The quality of the exposed avionics solder joints has a significant impact on the stable operation of the in-orbit spacecrafts. Nevertheless, the previously reported inspection methods for multi-scale solder joint defects generally suffer low accuracy and slow detection speed. Herein, a novel real-time detector VMMAO-YOLO is demonstrated based on variable multi-scale concurrency and multi-depth aggregation network (VMMANet) backbone and “one-stop” global information gather-distribute (OS-GD) module. Combined with infrared thermography technology, it can achieve fast and high-precision detection of both internal and external solder joint defects. Specifically, VMMANet is designed for efficient multi-scale feature extraction, which mainly comprises variable multi-scale feature concurrency (VMC) and multi-depth feature aggregation-alignment (MAA) modules. VMC can extract multi-scale features via multiple fix-sized and deformable convolutions, while MAA can aggregate and align multi-depth features on the same order for feature inference. This allows the low-level features with more spatial details to be transmitted in depth-wise, enabling the deeper network to selectively utilize the preceding inference information. The VMMANet replaces inefficient high-density deep convolution by increasing the width of intermediate feature levels, leading to a salient decline in parameters. The OS-GD is developed for efficacious feature extraction, aggregation and distribution, further enhancing the global information gather and deployment capability of the network. On a self-made solder joint image data set, the VMMAO-YOLO achieves a mean average precision mAP@0.5 of 91.6%, surpassing all the mainstream YOLO-series models. Moreover, the VMMAO-YOLO has a body size of merely 19.3 MB and a detection speed up to 119 frame per second, far superior to the prevalent YOLO-series detectors.
The smart toolholder is the core component in the development of intelligent and precise manufacturing. It enables in situ monitoring of cutting data and machining accuracy evolution and has become a focal point in academic research and industrial applications. However, current table and rotational dynamometers for milling force, vibration, and temperature testing suffer from cumbersome installation and provide only a single acquisition signal, which limits their use in laboratory settings. In this study, we propose a wireless smart toolholder with multi-sensor fusion for simultaneous sensing of milling force, vibration, and temperature signals. We select force, vibration, and temperature sensors suitable for smart toolholder fusion to adapt to the cutting environment. Thereafter, structural design, circular runout, dynamic balancing, static stiffness, and dynamic inherent frequency tests are conducted to assess its dynamic and static performance. Finally, the smart toolholder is tested for accuracy and repeatability in terms of force, vibration, and temperature. Experimental results demonstrate that the smart toolholder accurately captures machining data with a relative deviation of less than 1.5% compared with existing force gauges and provides high repeatability of milling temperature and vibration signals. Therefore, it is a smart solution for machining condition monitoring.
In fiber laser beam welding (LBW), the selection of optimal processing parameters is challenging and plays a key role in improving the bead geometry and welding quality. This study proposes a multi-objective optimization framework by combining an ensemble of metamodels (EMs) with the multi-objective artificial bee colony algorithm (MOABC) to identify the optimal welding parameters. An inverse proportional weighting method that considers the leave-one-out prediction error is presented to construct EM, which incorporates the competitive strengths of three metamodels. EM constructs the correlation between processing parameters (laser power, welding speed, and distance defocus) and bead geometries (bead width, depth of penetration, neck width, and neck depth) with average errors of 10.95%, 7.04%, 7.63%, and 8.62%, respectively. On the basis of EM, MOABC is employed to approximate the Pareto front, and verification experiments show that the relative errors are less than 14.67%. Furthermore, the main effect and the interaction effect of processing parameters on bead geometries are studied. Results demonstrate that the proposed EM-MOABC is effective in guiding actual fiber LBW applications.
