A perturbation signal based data-driven Gaussian process regression model for in-process part quality prediction in robotic countersinking operations

A typical manufacturing process consists of a machining (material removal) process followed by an inspection system for the quality checks. Usually these checks are performed at the end of the process and they may also involve removing the part to a dedicated inspection area. This paper presents an innovative perturbation signal based data generation and machine learning approach to build a robust process model with uncertainty quantification. The model is to map the in-process signal features collected during machining with the post-process quality results obtained upon inspection of the finished product. In particular, a probabilistic framework based on Gaussian Process Regression (GPR) is applied to build the process model that accurately and reliably predicts key process quality indicators. Raw data provided by multiple sensors including accelerometers, power transducers and acoustic emissions is first collected and then processed to extract a large number of signal features from both time and frequency domains. A strategy for the selection of most relevant features is also explored in this work in order to reduce the input space dimension and achieve faster training times. The proposed GPR model was tested on a multi-robot countersinking application for monitoring of the machined countersink depths in composite aircraft components. Experimental results showed that the model can be used as a tool to predict the part quality through in-process sensory information, which in turn, helps to reduce the total inspection time by identifying the parts that would require further investigation.     

In-process tool condition forecasting based on a deep learning method

It is widely acknowledged that machining precision and surface integrity are greatly affected by cutting tool conditions. In order to enable early cutting tool replacement and proactive actions, tool wear conditions should be estimated in advance and updated in real-time. In this work, an approach to in-process tool condition forecasting is proposed based on a deep learning method. A long short-term memory network is designed to forecast multiple flank wear values based on historical data. A residual convolutional neural network is built to enable in-process tool condition monitoring, using raw signals acquired during the machining process. The integration of them enables in-process tool condition forecasting. Median-based correction and mean-based correction are adopted to improve the accuracy. IEEE PHM 2010 challenge data has been used to illustrate and validate this approach. Experimental study and quantitative comparisons showed that future flank wear values could be precisely forecasted during the machining process. The proposed approach contributes to prompt and reliable cutting tool condition forecasting, which will support the decision-making about cutting tool replacement in data-driven smart manufacturing.     

A knowledge base model for complex forging die machining

Recent evolutions on forging process induce more complex shape on forging die. These evolutions, combined with High Speed Machining (HSM) process of forging die lead to important increase in time for machining preparation. In this context, an original approach for generating machining process based on machining knowledge is proposed in this paper. The core of this approach is to decompose a CAD model of complex forging die in geometrical features. Technological data and topological relations are aggregated to a geometrical feature in order to create machining features. Technological data, such as material, surface roughness and form tolerance are defined during forging process and dies design. These data are used to choose cutting tools and machining strategies. Topological relations define relative positions between the surfaces of the die CAD model. After machining features identification cutting tools and machining strategies currently used in HSM of forging die, are associated to them in order to generate machining sequences. A machining process model is proposed to formalize the links between information imbedded in the machining features and the parameters of cutting tools and machining strategies. At last machining sequences are grouped and ordered to generate the complete die machining process. In this paper the identification of geometrical features is detailed. Geometrical features identification is based on machining knowledge formalization which is translated in the generation of maps from STL models. A map based on the contact area between cutting tools and die shape gives basic geometrical features which are connected or not according to the continuity maps. The proposed approach is illustrated by an application on an industrial study case which was accomplished as part of collaboration.     

A flexible and effective NC machining process reuse approach for similar subparts

NC machining process reuse is widely accepted as an effective strategy for engineers to generate the process plan with less time and lower cost. However, there has been very little research on how to reuse the NC machining process of similar subparts. As a result, most reusable NC machining process still has to remain in the repository as tacit knowledge, which can easily get lost due to oblivion. This paper proposes a novel NC machining process reuse approach for similar subparts in which existing NC machining process cases are described in association with machining features. First, a feature-based parameter-driven model is established to formalize the links between information imbedded in the machining feature and the parameters of cutting tools, drive geometries, and machining strategies. Then, the NC process parameter-driven characteristic of similar feature is revealed from the perspective of machining geometry, machining precision of the feature, and cutter geometry. Moreover, an NC process reusability assessment approach of similar pocket/subpart is presented using the pocket’s medial axis transform. Finally, the NC machining process inheritance mechanisms are explored to implement the NC machining process reuse automatically and efficiently. A prototype system based on CATIA has been developed to verify the effectiveness of the proposed approach.     

