基于MLP的海上无人跨域协同效能评估系统的设计与实现

Design and Implementation of Maritime Unmanned Cross-Domain Collaborative Effectiveness Evaluation System Based on MLP

针对海上无人协同跨域系统的探测能力效能评估问题,需开展评估指标、评估算法等研究。将机器人自身参数与环境参数结合构建了评价指标计算模型,如探测覆盖率、重复探测率、单位面积上的像素数量、能量等指标和海上无人跨域协同系统探测能力指标评价体系,降低了评估过程中的主观性,采用ADC(availability dependability capability)法结合层次分析法生成训练数据,利用MLP(multilayer perceptron)神经网络法客观地衡量系统的效能,结果表明:生成的数据集规模达到2万,该模型评估误差在3%以下,验证了其有效性和适用性;利用PyQt5框架搭建了评估系统界面,实现了环境建模、数据录入、效能评估的功能。

In the face of the problem of evaluating the detection capability effectiveness of the maritime unmanned cross-domain collaborative system,it is necessary to study the evaluation indexes and evaluation algorithm.In this paper,the robot's own parameters and environmental parameters are combined to build a calculation model for evaluation indexes,such as detection coverage rate,repeated detection rate,the number of pixels per unit area,and energy as well as an evaluation system for detection capability of the maritime unmanned cross-domain collaborative system.The subjectivity in the evaluation process is reduced,and training data is generated by the availability dependability capability(ADC)method combined with analytic hierarchy process.The multilayer perceptron(MLP)neural network method was used to objectively measure the effectiveness of the system.The results showed that the size of the generated data set reached 20,000,and the evaluation error of the model was less than 3%,which verified its effectiveness and applicability.Meanwhile,the PyQt5 framework was used to build the evaluation system interface,realizing the functions of environment modeling,data entry,and effectiveness evaluation.