The use of artificial intelligence to process sensor data and predict the dimensional accuracy of machined parts is of great interest to the manufacturing community and can facilitate the intelligent production of many key engineering components. In this study, we develop a predictive model of the dimensional accuracy for precision milling of thin-walled structural components. The aim is to classify three typical features of a structural component—squares, slots, and holes—into various categories based on their dimensional errors (i.e., “high precision,” “pass,” and “unqualified”). Two different types of classification schemes have been considered in this study: those that perform feature extraction by using the convolutional neural networks and those based on an explicit feature extraction procedure. The classification accuracy of the popular machine learning methods has been evaluated in comparison with the proposed deep learning model. Based on the experimental data collected during the milling experiments, the proposed model proved to be capable of predicting dimensional accuracy using cutting parameters (i.e., “static features”) and cutting-force data (i.e., “dynamic features”). The average classification accuracy obtained using the proposed deep learning model was 9.55% higher than the best machine learning algorithm considered in this paper. Moreover, the robustness of the hybrid model has been studied by considering the white Gaussian and coherent noises. Hence, the proposed hybrid model provides an efficient way of fusing different sources of process data and can be adopted for prediction of the machining quality in noisy environments.
Ceramic structural parts are one of the most widely utilized structural parts in the industry. However, they usually contain defects following the pressing process, such as burrs. Therefore, additional trimming is usually required, despite the deformation challenges and difficulty in positioning. This paper proposes an ultrafast laser processing system for trimming complex ceramic structural parts. Opto-electromechanical cooperative control software is developed to control the laser processing system. The trimming problem of the ceramic cores used in aero engines is studied. The regional registration method is introduced based on the iterative closest point algorithm to register the path extracted from the computer-aided design model with the deformed ceramic core. A zonal and layering processing method for three-dimensional contours on complex surfaces is proposed to generate the working data of high-speed scanning galvanometer and the computer numerical control machine tool, respectively. The results show that the laser system and the method proposed in this paper are suitable for trimming complex non-datum parts such as ceramic cores. Compared with the results of manual trimming, the method proposed in this paper has higher accuracy, efficiency, and yield. The method mentioned above has been used in practical application with satisfactory results.
Tool failures in machining processes often cause severe damages of workpieces and lead to large quantities of loss, making tool condition monitoring an important, urgent issue. However, problems such as practicability still remain in actual machining. Here, a real-time tool condition monitoring method integrated in an in situ fiber optic temperature measuring apparatus is proposed. A thermal simulation is conducted to investigate how the fluctuating cutting heats affect the measuring temperatures, and an intermittent cutting experiment is carried out, verifying that the apparatus can capture the rapid but slight temperature undulations. Fourier transform is carried out. The spectrum features are then selected and input into the artificial neural network for classification, and a caution is given if the tool is worn. A learning rate adaption algorithm is introduced, greatly reducing the dependence on initial parameters, making training convenient and flexible. The accuracy stays 90% and higher in variable argument processes. Furthermore, an application program with a graphical user interface is constructed to present real-time results, confirming the practicality.
Machined surface roughness will affect parts’ service performance. Thus, predicting it in the machining is important to avoid rejects. Surface roughness will be affected by system position dependent vibration even under constant parameter with certain toolpath processing in the finishing. Aiming at surface roughness prediction in the machining process, this paper proposes a position-varying surface roughness prediction method based on compensated acceleration by using regression analysis. To reduce the stochastic error of measuring the machined surface profile height, the surface area is repeatedly measured three times, and Pauta criterion is adopted to eliminate abnormal points. The actual vibration state at any processing position is obtained through the single-point monitoring acceleration compensation model. Seven acceleration features are extracted, and valley, which has the highest R-square proving the effectiveness of the filtering features, is selected as the input of the prediction model by mutual information coefficients. Finally, by comparing the measured and predicted surface roughness curves, they have the same trends, with the average error of 16.28% and the minimum error of 0.16%. Moreover, the prediction curve matches and agrees well with the actual surface state, which verifies the accuracy and reliability of the model.
In industrial manufacturing, the deployment of dual-arm robots in assembly tasks has become a trend. However, making the dual-arm robots more intelligent in such applications is still an open, challenging issue. This paper proposes a novel framework that combines task-oriented motion planning with visual perception to facilitate robot deployment from perception to execution and finish assembly problems by using dual-arm robots. In this framework, visual perception is first employed to track the effects of the robot behaviors and observe states of the workpieces, where the performance of tasks can be abstracted as a high-level state for intelligent reasoning. The assembly task and manipulation sequences can be obtained by analyzing and reasoning the state transition trajectory of the environment as well as the workpieces. Next, the corresponding assembly manipulation can be generated and parameterized according to the differences between adjacent states by combining with the prebuilt knowledge of the scenarios. Experiments are set up with a dual-arm robotic system (ABB YuMi and an RGB-D camera) to validate the proposed framework. Experimental results demonstrate the effectiveness of the proposed framework and the promising value of its practical application.
