A systematic literature review of machine learning methods applied to predictive maintenance

Chatter suppression techniques in metal cutting

Effects of Minimum Quantity Lubrication (MQL) in machining processes using conventional and nanofluid based cutting fluids: A comprehensive review

Energy consumption model and energy efficiency of machine tools: a comprehensive literature review

In this paper, the use of the combined deterministic-stochastic subspace identification algorithm for the experimental modal analysis of mechanical structures is discussed. The algorithm requires artificial forces to be applied to the structure, so it can be used for experimental modal analysis (EMA). The algorithm can also be used for operational modal analysis (OMA), since the excitation level of the artificial force(s) can be low compared to the excitation level of the ambient forces. Both the modes that are artificially excited and those that are excited by the ambient forces are identified. This type of operational modal analysis is called an OMAX analysis (Operational Modal Analysis with eXogenous inputs) [1]. The main advantages of OMAX over OMA are that the modes that are excited by the artificial forces can be scaled to unity modal mass and that a higher number of modes can be identified.

Reference-based combined deterministic-stochastic subspace identification for experimental and operational modal analysis

In modern digital manufacturing, nearly 79.6% of the downtime of a machine tool is caused by its mechanical failures. Predictive maintenance (PdM) is a useful way to minimize the machine downtime and the associated costs. One of the challenges with PdM is early fault detection under time-varying operational conditions, which means mining sensitive fault features from condition signals in long-term running. However, fault features are often weakened and disturbed by the time-varying harmonics and noise during a machining process. Existing analysis methods of these complex and diverse data are inefficient and time-consuming. This paper proposes a novel method for early fault detection under time-varying conditions. In this study, a deep learning model is constructed to automatically select the impulse responses from the vibration signals in long-term running of 288 days. Then, dynamic properties are identified from the selected impulse responses to detect the early mechanical fault under time-varying conditions. Compared to traditional methods, the experimental results in this paper have proved that our method was not affected by time-varying conditions and showed considerable potential for early fault detection in manufacturing.

Early Fault Detection of Machine Tools Based on Deep Learning and Dynamic Identification

The dynamic characteristics of joint interfaces affect the dynamic behaviors of a whole machine tool structure notably. An analytic method of virtual material hypothesis-based dynamic modeling on fixed joint interface in machine tools was conducted so as to improve the modeling accuracy of whole machine tools. The microcontact part of two contact surfaces in fixed joint interface was assumed as a virtual isotropic material, which is rigidly connected with two components composing fixed joint interface. The interaction between normal and tangential characteristics of fixed interface was taken into account, a set of analytic solutions of elastic modulus, shear modulus, Poisson ratio and density was deduced from virtual material by adopting Hertz contact theory and fractal theory. Using the finite element structural dynamic modeling approach in existence, when some parameters of material’s elastic modulus, Poisson ratio, density, etc. are known, the dynamic model for virtual material composing a component could be established; therefore, the dynamic model for whole structure, including joint interface, would be obtained. The theoretical mode shapes were compared with the experimental ones (qualitative comparison of similar mode shape and quantitative comparison of the corresponding natural frequency). The comparison results show that the theoretical mode shapes are in excellent agreement with the experimental ones. The relative errors between the theoretical natural frequencies and the experimental ones are less than 9%. The good agreements of theoretical results with experimental ones confirm analytic solutions for virtual material’s parameters. The present solutions would be useful to the precise dynamic modeling of fixed joint interfaces in CNC machine tools in practice.

A new method of virtual material hypothesis-based dynamic modeling on fixed joint interface in machine tools

Dynamic properties of the whole machine tool structure including tool, spindle, and machine tool frame contribute greatly to the reliability of the machine tool in service and machining quality. However, they will change during operation compared with the results from static frequency response function measurements of classic experimental modal analysis. Therefore, an accurate estimation of the dynamic modal parameters of the whole structure is of great value in real time monitoring, active maintenance, and precise prediction of a stability lobes diagram. Operational modal analysis (OMA) developed from civil engineering works quite efficiently in modal parameters estimation of structure in operation under an intrinsic assumption of white noise excitation. This paper proposes a new methodology for applying this technique in the case of computer numerically controlled (CNC) machine tools during machining operations. A novel random excitation technique based on cutting is presented to meet the white noise excitation requirement. This technique is realized by interrupted cutting of a narrow workpiece step while spindle rotating randomly. The spindle rotation speed is automatically controlled by G-code part program, which contains a series of random speed values produced by MATLAB software following uniform distribution. The resulting cutting produces random pulses and excites the structure in all three directions. The effect of cutting parameters on the excitation frequency and energy was analyzed and simulated. The proposed technique was experimentally validated with two different OMA methods: the Stochastic Subspace Identification (SSI) method and the poly-reference least square complex frequency domain (pLSCF or PolyMAX) method, both of which came up with similar results. It was shown that the proposed excitation technique combined successfully with OMA methods to extract dynamic modal parameters of the machine tool structure.

Estimation of CNC machine–tool dynamic parameters based on random cutting excitation through operational modal analysis

Tool condition monitoring is critical in ultraprecision manufacturing in order to optimize the performance of the overall process, while maintaining the desired part quality. Recently, deep learning has been successfully applied to numerous classification tasks in manufacturing, often to forecast part quality. In this paper, a novel deep learning data-driven modeling framework is presented, which includes a fusion of multiple stacked sparse autoencoders for tool condition monitoring in ultraprecision machining. The proposed computational framework consists of two main structures. First, a training model that is designed with the ability to process multiple parallel feature spaces to learn the lower-level features. Second, a feature fusion structure that is used to learn the higher-level features and associations to tool wear. To achieve this learning structure, a modified loss function is utilized that enhances the feature extraction and classification tasks. A dataset from a real manufacturing process is used to demonstrate the performance of the proposed framework. Experimental results and simulations show that the proposed method successfully classifies the ultraprecision machining case study with over 96% accuracy, while also outperforming comparable methodologies.

/pdf/using-multiple-feature-spaces-based-deep-learning-for-tool-4idc3ohsf0.pdf

Using Multiple-Feature-Spaces-Based Deep Learning for Tool Condition Monitoring in Ultraprecision Manufacturing

Product configuration is one of the key technologies in the environment of mass customization. Traditional product configuration technology focuses on constraints-based or knowledge-based application, which makes it very difficult to optimize design of product configuration. In this paper, an approach based on multiobjective genetic algorithm is proposed to solve the problem. Firstly, a configuration-oriented product model is discussed. A multiobjective optimization problem of product configuration according to the model is described and its mathematical formulation is designed. Secondly, a multiobjective genetic algorithm is designed for finding near Pareto or Pareto optimal set for the problem. A matrix method used to check constraint is proposed, and the coding and decoding representation of the solution are designed, then a new genetic evaluation and select mechanism is proposed. Finally, performance comparison of the proposed genetic algorithm with three other genetic algorithms is made. The result shows that the proposed genetic algorithm outperforms the other genetic algorithms in this problem.

Bin Li

Papers

Early Fault Detection of Machine Tools Based on Deep Learning and Dynamic Identification

A new method of virtual material hypothesis-based dynamic modeling on fixed joint interface in machine tools

Estimation of CNC machine–tool dynamic parameters based on random cutting excitation through operational modal analysis

Using Multiple-Feature-Spaces-Based Deep Learning for Tool Condition Monitoring in Ultraprecision Manufacturing

Product configuration optimization using a multiobjective genetic algorithm