Search

• A multi-camera joint calibration algorithm for guiding machining robot positioning is proposed. • The positioning error is optimized by considering both the ambient light and error uncertainty. • High dynamic range imaging is used to enhance the ability to resist the ambient light interference. • Confidence threshold filtering and deviation feedback optimization are used to solve the error uncertainty problem. • The average absolute positioning error is 1.27 mm, the optimum can reach 0.43 mm, and the average relative positioning error is 0.34 mm. Multi-camera guided robotic machining is widely used in the removal of flash and burrs on the complex automotive castings and forgings. The multi-camera calibration process, however, is easily affected by the ambient light and uncertain error, thereby resulting in the undesired robot positioning accuracy. To overcome the challenging problem, this paper proposes a multi-camera joint calibration (MCJC) algorithm by considering both the ambient light and error uncertainty to optimize and compensate the positioning error of the image-guided machining robot. The high dynamic range imaging is used at first to obtain stable calibration image data for countering the effects of ambient light changes. Then the uncertainty error in camera self-calibration process is removed by the confidence threshold filtering. The hand-eye calibration matrix is corrected finally using the deviation feedback optimization for positioning accuracy enhancement of the image-guided machining robot. Taking the automotive flywheel shell as the experimental object, the results demonstrate that the average absolute positioning error is controlled within 1.3 mm, the optimum can reach 0.43 mm, and the average relative positioning error is smaller than 0.5 mm. Compared with the existing state-of-the-art algorithms, the proposed algorithm shows high positioning accuracy and strong algorithm robustness, and can meet the requirements for the subsequent image-guided robotic machining. [ABSTRACT FROM AUTHOR]

The prerequisite for realizing robotic self-adaptive grinding of the car body welding slags is to accurately identify the small and randomly distributed welding slags, and to segment their contour from the complex background. In this paper, an improved SegNet network model is proposed to address the challenging problems in small target detection and contour extraction. Both the ability to capture image features and to perceive global and local information is enhanced by adding the context extractor into the SegNet network. Furthermore, the residual structure and BN layer are used to optimize the decoder of the SegNet network, and the Dropout layer is employed to effectively avoid overfitting of the training model. Based on these strategies, the adaptability of the network to multi-scale targets is further enhanced. Experiments on car body welding slags detection indicate that the accuracy rate of the improved SegNet network model can reach 99.5%, which is 2.7% higher than that before improvement. Meanwhile, the boundary pixels at connection area among welding slags, metal plate, and background are accurately segmented, which provides data support for the subsequent robotic grinding of car body welding slags. [ABSTRACT FROM AUTHOR]

Motivated by the prevailing assisted techniques in wheel grinding of brittle and hard materials, an attempt is made in this paper to identify the feasibility of robot-assisted abrasive belt grinding of zirconia ceramics. Owing to the flexible machining system, the challenge of this attempt resides in achieving the required profile accuracy and surface quality, in which the evolution of grinding-induced micro-cracks is prioritized. The single-grit scratching simulation based on an improved chip-thickness model that incorporates elastic modules of tool-workpiece engagement is employed to explore the damage mechanism in terms of the initiation, propagation and suppression of micro-cracks. The simulation results demonstrate that the critical depth of cut for brittle-to-ductile transition of zirconia ceramics is determined as 0.42 μm according to the tentative maximum undeformed chip thickness (UCT) values. In ductile-regime grinding, the zirconia surface morphologies are independent of the abrasive particle velocity. Lateral cracks begin to initiate especially when the maximum UCT exceeds 0.42 μm, and the brittle removal becomes dominant. In brittle-regime grinding, high abrasive particle velocity could help substantially enhance the workpiece surface integrity by suppressing the median/radial cracks that initiate once the maximum UCT approaches 0.8 μm. Experiment concerning the force-controlled robotic belt grinding of zirconia ceramics is conducted to verify the simulation results via the microscope observation of ground surface morphologies. The findings are likely to provide experimental evidence on the feasibility of belt grinding of brittle and hard materials with a flexible industrial robot. [ABSTRACT FROM AUTHOR]