Mechanical manufacturing industry consumes substantial energy with low energy efficiency. Increasing pressures from energy price and environmental directive force mechanical manufacturing industries to implement energy efficient technologies for reducing energy consumption and improving energy efficiency of their machining processes. In a practical machining process, cutting parameters are vital variables set by manufacturers in accordance with machining requirements of workpiece and machining condition. Proper selection of cutting parameters with energy consideration can effectively reduce energy consumption and improve energy efficiency of the machining process. Over the past 10 years, many researchers have been engaged in energy efficient cutting parameter optimization, and a large amount of literature have been published. This paper conducts a comprehensive literature review of current studies on energy efficient cutting parameter optimization to fully understand the recent advances in this research area. The energy consumption characteristics of machining process are analyzed by decomposing total energy consumption into electrical energy consumption of machine tool and embodied energy of cutting tool and cutting fluid. Current studies on energy efficient cutting parameter optimization by using experimental design method and energy models are reviewed in a comprehensive manner. Combined with the current status, future research directions of energy efficient cutting parameter optimization are presented.
Low-carbon manufacturing (LCM) is increasingly being regarded as a new sustainable manufacturing model of carbon emission reduction in the manufacturing industry. In this paper, a two-stage low-carbon scheduling optimization method of job shop is presented as part of the efforts to implement LCM, which also aims to reduce the processing cost and improve the efficiency of a mechanical machining process. In the first stage, a task assignment optimization model is proposed to optimize carbon emissions without jeopardizing the processing efficiency and the profit of a machining process. Non-dominated sorting genetic algorithm II and technique for order preference by similarity to an ideal solution are then adopted to assign the most suitable batch task of different parts to each machine. In the second stage, a processing route optimization model is established to plan the processing sequence of different parts for each machine. Finally, niche genetic algorithm is utilized to minimize the makespan. A case study on the fabrication of four typical parts of a machine tool is demonstrated to validate the proposed method.
The distributed parameterized intelligent product platform (DPIPP) contains many agents of a product minimum approximate autonomous subsystem (generalized module). These distributed agents communicate, coordinate, and cooperate using their knowledge and skills and eventually accomplish the design for mass customization in a loosely coupled environment. In this study, a new method of isomorphism analysis on generalized modules oriented to DPIPP is proposed. First, on the basis of the bill of material partition and generalized module mining, the parameters of the main characteristics are extracted to construct the main characteristic parameter matrix. Second, similarity calculation of generalized modules is realized by improving the clustering using representatives algorithm, and isomorphism model sets are obtained. Generalized modules with a similar structure are combined to complete the isomorphism analysis. The effectiveness of the proposed method is verified by taking high- and medium-pressure valve data as an example.
Given the multiple varieties and small batches, the production of industrial robots faces the ongoing challenges of flexibility, self-organization, self-configuration, and other “smart” requirements. Recently, cyber physical systems have provided a promising solution for the requirements mentioned above. Despite recent progress, some critical issues have not been fully addressed at the shop floor level, including dynamic reorganization and reconfiguration, ubiquitous networking, and time constrained computing. Toward the next generation production system for industrial robots, this study proposed a hybrid architecture for smart assembly shop floors with closed-loop dynamic cyber physical interactions. Aiming for dynamic reorganization and reconfiguration, the study also proposed modularized smart assembly units for the deployment of physical assembly processes. Enabling technologies, such as multiagent system (MAS), self-organized wireless sensor actuator networks, and edge computing, were discussed and then integrated into the proposed architecture. Furthermore, a multijoint robot assembly process was selected as a target scenario. Thus, an MAS was developed to simulate the coordination and negotiation mechanisms for the proposed architecture on the basis of the Java Agent Development Framework platform.
