Jien Ma
YOU?
Author Swipe
View article: Learnable edge detectors can make deep convolutional neural networks more robust
Learnable edge detectors can make deep convolutional neural networks more robust Open
Deep convolutional neural networks (DCNNs) are vulnerable to examples with small perturbations. Improving DCNNs’ robustness is of great significance to the safety-critical applications, such as autonomous driving and industry automation. I…
View article: 3D bioprinting of mechanically graded GelMA hydrogels with tri-layered vascularized architecture for full-thickness skin regeneration
3D bioprinting of mechanically graded GelMA hydrogels with tri-layered vascularized architecture for full-thickness skin regeneration Open
Skin is the largest organ of the human body and serves as the primary barrier against external environmental insults. However, in cases of severe skin damage or pathologic conditions, the body's natural physiological repair mechanisms are …
View article: Design of infinite impulse response maximally flat stable digital filter with low group delay
Design of infinite impulse response maximally flat stable digital filter with low group delay Open
Maximally flat digital filters (MFDFs) are widely applied in applications where the energy of useful signals is concentrated around some specific frequencies. A typical design method of MFDFs is to impose constraints on the filter's freque…
View article: Avoiding catastrophic overfitting in fast adversarial training with adaptive similarity step size
Avoiding catastrophic overfitting in fast adversarial training with adaptive similarity step size Open
Adversarial training has become a primary method for enhancing the robustness of deep learning models. In recent years, fast adversarial training methods have gained widespread attention due to their lower computational cost. However, sinc…
View article: Design of Infinite Impulse Response Maximally Flat Stable Digital Filter With Low Group Delay
Design of Infinite Impulse Response Maximally Flat Stable Digital Filter With Low Group Delay Open
Maximally flat digital filters (MFDFs) are widely applied in applications where the energy of useful signals is concentrated around some specific frequencies. A typical design method of MFDFs is to impose constraints on the filter’s freque…
View article: Development of Fault Diagnosis Equipment for High Speed Maglev Traction Converter System
Development of Fault Diagnosis Equipment for High Speed Maglev Traction Converter System Open
This paper investigates the fault diagnosis technology of the high-speed maglev traction inverter system using IGCT three-level inverters.Due to the increase in output levels, the number of power devices increases.The circuit structure and…
View article: Development and application of a mechanical arm-based in situ 3D bioprinting method for the repair of skin wounds
Development and application of a mechanical arm-based in situ 3D bioprinting method for the repair of skin wounds Open
Current treatments for skin wounds typically involve multiple surgical procedures that require complex processes and expensive costs, making it difficult to achieve timely treatment in field environments. We developed an innovative in situ…
View article: Early-Stage Fault Diagnosis of Motor Bearing Based on Kurtosis Weighting and Fusion of Current–Vibration Signals
Early-Stage Fault Diagnosis of Motor Bearing Based on Kurtosis Weighting and Fusion of Current–Vibration Signals Open
To solve the problem of a low signal-to-noise ratio of fault signals and the difficulty in effectively and accurately identifying the fault state in the early stage of motor bearing fault occurrence, this paper proposes an early fault diag…
View article: Edge Detectors Can Make Deep Convolutional Neural Networks More Robust
Edge Detectors Can Make Deep Convolutional Neural Networks More Robust Open
Deep convolutional neural networks (DCNN for short) are vulnerable to examples with small perturbations. Improving DCNN's robustness is of great significance to the safety-critical applications, such as autonomous driving and industry auto…
View article: Modeling and Optimization for Submersible Pump Tubular Linear Motor Based on Dynamic Load Analysis
Modeling and Optimization for Submersible Pump Tubular Linear Motor Based on Dynamic Load Analysis Open
The structure of a submersible permanent magnet tubular linear motor (SPPMTLM) can significantly affect its load spectrum. However, the existing models do not account for this effect. This study proposes an advanced SPPMTLM model that inco…
View article: Development and Application of a Mechanical Arm-Based In Situ 3D Bioprinting Method for the Repair of Skin Wounds
Development and Application of a Mechanical Arm-Based In Situ 3D Bioprinting Method for the Repair of Skin Wounds Open
Current treatments for skin wounds typically involve multiple surgical procedures that require complex processes and expensive costs, making it difficult to achieve timely treatment in field environments. We developed an innovative in situ…
View article: Improving the Robustness of Deep Convolutional Neural Networks Through Feature Learning
Improving the Robustness of Deep Convolutional Neural Networks Through Feature Learning Open
Deep convolutional neural network (DCNN for short) models are vulnerable to examples with small perturbations. Adversarial training (AT for short) is a widely used approach to enhance the robustness of DCNN models by data augmentation. In …
View article: A novel estimation model for hysteresis loss based on semi-minor loops
A novel estimation model for hysteresis loss based on semi-minor loops Open
This paper proposes an estimation model of hysteresis loss based on the mapping of the hysteresis loop conducted through tiny material samples with the aid of the Superconducting Quantum Interference Device (SQUID). This approach allows pr…
