Application of Various Machine Learning Models for Process Stability of Bio-Electrochemical Anaerobic Digestion

The application of a machine learning (ML) model to bio-electrochemical anaerobic digestion (BEAD) is a future-oriented approach for improving process stability by predicting performances that have nonlinear relationships with various operational parameters. Five ML models, which included tree-, regression-, and neural network-based algorithms, were applied to predict the methane yield in BEAD reactor. The results showed that various 1-step ahead ML models, which utilized prior data of BEAD performances, could enhance prediction accuracy. In addition, 1-step ahead with retraining algorithm could improve prediction accuracy by 37.3% compared with the conventional multi-step ahead algorithm. The improvement was particularly noteworthy in tree- and regression-based ML models. Moreover, 1-step ahead with retraining algorithm showed high potential of achieving efficient prediction using pH as a single input data, which is plausibly an easier monitoring parameter compared with the other parameters required in bioprocess models.

Effect of Process Modes on Tangential Component of Cutting Force during Belt Rotary Grinding of Aluminium Alloy Blanks D 16

These days, in the manufacture of units and mechanisms of ships, aircraft and other technological machines, industrial robots, long-sized products from D 16 (Standart GOST-R) aluminum alloy are used, for the processing of which a complex for belt rotary grinding has been developed. The outcome measures of the rotary belt grinding process depend on the cutting forces generated during the processing process. According to cutting forces, process stability is diagnosed, values of surface roughness indices, temperatures and cutting modes are calculated according to displacement balance equation. The article is devoted to obtaining a mathematical model establishing the relationship between the tangential component of the cutting force and cutting modes during belt rotary grinding of D 16 aluminum alloy.

Evaluating fixed-film nitrification systems in autotrophic mode: Enhanced biomass retention does not improve bioreactor performance during alkalinity induced stress

Use of fixed-film systems has shown promise towards improving the process stability of biological nitrogen removal (BNR). It allows for biofilm formation, which can offer enhanced resilience to environmental stressors...

Impact of the thickness of the wall of optical lenses on the production process stability

The article compares the stability of the production process of plastic optical lenses produced by the injection molding process. Moreover, it evaluates the effects caused by using very thick walls and very thin walls in plastic optical lenses. The injection process are divided into three fundamental stages. The first is the injection of plastic into the mold itself (filling). During this phase, 95–99% of the cavity volume is filled. The second phase is the so-called after-pressure, where the remaining cavity spaces are filled, and the part reaches dimensional stability. The last stage is called cooling. During the final phase, the element is solidified and becomes dimensionally stable in lower temperatures. In the current work, the authors compare the lenses that differ only in the maximum wall thickness. In the experiments, the conditions of changing pressure and injection speed were simulated. During injection, slight changes in the injection parameters may occur due to the random external influences. Those influences include the change in ambient air temperature, voltage fluctuations in the electrical system, machine vibrations, imperfect homogeneity of the material used, etc. The common process parameters that the organization uses by default were used as a basis. The after-pressure and injection pressure were changed to 102%, 105%, 98%, and 95% in the experiments. The results evaluate the proportion of non-conforming products (scrap) that appertain to each change in the parameters of production. The research proves the dependence between the thickness of the lens wall and the stability of the process. Although a higher total waste is expected for thick-walled lenses, the knowledge of the stability of the process in the production of lenses has not yet been recorded though it is a significant indicator for the production planning. It is known that a lower process stability is expected based on the design for these types of elements, and the researrchers were able to take measures to eliminate this risk and thus reduce the total waste and other negative impacts on production. Modifications to the mold can also achieve some improvement in this condition. The first step is to expand the cross-section of the inlet channel gate. The pressure is transmitted to the cavity through this cross-section. Its enlargement ensures a more even distribution of the pressure in the entire volume of the part. Another way to facilitate production is to guarantee optimal cooling of the cavity. It can be achieved by placing the cavity away from the hot runner system so that the cooling can be evenly distributed around each side of the part. The last way to solve the problem of collapse is to create a counter-deformation in the mold. That is to enlarge the cavity so that the lens sinks into the desired shape. These measures may include preventive debugging of the mold for multiple presses in case the press needs to be changed and preferably placing such elements on newer injection molding machines where parameters are less likely to fluctuate and avoiding moving such molds to presses for which they have not been debugged unless necessary. The work aims to prove the dependence between the thickness of the optical lens and the stability of the injection process. While waste percentage, cycle time, and other parameters are considered and quantified at the design stage of the optical lens, process stability has not yet been quantified. Proving the dependence between the above-mentioned phenomena will allow predicting the process stability of new lens designs more precisely.

