As part of our AI x CAE activities, we have also been investigating and researching surrogate models. Here are some of the topics we have discussed.
What is CAE simulation?
CAE stands for Computer Aided Engineering, and is a method of reducing the cost and increasing the efficiency of product design and evaluation by using computers to simulate the performance of products affected by external forces, heat, fluids, and electromagnetic waves, mainly in the product design stage.
CAE simulation has the following advantages:
・ Not only is it more cost effective and efficient than experiments using actual objects, but it also enables design and evaluation even when actual objects are not available.
・ With the recent development of PC processing speed, CAE can be applied to a wider range of applications and time can be reduced.
Problems with CAE simulation
As the application of CAE expands, more and more people are looking for higher accuracy and shorter simulation times.
This has led to the following problems with CAE simulation.
→As the content of the study became more and more complex, the simulation time became more and more time consuming to perform the calculations from scratch.
→As CAE simulation methods have become more complex, the cost of software and hardware has increased, there has been a shortage of specialized engineers, and training costs have increased. Software maintenance costs have also risen.
Addressing problems in CAE simulation
In order to meet the challenges of CAE simulation, the idea of a “surrogate model” that replaces CAE analysis (simulation) with an AI model has emerged.
A surrogate model can be used to address the issues of CAE simulation.
・Since AI does not calculate the analysis from scratch, the time required to run the analysis can be significantly reduced.
AI model training takes time, but AI model execution time can be reduced. In addition, the training of AI models can be done without human intervention.
・No specialized knowledge of AI is required and it is easy to use.
Training of AI models requires specialized knowledge, but evaluation of AI models does not require specialized knowledge.
Comparison of surrogate models using conventional CAE and 2D AI
Problems with surrogate models using 2D AI
Although surrogate models can address some of the problems of CAE simulation, there are also problems with 2D AI-based surrogate models, as follows.
・In the design field, handling 3D data instead of 2D data has become the mainstream, and existing 3D data cannot be used.
・Even if AI is trained on a 3D object using 2D data, the accuracy of AI evaluation is poor.
・In order to train the AI, it is necessary to create new 2D data. In addition, a large amount of training data is required to create 2D data by photographing 3D objects from multiple angles.
Responding to problems with surrogate models using 2D AI
In order to deal with the problems of the surrogate model by 2D AI, a surrogate model of 3D AI that can handle 3D data is required instead of the surrogate model of 2D AI.
-Since AI learns a three-dimensional object with three-dimensional data, the accuracy of AI evaluation is high.
-Since existing 3D data can be utilized, there is no need to prepare new 2D data.
However, in the world of AI (deep learning), it is difficult to handle 3D data.
Convolutional techniques for 3D meshes (CNNs for 3D meshes) are necessary to realize a surrogate model for 3D AI.
We are the only company that actually provides this CNN for 3D mesh at this time.
Using CNN technology for 3D meshes, we are the pioneer in the world in realizing 3D shape classification that can classify 3D data, 3D new shape synthesis that designs a new 3D shape by combining two 3D data, and 3D similarity judgment technology that can match 3D data by shape and size.
Furthermore, by applying CNN technology for 3D meshes, we are constantly researching and developing world-leading 3D AI surrogate models.
Comparison of 2D AI surrogate model and 3D AI surrogate model
Preparing for Surrogate Models with 3D AI
• A surrogate model can be used to solve the problems of CAE simulation. Furthermore, the limits of CAE simulation can be exceeded.
• AI is mainly based on 2D data and does not handle 3D data very well. 3D proxy models would allow for more accurate and precise simulations.
• In order to realize a 3D surrogate model, 3D mesh convolution technology (CNN for 3D mesh) is essential, and we are the only company that actually provides this CNN for 3D mesh at this time.