It is necessary to conduct a real-time, intelligent, and self-adaptive computer numerical control machine tool system due to its basic executor role in the manufacturing process. The digital twin (DT), evolved from the cyber-physical system, provides a solution to this demand. However, most commercial DT software focuses on simulation, lacking online diagnosis and prediction of the manufacturing process. Meanwhile, conventional research concentrates on component modeling of machine tools rather than cutters and workpieces, leading to poor correlation to product quality. Furthermore, tool wear compensation is seldom considered for quality improvement. To address these issues, this article proposes a hybrid knowledge-based DT for cutters of machine tools. A novel DT architecture of a machine tool is demonstrated and explained first. Then, the implementation methods for how to construct digital shadow via the machining process, generated and real-time measured signals, to integrate knowledge from physics and data domain for diagnosis and tool wear prediction, and to compensate for the tool wear for machining process online optimization are discussed. Finally, a case study shows the shadow fidelity, prediction accuracy, and compensation effectiveness. Results show that the proposed method can be implemented in the practical machining process and improve the workpiece quality efficiently.

Tool condition monitoring is essential to maintain the final product quality and machining efficiency of the manufacturing process. However, traditional physics-based and data-driven approaches have limitations either on prediction efficiency or performance generalization, due to the nature of the respective approaches. To address these issues, in this article, a physics-informed deep learning approach is developed, which integrates the tool wear mechanism into the data-driven model. First, some representative physical information is selected for the task learning. Then, four practical physics-informed methods are proposed to integrate various physical information into the data-driven models. Based on these physical constraints, a physics-informed deep learning model is specially designed for tool wear monitoring. Compared with previous studies, more diverse physical information can be effectively utilized to guide the hypothesis space, thereby improving the generality of the model. The effectiveness and feasibility of this model under various working conditions are verified in high-speed milling experiments. The results show that the wear prediction of the proposed approach is more accurate and consistent under unknown machining conditions.

The condition monitoring is essential to the advanced manufacturing process in the era of the fourth industrial revolution because it ensures the prediction and optimization of machine tool conditions via data analytics or physical modeling methods. The cyber-physical system (CPS) has the property of intellectuality, scalability, adaptability, and openness, making it suitable for machine tool monitoring. The current data-driven CPS method is prone to interpretability and generalization limitations due to the empirical selection of hyper-parameters in the model and the need for heterogeneous data. On the other hand, traditional model-driven systems are difficult to adjust models to practical working conditions data due to empirical equations constructed by offline data. This article proposes a novel model-driven cyber-physical system (MDCPS) to overcome these weaknesses. First, the physical model generates a counterpart of the machining process to form a cyber world, and sensors depict the real-time state of the machining process to form a physical world. Second, for deep fusion between the cyber and physical worlds, the extended Kalman filter (EKF) approach is applied to calibrate the empirical model with online measured data. Third, the model-based diagnosis and prediction methods are used for online monitoring and control. Case studies of MDCPS for machining monitoring are presented to prove the feasibility of this model-driven system.

Hidden semi-Markov model (HSMM) has been widely used in equipment condition monitoring. However, the HSMM is usually modeled in fixed working mode. It is incompetent to monitor the condition when the working mode is varying in the equipment's lifetime. In this article, taking time-varying working mode into account, we propose a novel switching HSMM (SHSMM) to represent the equipment's degradation process. The reciprocal of duration is modeled and utilized to quantize the influence of working mode on the degradation process. Compared to traditional HSMM and time-varying HMM, the proposed SHSMM has a more generalized form and a more powerful ability to describe the degradation process with time-varying working mode. The proposed SHSMM is then applied to tool wear monitoring with time-varying cutting mode. Experimental results show that, via the proposed SHSMM, the monitoring confidence increases and the estimation of remaining useful life has a great improvement.

In this article, a method of hybrid convolutional neural networks (CNNs) is proposed for powder-bed fusion (PBF) process monitoring. The proposed method can learn both the spatial and temporal representative features from the raw images automatically based on the advantages of the CNN architecture. The results demonstrate the superior performance of the proposed method compared with the traditional methods with handcrafted features. The overall detection accuracy of four process conditions, e.g., overheating, normal, irregularity, and balling, can be up to 0.997. In addition, it is found that the temporal information for PBF process monitoring by the vision detection of the process zone (including melt pool, plume, and spatters) is significant. As the proposed method can save image processing steps, it simplifies the procedure on feature extraction. This makes it more suitable for online monitoring applications.

The computer numerical control (CNC) machining is the technical foundation of modern high-end manufacturing. To satisfy the productivity and precision requirement, it is required to monitor and adaptively control the machining process in real time under varying working conditions. The current CNC machining system is limited by the data acquisition methods and modeling approaches, and it is difficult to make full use of monitoring information to smartly assess and optimize the cutting conditions online. This article proposes a new idea and a novel model to solve the problem, with a big data analytics framework for smart tool condition monitoring (TCM). Driven by the monitored big data, this article systematically investigates the key issues for TCM, such as machining dynamics, intelligent tool wear monitoring and compensation algorithms, heterogeneous big data fusion, and deep learning methods. Under this scheme, it develops the smart TCM system that could improve the CNC machining precision and productivity significantly.

