Predicting part deformation based on deformation force data using Physics-informed Latent Variable Model

Part deformation prediction and control is a crucial issue for obtaining tight dimensional accuracy so as to ensure product quality with high performance, and deformation prediction is the fundamental of the deformation control. However, existing machining deformation prediction methods are based on the prediction or measurement of residual stress and suffering from two challenges: (i) the measurement accuracy of residual stress field is limited by physical principle and (ii) low prediction in accuracy. In order to address these issues, this paper presents a method for predicting part machining deformation based on deformation force using the proposed Physics-informed Latent Variable Model involved physics knowledge. Deformation force is introduced to represent the inner unbalanced residual stress state of the workpiece, and it is a much easier and more accurate signal compared with residual stress. Machining deformation is predicted by fusing the data-driven method and the prior knowledge of deformation mechanical relationship by taking advantage of the latent variable. The proposed method was verified both in simulation and actual machining environment, and accurate machining deformation prediction has been achieved. The proposed method can be readily extended to the prediction problems involved with difficult-to-measure physical quantities.     

Online tool wear prediction system in the turning process using an adaptive neuro-fuzzy inference system

Tool wear is a detrimental factor that affects the quality and tolerance of machined parts. Having an accurate prediction of tool wear is important for machining industries to maintain the machined surface quality and can consequently reduce inspection costs and increase productivity. Online and real-time tool wear prediction is possible due to developments in sensor technology. Recently, various sensors and methods have been proposed for the development of tool wear monitoring systems. In this study, an online tool wear monitoring system was proposed using a strain gauge-type sensor due to its simplicity and low cost. A model, based on the adaptive network-based fuzzy inference system (ANFIS), and a new statistical signal analysis method, the I-kaz method, were used to predict tool wear during a turning process. In order to develop the ANFIS model, the cutting speed, depth of cut, feed rate and I-kaz coefficient from the signals of each turning process were taken as inputs, and the flank wear value for the cutting edge was an output of the model. It was found that the prediction usually accurate if the correlation of coefficients and the average errors were in the range of 0.989–0.995 and 2.30–5.08% respectively for the developed model. The proposed model is efficient and low-cost which can be used in the machining industry for online prediction of the cutting tool wear progression, but the accuracy of the model depends upon the training and testing data.     

应用前馈神经网络的大柔性机翼阵风响应分析

大柔性飞行器因结构重量低、柔性大使得机翼等部件在受载时产生较大的弹性变形,呈现显著的几何非线性效应,因此准确的结构大变形建模方法对于几何非线性气动弹性分析至关重要,而神经网络对非线性系统具有强大的拟合能力,可通过将神经网络应用于非线性结构建模,构造适用于结构大变形的前馈神经网络预测模型,在样本特征和数据结构相对较优的条件下结合曲面涡格法,搭建非线性气动弹性分析框架,对某机翼模型进行阵风响应计算;结果表明神经网络模型能准确预测大柔性机翼结构大变形,应用到气动弹性分析后能进行准确的阵风响应计算,验证了将神经网络应用到结构大变形预测的可行性,为以后机器学习技术与气动弹性分析结合的研究提供思路和方法。     

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.     

On the role of complexity in machining time estimation

Early cost estimation of machined parts is difficult as it requires detailed process information that is not usually available during product design. Parametric methods address this issue by estimating machining time from predictors related to design choices. One of them is complexity, defined as a function of dimensions and tolerances from an analogy with information theory. However, complexity has only a limited correlation with machining time unless restrictive assumptions are made on part types and machining processes. The objective of the paper is to improve the estimation of machining time by combining complexity with additional parameters. For this purpose, it is first shown that three factors that influence machining time (part size, area of machined features, work material) are not fully captured by complexity alone. Then an optimal set of predictors is selected by regression analysis of time estimates made on sample parts using an existing feature-based method. The proposed parametric model is shown to predict machining time with an average percentage error of 25% compared to the baseline method, over a wide range of part geometries and machining processes. Therefore, the model is accurate enough to support comparison of design alternatives as well as bidding and make-or-buy decisions.