Local identifiability and sensitivity analysis of neuromuscular blockade and depth of hypnosis models

This paper addresses the local identifiability and sensitivity properties of two classes of Wiener models for the neuromuscular blockade and depth of hypnosis, when drug dose profiles like the ones commonly administered in the clinical practice are used as model inputs. The local parameter identifiability was assessed based on the singular value decomposition of the normalized sensitivity matrix. For the given input signal excitation, the results show an over-parameterization of the standard pharmacokinetic/pharmacodynamic models. The same identifiability assessment was performed on recently proposed minimally parameterized parsimonious models for both the neuromuscular blockade and the depth of hypnosis. The results show that the majority of the model parameters are identifiable from the available input–output data. This indicates that any identification strategy based on the minimally parameterized parsimonious Wiener models for the neuromuscular blockade and for the depth of hypnosis is likely to be more successful than if standard models are used.     

Identifiability and identification of a Synthesis Load Model

A Synthesis Load Model (SLM) including both the power load and the distribution network has been proposed in the references. The identifiability of SLM is analyzed at first, it is concluded that the model parameters are identifiable if one of the resistance, reactance and the ratio of them is known. The conclusion is validated through a simulation example. A strategy for parameter identification of SLM is proposed with the combination of the component based approach and the measurement based approach. Durin...     

Nonlinear predictive control of irregularly sampled multirate systems using blackbox observers

This work aims the development of an inferential nonlinear model predictive control (NMPC) scheme based on a nonlinear fast rate model that is identified from irregularly sampled multirate data, which is corrupted with unmeasured disturbances and measurement noise. The model identification is carried out in two steps. In the first step, a MISO fast rate nonlinear output error (NOE) model is identified from the irregularly sampled output data. In the second step, a time varying nonlinear auto-regressive (NAR) type model is developed using the residuals generated in the first step. The deterministic and stochastic components of the observer are parameterized using generalized ortho-normal basis filters (GOBF). The identified NOE and NAR models are combined to form MISO state observers. We then proceed to use these identified observers to formulate a nonlinear MPC strategy for controlling irregularly sampled multirate systems. The identified observers are used to generate inter-sample estimates of the irregularly sampled outputs and for performing future trajectory predictions. The efficacy of the proposed modeling and control scheme is demonstrated using simulations on a benchmark continuous fermentation process. This process exhibits input multiplicity and change in the sign of steady state gain in the operating region. The validity of the proposed modeling and control scheme is also established by conducting identification and control experiments on a laboratory scale heater-mixer setup. The proposed NMPC gives satisfactory regulatory as well as servo performance over a wide operating range in the irregularly sampled multirate scenario.     

Mechanistic modelling of the milling process using an adaptive depth buffer

A mechanistic model of the milling process based on an adaptive and local depth buffer is presented. This mechanistic model is needed for speedy computations of the cutting forces when machining surfaces on multi-axis milling machines. By adaptively orienting the depth buffer to match the current tool axis, the need for an extended Z-buffer is eliminated. This allows the mechanistic model to be implemented using standard graphics libraries, and gains the substantial benefit of hardware acceleration. Secondly, this method allows the depth buffer to be sized to the tool as opposed to the workpiece, and thus improves the depth buffer size to accuracy ratio drastically. The method calculates tangential and radial milling forces dependent on the in-process volume of material removed as determined by the rendering engine depth buffer. The method incorporates the effects of both cutting and edge forces and accounts for cutter runout. The simulated forces were verified with experimental data and found to agree closely. The error bounds of this process are also determined.     

Digital twin modeling method based on biomimicry for machining aerospace components

High-performance aerospace component manufacturing requires stringent in-process geometrical and performance-based quality control. Real-time observation, understanding and control of machining processes are integral to optimizing the machining strategies of aerospace component manufacturing. Digital Twin can be used to model, monitor and control the machining process by fusing multi-dimensional in-context machining process data, such as changes in geometry, material properties and machining parameters. However, there is a lack of systematic and efficient Digital Twin modeling method that can adaptively develop high-fidelity multi-scale and multi-dimensional Digital Twins of machining processes. Aiming at addressing this challenge, we proposed a Digital Twin modeling method based on biomimicry principles that can adaptively construct a multi-physics digital twin of the machining process. With this approach, we developed multiple Digital Twin sub-models, e.g., geometry model, behavior model and process model. These Digital Twin sub-models can interact with each other and compose an integrated true representation of the physical machining process. To demonstrate the effectiveness of the proposed biomimicry-based Digital Twin modeling method, we tested the method in monitoring and controlling the machining process of an air rudder.     