The scheduling of parallel machines and the optimization of multi-line systems are two hotspots in the field of complex manufacturing systems. When the two problems are considered simultaneously, the resulting problem is much more complex than either of them. Obtaining sufficient training data for conventional data-based optimization approaches is difficult because of the high diversity of system structures. Consequently, optimization of multi-line systems with alternative machines requires a simple mechanism and must be minimally dependent on historical data. To define a general multi-line system with alternative machines, this study introduces the capability vector and matrix and the distribution vector and matrix. A naive optimization method is proposed in accordance with classic feedback control theory, and its key approaches are introduced. When a reasonable target value is provided, the proposed method can realize closed-loop optimization to the selected objective performance. Case studies are performed on a real 5/6-inch semiconductor wafer manufacturing facility and a simulated multi-line system constructed on the basis of the MiniFAB model. Results show that the proposed method can effectively and efficiently optimize various objective performance. The method demonstrates a potential for utilization in multi-objective optimization.
Thermal error is one of the main factors that influence the machining accuracy of computer numerical control (CNC) machine tools. It is usually reduced by thermal error compensation. Temperature field monitoring and key temperature measurement point (TMP) selection are the bases of thermal error modeling and compensation for CNC machine tools. Compared with small- and medium-sized CNC machine tools, heavy-duty CNC machine tools require the use of more temperature sensors to measure their temperature comprehensively because of their larger size and more complex heat sources. However, the presence of many TMPs counteracts the movement of CNC machine tools due to sensor cables, and too many temperature variables may adversely influence thermal error modeling. Novel temperature sensors based on fiber Bragg grating (FBG) are developed in this study. A total of 128 FBG temperature sensors that are connected in series through a thin optical fiber are mounted on a heavy-duty CNC machine tool to monitor its temperature field. Key TMPs are selected using these large-scale FBG temperature sensors by using the density-based spatial clustering of applications with noise algorithm to reduce the calculation workload and avoid problems in the coupling of TMPs for thermal error modeling. Back propagation neural network thermal error prediction models are established to verify the performance of the proposed TMP selection method. Results show that the number of TMPs is reduced from 128 to 5, and the developed model demonstrates good prediction effects and strong robustness under different working conditions of the heavy-duty CNC machine tool.
Spinning production is a typical continuous manufacturing process characterized by high speed and uncertain dynamics. Each manufacturing unit in spinning production produces various real-time tasks, which may affect production efficiency and yarn quality if not processed in time. This paper presents an edge computing-based method that is different from traditional centralized cloud computation because its decentralization characteristics meet the high-speed and high-response requirements of yarn production. Edge computing nodes, real-time tasks, and edge computing resources are defined. A system model is established, and a real-time task processing method is proposed for the edge computing scenario. Experimental results indicate that the proposed real-time task processing method based on edge computing can effectively solve the delay problem of real-time task processing in spinning cyber-physical systems, save bandwidth, and enhance the security of task transmission.
Intelligent machining is a current focus in advanced manufacturing technology, and is characterized by high accuracy and efficiency. A central technology of intelligent machining—the cutting process online monitoring and optimization—is urgently needed for mass production. In this research, the cutting process online monitoring and optimization in jet engine impeller machining, cranio-maxillofacial surgery, and hydraulic servo valve deburring are introduced as examples of intelligent machining. Results show that intelligent tool path optimization and cutting process online monitoring are efficient techniques for improving the efficiency, quality, and reliability of machining.
Hydraulic servo system plays a significant role in industries, and usually acts as a core point in control and power transmission. Although linear theory-based control methods have been well established, advanced controller design methods for hydraulic servo system to achieve high performance is still an unending pursuit along with the development of modern industry. Essential nonlinearity is a unique feature and makes model-based nonlinear control more attractive, due to benefit from prior knowledge of the servo valve controlled hydraulic system. In this paper, a discussion for challenges in model-based nonlinear control, latest developments and brief perspectives of hydraulic servo systems are presented: Modelling uncertainty in hydraulic system is a major challenge, which includes parametric uncertainty and time-varying disturbance; some specific requirements also arise ad hoc difficulties such as nonlinear friction during low velocity tracking, severe disturbance, periodic disturbance, etc.; to handle various challenges, nonlinear solutions including parameter adaptation, nonlinear robust control, state and disturbance observation, backstepping design and so on, are proposed and integrated, theoretical analysis and lots of applications reveal their powerful capability to solve pertinent problems; and at the end, some perspectives and associated research topics (measurement noise, constraints, inner valve dynamics, input nonlinearity, etc.) in nonlinear hydraulic servo control are briefly explored and discussed.
