Feasibility Study on the Use of Dynamic Neural Networks (DNN’s) for Modeling a Variable Displacement Load Sensing Pump
Bibliographic record
Abstract
The feasibility of using a particular form of neural networks, defined as Dynamic Neural Units (DNU's), to model a pump in a load sensing system is investigated in this paper. Because of the highly complex structure of the pump, its compensators and controlling elements, simulation of load-sensing pump systems pose many challenges to researchers. Several models of pumps, compensators and valves have been developed and published in the literature but they are overly simplified or are in an extremely complex form. One modeling approach which can capture the nonlinear dynamic properties of the pump yet still retain reasonable simplicity in its basic form is to use neural network technology. Previous studies have shown some limited success in using feed forward neurons with dynamic properties being introduced using time delays. A problem referred to a error accumulation has prevented these neural based models from being practical dynamic representations of load sensing systems. Based on the topology of the biological neural systems several new structures, Dynamic Neural Units (DNU's) have been developed. Only one DNU is necessary to capture or represent some of the dynamics of a plant, which a static (feed forward) neuron cannot do. The main advantage of the dynamic neuron is that it reduces the network dimension and the amount of computational requirement and has the potential to avoid this error accumulation problem. The use of Dynamic Neural Networks with Dynamic Neural Units in simulating a variable displacement pump is presented in this paper. Only the pump portion of the load sensing pump system is considered due to problems of interacting operating points. A DNU structure and a DNN (which is comprised of DNU's) are introduced. The simulation results establishes the feasibility of using a Dynamic Neural Networks with DNU's to model a simulated nonlinear hydraulic system such as a load sensing pump.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".