forecasting (WRF) model. Twelve one-month simulations were conducted with the PBL schemes, six each for April (pre-monsoon) and July (monsoon), and the model outputs were compared against observations. Three non-local schemes, Asymmetric Convective Model (ACM2), Yonsei University (YSU), Shin-Hong (HONG), and three local schemes, Quasi Normal Scale Elimination (QNSE), Mellor Yamada Janjic (MYJ) and Mellor Yamada Nakanishi Nino (MYNN3), were tested. The meteorological variables of temperature, relative humidity (RH), wind speed, wind direction, and rainfall were evaluated, and the performance of each scheme for each meteorological variable is reported. The 2m temperature (T2) variable was well simulated by ACM2, MYJ in April, and YSU in July, while MYNN3 best simulated the 2m RH (RH2) during both seasons. 10m wind speed (WS10) and directions (WD10) were better simulated by MYNN3, HONG and YSU. HONG also best-simulated rainfall in April and MYJ in July. April and July being rainfall periods, an analysis of the schemes’ simulated rainfall frequency was also carried out. Moreover, the PBL schemes were also ranked, considering their combined performance with all the above meteorological parameters. While considering both the seasons and all meteorological variables, the scale-aware scheme, HONG, was the best scheme and can be used to simulate both seasons. Additionally, an in-depth analysis of surface and atmospheric parameters was also carried out to reason the simulated meteorology. QNSE expends the highest amount of its surface energy through surface evaporation, leading to the lowest surface skin temperature and T2 predictions. In contrast, MYNN3 produced the lowest mixing, which caused the moistest boundary layer, highest RH, cloud cover, and highly overestimated rainfall. Besides evaluation, which will help to choose a suitable PBL scheme for weather predictions in this region, this study also identifies the characteristics and deficiencies of PBL and surface layer schemes for improvement.

Assesment of wind potential energy of four major cities in Cote d’ivoire using satellite data from 2015 to 2022

In Côte d’Ivoire, the use of renewable energy is becoming a major challenge in the context of climate change and global warming. Therefore, the aim of this study is to characterize the wind profile for potential energy in Abidjan, Man, Bouaké and Korhogo of Côte d’Ivoire using satellite data. Wind speed and direction data from Copernicus Centre from 2015 to 2022 are used for these major cities. The frequency method is used to build wind rose and power density formula to estimate the potential energy for each city, at ground level (10 m) and in particular level at 100 m and 500 m. The results showed a slightly wind speed and direction variation from 2015 to 2022. This suggests that wind has a seasonal (wet and dry) evolution over the year. However, wind speeds increase for each city with the altitude. The higher average wind speed is observed in Abidjan with a power density of 58 W/m2. The lower wind speed and power density are observed in Man, Bouaké and Korhogo. So, the coastline of Côte d’Ivoire has the higher wind energy resource than the inland regions of the country.

Investigation of Joinability Of 25% Recycled Al6016 Sheets By Friction Stir Butt Welding At Different Tool Rpm

In this study, 25% recycled 2 mm thick Al6016 sheets used in the production of automotive body and chassis parts were used. They were joined in the butt position using different tool speeds on the mold milling machine. The tool tip was selected as 2379 quality steel and the surface hardness was increased to 62-64 HRC. The sinking tip was designed as a conical geometry. In the joints, 400 mm/min welding progress speed, 1.8 mm tool tip immersion depth, 15 mm shoulder width and 90o tool inclination angle were kept constant. The rotation speed of the stirring tip was determined as 600 rpm, 1200 rpm, 1800 rpm, 2400 rpm, 3000 rpm, 3600 rpm as variable parameters. Heat inputs were calculated according to variable speeds. Samples taken from the welded joint with the friction stir method were examined with tensile, bending and hardness tests. Macro and micro images were examined and the fracture surfaces were compared. While the highest tensile strength at 400 mm/min feed speed was determined as 214 MPa at 1800 rpm and the lowest value was determined as 83 MPa at 600 rpm, no fracture was observed at 2400 and 3000 rpm as a result of the bending test and it was successful. The highest results of the hardness values of the joint area were measured as 97.4 Hv at 600 rpm rotation speed. It was determined that penetration occurred in the macro structure at all rpm speeds. When the micro images were examined, it was seen that the grain structure thinned from the base metal to the joint area.