This paper reviews recent developments in digital switched hydraulics particularly the switched inertance hydraulic systems (SIHSs). The performance of SIHSs is presented in brief with a discussion of several possible configurations and control strategies. The soft switching technology and high-speed switching valve design techniques are discussed. Challenges and recommendations are given based on the current research achievements.
This paper deals with the conceptual design, kinematic analysis and workspace identification of a novel four degrees-of-freedom (DOFs) high-speed spatial parallel robot for pick-and-place operations. The proposed spatial parallel robot consists of a base, four arms and a 1½ mobile platform. The mobile platform is a major innovation that avoids output singularity and offers the advantages of both single and double platforms. To investigate the characteristics of the robot’s DOFs, a line graph method based on Grassmann line geometry is adopted in mobility analysis. In addition, the inverse kinematics is derived, and the constraint conditions to identify the correct solution are also provided. On the basis of the proposed concept, the workspace of the robot is identified using a set of presupposed parameters by taking input and output transmission index as the performance evaluation criteria.
The Inconel 718 alloy is widely used in the aerospace and power industries. The machining-induced surface integrity and fatigue life of this material are important factors for consideration due to high reliability and safety requirements. In this work, the milling of Inconel 718 was conducted at different cutting speeds and feed rates. Surface integrity and fatigue life were measured directly. The effects of cutting speed and feed rate on surface integrity and their further influences on fatigue life were analyzed. Within the chosen parameter range, the cutting speed barely affected the surface roughness, whereas the feed rate increased the surface roughness through the ideal residual height. The surface hardness increased as the cutting speed and feed rate increased. Tensile residual stress was observed on the machined surface, which showed improvement with the increasing feed rate. The cutting speed was not an influencing factor on fatigue life, but the feed rate affected fatigue life through the surface roughness. The high surface roughness resulting from the high feed rate could result in a high stress concentration factor and lead to a low fatigue life.
An inverse dynamic model of a high-speed parallel robot is established based on the virtual work principle. With this dynamic model, a new evaluation method is proposed to measure the power consumption of the robot during pick-and-place tasks. The power vector is extended in this method and used to represent the collinear velocity and acceleration of the moving platform. Afterward, several dynamic performance indices, which are homogenous and possess obvious physical meanings, are proposed. These indices can evaluate the power input and output transmissibility of the robot in a workspace. The distributions of the power input and output transmissibility of the high-speed parallel robot are derived with these indices and clearly illustrated in atlases. Furtherly, a low-power-consumption workspace is selected for the robot.
This paper presents a survey of recent advancements and upcoming trends in motion control technologies employed in designing multi-actuator hydraulic systems for mobile machineries. Hydraulic systems have been extensively used in mobile machineries due to their superior power density and robustness. However, motion control technologies of multi-actuator hydraulic systems have faced increasing challenges due to stringent emission regulations. In this study, an overview of the evolution of existing throttling control technologies is presented, including open-center and load sensing controls. Recent advancements in energy-saving hydraulic technologies, such as individual metering, displacement, and hybrid controls, are briefly summarized. The impact of energy-saving hydraulic technologies on dynamic performance and control solutions are also discussed. Then, the advanced operation methods of multi-actuator mobile machineries are reviewed, including coordinated and haptic controls. Finally, challenges and opportunities of advanced motion control technologies are presented by providing an overall consideration of energy efficiency, controllability, cost, reliability, and other aspects.
Brittle materials have been widely employed for industrial applications due to their excellent mecha-nical, optical, physical and chemical properties. But obtaining smooth and damage-free surface on brittle materials by traditional machining methods like grinding, lapping and polishing is very costly and extremely time consuming. Ductile mode cutting is a very promising way to achieve high quality and crack-free surfaces of brittle materials. Thus the study of ductile mode cutting of brittle materials has been attracting more and more efforts. This paper provides an overview of ductile mode cutting of brittle materials including ductile nature and plasticity of brittle materials, cutting mechanism, cutting characteristics, molecular dynamic simulation, critical undeformed chip thickness, brittle-ductile transition, subsurface damage, as well as a detailed discussion of ductile mode cutting enhancement. It is believed that ductile mode cutting of brittle materials could be achieved when both crack-free and no subsurface damage are obtained simultaneously.
