Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy

Purpose As complex analysis of contact models is required in the traditional assembly strategy, it is still a challenge for a robot to complete the multiple peg-in-hole assembly tasks autonomously. This paper aims to enable the robot to complete the assembly tasks autonomously and more efficiently, with the strategies learned by reinforcement learning (RL), a learning-accelerated deep deterministic policy gradient (LADDPG) algorithm is proposed. Design/methodology/approach The multiple peg-in-hole assembly strategy is designed in two modules: an advanced planning module and a bottom control module. The advanced module is completed by the LADDPG agent, which is used to derive advanced commands based on geometric and environmental constraints, that is, the desired contact force. The bottom-level control module will drive the robot to complete the compliant assembly task through the adaptive impedance algorithm according to the command set issued by the advanced module. In addition, a set of safety assurance mechanisms is developed to safely train a collaborative robot to complete autonomous learning. Findings The method can complete the assembly tasks well through RL, and it can realize satisfactory compliance of the robot to the environment. Compared with the original DDPG algorithm, the average values of the instantaneous maximum contact force and contact torque during the assembly process are reduced by approximately 38% and 74%, respectively. Practical implications The entire algorithm can also be applied to other robots and the assembly strategy can be applied in the field of the automatic assembly. Originality/value A compliant assembly strategy based on the LADDPG algorithm is proposed to complete the automated multiple peg-in-hole assembly tasks.

Integrated Tolerance and Fixture Layout Design for Compliant Sheet Metal Assemblies

Part tolerances and fixture layouts are two pivotal factors in the geometrical quality of a compliant assembly. The independent design and optimization of these factors for compliant assemblies have been thoroughly studied. However, this paper presents the dependency of these factors and, consequently, the demand for an integrated design of them. A method is developed in order to address this issue by utilizing compliant variation simulation tools and evolutionary optimization algorithms. Thereby, integrated and non-integrated optimization of the tolerances and fixture layouts are conducted for an industrial sample case. The objective of this optimization is defined as minimizing the production cost while fulfilling the geometrical requirements. The results evidence the superiority of the integrated approach to the non-integrated in terms of the production cost and geometrical quality of the assemblies.

Assembly research of aero-engine casing involving bolted connection based on rigid-compliant coupling assembly deviation modeling

Assembly analysis is necessary for mechanical product to optimize design and improve the product quality since assembly deviation is the key factor affecting the assembly quality. In this paper, the rigid-compliant assembly of thin-walled aero-engine casing is studied to evaluate the assembly quality at the design stage. First, the Jacobian–Torsor model is proposed to construct multistage casing assembly owing to its effectiveness to express assembly deviation. The torsor expression is modified and expanded to present the rigid-compliant coupling tolerance. Then, the partial parallel chain is addressed via combination operation. By using extremum and statistical method, the tolerance zone and the distribution of the objective deviation are obtained. Furthermore, to study the effect of specified compliant deviation on statistical distribution, the bolt looseness and positional deformation are investigated to provide an effective means for geometric deviation and connecting joints of aero-engine casing components of precision assembly. The presented method can address compliant deformation tolerance and geometrical manufacturing tolerance together, and is reliable for casing assembly to predict assembly quality at the design stage. In addition, it also has a great significance to guide tolerance design and product optimization.

A Modeling Approach for Elastic Tolerance Simulation of the Body in White Hang-On Parts

Computer aided tolerancing (CAT) in the automobile industry is implemented by CAD tools. These tools analyze the manufacturability of complex assemblies with rigid single parts in an early stage to reduce the product development time and the cost for hardware prototypes. This paper proposes an approach to implement tolerance simulation for a compliant assembly, which includes manufacturing processes such as clinching, bolting and hemming by applying tolerance simulation tool. The fender- BIW system is simulated as a compliant–rigid system and the simulation model is applied to two production scenarios. The simulation results are compared with real measurement data, which demonstrates the efficacy of using simulation in early production as opposed to prototyping or other methods of design by showing the strong correlation between simulation results and as-built products.

Compliant assembly analysis including initial deviations and geometric nonlinearity—Part I: Beam structure

In the past decades, several compliant assembly analysis models have been developed to consider structural deformations during assembly progresses. Available methods address the influence of linear elastic deformations, whereas for the case of large-scale flexible structures with complex boundary conditions, the geometric nonlinearity will be a significant factor affecting the accuracy of assembly variation prediction. This paper introduces a refined mechanical model to develop a variation analysis method for beam structures. Based on the Timoshenko theory, governing equations of flexible beam are obtained by using the principle of virtual work with consideration of initial deviations and a von Kármán type of kinematic nonlinearity. Moreover, corresponding finite element formulas are presented, which also can be degenerated into non-initial deviation form or the linearized form. With the nonlinear beam model, an assembly variation analysis method is proposed for beam structures, which takes initial deviations, fixture errors, and matching deviations into account. Case studies of static loading analysis and slender beam assembly springback analysis are demonstrated to verify the feasibility and accuracy of the presented method.

Compliant assembly analysis including initial deviations and geometric nonlinearity, part II: Plate structure

Part I of this paper (Liu et al., “Compliant assembly analysis including initial deviations and geometric nonlinearity, part I: Beam structure”) has studied the variation propagation of beam structures with consideration of initial deviations and geometric nonlinearity. In practices, plate structures are more commonly used in manufacturing fields, and the attempt of this paper is to expand previous methodology for the assembly process of orthotropic composite plate structures. Similarly, initial deviations and von Kármán-type geometric nonlinearity are introduced into variation analysis model, with Mindlin plate theory accounting for shear effect. The analyzed plates are set as orthotropic composite materials, which also preserve the compatibility with isotropic metal materials. Governing equations and corresponding finite element expressions can be obtained by applying the principle of virtual work. Also, a linearized model or noninitial model can be regarded as a degradation of origin governing equations. A variation analysis approach for plate structures is proposed to make more refined assembly variation predictions with consideration of initial deviations, fixture errors, and matching deviations. The verification of the developed method is implemented with case studies on springback prediction of two composite plates assembly.