Variable speed limit control strategy considering traffic flow lane assignment in mixed-vehicle driving environment

To accurately predict traffic flow and optimize the operations of freeway bottleneck areas in a mixed-vehicle driving environment, this paper proposes a traffic prediction model and a variable speed limit (VSL) cooperative control strategy. Firstly, a lane-level short-term traffic prediction model, physics informed Transformer and cell transmission model (PIT-CTM), is constructed by combining the Transformer neural network and lane-level cell transmission model (CTM) based on the physics-informed deep learning framework. On this basis, the accuracy and transferability of PIT-CTM are analysed. Secondly, a lane assignment decision model is presented, which enables the dynamic planning of the optimal traffic distribution across lanes. Furthermore, a lane-level VSL control model is constructed based on the model predictive control (MPC) framework. The model induces vehicles to change lanes earlier by setting the speed limit difference between lanes. By regulating the input flow in the bottleneck area of the freeway, it reduces conflicts between mainline vehicles and ramp vehicles. Finally, the feedback regulation between the lane assignment decision model and the lane-level VSL control model promotes the cooperative optimisation of the lateral and longitudinal flows and adapts the control strategy to the dynamic traffic characteristics. A three-lane freeway merging zone is selected, the numerical experiment is conducted and compared with differential lane-level VSL. The results show that the strategy can effectively optimise the mixed-vehicle traffic state and maintain better control performance under any connected and autonomous vehicle (CAV) penetration rates.

Evaluation method and enhanced strategy for frosting suppression performance of variable speed air source heat pump based on frosting suppression performance map

It is well established that the configuration and operation of variable speed air source heat pumps (VS ASHPs) can significantly influence their frosting performance. However, there is currently no effective method to conveniently and accurately evaluate the frosting suppression performance of these units. This paper addresses this gap by proposing a novel evaluation method based on a frosting suppression map for VS ASHPs. Firstly, an experimental setup with four ASHP units and developed frosting suppression maps is described. Second, a method for evaluating the frosting suppression performance of VS ASHP is developed based on the map. Thirdly, a comprehensive evaluation of the frosting suppression performance of the experimental unit is carried out. It is shown that the β values of the four units under the constitutive configuration were 0.74, 0.12, 0.21, and 0.52, and the frosting suppression performance was evaluated as Good, Poor, Fair, and Average, respectively. It could be enhanced and improved to 0.89 (Excellent), 0.24 (Fair), 0.64 (Good), and 0.63 (Good) after applying the frosting suppression operation method. The proposed novel frosting suppression evaluation method is simple and easy to implement, which could contribute to further guiding manufacturers to improve the frosting suppression performance of VS ASHPs.

The effect of High Intensity Interval Training (HIIT) tuja shuttle run model on agility and speed of female volleyball school athletes bank Jatim Surabaya

This study aims to evaluate the effectiveness of high-intensity interval training (HIIT) using the Tuja Shuttle Run model in enhancing agility and speed among volleyball athletes. The research employs a quasi-experimental non-equivalent control group design, involving 24 female volleyball athletes from Bank Jatim Surabaya, consisting of 12 athletes in the treatment group and 12 in the control group. Data were collected through pre-test and post-test assessments to measure changes in agility and speed variables. Data analysis was conducted using paired sample t-test and independent sample t-test. The results indicate that the treatment group experienced an average increase in agility of 3.31% and speed of 5.76% following the HIIT Tuja Shuttle Run intervention, while the control group showed no significant changes. These findings conclude that the HIIT Tuja Shuttle Run model is effective in improving agility and speed among athletes (particularly in speed), thereby supporting the application of this method within training programmed to optimize volleyball athlete performance.

Aerodynamic Study of a Horizontal Axis Wind Turbine in Surge Motion Under Angular Speed and Blade Pitch Controls

Abstract Floating offshore wind turbines (FOWTs) experience dynamic conditions due to platform motion, requiring specific control strategies to mitigate loads and promote the wake diffusion improving overall wind farm efficiency. These problems can be appropriately modeled by medium-fidelity solvers, which rely on a computational fluid dynamics (CFD) resolution of the flow while avoiding its detailed resolution around the blades, preserving high-fidelity in simulating the wake at an acceptable computational cost. This work adopts a medium-fidelity actuator line model (ALM), implemented in the openfoam environment, previously validated against experiments and multifidelity models in the frame of the OC6 Phase III project. The study analyses several operating conditions during surge motion: a variable angular speed in below-rated condition, conceived to maximize the turbine efficiency, and a collective blade pitch control employable in above-rated conditions to limit surge-induced loads fluctuations. The effect of each control strategy is assessed individually through a systematic comparison with the baseline case with constant angular speed and blade pitch. Results indicate that the angular speed control succeeds in increasing the turbine power and reduces the spanwise variability of the induction factor amplitudes. Conversely, the pitch angle control reduces the force amplitude but does not alter the spanwise trend of the induction factor amplitude.

