Capacitive force sensor is susceptible to ambient temperature when operating.In order to reduce the influence of temperature

temperature compensation of the sensor is carried out by algorithm model based on particle swarm optimization least squares support vector machine(PSO-LSSVM).In different temperature environments

two-dimensional calibration experiments are carried out on the capacitive force sensor

the LM35 temperature sensor is used to obtain the experimental environmental temperature data

and the temperature compensa

tion model is established

and the model uses particle swarm optimization(PSO) algorithm to continuously optimize the selection of regularization parameter

γ

and kernel function parameter

σ

in least squares support vector machine(LSSVM) until the expected fitness function and number of iterations are reached.Comparing the data before and after the temperature compensation experiment

the zero temperature coefficient of the capacitive force sensor is increased from 1.393×10

-2

/℃ to 8.577×10

-5

/℃ .The sensitivity temperature coefficient is increased from 1.550×10

-2

/℃to 1.048×10

-4

/℃.The relative value of the additional error of temperature is increased from 65.094% to 0.440%.The precision and reliability of capacitive force sensors are improved by the PSO-LSSVM algorithm model.