CAJ | 학술논문

介绍了一种重要的人工神经网络——最优线性联想网络，并将其应用在X射线谱分析中，成功地克服了传统解谱方法速度慢、不能准确分析含有重峰的复杂X射线谱的缺点。最优线性联想网络解谱方法广泛应用于快速在线测量及现场分析的各种场合，特别是当待分析样品组分固定时，解谱效果更好。
개소료일충중요적인공신경망락——최우선성련상망락，병장기응용재X사선보 분석중，성공지극복료전통해보방법속도만、불능준학분석함유중봉적복잡X사선보적결점 。최우선성련상망락해보방법엄범응용우쾌속재선측량급현장분석적각충장합，특별시당대 분석양품조분고정시，해보효과경호。
This paper describes a new approach to the au tomatic radioisotope identificat ion problem based on the use of OLAM network. Different from the t raditional methods, the OLAM network takes the spectrum as a whole comparing it s shape with the patterns learned during the training period of the network. In this paper, it is found that the OLAM network, once adequately trained, is quite suitable to identify a given isotope present in a mixture of elements as well as the relative proportions of each identified substance.Preliminary results are good enough to consider OLAM network as powerful and sim ple tools in the automatic spectrum analysis.