The artificial neural network (ANN) model and its user interface were developed using a widely-used visual programming tool, Visual Basic (VB), on the Windows platform. The ANN module was designed based on the fundamental principles of neural networks, incorporating the characteristics of spring permanent deformation and data from various influencing factors. The system has been fully implemented and is now in operation.
Once the self-learning neural network module of the prediction model is connected to the database samples, it performs self-learning on the sample data, classifying them to establish the relationship between the spring's permanent deformation and each influencing factor. This process has achieved a high level of prediction accuracy. In future applications, the system's forecasting capabilities and scope will be further expanded.
During the trial operation, the system's interface was aesthetically designed, auxiliary functions such as help files were improved, and installation files were generated. As a result, the system can now be installed and run in real production environments.
To use the software, users can click on "Spring Residual Deformation Prediction" under the "Prediction" menu or the corresponding button on the toolbar. A prediction interface will then appear. Users are required to input the design height of the spring based on drawings or actual conditions, along with other parameters such as free height, load, spring diameter, wire diameter, and the number of effective coils. Optional inputs like maximum load and height can also be provided for reference. If these are not entered, the system will prompt the user to confirm the input. After verifying the data, pressing the "Predict" button will display the predicted spring height before the strong pressure test and the residual deformation (permanent deformation) after the test in the result box.
Practical application has shown that the artificial neural network is highly feasible in predicting the permanent deformation of helical compression springs, achieving satisfactory results with minimal error (as shown in Table 1). Additionally, the system can manage and store spring test data, making it highly practical. However, due to the limited number and distribution of existing data samples, and the fact that ANNs excel at interpolation but struggle with extrapolation, some predictions may have minor inaccuracies. These issues will be addressed and improved upon in future updates.
The software has already been developed and is in active use by the technical department to predict failures in various compression springs. By inputting key parameters such as the design height of the spring, elastic modulus, spring diameter, wire diameter, and the number of effective coils, the system can predict the spring’s height and permanent deformation before production. This predictive capability helps guide the manufacturing process, ensuring better quality control prior to the strong pressure test.
Center Valve,Rotation Type Center Valve,Sanitary Center Valve,Beer Racking Arm Valve
Ningbo Wenhan Fluid Equipments Co., Ltd. , https://www.wenhanvalves.com