     

ForceNet: An offline cutting force prediction model based on neuro-physical learning approach

Accurate cutting force prediction serves as an important reference to the optimization of numerically controlled machining process. Traditional cutting force modeling via theoretical cutting mechanism hampers accurate prediction for actual machining process due to its highly suppressed modeling flexibility. On the other hand, machine learning based modeling approaches demand large amount of diversified labeled samples to achieve comparable prediction results, while collecting these samples can be tedious and costly because the cutter workpiece engagement (CWE) keeps changing during actual process. This paper presents a cutting force prediction model, named ForceNet, which incorporates elementary physical priori into structured neural networks to predict cutting force for end-milling process of complex CWE. The main idea is to use grayscale images to represent CWE geometry, providing a universal input to the ForceNet. Unlike traditional deep neural networks served as an unexplainable black box, the core of the ForceNet is constructed by the vector summation of directional primitive cutting force elements, which are approximated using elementary neural networks. Preliminary results indicate that ForceNet outperformed existing methods not only with greater prediction accuracy in unseen cutting situations, but also with less training data needed thanks to its inherent neuro-physical structure.     

Research on multi-signal milling tool wear prediction method based on GAF-ResNext

A key aspect impacting the quality and efficiency of machining is the degree of tool wear. If the tool failure is not discovered in time, the quality of workpiece processing decreases, and even the machine tool itself may be harmed. To increase machining quality, efficiency and facilitate the intelligent advancement of the manufacturing industry, tool wear prediction is crucial. This research offers a multi-signal tool wear prediction method based on the Gramian angular field (GAF) and depth aggregation residual transform neural network (ResNext), enabling fast and accurate tool wear prediction. Specifically, the required one-dimensional signal is obtained through preprocessing including intercepting, splicing and wavelet threshold denoising of the force and vibration signals, and GAF is used to encode the obtained one-dimensional signal to generate a (224 × 224) data matrix. ResNext automatically extracts the features of the data matrix, establish the relationship between features and tool wear, and creates a tool wear prediction model based on GAF-ResNext. The ability of this method to predict tool wear has been trained and tested by milling experimental data. The experimental findings demonstrate the real-time, accuracy, dependability and universality of this method. This method has a better effect when compared to other research methods. The study's findings can boost machining productivity and offer technical support for intelligent tool wear early warning and intelligent manufacturing.     

Multi-layer integration framework for low carbon design based on design features

Global warming has currently become the most discussed environmental issue. The major portion of the carbon emission for a product is determined at the design stage of its life cycle. Given that products are made of parts, one of the major difficulties is that existing carbon emission assessment methods are machining process-oriented and lack association with design information, which makes it difficult to support low-carbon design. To address this problem, this paper develops a multi-layer integration framework for part low-carbon design based on the association mechanism among five layers, i.e., design feature, machining process, machining feature, operation feature, and carbon emission feature. The carbon emission assessment model of the part could be obtained by the method of top-down expansion and bottom-up assessment in terms of the design features through the developed framework. To obtain a low carbon design scheme, an improved differential evolution algorithm (IDE) with the multi-layer encoding method is proposed based on the hierarchical relationship of the framework, which aims to minimize the potential carbon emissions of parts and makespan of its machining processes. The proposed methodology is verified by the low carbon design of a flange plate.     

A New assembly precision prediction method of aeroengine high-pressure rotor system considering manufacturing error and deformation of parts

The accurate prediction of high-pressure rotor system assembly precision before assembly is the premise of improving aeroengine assembly quality and performance. The existing assembly precision prediction models (APPM) only consider the manufacturing error factors of parts, but rarely involve the deformation of parts under load, so there is a certain gap between the prediction results and the actual situation. This article studies the construction method of APPM considering the manufacturing error and deformation factors of parts. Firstly, the fitting algorithm is used to obtain the fitting deformation surface(FDS) of each mating surface under load, which provides the basis for constructing assembly error model considering manufacturing error and deformation of parts; secondly, according to the relative position relationship between the FDS and the datum plane, the error model of each mating surface of the assembly is effectively constructed by the small displacement torsor theory; thirdly, according to the different errors of each fitting end face, a prediction model of assembly precision for two rough surfaces is constructed by homogeneous coordinate transformation method; finally, a high-pressure compressor rotor system is used as an example to verify the effectiveness of the precision prediction model. The results show that the prediction results based on the proposed model are closer to the actual conditions. This paper provides an effective prediction model for high-pressure rotor system assembly precision, and has important application value for improving the assembly quality and performance of aeroengine.     

