Association rules are the discovery of previously unknown, potentially useful and hidden knowledge in databases. Many algorithms have been proposed to find association rules in databases. Due to the diverse use's interest and preference to items, former algorithms do not work well in real world application. That is to say, in most algorithms of mining association rules, the items are considered to have equal time weight and are not dealt with quantitative attributes. Hence, to improve former algorithms, we propose an algorithm in this paper to mine fuzzy association rules considering time weight of each item and quantity of each item.