消化道微诊疗装置的定位微粒群算法研究

Research on particle swarm optimization for localizing medical micro-device in alimentary tract

为了对消化道内的微诊疗装置实现无创遥测跟踪,采用了多磁源的交流励磁定位新方法,在体外布置多个线圈,分时励磁产生交变磁场,通过无线磁传感器检测消化道内目标物所处的空间磁场,即可结合定位模型求解出目标方位。在方位求解中,针对高次非线性定位方程组变量多、不单调、具有多个局部极值点的特点,将方程组求解问题转化成非线性无约束寻优问题,创新地运用参数自调整的邻域微粒群优化定位算法对其求解。实验结果表明,定位算法具有不依赖于初值、精度高、收敛速度快的特点,成功解决了定位中多局部极值的高维优化问题,为定位方案的实现提供了理论依据。

In order to non-invasively track a medical micro-device in gastrointestinal tract,a novel telemetric method based on alternating magnetic fields was presented.In the telemetric method,several cylindrical energizing coils are located on the abdomen.All the coils are excited by time-sharing sinusoidal signals to generate alternating magnetic fields.And a wireless magnetic sensor is used to measure the magnetic field strength at the location of the micro-device.According to the relationship between the magnetic field strength and the location,the position and orientation of the micro-device could be obtained by solving a nonlinear system of equations.To simplify calculation,the system of equations for localization is transformed into an unconstrained nonlinear optimization problem.Then an improved particle swarm optimization （PSO） algorithm is employed to solve the unconstrained nonlinear optimization.Experiment result shows that the improved PSO algorithm succeeds in solving the high dimensional problem.Compared with conventional algorithms,the improved algorithm does not require a good initial guess to guarantee convergence.Furthermore,it has high precision and fast convergence speed.