A tentative work from the perspective of cutting forces is carried out in this paper to analyse and assess the robotic belt grinding mechanisms. Firstly, a microscopic scale of cutting force model consisting of sliding, ploughing and cutting components is introduced, then the effects of force components on the machined surface roughness are explored based on the force control experiments, and finally a typical case on the robotic belt grinding of aero-engine blade with constant contact force is conducted to validate the practicality and effectiveness of force control. The results reveal two significant findings with respect to the high sliding force percentage and low cutting efficiency in comparison with the robotic belt grinding without force control. [ABSTRACT FROM AUTHOR]

Calibration in the robot-assisted belt grinding of complex blades is regarded as one of the key bottlenecks of measurement accuracy. To enhance the accuracy, a TCP-based (tool center point) calibration method is proposed in this paper to calibrate the relationship between the precalibrated 3D laser scanner and the robot end-effector by using criterion spheres as the calibration object. Based on the description of the robot-scanning system from the perspectives of coordinates and scanner measurement modes, the calibration strategies on translational and rotational motions of the robot are provided to determine the translation vector and the orientation matrix. Calibration experiments on the criterion sphere are performed, both the calibration errors (positioning error and orientation error) and sphere fitting error are calculated. A typical case on the robotic belt grinding of 84K-2R1 aviation blade is conducted to validate the calibration results. Finally, the key factors influencing the calibration accuracy are analyzed. It has been demonstrated that the TCP-based calibration method proposed is effective, concise, and time-saving, and can be widely applied in the robot-assisted belt grinding operation. [ABSTRACT FROM AUTHOR]

This paper provides a simple and effective numerical modeling procedure to determine the thermal effects of initial workpiece temperature ( T w ) and preheated die temperature ( T d ) on the die wear behavior in turbine blade forging. In particular, a local 3D finite element (FE) approach embedded with the modified Archard wear model is developed for the numerical modeling and subsequently validated by comparing the simulated average contact pressure to the analytical one, as well as the experiment from literature. Then, the wear evolution and distribution of blade forging dies are characterized numerically. Further, the thermal effects of both initial workpiece and preheated die temperatures on the die wear characteristics are assessed, and the strategies for decreasing the die wear volume are consequently suggested. The results show that the die wear depth distribution is uneven and the wear volume is more influenced by the preheated die temperature in hot forging process of the blade. [ABSTRACT FROM AUTHOR]

This work is motivated by the fact that one key parameter of sliding velocity at die-workpiece interface in numerical analysis of blade forging process is usually ignored, thereby resulting in poor prediction accuracy and limited application of friction model. A realistic description of the friction boundary conditions shows great practical importance for the usability of simulation results. In this paper, an advanced friction model named IFUM considering the influence of sliding velocity is introduced in the simulation of Ti-6Al-4V turbine blade forging operation, and its effects on metal flow and forging forces are compared and evaluated with two traditional friction models. The results indicate that the Institute of Metal Forming and Metal-Forming Machines (IFUM) friction model gives the better match with the experimental results than the traditional ones, in which the material flow velocity distribution and forging forces characterized by the sliding velocity are found to be more uneven and smaller, respectively. This research improves the accuracy of the simulation results and can be served as a basis for design and optimization of blade forging process. [ABSTRACT FROM AUTHOR]

This work is motivated by the overestimation of chip formation contribution due to the unspecified proportion of ploughing and chip formation in previous studies on mechanisms of belt grinding. In this paper, a microscopic scale of ploughing force model is introduced, and the characterisation of cutting mechanisms generated by robot-assisted belt grinding of titanium alloys is provided from the energetic aspect based on experimental forces. It has been demonstrated that sliding is more predominant than ploughing and chip formation in robot-assisted belt grinding process, resulting in lower energy efficiency. Strategies for balancing energy consumption and energy efficiency are suggested. [ABSTRACT FROM AUTHOR]

