CSAPSO-BPNN based modeling of end airbag stiffness of nursing transfer robot

The use of nursing transfer robots is a vital solution to the problem of daily mobility difficulties for semi-disabilities. However, the fact that care-receivers have different physical characteristics leads to force concentration during human-robot interaction, which affects their comfort. To address this problem, this study installs an array of double wedge-shaped airbags onto the end-effector of a robot, and analyses airbag mechanical properties. Firstly, this study performed the mechanical testing and data collection of the airbag, including its external load and displacement, at various gas masses. Then the performance of the Back Propagation (BP) neural network is improved by using chaos (C) theory and simulated annealing particle swarm optimization (SAPSO), resulting in the establishment of the CSAPSO-BP neural network. By this method, a fitting model is developed to determine the mechanical parameters of the wedge-shaped airbag stiffness, and the fitting relation of external load-displacement is obtained. Data analyses show that the wedge-shaped airbag stiffness increases quadratically, linearly, and with a constant rate as the gas mass increases. The airbag stiffness regulation and model describe its 3 distinct phases with quadratic, linear, and linear invariant characteristics as the gas mass changes. These findings contribute to the structural optimization of airbags.

Methods
Fig. 2 depicts the test platform for the end airbag of the nursing transfer robot, which includes a universal material test machine, data acquisition system, double wedge-shaped airbag, airbag control system, gas mass flow meter, and air pump. The air pump serves as the air source for inflating airbags, while the control system enables the inflation and deflation of each airbag. The airbag mechanical parameters are evaluated by using the universal material test machine, while the data acquisition system is used to obtain mechanical parameters associated with airbag stiffness.

Before conducting the mechanical parameter tests, the first step is to determine the range of tests for the airbag gas mass and external load. The gas mass flow meter is used to measure the airbag’s gas mass (the product of cumulative gas flow rate and density). The external load test range is dependent on the adult body weight and the number of airbags being directly loaded. Since most adults weigh between 40–120kg, and 8 wedge-shaped airbags are loaded directly onto a human body, the external load range for each airbag falls within 11.53–34.58N. To meet actual load requirements, the external load test range is enlarged by a 1.5 factor, resulting in a range of 0–51.88N.

The mechanical test of the wedge-shaped airbag aims to evaluate its stiffness parameters such as gas mass, external load, original height of the airbag (vertical height under no-load), displacement (the difference between original height and height under load), among others. It is vital to note that the tiny gas mass inside the airbag greatly impacts the accuracy of the mechanical parameter test results. Therefore, as a starting point, the gas mass just filling the airbag (1.29g) is used as the initial experimental group, with an increment of 0.258g per group and a maximum gas mass of 4.902g.