Technological developments enable the design and manufacturing of products tailored to individual consumers. Cellular Manufacturing Systems (CMS) can be considered as to ease flexibility, to reduce setup time, throughput time, work-in-process inventories, and material handling costs. Cell formation problem (CFP) that is one of the critical CMS design problems is the assignment of parts and machines to specific cells based on their similarity. This study introduces a Clonal Selection Algorithm (CSA) with a novel encoding structure that is efficient to solve real-sized problems. Unlike the methods in literature that define the number of cells as a constant number, this algorithm is significant because it can obtain the optimum number of cell to generate best efficacy value. Proposed CSA is tested by using 67 (35 well-known and 32 less-known) test problems. CSA obtains the same 63 best-known optimal solutions, provides solutions for the 3 of the well-known test problem and a new solution for the largest test problem (50 machine 150 part) that was not possible to be solved by the mixed integer linear programming model due to the high computational complexity. Final CSA grouping results are illustrated with figures to attract attention to the singleton and residual cells.