This work is motivated by a fact that an excessively worn tool will continue to be used in practical machining of difficult-to-cut materials, such as nickel-based superalloys. Quantitative comparison of worn tool temperature variations with a sharp tool shows great practical significance. A thermal model is presented to describe the coated tool temperature variation in dry milling of nickel-based superalloys for a turbine blade. The influence of flank wear is considered according to the rapid tool wear. In the proposed model, both heat fluxes into the tool from the rake face and due to flank wear are calculated to estimate the tool temperature distribution at different tool states. Feed rate optimization at the convex and concave surfaces of blade based on the force constraints is employed to investigate its influence on heat generation and tool temperature rise. A comparative experiment for dry milling of an Inconel 718 turbine blade is carried out to validate the model. Considering a set of experimental data and the output of the numerical simulations in the present work, a key global heat transfer coefficient (HTC), working as a partitioning coefficient which determines the heat amounts flowing into the chip and the tool, respectively, is assessed through an inverse procedure. This comparison indicates a good agreement in both trends and values. With the alternative method, an accurate simulation of the tool temperature variation can be achieved by the assessed global HTC which is used as an input in the FE model. As the influence of tool wear should be considered, this work can be further employed into the feed rate scheduling guidance in machining complex parts. [ABSTRACT FROM AUTHOR]

The alumina-based ceramic cutting tools are a kind of promising tools used in machining of heat-resistant-super-alloys, such as nickel-based super alloy, due to its high wear resistance, low thermal expansion and good oxidation resistance up to above 1000�°C. Sharp temperature rise mainly caused by excessive plastic deformation as well as the friction in machining of nickel-based super alloys is considered to be the key for rapid tool wear, especially the notch wear, which is the predominant type of catastrophic failure mechanism for the round type ceramic cutting tools. In this study, the wear mechanism of alumina-based ceramic cutting tools during dry turning of Inconel 718 is experimentally investigated. Based on the observation of tool wear, an attempt by employing the hardened layer beneath the workpiece surface is made to explain the occurrence of notch wear. Consequently, a predictive model of notch wear depth considering the influence of work hardened layer is developed. Series of cutting tests are used to validate the proposed notch wear model, and the result indicates that the proposed model is feasible. The contribution of this work can guide the effective control of tool wear by reducing the work hardened layer through the optimization of processing parameters. [ABSTRACT FROM AUTHOR]

This work is motivated by the fact that one key parameter of r, which is defined as the effective contact radius of grain, in grinding temperature calculation model (TCM) proposed by Marinescu et al. is usually assumed as a constant in the range of 5-20 μm in different grinding conditions, and this assumption often leads to poor prediction accuracy and limits the widespread application of this model. In this paper, an improved temperature calculation model (I-TCM) considering the grain geometry and distribution is proposed to further optimize the grinding temperature. In this new model, the convection heat transfer coefficient ( h) is modified considering the cone angle ( θ), grain size ( g), and grain concentration ( V) effects, and the 'workpiece-wheel' partition ratio ( R) is improved considering the cone angle effect. Theoretical analysis and experiments are carried out for verification in details. The results show that the I-TCM gives the better match with the experimental results than the existing TCM, in which the R values characterized by the cone angle and effective contact radius of grain are more sensitive to the grinding temperature than the convection heat transfer coefficient. Furthermore, the effects by the grain size and grain concentration on the grinding temperature could be negligible for the simplification of the calculation process. The I-TCM given in this paper is helpful to the optimization and control of temperature in a practical grinding process. [ABSTRACT FROM AUTHOR]

Abstract: Nickel-based superalloy is widely employed in aircraft engines and the hot end components of various types of gas turbines with its high strength, strong corrosion resistance and excellent thermal fatigue properties and thermal stability. However, nickel-based superalloy is one of the extremely difficult-to-cut materials. During the machining process, the interaction between the tool and the workpiece causes the severe plastic deformation in the local area of workpiece, and the intense friction at the tool–workpiece interface. The resulting cutting heat coupled with the serious work hardening leads to a series of flaws, such as excessive tool wear, frequent tool change, short tool life, low productivity, and large amount of power consumption etc., in which the excessive tool wear has become one of the main bottlenecks that constraints the machinability of nickel-based superalloys and its wide range of applications. In this article, attention is mainly focused on the tool wear characteristics in the machining of nickel-based superalloys, and the state of the art in the fields of failure mechanism, monitoring and prediction, and control of tool wear are reviewed. The survey of existing works has revealed several gaps in the aspects of tool self-organizing process based on the non-equilibrium thermodynamics, tool wear considering the tool nose radius, thermal diffusion layer in coated tools, tool life prediction based on the thermal–mechanical coupling, and industrial application of tool wear online monitoring devices. The review aims at providing an insight into the tool wear characteristics in the machining of nickel-based superalloys and shows the great potential for further investigations and innovation in the field of tool wear. [Copyright &y& Elsevier]