A Data-drivenParameter Planning Method for Structural Parts NC Machining

Structural parts are generallyused to compose the main load-bearing components in various mechanical products, and are usuallyproduced by NC machining where the machining parameters heavily determine the final production quality, efficiency and cost. Due to the complex structures and high precision requirements, a large amount of human interactions are usually required to modify the machining parameters generated by existing optimisation model-based or expert system-based methods, which will induce unstable machining quality and low efficiency. This paper proposes a data-driven methodfor machining parameter planning by learningthe parameter planning knowledge from thehigh-qualityhistorical processing files. An attribute graph is first defined to represent the part model. Then for each of the machining operations in the historical processing files, the machining parameters are correlated to a sub-graph that refers to the faces to be machined in this operation. By this way, a graph dataset of machining parameters could beconstructed from the historical processing files, and graph neural networks (GNN) are established to learn the planning models for machining parameters. The proposed method provides an end-to-end strategy for constructing machining parameter planning models thus human interactions can be greatly reduced and the performance of the models are able to be improved as the increase in historical processing files. In the case study, the historical processing files of aircraft structural parts machining are used to train the GNN models for planning cutting width, cutting depth and machining feedrate, and the prediction accuracies reach 95.50%, 94.79%, 95.02% respectively.     

A comparison of several neural networks to predict the execution times in injection molding production for automotive industry

In the industrial environment, specifically in the automotive industry, an accurate prediction of execution times for each production task is very useful in order to plan the work and to optimize the human, technical and material resources. In this paper, we applied several regression neural networks to predict the execution times of the tasks in the production of parts for plastic injection molds. These molds are used to make a variety of car components in automotive industry. The prediction is based on the geometric features of the mold parts to be made. The accuracy of the predicted times is high enough to be used as a tool for the design stage of the mold parts, e.g. guiding the design process in order to get the lowest production time.     

Dimensional and geometrical errors of three-axis CNC milling machines in a virtual machining system

Virtual machining systems are applying computers and different types of software in manufacturing and production in order to simulate and model errors of real environment in virtual reality systems. Many errors of CNC machine tools have an effect on the accuracy and repeatability of part manufacturing. Some of these errors can be reduced by controlling the machining process and environmental parameters. However geometrical errors which have a big portion of total error need more attention. In this paper a virtual machining system which simulates the dimensional and geometrical errors of real three-axis milling machining operations is described. The system can read the machining codes of parts and enforce 21 errors associated with linear and rotational motion axes in order to generate new codes to represent the actual machining operation. In order to validate the system free form profiles and surfaces of virtual and real machined parts are compared in order to present the reliability and accuracy of the software.     

基于AFSA—BP神经网络的基坑变形预测模型研究

为改善BP神经网络收敛速度慢、初始权阈值对计算结果影响较大且易陷入局部最优等缺陷,为提高模型的预测精度和稳定性,使用具有全局优化能力的鱼群算法优化BP神经网络的初始权阈值,依托工程实例,将BP模型及改进的模型用于基坑变形预测中,通过预测值与实测值进行对比,结果表明：AFSA-BP模型的预测精度要高于BP模型,且预测结果稳定、预测速度较快、预测误差可以满足工程的要求,对于下一步施工具有良好的指导作用,所以AFSA-BP模型是一种有效的基坑变形预测模型。     

An optimized combination prediction model for concrete dam deformation considering quantitative evaluation and hysteresis correction

Certain degree of deformation is natural while dam operates and evolves. Due to the impact of internal and external environment, dam deformation is highly nonlinear by nature. For dam safety, it is of great significance to analyze timely deformation monitoring data and be able to predict reliably deformation. A comprehensive review of existing deformation prediction models reveals two issues that deserves further attention: (1) each environmental influencing factor contributes differently to deformation, and (2) deformation lags behind environmental factors (e.g., water level and air temperature). In response, this study presents a combination deformation prediction model considering both quantitative evaluation of influencing factors and hysteresis correction in order to further improve estimation accuracy. In this study, the complex relationship in deformation prediction is effectively captured through support vector machine (SVM) modeling. Furthermore, a modified fruit fly optimization algorithm (MFOA) is presented for SVM hyper-parameter optimization. Also, a synthetic evaluation method and a hysteresis quantification algorithm are introduced to further enhance the MFOA-SVM-based model in regards to contribution quantification and phase correction respectively. The accuracy and validity of the proposed model is evaluated in a concrete dam case, where its performance is compared with other existing models. The simulated results indicated that the proposed nonlinear MFOA-SVM model considering both quantitative evaluation and hysteresis correction, abbreviated as SEV-MFOA-SVM, is more accurate and robust than conventional models. This novel model also provides an alternative method for predicting and analyzing dam deformation and evolution behavior of other similar hydraulic structures.     