The nine papers in this special section focus on Big Data analytics in intelligent manufacturing systems. These systems can automatically adapt to changing environments and varying process requirements with minimal supervision and assistance from operators. It is essentially a cyber–physical production system that has enhanced intelligence due to learning, reasoning, adaptation, and decision making. The success of intelligent manufacturing relies on the timely acquisition, distribution, and utilization of various types of data from machines, manufacturing process, and products. The efficient use of big data can enhance the intelligence and automation of manufacturing process, provide high quality products and just-in-time production, and increase productivity and reduce costs. For example, by analyzing the factory floor data, equipment monitored data, and the enterprise manufacturing database, it could help to store, explore, and make complex decisions for the manufacturing system. While these big data topics have been widely discussed in the public media and the theory has been rigorously treated by statisticians and computer scientists from academia, little has been explored in the manufacturing research community from an engineering point of view. This special section aims to bridge the gap, and provides a platform for the communities to report recent findings and emerging research developments in the field.

Sparse decomposition has been successfully applied in manufacturing process condition monitoring. In the sparse decomposition-based approaches, the representation dictionary plays an important role. However, most current dictionary learning based methods do not consider the atoms corresponding to the specific states in the dictionary, and the coding coefficients lack discrimination between different states. This study develops an approach capable of multiscale dictionary learning for tool condition monitoring (TCM) and improving the discrimination power by maximizing the between-class and within-class coding coefficients. In addition, through the use of the discriminant distance without signal reconstruction, it enhances the state discrimination and increases the speed of online monitoring. The experimental results have validated the effectiveness of the approach with applications to micromilling TCM.

Securing multi-domain network performance monitoring (NPM) systems that are being widely deployed as `Measurement Infrastructure-as-a-Service' (MIaaS) in high-performance computing is becoming increasingly critical. It presents an emerging set of research challenges in cloud security given that security mechanisms such as policy-driven access to federated NPM services across multiple domains need to be designed carefully to protect MIaaS resources and data. In this paper, we advocate the design of a security middleground between default open/closed access settings and present policy-driven access controls of measurement functions for a multi-domain federation using a MIaaS. Our approach involves an analytical investigation based on a set of custom metrics to compare and contrast the legacy, role-based and more fine-grained, attribute-based access control schemes to design a security middleground. We implement the chosen middleground with a secured middleware, viz., “OnTimeSecure”. Our middleware enables `user-to-service' and `service-to-service' authentication, and enforces federated authorization entitlement policies for timely orchestration of MIaaS services. Lastly, we evaluate OnTimeSecure in a real multi-domain MIaaS testbed by performing threat modeling and security risk assessments to validate the analysis outcomes and demonstrate its effectiveness for easy integration and sustainable adoption.

In modern manufacturing, retrieval and reuse of the pre-existed three-dimensional (3-D) computer-aided design (CAD) models would greatly save time and cost in the product development cycle. For the 3-D CAD model retrieval, one is confronted with the quality of searching in large databases with models in complex structure and high dimension. This paper proposes a new 3-D model matching approach that reduces the data dimension and matches the models effectively. It is based on diffusion maps which integrate the random walk and anisotropic kernel to extract intrinsic features of models with complex geometries. The high-dimensional data points in diffusion space are projected into low-dimensional space and the low-dimension embedding coordinates are extracted as features. They are then used with the Grovmov Hausdorff distance for model retrieval. These coordinates could capture multiscale spectral properties of the 3-D geometry and have shown good robustness to noise. In the experiments, the proposed algorithm has shown better performance compared to the celebrated eigenmap approach in the 3-D model retrieval from the aspects of precision and recall.

The tool wear monitoring (TWM) system that could estimate tool wear conditions and predict remaining useful life (RUL) is important to meet the high precision requirement and improve productivity in automated machining. Due to its good properties in representing nonstationary and complex physical process, hidden semi-Markov Model (HSMM) is adapted to model the progressive tool wear in this paper. In order to describe the time-variant transition probability of tool wear states and the state duration dependency, the HSMM is improved by learning the duration parameters and RUL distribution database. The Forward algorithm is utilized for online tool wear estimation and remaining life prognosis, and an online implementation approach is developed to reduce computational cost. Experimental results show that the approach is effective and the proposed method of duration dependency modeling leads to more accurate TWM in high speed milling.

In the product life cycle, design reuse can save cost and improve existing products conveniently in most new product development. To retrieve similar models from big database, most search algorithms convert CAD model into a shape descriptor and compute the similarity two models according to a descriptor metric. This paper proposes a new 3D shape matching approach by matching the coordinates directly. It is based on diffusion maps which integrate the rand walk and graph spectral analysis to extract shape features embedded in low dimensional spaces and then they are used to form coordinations for non-linear alignment of different models. These coordinates could capture multi-scale properties of the 3D geometric features and has shown good robustness to noise. The results also have shown better performance compared to the celebrated Eigenmap approach in the 3D model retrieval.

Multi-domain network monitoring systems based on active measurements are being widely deployed in high-performance computing and other communities that support large-scale data transfers. Security mechanisms such as policy-driven access to related federated Network Performance Monitoring (NPM) services are important to protect measurement resources and data. In this paper, we present a novel, secure middleware framework viz., “OnTimeSecure” that enables `user-to-service' and `service-to-service' authentication, and enforces federated authorization entitlement policies for timely orchestration of NPM services. OnTimeSecure is built using RESTful APIs and features a hierarchical policy-engine that interfaces with a meta-scheduler for prioritization of measurement requests when there is contention of users concurrently attempting to utilize measurement resources. We validate OnTimeSecure in a federated multi-domain NPM infrastructure by performing threat modeling and security risk assessments based on overall attack likelihood and impact factors.