In order to estimate temperature distribution and the influence of grinding parameters on grinding temperature in the grinding zone, a theoretical model used for calculating and simulating the grinding process must be established. Many simplified heat source models developed previously have some errors compared with the actual heat flux to the workpiece. Therefore, based on the triangular heat flux distribution model and temperature distributions measured, an inverse method for the heat transfer mechanism in the grinding zone was investigated and a quadratic curve heat flux distribution model was developed to determine the heat flux distribution and predict the surface temperature of the workpiece. From the theoretical expression of heat flux to the workpiece, it has been found that the quadratic curve heat flux is the superposition of square law heat flux, triangular heat flux, and uniform heat flux in the grinding zone. By comparison of theoretical analysis with the experimental results, it has been demonstrated that the solution using a quadratic curve heat flux can improve the grinding model by decreasing the error, although the uniform and triangular heat fluxes can explain the condition of the heat flux to the workpiece along the grinding zone. [ABSTRACT FROM AUTHOR]

• An accurate method for detecting complex component surface defects is proposed. • The defect detection accuracy is high to 99.3% for the complex components. • Normal feature misdetection can be guaranteed by machine learning method. • Spreading algorithm is proposed to classify and recognize the number of defects. • Sizes of defects can be detected by the covariance matrix 3D measurement method. Detecting the surface defects of complex components exhibiting different visual properties in positions, shapes, number and sizes is a challenging problem. In this paper a novel computational framework is developed to accurately detect the component surface defects through three steps. In the framework, the positions and shapes of the components surface defects are extracted based on the support vector machine and the point cloud model. Then a novel unsupervised classification method termed as spreading algorithm is proposed to classify the defects for the recognition of the number of defects, and finally the sizes of defects are calculated using the covariance matrix 3D measurement method. Experimental cases on two typical complex components, the blade with depression and protrusion defects and the transmission case with defect and normal features, are investigated. The results are particularly compared with the ones with the state-of-the-art methods, showing the practicality and effectiveness of the proposed technique. [ABSTRACT FROM AUTHOR]

As a typical difficult-to-machine material, the strong wear resistance and high hardness of carbon fiber in carbon fiber–reinforced plastics (CFRPs) lead to rapid tool wear during the cutting process, exacerbating surface damage of the hole and significantly increasing production costs. The investigation of tool wear has always been the pivotal focus in low-cost manufacturing. However, no similar work has been reported yet in tool wear of CFRP helical milling To fill this gap, this paper aims to conduct a theoretical analysis of the tool wear mechanism in helical milling of CFRPs and summarize the trends in tool wear under different cutting amounts as well as the impact of tool wear on cutting force and hole quality. Tool wear characteristics in terms of helical milling were studied carefully. Discussions on the tool wear morphology, cutting parameters, cutting force, and hole wall roughness were also provided. The findings in this paper might offer guidance on tool wear mechanisms for extending tool life and increasing hole-making quality in helical milling of CFRPs. [ABSTRACT FROM AUTHOR]

Motivated by our previous work which proposed an improved microforce model considering the effects of cut-in and cut-off in robotic belt grinding operation, we further extend this novel idea into the analysis and optimization of the cut-in and cut-off phenomenon which seriously affects the surface contour accuracy and machining quality. Firstly, a practical material removal rate (MRR) model is introduced to characterize the material removal characteristics, especially at the cut-in and cut-off paths. Then, a strategy framework using the combination of active and passive force control, variable-feed finishing, and longitudinal grinding style is constructed to further enhance the surface profile accuracy and processing quality. Finally, robotic machining experiments of titanium alloy test workpiece are implemented to test the reliability and reasonability of the strategy framework. [ABSTRACT FROM AUTHOR]