A time-varying geometry modeling method for parts with deformation during machining process

Deformation due to residual stress is a significant issue during the machining of thin-walled parts with low rigidity. If there are multiple processes with deformation during machining, some process suitability issues will appear. On this occasion, the actual geometric state of the deformed workpiece is needed for process adjustment. However, it is still a challenge to obtain the complete geometry information of deformed workpiece accurately and efficiently. In order to address this issue, a time-varying geometry modeling method, combining cutting simulation and in-process measurement, is proposed in this paper. The deformed workpiece model can be reconstructed via transforming the deformed workpiece with only a small amount of the measurement points by superimposing material removal and workpiece deformation simulation according to a time sequence, which takes advantage of the proposed Curved Surface Mapping based Geometric Representation Model (CSMGRM). Machining experiment of a typical structural part has shown that the deformed geometry model of the whole workpiece can be reconstructed within the error of 0.05mm, which is less than one tenth of the finish machining allowance in general cases, and it is sufficient to meet the accuracy requirements for interference or overcut/undercut analysis and process adjustment.     

Polygon subdivision for pocket machining process planning

This paper presents a new approach to improve tool selection for arbitrary shaped pockets based on an approximate polygon subdivision technique. The pocket is subdivided into smaller sub-polygons and tools are selected separately for each sub-polygon. A set of tools for the entire pocket is obtained based on both machining time and the number of tools used. In addition, the sub-polygons are sequenced to eliminate the requirement of multiple plunging operations. In process planning for pocket machining, selection of tool sizes and minimizing the number of plunging operations can be very important factors. The approach presented in this paper is an improvement over previous work in its use of a polygon subdivision strategy to improve the machining time as well as reducing the number of plunges. The implementation of this technique suggests that using a subdivision approach can reduce machining time when compared to solving for the entire polygonal region.     

永磁同步电机多采样率EKF转速辨识

永磁同步电机（Permanent Magnet Synchronous Motor,PMSM）具有响应快、高精度、高转矩比等诸多优点,同时无传感器控制策略研究能有效提高PMSM系统的简易性和鲁棒性。在分析EKF和多采样率数字控制系统的基础上,建立永磁同步电机输入多采样率EKF算法,将其用于转速估计。通过仿真和实时实验验证其算法在辨识精度及收敛稳定性方面均优于单采样率EKF算法,并和高频单采样率EKF有着一致的辨识效果,而多采样率EKF算法的数据量及运算量均小于高频单采样率EKF。     

铅锌烧结过程烧穿点的集成预测模型

针对影响铅锌烧结过程烧穿点的因素具有不确定性的特点, 提出一种基于信息熵技术的烧穿点集成预测模型. 首先利用软测量技术获得烧穿点. 然后建立基于满意聚类的T-S预测模型以降低不确性因素所带来的影响,并将共轭梯度法和粒子群优化算法有机结合起来进行T-S模型中各个子模型的参数辨识, 以提高辨识精度. 接着建立基于工艺参数的神经网络预测模型. 最后考虑到信息熵技术具有信息融合和降低不确定性的能力, 利用其将以上预测模型进行集成. 实验结果表明所提出的集成预测模型具有较高的预测精度和较强的适应性.     

An expert system for setting parameters in machining processes

In this paper, an hybrid system is proposed for setting machining parameters from experimental data. A symbolic regression alpha–beta is used to build mathematical models. Every model is validated using statistical analysis then evolutionary computation is used to minimize or maximize the generated model. Symbolic regression α–β is used to build mathematical models by estimation of distribution algorithms. A practical case considering measured data of two machining process on three materials are used to illustrate the utility of the expert system because generates a set of parameters that improve the machining process.     

