In addition to the statistical advantages of JMP, from a design perspective, the advantage of JMP as a design platform lies in the flexibility of constructing formula-based simulators and data-based dashboards. All tasks, including CAE (Computer Aided Engineering) and experiments (Test), boil down to the process of acquiring data through process integration and how useful the results are from the acquired data. From this perspective, we recently defined all design processes as "Python Process Integration and JMP Machine Learning Optimal Design" to proceed with the task by taking advantage of Python's remarkable extensibility in the engineering field and JMP's advantages as a decision-making platform in the engineering field.
The "Python Process Integration and JMP Machine Learning Optimal Design" process is defined by three design items: "Python Process Integration", "JMP Machine Learning", and "JMP Optimal Design". In particular, from the perspective of "JMP Machine Learning", it determines whether or not a machine learning model is built. If a machine learning model is built, the "Machine Learning Simulator" of "JMP Optimal Design" is applied. If the machine learning model is not built, the "Decision Dashboard" of "JMP Optimal Design" is applied.
In this study, we will cover various successful cases in the fields of navy, aviation, CAE, and experimentation from the perspective of “machine learning simulator” and “decision dashboard”.