A tentative study from the perspective of abrasive grain geometry in this paper is conducted to investigate the specific energy and energy efficiency for clarifying the robotic belt grinding mechanisms. The energy efficiency model is established based on the friction coefficient model of the single spherical grain, then the experiments and simulation are implemented to energetically evaluate the microscale material removal mechanisms from the specific energy contributions. It has been demonstrated that the specific plowing energy is more predominant than both the specific cutting and sliding energy in robotic belt grinding, resulting in the energy efficiency ranges between 17 and 41 %. Both the large grain size and normal contact force can be taken as optimization strategies to maximize the energy efficiency for material removal. [ABSTRACT FROM AUTHOR]

This paper is motivated by the fact that machining of Inconel 718 involves rapid tool wear and poor surface integrity. We investigate the performance of ceramic cutting inserts in turning of Inconel 718 by virtue of two different assisted machining conditions, plasma preheating- and cryogenic cooling-assisted technologies. The plasma nozzle placed in front of the cutting zone is used to soften the materials before machining. The liquid nitrogen flow located in the cutting area is used to reduce the cutting temperatures in the contact area. The cutting experiments are set for reducing tool wear and improving surface integrity, including surface roughness and micro-hardness beneath workpiece surface. With these two assisted techniques, the tool wear including flank wear and notch wear and the surface microstructure including surface roughness and micro-hardness are assessed and compared with conventional machining. Tool wear reduction and surface integrity improvement can be obtained with these two assisted technologies in turning of Inconel 718 with ceramic cutting inserts. The main causation of notch wear of the ceramic cutting inserts may be the hardened layer beneath the surface. By comparing these two assisted cutting techniques with opposite effects on the cutting tool and workpiece, it has been found that the surface roughness is reduced by 50 %, the micro-hardness is smaller, and the tool life is extended up to more than 40 % over conventional machining. [ABSTRACT FROM AUTHOR]

When the non-standard customized brush roller tool is used for robotic grinding of large-scale components, the clamping and positioning error of the brush roller at the end of the robot is extremely easy to cause misalignment at the brush roller-workpiece contact interface, which will affect the machining accuracy and surface quality. In order to ensure the parallel contact between the brush roller and the workpiece surface during the machining process, a calculation model of the angular misalignment at the brush roller-workpiece contact interface is proposed based on the elastic contact force perception, and then the accurate positioning of the robot end brush roller is realized by a fast compensation method. Firstly, according to the geometric force relationship between the brush roller and the workpiece, as well as the determined brush roller material property parameters, the estimation model of angular misalignment is established. Secondly, both the axial force and normal torque at the time of initial contact detected by the force-controlled sensor are regarded as the input parameters in the model. Furthermore, the calculated brush roller-workpiece contact offset is used as the geometric error compensation amount, and the brush roller is deflected to achieve error compensation by the robot RAPID program control command. The finite element simulation results are compared with the theoretical calculation values, and the average relative error is 15.1%. The experiment on robotic grinding and brushing of high-speed rail body indicates that the compensated angle can be reduced to 0.024° from an average of 0.179° before compensation, coupled with uniform material removal depth. The proposed method can significantly improve the contour accuracy of large-scale components. [ABSTRACT FROM AUTHOR]

Industrial robots are characterized by good flexibility and a large working space, and offer a new approach for the machining of large and complex parts with small machining allowances (extra material allowed for subsequent machining). Parts of this type (such as aircraft skin parts, wind turbine blades, etc.) are easily deformed due to their large scale and low stiffness. Therefore, these parts cannot be directly machined according to the designed model. A feasible method is to plan a robotic machining path by using the point clouds of parts after clamping from onsite measurement which contains inherent defects of measurement such as noise points and abrupt points. In this article, a novel method is proposed to plan and optimize a robotic machining path that meets the requirements of smoothness, dexterity, and stiffness based on the point cloud from onsite measurement. The dual nonuniform rational B-spline curves of the machining path points and tool axis points are generated at first. Next, an objective function of smoothness optimization is established to filter out the local mutation of the path by considering the constraints of both the deformation energy and the deviation. Then, the objective function of robot postures optimization is established to optimize dexterity and Cartesian stiffness of a robot during the machining process. To show the feasibility of the proposed method, simulation and experiments are carried out. It is proved that the proposed method can generate a smooth machining trajectory. The stability of joint rotation and the rigidity and dexterity of the robot are improved during the machining process. [ABSTRACT FROM AUTHOR]

