CAJ | 학술논문

为了准确快速地对结构进行健康检测，文章将遗传算法用于框架结构的损伤识别，以刚度系数损伤因子为设计变量，计算与测量出的结构固有频率和振型加权组合差值为目标函数；针对基本算法在选择交叉率和变异率时的问题，对遗传算法的选择算子、交叉算子和变异算子流程进行了改进；将操作算子并行地施加在父代个体上，提高交叉率和变异率至100％，同时，对相似个体施加惩罚算子，以保持个体的差异性，既保存了父代中的较优个体，又不至于陷入局部最优。3层的钢框架单变量和多变量损伤算例分析结果表明，改进遗传算法能较好地识别出结构的损伤位置和损伤程度。
위료준학쾌속지대결구진행건강검측，문장장유전산법용우광가결구적손상식별，이강도계수손상인자위설계변량，계산여측량출적결구고유빈솔화진형가권조합차치위목표함수；침대기본산법재선택교차솔화변이솔시적문제，대유전산법적선택산자、교차산자화변이산자류정진행료개진；장조작산자병행지시가재부대개체상，제고교차솔화변이솔지100％，동시，대상사개체시가징벌산자，이보지개체적차이성，기보존료부대중적교우개체，우불지우함입국부최우。3층적강광가단변량화다변량손상산례분석결과표명，개진유전산법능교호지식별출결구적손상위치화손상정도。
In order to detect the health of structure accurately and quickly ,genetic algorithm was used to iden-tify the damage of frame structure .Stiffness coefficient damage factor was selected as design variable ,and the weighted array difference value calculated and measured between inherent frequency and vibration mode of structure as objective function .In view of the difficulty in selecting crossover rate and mutational rate for fun-damental algorithm , the process of selection operator ,crossover operator and mutation operator was im-proved .All operators were operated on parent individual .Crossover rate and mutational rate were set for 100% .Punishment function was applied for keeping the difference among individuals .The improved genetic algorithm can conserve the better individual in parent and keep off falling into local optimum .The numerical analysis of a three-story frame with single variable damage and multiple variables damage was conducted ,and the results showed that the improved genetic algorithm could identify the damage location and degree .