In the general frame of process surveillance, principal component analysis (PCA) has been often selected due to its simplicity and ability to capture the linear relations between the stationary process variables. However, the method showed limitations when dealing with industrial data that generally presents non-linear and multiscale features. The approach proposed in this study rests on the modelling using non-linear PCA coupled with artificial neural networks (ANNs) to extract the non-linear inter-correlation between variables and on the wavelet analysis to decompose each sensor signal into a set of coefficients at different scales. The contribution of each variable for each scale is then collected in separated matrices and a non-linear PCA model is constructed for each matrix. The proposed approach is applied to fault detection of pollution parameters affecting the region of Annaba in Algeria. The performance of the approach is then illustrated and compared with those of classic PCA and multiscale PCA (MSPCA).
- Inderscience Publishers
- Non-linear multiscale principal component analysis for fault ...
Tetrapak, Alfa Laval, Westfalia, Cream separators and Sialex®Ring - Case Study
Tipperary Co-operative, use Sialex®Ring to help control "Scaling" on Plate Heat and Shell and Tube heat exchangers on their " hot water circuits". A further area suitable to benefit from Sialex® is in the Cream separators. These devices are prone to "Scale" build up on flushing jets. Cleaning requires did-assembly and cleaning. This can occur several times during a year. Platetek Engineering proposed installing Sialex®Ring onto the water "feed lines" to the cream separators (Alfa Laval, westphalia)....
Case Study PHE (Plate Heat Exchanger) test results in hard water region
Industry, hotels, commercial buildings even private homes in "Hard" water areas are at a disadvantage due to "Scale" formation on devices, particularly those attached to "Hot" water circuits. A PHE (Plate Heat Exchanger) with a known "Scaling" problem is selected for testing. The attached case study demonstrates how with an "Open" mind, even those sceptical of our products capabilities, do not dispute the achieved results.
Maximizing membrane life: lessons learned from a three year study on performance recovery
Abstract Reverse Osmosis (RO) membranes are susceptible to several different types of foulants and scales. Common foulants observed in RO systems are organics, metals, clays and colloidal material. Common scales that are observed are carbonate, phosphate, sulfate and silica. Onsite cleaning is the norm to remove these foulants and scales but sometimes a desire for cleaning optimization or a requirement for process troubleshooting leads operators to undertake a more detailed investigation. Therefore, one option...
Advancements in Scaling Calculations and an in depth look at Antiscalant dosing for stressed waters ...
Abstract Over the past few decades the Reverse Osmosis (RO) industry has observed an increase in applications in challenging waters. Water sources that were never considered suitable for RO are now commonplace, including municipal waste streams, industrial waste, and even mining waste. Furthermore, regulatory restrictions, environmental obligations, solid waste expenses, and water supply shortages have forced the industry to push system recoveries to higher and higher limits. Many systems are now running at...
Case Study PHE Solving fouling test results
Industry, hotels, commercial buildings even private homes in "Hard" water areas are at a disadvantage due to "Scale" formation on devices, particularly those attached to "Hot" water circuits. A PHE (Plate Heat Exchanger) with a known “Scaling” problem is selected for testing. The attached case study demonstrates how with an “open mind”, even those sceptical of our products capabilities, do not dispute the achieved results. A simple to understand test procedure was followed. Information...