• A novel robot hand-eye calibration method is proposed without complicated error identification. • Robot hand-eye can be effectively calibrated without calculating the complex matrix equations. • Robot relocalization is implemented to reduce the introduction of robot kinematic error. • The IRLS spherical fitting algorithm is used to suppress the influence of measurement noise. • The error of the proposed method in the criterion sphere splicing verification is only 0.0323 mm. The accuracy of hand-eye calibration is easily affected by robot kinematic error, measurement error, random error, etc., and can be to a certain extent enhanced by the complicated error identification. To address this problem, we propose a novel errors-unidentified hand-eye calibration method. A relocalization-based hand-eye calibration is implemented to overcome the challenge from robot kinematics at first owing to the high robot relocalization accuracy. The tool center point (TCP) coordinates are then obtained based on an iterative reweighted least squares (IRLS) spherical fitting algorithm. An iterative combinatorial refinement algorithm is finally presented to search the solutions in the form of permutation and combination when solving the rigid transformation matrix. Experiments on criterion sphere and blade demonstrate that by converting the hand-eye matrix solving problem into a point set matching problem, the accuracy of the proposed method is enhanced by 60% on average compared with three state-of-the-art hand-eye calibration methods. [ABSTRACT FROM AUTHOR]

Reliable prediction and evaluation of material removal (MR) is a continuing pursuit in the grinding process. Mechanistic and empirical MR models always suffer from inaccuracies and restricted applicability, whereas data-driven approaches remain deficient in sample dependence, generalization, and physical interpretability. This motivates us to develop a knowledge-wrapping method (KWM) to predict and characterize the material removal behavior in robotic belt grinding. A physical material removal profile model (PHY) that suits the robotic belt grinding is first presented by appealing to the Archard law and Hertzian theory. Next, the knowledge-wrapping matrix is designed to wrap the physical constraints into a form of design matrix by transforming the mechanistic and empirical models into a linear system. The knowledge-wrapping matrix and the experimental data are then connected via a likelihood function with the consideration of measuring noise, yielding a hybrid-driven learning process that preserves interpretability from PHY. Comparative experiments and MR mechanism interpretations are finally presented to demonstrate the effectiveness and superiority of the proposed method. [Display omitted] • The knowledge-wrapping method achieves reliable prediction and evaluation. • A mechanistic model is used to provide physical constraints to learning model. • Comparative experiments and mechanism interpretations demonstrate its superiority. • The proposed method can be easily deployed to other prediction and evaluation scenarios. [ABSTRACT FROM AUTHOR]

Carbon fiber reinforced polymers (CFRPs) are becoming increasingly prevalent in the industries including automobile, aerospace, and military due to their light quality, high specific strength, high corrosion resistance, excellent thermodynamics performance, etc. However, these excellent properties easily result in intensive tool wear, short tool life, and reduced machining accuracy. Although ultrasonic vibration–assisted drilling (UVAD) was considered an effective drilling method to reduce tool wear, most reported studies focused on machining kinematics or mechanics, and very few studies systematically explored the tool wear behaviors in UVAD of CFRP. To fill this gap, this paper aims to investigate tool wear of high-speed steel (HSS) twist drill in UVAD of CFRP and compares these wear behaviors with those in conventional drilling based on the experimental observation of the worn drill morphologies. The effects of cutting parameters on tool wear were discussed with the special focus on the differences in tool wear between conventional drilling (CD) and UVAD. The observed wear behaviors can include abrasion, adhesion, oxidization, or the combination of them. The introduction of UVAD can effectively reduce the average width of tool flank wear with a maximum reduction of 13.0% when compared with CD. Both increased feed rate and decreased spindle speed can lead to decreased tool wear. The findings in this paper might offer guidance on the selection of cutting parameters for extending tool life in UVAD of CFRP. [ABSTRACT FROM AUTHOR]