Reconfigurable manufacturing systems (RMSs), which possess the advantages of both dedicated serial lines and flexible manufacturing systems, were introduced in the mid-1990s to address the challenges initiated by globalization. The principal goal of an RMS is to enhance the responsiveness of manufacturing systems to unforeseen changes in product demand. RMSs are cost-effective because they boost productivity, and increase the lifetime of the manufacturing system. Because of the many streams in which a product may be produced on an RMS, maintaining product precision in an RMS is a challenge. But the experience with RMS in the last 20 years indicates that product quality can be definitely maintained by inserting in-line inspection stations. In this paper, we formulate the design and operational principles for RMSs, and provide a state-of-the-art review of the design and operations methodologies of RMSs according to these principles. Finally, we propose future research directions, and deliberate on how recent intelligent manufacturing technologies may advance the design and operations of RMSs.
Information and communication technology is undergoing rapid development, and many disruptive technologies, such as cloud computing, Internet of Things, big data, and artificial intelligence, have emerged. These technologies are permeating the manufacturing industry and enable the fusion of physical and virtual worlds through cyber-physical systems (CPS), which mark the advent of the fourth stage of industrial production (i.e., Industry 4.0). The widespread application of CPS in manufacturing environments renders manufacturing systems increasingly smart. To advance research on the implementation of Industry 4.0, this study examines smart manufacturing systems for Industry 4.0. First, a conceptual framework of smart manufacturing systems for Industry 4.0 is presented. Second, demonstrative scenarios that pertain to smart design, smart machining, smart control, smart monitoring, and smart scheduling, are presented. Key technologies and their possible applications to Industry 4.0 smart manufacturing systems are reviewed based on these demonstrative scenarios. Finally, challenges and future perspectives are identified and discussed.
As an important part of product design and manufacturing, assembly sequence planning (ASP) has a considerable impact on product quality and manufacturing costs. ASP is a typical NP-complete problem that requires effective methods to find the optimal or near-optimal assembly sequence. First, multiple assembly constraints and rules are incorporated into an assembly model. The assembly constraints and rules guarantee to obtain a reasonable assembly sequence. Second, an algorithm called SOS-ACO that combines symbiotic organisms search (SOS) and ant colony optimization (ACO) is proposed to calculate the optimal or near-optimal assembly sequence. Several of the ACO parameter values are given, and the remaining ones are adaptively optimized by SOS. Thus, the complexity of ACO parameter assignment is greatly reduced. Compared with the ACO algorithm, the hybrid SOS-ACO algorithm finds optimal or near-optimal assembly sequences in fewer iterations. SOS-ACO is also robust in identifying the best assembly sequence in nearly every experiment. Lastly, the performance of SOS-ACO when the given ACO parameters are changed is analyzed through experiments. Experimental results reveal that SOS-ACO has good adaptive capability to various values of given parameters and can achieve competitive solutions.
Practice experimentation that integrates the manufacturing processes and cutting-edge technologies of smart manufacturing (SM) is essential for future academic and applied engineering personnel. The broadening efficacy of hands-on experience in SM engineering education has been manifested. In this regard, a reference practical system is proposed in this study for hands-on training in SM crucial advancements. The system constructs a mobile robot-based production line (MRPL) to increase participants’ interest in theoretical learning and professional skills. The MRPL-based reference system includes the comprehensive principles and processes involved in modern SM factories from warehousing to logistics, processing, and testing. With key features of modularity, integrability, customizability, and open architecture, this system has a threefold objective. First, it is an interdisciplinary subject that enables students to translate classroom learning into authentic practices, thus facilitating knowledge synthesis and training involvements. Second, it offers effective support to cultivate the attributions and behavioral competencies of SM talents, such as perseverance, adaptability, and cooperation. Third, it promotes students’ capacities for critical thinking and problem solving so that they can deal with the difficulties that physical systems have and motivates them to pursue careers with new syllabi, functions, and process techno-logies. The received positive evaluations and assessments confirm that this MRPL-based reference system is beneficial for modern SM talent training in higher engineering education.
