PREDICTION OF OPERATOR PERFORMANCE DURING LEARNING OF REPETITIVE TASKS

Abstract

SUMMARY Learning effects in the execution of repetitive tasks may often be adequately described by an exponential law commonly found in physical systems. This law is characterised by the rise time and the final value of output rate. An iterative method is developed for the determination of rise time and final value using only performance data recorded during early stages of learning, and is shown to predict these parameters sufficiently accurately for use in costing and in continuously updating lime standards. Further uses of the predictive technique include highlighting the need for increased supervision, or the replacement of particular operatives. When experimental data is oscillatory in nature, prediction errors are greatly reduced by three-point averaging tuned to the period of oscillation. Much of the experimental data has been recorded in industrial environments, frequently for long production runs.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 67 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.