机床主轴热误差建模算法*

针对机床主轴热误差补偿过程中现有建模方法的不足,提出一种新的热误差建模算法。首先应用FCM算法将众多温度测点予以分类,减少测点数量,提高测量精度。其次应用GCA算法对同类测点的热敏感度进行排序,选出该类中的关键测点。最后以优选出的测点为输入变量,以热位移为输出变量,利用ANFIS进行热误差模型设计,并与BP算法建立的模型进行了比较。实验数据表明：该方法降低了机床热误差,具有预测精度高的优点,能较好的实现机床主轴热误差的补偿。     

Digital twin-driven clamping force control for thin-walled parts

Clamping quality is one of the main factors that will affect the deformation of thin-walled parts during their processing, which can then directly affect parts’ performance. However, traditional clamping force settings are based on manual experience, which is a random and inaccurate manner. In addition, dynamic clamping force adjustment according to clamping deformation is rarely considered in clamping force control process, which easily causes large clamping deformation and low machining accuracy. To address these issues, this study proposes a digital twin-driven clamping force control approach to improve the machining accuracy of thin-walled parts. The total factor information model of clamping system is built to integrate the dynamic information of the clamping process. The virtual space model is constructed based on finite element simulation and deep neural network algorithm. To ensure bidirectional mapping of physical-virtual space, the workflow of clamping force control and interoperability method between digital twin models are elaborated. Finally, a case study is used to verify the effectiveness and feasibility of the proposed method.     

基于EMD-GAELM-ARIMA算法的大坝变形预测

In view of the fact that it is difficult for statistical models to make good predictions of nonlinear and non-stationary dam deformation, artificial intelligence algorithms are induced. The empirical mode decomposition method (EMD), genetic algorithm (GA) optimized extreme learning machine (ELM), and ARIMA error correction model were used to construct a dam deformation prediction model. First this paper uses EMD to decompose and reconstruct the monitoring data to stabilize it and obtain eigenmode functions and residual sequences with physical significance; then uses GAELM to analyze and predict the decomposition results; finally, uses ARIMA model to correct errors. Taking a concrete rockfill dam as an example, the dam deformation prediction model constructed by the optimization algorithm is used to analyze and predict it. The analysis results show that the EMD-GAELM-ARIMA model algorithm has higher prediction accuracy than the traditional single algorithm. It is feasible in dam deformation prediction.     

Prediction simulation of sports injury based on embedded system and neural network

Sports injury prediction is one of the most important parts of the challenge of prevention and harm challenging in motion. Sports injury contemplated wherein a simplified view of the phenomenon to study the reduction unit's cause. A linear analysis is viewed as the unidirectional manner a substantial portion of, and causality. This reduction method depends on the correlation and regression analysis. Despite the extensive efforts to predict sports injuries, the existing method is the inability to identify the predictors that were and have been limited. The risk of the very important element for sports players' injury when developing prevention and risk mitigation strategies for work-related accidents. Some signs can be used in many ways to identify risk factors for injury. However, it can be made from the data and lead to incorrect inferences and difficulty understanding the nuances of different statistical methods. The proposed Neural Network (NN) and the embedded system classify the sports player's injury prediction to solve the problem. The proposed Neural Network (NN) and the embedded system have attracted a simple calculation and interpretation of the reliable results for sports injury prediction. The simulation results show the high performance compared to other existing methods.     

Zigzag machining surface roughness modelling using evolutionary approach

Milling is one of the common machining methods that cannot be abandoned especially for machining of metallic materials. The cutters with appropriate cutting parameters remove material from the workpiece. Surface roughness has the major influence on both obtaining dimensional accuracy and quality of the product. A number of cutter path strategies are employed to obtain the required surface quality. Zigzag machining is one of the mostly appealing cutting processes. Modeling of surface roughness with traditional methods often results in inadequate solutions and can be very costly in terms of the efforts and the time spent. In this research Genetic Programming (GP) has employed to predict a surface roughness model based on the experimental data. The model has produced an accuracy of 86.43%. In order to compare GP performance, Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) techniques were utilized. It was seen that the surface roughness model produced by GP not only outperforms but also enables to produce more explicit models than of the other techniques. The effective parameters can easily be investigated based on the appearances in the model and they can be used in prediction of surface roughness in zigzag machining process.     

夹紧顺序、夹具布局和夹紧力对装夹变形影响与同步优化分析研究

为减小工件装夹变形,提高薄壁件加工精度,以薄壁零件装夹变形最小化为目标 函数,通过遗传算法和有限元方法相结合,提出夹紧顺序、装夹布局和夹紧力同步分析方法。用 该方法对一航空薄壁零件装夹进行优化分析,优化结果与经验设计及传统分析结果进行对比,有 效地降低了工件因装夹不当引起的变形,验证了夹紧顺序、夹具布局和夹紧力同步优化方法的 有效性。