Concurrent control chart pattern recognition in manufacturing processes based on zero-shot learning.

In real industrial settings, collecting and labeling concurrent abnormal control chart pattern (CCP) samples are challenging, thereby hindering the effectiveness of current CCP recognition (CCPR) methods. This paper introduces zero-shot learning into quality control, proposing an intelligent model for recognizing zero-shot concurrent CCPs (C-CCPs). A multiscale ordinal pattern (OP) feature considering data sequential relationship is proposed. Drawing from expert knowledge, an attribute description space (ADS) is established to infer from single CCPs to C-CCPs. An ADS is embedded between features and labels, and the attribute classifier associates the features and attributes of CCPs. Experimental results demonstrate an accuracy of 98.73 % for 11 unseen C-CCPs and an overall accuracy of 98.89 % for all 19 CCPs, without C-CCP samples in training. Compared with other features, the multiscale OP feature has the best recognition effect on unseen C-CCPs.

A MOGA and extended RPN based approach for heuristic key reliability characteristics analysis in manufacturing.

The manufacturing process is the last opportunity to build an ideal design reliability index into a product. With the advancement of intelligent manufacturing technology, the concept of quality evolves from conformance to fitness for use, which emphasizes that reliability should be built into product with quality control. To effectively implement reliability assurance in the manufacturing process, it is necessary to accurately identify the vital few characteristics that are critical to reliability. Thus, a heuristic key reliability characteristic (KRC) analysis in manufacturing model fusing big quality data is proposed. First, on the basis of the fusion big quality data in manufacturing-by-manufacturing system Reliability-operational process Quality- output product Reliability (RQR) chain, a data driven KRC analysis model is proposed, and a reliability proactive control framework in manufacturing driven by KRC is expounded. Second, considering mass quality and reliability data, an effective KRC identification method based on data mining using multi-objectives genetic algorithm (MOGA) is established. Third, considering manufacturing data and product failure risk, an extended risk priority number (RPN) for KRC ranking is proposed. Finally, an example of an insulating base of subway locomotive is provided to verify the proposed approach.

Effects of axial pressure on the evolution of core-shell heterogeneous structures and magnetic properties of Fe-Si soft magnetic powder cores during hot-press sintering.

Silicon dioxide (SiO2) has attracted much attention as an ideal coating material for iron (Fe)-based soft magnetic powder cores (SMPCs). However, maintaining the integrity and uniformity of Fe-based/SiO2 core-shell heterostructures is still a challenge. The evolution mechanism of core-shell heterostructures determines the performance of Fe-based SMPCs. Herein, the evolution of the core-shell structures and heterogeneous interfaces of Fe-Si@SiO2 SMPCs with axial pressure and the influence of the evolution on the SMPCs performance were investigated. The results show that in the axial pressure range of 10-15 kN, the core-shell heterostructures were gradually integrated, whereas the SiO2 insulation coatings underwent an amorphous-to-crystalline transformation. At axial pressure above 16 kN, the Fe-Si powder melted partially, and the core-shell heterostructure collapsed due to overheating, caused by the gradient temperature field during the hot-press sintering. When the core-shell heterostructure was intact, the Fe-Si@SiO2 SMPCs showed a permeability of over 38 with a wide and stable frequency range of 100-300 kHz, a saturation magnetisation of 231.7 emu g-1, resistivity of 0.8 mΩ cm and total loss of 704.7 kW m-3 at 10 mT and 100 kHz. When the core-shell heterostructure was destroyed, the resistivity dropped dramatically and the loss increased to 765.0 and 897.4 kW m-3. These results show the relationship between the core-shell heterostructure of Fe-Si@SiO2 SMPCs, axial pressure and magnetic properties, which would be vital in achieving high power density, high efficiency and miniaturisation in SMPCs.

Modeling Product Manufacturing Reliability with Quality Variations Centered on the Multilayered Coupling Operational Characteristics of Intelligent Manufacturing Systems.

For intelligent manufacturing systems, there are many deviations in operational characteristics, and the coupling effect of harmful operational characteristics leads to the variations in quality of the work-in-process (WIP) and the degradation of the reliability of the finished product, which is reflected as a loss of product manufacturing reliability. However, few studies on the modeling of product manufacturing reliability and mechanism analysis consider the operating mechanism and the coupling of characteristics. Thus, a novel modeling approach based on quality variations centered on the coupling of operational characteristics is proposed to analyze the formation mechanism of product manufacturing reliability. First, the PQR chain containing the co-effects among the manufacturing system performance (P), the manufacturing process quality (Q), and the product manufacturing reliability (R) is elaborated. The connotation of product manufacturing reliability is defined, multilayered operational characteristics are determined, and operational data are collected by smart sensors. Second, on the basis of the coupling effect in the PQR chain, a multilayered product quality variation model is proposed by mining operational characteristic data obtained from sensors. Third, an integrated product manufacturing reliability model is presented on the basis of the variation propagation mechanism of the multilayered product quality variation model. Finally, a camshaft manufacturing reliability analysis is conducted to verify the validity of the proposed method. The method proposed in this paper proved to be effective for evaluating and predicting the product reliability in the smart manufacturing process.

Risk-Oriented Product Assembly System Health Modeling and Predictive Maintenance Strategy.

Assembly quality is the barometer of assembly system health, and a healthy assembly system is an important physical guarantee for producing reliable products. Therefore, for ensuring the high reliability of products, the operational data of the assembly system should be analyzed to manage health states. Therefore, based on the operational data of the assembly system collected by intelligent sensors, from the perspective of quality control based on risk thinking, a risk-oriented health assessment method and predictive maintenance strategy for managing assembly system health are proposed. First, considering the loss of product reliability, the concept of assembly system health risk is proposed, and the risk formation mechanism is expounded. Second, the process variation data of key reliability characteristics (KRCs) collected by different sensors are used to measure and assess the health risk of the running assembly system to evaluate the health state. Third, the assembly system health risk is used as the maintenance threshold, the predictive maintenance decision model is established, and the optimal maintenance strategy is determined through stepwise optimization. Finally, the case study verifies the effectiveness and superiority of the proposed method. Results show that the proposed method saves 37.40% in costs compared with the traditional method.

A Mission Reliability-Driven Manufacturing System Health State Evaluation Method Based on Fusion of Operational Data.

The rapid development of complexity and intelligence in manufacturing systems leads to an increase in potential operational risks and therefore requires a more comprehensive system-level health diagnostics approach. Based on the massive multi-source operational data collected by smart sensors, this paper proposes a mission reliability-driven manufacturing system health state evaluation method. Characteristic attributes affecting the mission reliability are monitored and analyzed based on different sensor groups, including the performance state of the manufacturing equipment, the execution state of the production task and the quality state of the manufactured product. The Dempster-Shafer (D-S) evidence theory approach is used to diagnose the health state of the manufacturing system. Results of a case study show that the proposed evaluation method can dynamically and effectively characterize the actual health state of manufacturing systems.