The invention discloses an intelligent manufacturing industry parameter optimization method based on machine learning and industrial Internet of Things, and the method comprises the following steps: S1, building an industrial Internet of Things system, bottom-layer equipment being connected into the industrial Internet of Things system, and extracting the operation data of the bottom-layer equipment; S2, analyzing process steps of the intelligent production line, building a digital production model of the intelligent production line, and the collected data corresponding to variables in the model and storing at different positions in a database; S3, building an association analysis model; S4, building a sequence model, and quantifying relevance rules; and S5, obtaining the relationship between different sections of the production line, and then building a gray model to calculate the change trend of the data between different sections. By importing the industrial Internet of Things system, centralized collection, centralized cleaning and centralized processing of production data are achieved, data support is provided for subsequent work, the optimal value of each part is calculated through a machine learning model, an engineer adjusts with the optimal value as the reference value, and a large amount of debugging workloads are reduced.