Modal Analysis of Systems Using a Neuro-Fuzzy Approach
Bibliographic record
Abstract
A novel method of modal analysis for vibration modeling of systems is presented in this paper. In the developed method, first, mode shapes of the structure that is being analyzed are approximated. The approximate mode shapes are expressed by fuzzy sets where approximate deflections or displacement magnitudes of the mode shapes are described by fuzzy linguistic terms such as Zero, Medium, and Large. Fuzzy membership functions provide a means of dealing with the imprecisely defined system and it gives access to a large repertoire of tools available in the field of fuzzy reasoning. Second, fuzzy representations of the approximate mode shapes, called Fuzzy Mode Shapes in this paper, are updated using modal analysis data as obtained through experimentation. Finally, artificial neural networks are used as a tool to obtain an accurate version of the mode shape data by learning the target set of the data. An appropriate analogy of the application of Fuzzy Mode Shapes in the first step is the Starting Mode Shape Vectors in numerical eigenvector problem where the starting vector is updated through an iterative process. In this paper iterative updating process of mode shapes is carried out for the application of experimental modal testing. In this approach the differences between the fuzzy mode shapes and the corresponding measured modal testing data are minimized through an iterative process. In validating the developed technique for vibration modeling of one-dimensional and two-dimensional elastic bodies and structures, modeling of elastic beams, a clamped-free-clamped-free plate and a frame are used as illustrative examples. The solutions of the corresponding simulations are compared with the results from finite element computations and analytical model solutions. The good agreement of the results obtained for these models justifies the application of the developed method in experimental vibration modeling of systems. Use of the fuzzy-neural approach as developed in the paper expands the coverage of experimentally measured data, which is normally limited to a small number of measurement sets due to the limited number of available vibration sensors in the analyzed system. Neural networks provide a satisfactory interpolation of two sets of data including a) modal test data, which is accurate but is normally available only for a few measured points, and b) Fuzzy Mode Shapes, which are available for large number of points but are approximate.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".