Early performance degradation of ceramic bearings by a twin-driven model

Mechanical Systems and Signal Processing, Год журнала: 2023, Номер 204, С. 110826 - 110826

Опубликована: Окт. 6, 2023

Язык: Английский

---

A novel digital twin model for dynamical updating and real-time mapping of local defect extension in rolling bearings

Mechanical Systems and Signal Processing, Год журнала: 2023, Номер 193, С. 110255 - 110255

Опубликована: Март 4, 2023

Язык: Английский

---

A Digital Twin Model of Life-Cycle Rolling Bearing With Multiscale Fault Evolution Combined With Different Scale Local Fault Extension Mechanism

IEEE Transactions on Instrumentation and Measurement, Год журнала: 2023, Номер 72, С. 1 - 11

Опубликована: Янв. 1, 2023

The digital twin of life-cycle rolling bearing is significant for its degradation performance analysis and condition prediction. To solve the problem which not reliable to arrange production cycle by predicting diagnostic results in existing studies, because it accurate only consider single-scale fault modeling. It studied that multiscale evolution law close true involves microscopic cracks, mesoscopic spall, macroscopic defect, establishing model with outer ring fault. Based on measured signals dynamic fault, time-varying 2-D sizes faults are estimated. mapping relationship between dimensions established using BP network, progressive mechanism whole life analyzed. Then, substituting excitation evolutionary into model, virtual space. real-time update realized integrating sensor data faulty bearings subspace. accuracy verified comparing twinning time domain signals. proposed improve efficiency extension accurately.

Язык: Английский

---

Rolling bearing performance assessment with degradation twin modeling considering interdependent fault evolution

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 224, С. 112194 - 112194

Опубликована: Дек. 6, 2024

Язык: Английский

---

Quality control in manufacturing – review and challenges on robotic applications

International Journal of Computer Integrated Manufacturing, Год журнала: 2024, Номер 38(1), С. 79 - 115

Опубликована: Фев. 22, 2024

Quality control methods and techniques have been investigated in different fields of manufacturing during the last decades. The introduction robots processes has created a rapid deployment robotic applications, leading to an increased research interest aspect quality such industrial environments. This paper summarizes presents review recent progress on technologies, focusing robot-based production systems. role parameters affecting tasks is also discussed, incorporating impact operator support systems human robot collaborative Research gaps implications applications are described, future outlook particular field provided.

Язык: Английский

---

Applications of Machine Learning in Real-Time Control Systems: A Review

Measurement Science and Technology, Год журнала: 2024, Номер 36(1), С. 012003 - 012003

Опубликована: Окт. 21, 2024

Abstract Real-time control systems (RTCSs) have become an indispensable part of modern industry, finding widespread applications in fields such as robotics, intelligent manufacturing and transportation. However, these face significant challenges, including complex nonlinear dynamics, uncertainties various constraints. These challenges result weakened disturbance rejection reduced adaptability, which make it difficult to meet increasingly stringent performance requirements. In fact, RTCSs generate a large amount data, presents important opportunity enhance effectiveness. Machine learning, with its efficiency extracting valuable information from big holds potential for RTCSs. Exploring the machine learning is great importance guiding scientific research industrial production. This paper first analyzes currently faced by RTCSs, elucidating motivation integrating into systems. Subsequently, discusses aspects, system identification, controller design optimization, fault diagnosis tolerance, perception. The indicates that data-driven methods exhibit advantages addressing multivariable coupling characteristics systems, well arising environmental disturbances faults, thereby effectively enhancing system’s flexibility robustness. compared traditional methods, also faces issues poor model interpretability, high computational requirements leading insufficient real-time performance, strong dependency on high-quality data. proposes future directions.

Язык: Английский

---

Proactive Safety Risk Control System for Deep Foundation Pit Construction: Situational Tailoring of Integrated Cybernetics and Dual-System Theory

Journal of Construction Engineering and Management, Год журнала: 2025, Номер 151(4)

Опубликована: Фев. 8, 2025

Язык: Английский

---

Servo torque fault diagnosis implementation for heavy-legged robots using insufficient information

ISA Transactions, Год журнала: 2024, Номер 147, С. 439 - 452

Опубликована: Фев. 8, 2024

Язык: Английский

---

Review on Fault Diagnosis and Fault-Tolerant Control Scheme for Robotic Manipulators: Recent Advances in Ai, Machine Learning, and Digital Twin

Опубликована: Янв. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

---

A model-data combination driven digital twin model for few samples fault diagnosis of rolling bearings

Measurement Science and Technology, Год журнала: 2024, Номер 35(9), С. 095103 - 095103

Опубликована: Май 28, 2024

Abstract Deep learning-based fault diagnosis methods for rolling bearings are widely utilized due to their high accuracy. However, they have limitations under conditions with few samples. To address this problem, a model-data combination driven digital twin model (MDCDT) is proposed in work samples of bearings. The simulation signals generated by different dynamic models and the measured mixed through MDCDT. MDCDT generates virtual bridge gap between simulated combining respective advantages. This paper also proposes image coding method based on Markov transfer matrix (MTMIC) convert one-dimensional vibration into two-dimensional images both frequency domain information time information, making it easier extract features neural network training. In end, developed was evaluated using real bearing data. Experiments show that can generate data diagnosis, accuracy significantly improved.

Язык: Английский

---