Influence of Ring-Shaped Beam Profiles on Process Stability and Productivity in Laser-Based Powder Bed Fusion of AISI 316L

A major factor slowing down the establishment of additive manufacturing processes as production processes is insufficient reproducibility and productivity. Therefore, this work investigates the influence of ring-shaped beam profiles on process stability and productivity in laser-based powder bed fusion of AISI 316L. For this purpose, the weld track geometries of single tracks and multi-track segments with varying laser power, scan speed, hatch distance, and beam profile (Gaussian profile and three different ring-shaped profiles) are analyzed. To evaluate the process robustness, process windows are identified by classifying the generated single tracks into different process categories. The influence of the beam profiles on productivity is studied by analyzing the molten cross-sectional areas and volumes per time. When using ring-shaped beam profiles, the process windows are significantly larger (up to a laser power of 1050 W and a scanning speed of 1700 mm/s) than those of Gaussian beams (laser power up to 450 W and scanning speed up to 1100 mm/s), which suggests a higher process robustness and stability. With ring-shaped beam profiles, larger volumes can be stably melted per track and time. The weld tracks created with ring-shaped profiles are significantly wider than those generated with Gaussian profiles (up to factor 2 within the process window), allowing enlargement of the hatch distances. Due to the higher scanning speeds and the enlarged hatch distances for ring-shaped beam profiles, the process can be accelerated by a factor of approximately 2 in the parameter range investigated.

Quality control in the production process of sunflower oil

The typical problem of vegetable oil processing is to ensure the consistency of the output quality. The one parameter that mostly affects quality is the presence of wax, which commands control at all stages of the process (refinement, odours removal, freezing). Statistical methods of analysis can be usefully applied to the improvement of vegetable oil processing, as demonstrated by this study. The authors in fact used statistical methods in order to: a) optimize parameters consistency, b) enhance process efficiency, c) improve economic performance and finally, d) assess process stability. The following statistical tools were used in the study: 1) Histograms, 2) Shewhart Charts, 3) Ishikawa Diagrams and, 4) Pareto Chart. A first major finding was that the occurrence of process flaws that would result in product rejection had a 5% probability of happening at all stages of the process. Moreover, the analysis of process stability with maps of average values and ranges leads to the finding that the process itself is statistically unstable. Finally, cause-and-effect relationships of influencing factors (such as the quality of feedstock) were investigated, thus determining the main causes of flaw in the production process. This leads to the definition of corrective actions, the effectiveness of which was then investigated and evaluated.

Laser Polishing of Additive Manufactured Aluminium Parts by Modulated Laser Power

In this study a new approach to laser polishing with periodic modulated laser power in the kilohertz regime is introduced. By varying the modulation frequency and modulation time, different periodic laser power curves with varying minimum, peak and average laser power can be created. The feasibility of the method is shown by polishing of vertical built AlSi10Mg L-PBF parts with an initial roughness of Ra = 12.22 µm. One polishing pass revealed a decreasing surface roughness with increasing energy density on the surface up to Ra = 0.145 µm. An increasing energy density results in a rising remelting depth between 50 and 255 µm and a rising relative porosity of 0.3% to 4.6%. Furthermore, the thermal process stability, analysed by the melt pool length in scanning direction, reveals a steadily increasing melt pool dimension due to component heating. Multiple laser polishing passes offers a further reduced surface roughness, especially at higher modulation frequencies and provides an improved orientation independent roughness homogeneity. The process stability regarding varying initial surface roughness revealed an almost constant relative roughness reduction rate with an achievable roughness variation after two polishing passes between Ra = 0.13–0.26 µm from an initial state of Ra = 8.0−19.2 µm.