An intelligent decision-making strategy based on the forecast of abnormal operating mode for iron ore sintering process

The abnormal operating mode of the iron ore sintering process will produce sinter ore with low yield and poor quality. It is of high economic value to ensure that the sintering process runs under normal operating mode. An intelligent decision-making strategy based on the forecast of the abnormal operating mode for the iron ore sintering process is presented in this paper. First, a fuzzy rule-based model is used to construct the forecast model of operating mode, of which inputs are selected by the one-way analysis of variance. Then, an intelligent decision-making strategy for operating parameters is proposed based on the priority. Finally, experiments are performed by using the actual running data collecting from the industrial site. The originality of this study comes with establishing a fuzzy rule-based model to forecast the operating mode and designing an intelligent decision-making strategy based on priority to improve the abnormal operating mode. The result shows that the constructed forecast model of operating mode forecasts well in abnormal operating mode. The proposed intelligent decision-making strategy can effectively improve abnormal operating mode, which has a good application prospect in the iron ore sintering process.     

Feature-based generation of machining process plans for optimised parts manufacture

Efficacious integration of such CAx technologies as CAD, CAM and CAPP still remains a problem in engineering practice which constantly attracts research attention. Design by feature model is assumed as a main factor in the integration effort in various engineering and manufacturing domains. It refers principally to feature clustering and consequently operation sequencing in elaborated process plan designs. The focus of this paper is on CAPP for parts manufacture in systems of definite processing capabilities, involving multi-axis machining centres. A methodical approach is proposed to optimally solve for process planning problems, which consists in the identification of process alternatives and sequencing adequate working steps. The approach involves the use of the branch and bound concept from the field of artificial intelligence. A conceptual scheme for generation of alternative process plans in the form of a network is developed. It is based on part design data modelling in terms of machining features. A relevant algorithm is proposed for creating such a network and searching for the optimal process plan solution from the viewpoint of its operational performance, under formulated process constraints. The feasibility of the approach and the algorithm are illustrated by a numerical case with regard to a real application and diverse machine tools with relevant tooling. Generated process alternatives for complex machining with given systems, are studied using models programmed in the environment of Matlab^® software.     

输入多采样率离散时间系统准滑模控制器设计

针对不确定离散时间系统,结合多采样率控制理论,提出一种输入多采样率准滑模控制方法。该方法在状态损失数据下,考虑系统不确定干扰,有效利用多率输入量,缩窄系统的准滑模带宽,增强系统鲁棒性,改善系统动态品质。通过仿真实验验证了所提出方法的有效性。     

Digital twin-driven surface roughness prediction and process parameter adaptive optimization

In the process of parts machining, the real-time state of equipment such as tool wear will change dynamically with the cutting process, and then affect the surface roughness of parts. The traditional process parameter optimization method is difficult to take into account the uncertain factors in the machining process, and cannot meet the requirements of real-time and predictability of process parameter optimization in intelligent manufacturing. To solve this problem, a digital twin-driven surface roughness prediction and process parameter adaptive optimization method is proposed. Firstly, a digital twin containing machining elements is constructed to monitor the machining process in real-time and serve as a data source for process parameter optimization; Then IPSO-GRNN (Improved Particle Swarm Optimization-Generalized Regression Neural Networks) prediction model is constructed to realize tool wear prediction and surface roughness prediction based on data; Finally, when the surface roughness predicted based on the real-time data fails to meet the processing requirements, the digital twin system will warn and perform adaptive optimization of cutting parameters based on the currently predicted tool wear. Through the development of a process-optimized digital twin system and a large number of cutting tests, the effectiveness and advancement of the method proposed in this paper are verified. The organic combination of real-time monitoring, accurate prediction, and optimization decision-making in the machining process is realized which solves the problem of inconsistency between quality and efficiency of the machining process.     

In-process regressions and adaptive multicriteria neural networks for monitoring and supervising machining operations

The authors develop a monitoring and supervising system for machining operations using in-process regressions (for monitoring) and adaptive feedforward artificial neural networks (for supervising). The system is designed for: (1) in-process tool life measurement and prediction; (2) supervision of machining operations in terms of the best machining setup; and (3) catastrophic tool failure monitoring. The monitoring system predicts tool life by using different sensors for gathering information based on a regression model that allows for the variations between tools and different machine setups. The regression model makes its prediction by using the history of other tools and combining it with the information obtained about the tool under consideration. The supervision system identifies the best parameters for the machine setup problem within the framework of multiple criteria decision making. The decision maker (operator) considers several criteria, such as cutting quality, production rate and tool life. To make the optimal decision with several criteria, an adaptive feedforward artificial neural network is used to assess the decision maker's preferences. The authors' neural network approach learns from the decision maker's complex behavior and hence, in automatic mode, can make decisions for the decision maker. The approach is not computationally demanding, and experiments demonstrate that its predictions are accurate.