• An interference-resistant gear defect detection method is proposed based on improved YOLOv5. • Ability of the network to extract defect features is enhanced by new module CBAMC3. • Combined module BiFPN_concat makes the network capable of fusing the features. • Cosine annealing function is used to improve the learning ability of the network. • Improved YOLOv5 network enhances the recall rate by 13.1% and the mAP @0.5 by 12%. Automatically detecting the metallic gear defects may encounter the misdetected and undetected errors when the defect features are very close to the interferences of oil stains and image shadow. To address these challenges, in this paper an industrial interference-resistant gear surface defect detection method is presented based on the improved YOLOv5 network. The method combines the approach using the attention module CBAMC3 constituted by CBAM and C3 modules together with the analysis of the module BiFPN_concat, which makes the network capable of extracting and fusing defect features, respectively. The cosine annealing function is then employed to improve the learning ability of the network by modifying the learning rate. The experimental results indicate that the improved YOLOv5 network enhances both the recall rate by 13.1% and the mAP @0.5 by 12% compared with the original YOLOv5 network, and also outweighs the classical algorithms in detection speed with average 25 frames per second. [ABSTRACT FROM AUTHOR]

The elastic state at contact wheel–workpiece interface is a critical issue during robotic belt grinding process that significantly influences the finishing profile accuracy. Establishing a reasonable undeformed chip-thickness (UCT) model that suits to this operation is considered a feasible approach to clarify the cutting mechanisms. In the present paper, an elastic state–driven robotic belt grinding chip-thickness model is established to predict the workpiece surface roughness. In this new model, the combined modulus of elasticity of the contact wheel is calculated according to the formula of Young's modulus, and the exponent with respect to the effects of linear and nonlinear deflection is further determined based on the energy balance hypothesis. Experiments are conducted to verify the reasonability of the improved chip-thickness model from the perspective of surface roughness, and the findings are likely to clarify the differences in material removal mechanism between wheel grinding and robotic belt grinding essentially. [ABSTRACT FROM AUTHOR]

Abstract The sharp increase of heat generated when processing difficult-to-machine materials is the main reason of short tool life and poor surface integrity. Temperature modeling plays a significant role in the mechanism of metal cutting, which can guide the optimization of cutting parameters. This paper proposes a modified three-dimensional analytical model of temperature prediction for oblique turning Inconel 718 with round carbide insert. The discretization of heat sources is indispensable to analyze the temperature rise due to the complicated geometry of uncut chip area. In this study, primary heat source (shear band) and secondary heat source (tool-chip interface) that divided into many increments through different discretization methods are considered to analyze thermal effects. For each increment of secondary heat source, the local contact length is calculated through a modified function considering global chip flow angle in oblique cutting. The local heat liberation intensities of primary and secondary heat sources are determined through analytical force prediction model. The variation of heat partition fraction with respect to immersion angle is given to study the characteristics of secondary heat source. Finally, a modified three-dimensional expression of temperature rises when turning with round insert considering semi-infinite medium is proposed based on classical thermal theory. The temperature distributions in chip, tool and workpiece can be determined through the proposed model. The results calculated through predictive model show good agreement with that given by finite element method (FEM) and experiments, which validates the correctness of the proposed model. [ABSTRACT FROM AUTHOR]

Turning operation is a fundamental machining method that is indispensable in aviation industry and automotive sectors, what is more, round insert is an important type of cutter due to its relatively massive engaged edge. Modeling of cutting force is important to forecast the machining process, what is more, to predict tool wear and surface quality of components. The cutting force distribution, often studied in milling and drilling operation, is necessary to be discussed in turning operation with round shape insert due to its complex and unique cutting geometry. In this paper, an analytical force prediction model for turning process is proposed based on the discretization of cutting edge and detailed geometric analysis with the consideration of edge effect and size effect, and applied to the force distribution of round insert. Firstly, a novel way is developed to divide the uncut chip area of round insert into many increments and the local parameters of each increment can be calculated by the classical oblique cutting theory. Secondly, shear flow stress of the workpiece at the primary shear zone is determined based on unequal division shear zone model and modified with the influence of size effect. The cutting force of each increment is predicted based on the oblique cutting theory with the consideration of edge effect. Then, an in-depth discussion of the distributions of local parameters is presented for each increment along the cutting edge of round insert, which indicates the characteristics of round insert. Finally, series of cutting experiments are performed on Inconel 718 and Ti6Al4V to verify the effectiveness of the developed model. The predicted results show good agreement with the measured ones, which proves the correctness and accuracy of the proposed analytical model. [ABSTRACT FROM AUTHOR]