Outdoor Pollution Comparison Between Bucharest and Its Outskirts Using Mobile Laboratory

This study presents a modern mobile laboratory to monitor outdoor air quality in Bucharest, Romania, with a focus on pollutants associated with transportation. Particulate matter (PM2.5, PM10), carbon monoxide (CO), ozone (O3), sulfur dioxide (SO2), nitrogen oxides (NO, NO2), and BTEX compounds (benzene, toluene, ethylbenzene, and xylenes) were among the significant pollutants that were examined in the lab. Meteorological variables such wind direction and speed, temperature, humidity, and solar radiation were also routinely observed in order to assess their influence on pollution levels. The study looked at two locations—a bustling city road in Bucharest and a remote community 40 kmawayin Snagov—under a range of weather conditions, including sunny, rainy, warm, and chilly days. The findings showed that the primary source of pollution in the urban area, which had significantly higher pollution levels than the rural site, was transportation. Particularly in the city, alarming concentrations of harmful particulate matter and carcinogens like benzene were found, underscoring the need for continuous air quality monitoring. The weather has a major impact on the dispersal of contaminants. Because of washout effects, rainy days decreased airborne pollutants, but sunny days showed higher pollution deposition. This study highlights the importance of outdoor air quality monitoring, particularly in urban environments, where traffic and weather have a significant impact on pollution levels. These findings provide crucial data that policymakers can utilize to implement targeted pollution control measures that protect human health.

Meta-learning-based fault diagnosis method for rolling bearings under cross-working conditions

Abstract Accurate prediction of bearing failures is crucial for reducing maintenance costs and enhancing production efficiency in rotating machinery. However, the variable speed conditions and complex working environments encountered during operation pose significant challenges to fault diagnosis. Problems such as domain shift and insufficient sample quantity may occur during fault diagnosis under cross-working conditions, which can decrease the accuracy and generalization of deep learning algorithms. In this paper, we introduce a fault diagnosis framework grounded in meta-learning. Centered on a dual-channel feature fusion network and employing a meta-learning training paradigm, the framework not only performs well in cross-condition fault diagnosis tasks but also demonstrates superior performance in few-shot learning scenarios. Firstly, dual-channel network is used to extract the classification features of different domains, and the features are fused. Next, training is conducted using a meta-learning strategy to acquire prior knowledge, enabling rapid model adaptation to cross-working conditions and addressing the challenge of limited training samples. Finally, two public rolling bearing data sets are used to demonstrate the efficacy of the proposed method across different operational conditions. Prior to this, we selected the appropriate sample length and fusion domain through experimental validation. The proposed method also has good fault diagnosis accuracy in cross-device tasks. The experimental results verify the effective classification capability and robustness of the proposed method. Furthermore, comparisons with other meta-learning approaches confirm the superior performance of our method. The ablation experiments validated the importance and irreplaceability of each component of the proposed method.

Transfer twin support matrix machine using rescaled pinball loss for roller bearing fault diagnosis

Abstract The support matrix machine (SMM) takes matrix-based data as input elements, which can protect the structural information of matrix-based data extracted from vibration signals and has good classification performance. However, in practical applications, due to the limitation of mechanical equipment and monitoring technology, there is often an insufficient number of annotation samples for SMM to find the optimal hyperplane. Therefore, a novel transfer twin SMM (TTSMM) is proposed in this article. In TTSMM, the structural information from the source data is transferred to the target model by simultaneously training on both the source and target data, which helps to establish a high-performance model using a limited number of labeled samples. Furthermore, a rescaled pinball loss function is used in TTSMM, which is bounded and utilizes quantile distance to further improve the generalization ability of the model. Finally, the proposed method is implemented on two kinds of roller bearing fault data sets including the variable speed vibration signal from Anhui University of Technology (AHUT) and the constant speed vibration signal from Case Western Reserve University (CWRU). The experimental results show that TTSMM effectively utilizes samples from both the source and target domains for modeling and has superior classification ability with a limited number of labeled samples.