View article: Effect of Repeated Weld Repairs on Microstructure and Mechanical Properties of Heat-Affected Zone in CA6NM Stainless Steel
Effect of Repeated Weld Repairs on Microstructure and Mechanical Properties of Heat-Affected Zone in CA6NM Stainless Steel Open
The low-carbon martensitic stainless steel CA6NM is widely used in the impellers of hydroelectric and nuclear power units due to its advantages of high hardness, corrosion fatigue strength, and good fracture toughness. In order to analyze …
View article: Experimental Research of the Heat Storage Performance of a Magnesium Nitrate Hexahydrate-Based Phase Change Material for Building Heating
Experimental Research of the Heat Storage Performance of a Magnesium Nitrate Hexahydrate-Based Phase Change Material for Building Heating Open
Phase change heat storage material is a preferred material in solar building heating or off-peak electric-heat storage heating technology and is the research focus. A compact phase change thermal storage device has been designed and experi…
View article: Wasserstein distance-based distributionally robust optimal scheduling in rural microgrid considering the coordinated interaction among source-grid-load-storage
Wasserstein distance-based distributionally robust optimal scheduling in rural microgrid considering the coordinated interaction among source-grid-load-storage Open
The microgrid (MG) is an effective way to alleviate the impact of the large-scale penetration of distributed generations. Due to the seasonal characteristics of rural areas, the load curve of the rural MG is different from the urban MG. Be…
View article: Energy-saving rating of green Bed and Breakfast based on the fuzzy comprehensive evaluation
Energy-saving rating of green Bed and Breakfast based on the fuzzy comprehensive evaluation Open
Formulating a reasonable energy-saving strategy for Bed and Breakfast (B&B) can effectively reduce the operating costs, increase the revenue and achieve sustainable development. Given this background, a fuzzy evaluation-based energy-saving…
View article: Two-dimensional evaluation model of electrical equipment based on combined weighting and rating algorithm
Two-dimensional evaluation model of electrical equipment based on combined weighting and rating algorithm Open
In the process of electric energy substitution, many industries have gradually replaced the traditional energy consumption equipment with new electrical ones. To avoid the disadvantage of one-sidedness in equipment evaluation and provide a…
View article: An Overmodulation Strategy for Matrix Converter Under Unbalanced Input Voltages
An Overmodulation Strategy for Matrix Converter Under Unbalanced Input Voltages Open
In this article, an improved space vector pulsewidth modulation strategy for matrix converter is proposed under unbalanced input voltages. First, to obtain the higher output voltage, two novel space vector pulsewidth modulation strategies …
View article: Fast Finite-Set Model Predictive Control for Three-Phase Four-Arm Active Front End Modular Multilevel Converters Under Unbalanced and Distorted Network Conditions
Fast Finite-Set Model Predictive Control for Three-Phase Four-Arm Active Front End Modular Multilevel Converters Under Unbalanced and Distorted Network Conditions Open
This paper focuses on a fast finite-set model predictive control (FFS-MPC) for three-phase four-arm active front end modular multilevel converters (AFE-MMCs) under unbalanced and distorted network conditions. The main aim of this paper is …
View article: Torque Ripple Reduction of a Salient-Pole Permanent Magnet Synchronous Machine With an Advanced Step-Skewed Rotor Design
Torque Ripple Reduction of a Salient-Pole Permanent Magnet Synchronous Machine With an Advanced Step-Skewed Rotor Design Open
In this paper, a salient-pole permanent magnet synchronous machine (SPPMSM) is introduced to high-speed trains, taking advantage of its high utilization of the reluctance torque from the unbalanced reactance. Torque characteristics, such a…
View article: Passivity-Based Cascade-Free Finite-Set Model Predictive Control for Nested Neutral Point-Clamped Converters
Passivity-Based Cascade-Free Finite-Set Model Predictive Control for Nested Neutral Point-Clamped Converters Open
This paper focuses on a novel passivity-based cascade-free finite-control-set model predictive control scheme (CFFCS-MPC) for nested neutral point-clamped converters (NNPCs). It can be realized by combining an FCS-MPC and a passivity-based…
View article: A modified jiles-atherton model for estimating the iron loss of electrical steel considering DC bias
A modified jiles-atherton model for estimating the iron loss of electrical steel considering DC bias Open
This paper proposed a novel approach to calculate the iron loss under DC bias condition using modified Jiles-Atherton (JA) model. The influence of DC bias on the JA model is analyzed. The parameters in the JA model are extracted from BH lo…
View article: A Performance Test and Internal Flow Field Simulation of a Vortex Pump
A Performance Test and Internal Flow Field Simulation of a Vortex Pump Open
Vortex pumps have good non-clogging performance and are widely used in the fluid transportation of food, sewage treatment, and mineral and coal slurry transportation. In order to design and manufacture a vortex pump with good performance a…
View article: Performance analysis of a high-speed on/off valve based on an intelligent pulse-width modulation control
Performance analysis of a high-speed on/off valve based on an intelligent pulse-width modulation control Open
Dynamic performance is an important index of high-speed on/off valve in the digital hydraulic field. Optimizing the control algorithm is an effective method to improve the dynamic performance of existing high-speed on/off valves. Usually, …