• A convergent binocular vision algorithm under extended imaging dynamic range is proposed. • The proposed method is used to guide the machining robot for precise positioning. • Re-projection error with the extended dynamic range is enhanced by nearly 1 pixel level. • The average positioning error of the robot can be controlled within 3%. • This work provides reference for subsequent vision-guided robotic machining. The machining quality of large and complex components highly depends on the positioning accuracy of the vision guided robot. In order to solve the problems of limited imaging field-of-view and dynamic range of existing parallel binocular cameras, a convergent binocular vision algorithm under extended imaging dynamic range is proposed to guide the machining robot for precise positioning. Specifically, synthesize high dynamic range images combined with sigmoid function model, and chromaticity space color correction algorithm introduced for adaptive correction of image chromaticity information. The pose between the convergent binocular camera and the robot is calibrated to correct the three-dimensional coordinates of the target workpiece CAD model. The experimental results indicate that the high dynamic images synthesized by the proposed algorithm have clear surface details and balanced colors. This work further enhances the positioning accuracy of the machining robot to the target workpiece which is placed in arbitrary pose within the field-of-view. [ABSTRACT FROM AUTHOR]

Position guidance plays an essential role in guaranteeing welding quality. However, the current position guidance methods usually rely on the teaching trajectory or a similarly designed weld path. The innovation of this manuscript is to establish a teaching-free position guidance method combining the position detected by laser vision with the data bidirectionally sent by externally guided motion (EGM) at a high rate. A feature point extraction method based on Steger algorithm and slope determination is proposed. A dense zig-zag path is generated according to the position guidance based on EGM. Meanwhile, the position guidance experiments for fillet weld (horizontal deflection angle α = 9.2°, 13.3° and vertical deflection angle β = 5.5°, 9.2°) are finished. The mean absolute error (MAE) of position guidance in the Y -axis and Z -axis can be controlled in 0.21 and 0.13 mm, respectively. Moreover, the robot welding experiments for fillet weld in three different horizontal and vertical deflection angles (α = 30°, β = 25°, α = 30° and β = 25°) show that this method can obtain good weld surface morphology and metallographic morphology, and have a potential application value in industrial automation. [ABSTRACT FROM AUTHOR]

• A novel material removal prediction model for robotic belt grinding is developed. • The material removal volume of single abrasive grain is shaped like a semi-elliptic cone. • The mean absolute percentage error of material removal rate prediction is less than 1.725. • The material removal depth is positively correlated with normal force and negatively correlated with belt linear speed and robot feed speed. • Optimization strategy is implemented to balance the grinding quality and efficiency. Comprehensive study of the microscopic material removal mechanism remains an open challenge facing the robotic belt grinding of complex geometries. In the present paper, a new material removal rate (MRR) model is developed underlying the motion trajectory of single spherical abrasive grain by taking into consideration the elastic deformation of the heterogeneous contact wheel. In this model, the contact pressure distribution at the contact wheel–workpiece interface is determined by converting the three-dimensional contact problem into a one-dimensional linear spring model with respect to the large deformation of the contact wheel. In addition, the combined modulus and Poisson's ratio of the heterogeneous contact wheel are further considered based on the geometric relation of the Young's modulus and Poisson's ratio. Compared with the existing MRR model, the proposed MRR model can significantly reduce both the root mean square error (RMSE) and mean absolute percentage error (MAPE) values from 2.401 to 1.725, and 18.426% to 14.942%, respectively. Particularly, an optimization strategy from the perspective of process parameters is implemented to balance the grinding quality and efficiency. Image, graphical abstract [ABSTRACT FROM AUTHOR]