Identifying Flow Patterns in a Narrow Channel via Feature Extraction of Conductivity Measurements with a Support Vector Machine

Yang, Kai; Li, Jiajia; Wang, Min; Wang, Hua; Xiao, Qingtai

doi:10.3390/s23041907

Cited by 15 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the fluids mixing process of the metallurgical process always involves gas-liquid two-phase flow. [8][9][10] For instance, He et al obtained the images of the flow field inside the molten pool by numerical simulation. [11] Liu et al simulated the gas-liquid flow in horizontal stirred tank and investigated the multi-objective parameter optimization.…”

Section: Introductionmentioning

confidence: 99%

Dynamic chaos of imaging measurements for characterizing gas–liquid nonlinear flow behaviour in a metallurgical reactor stirred by top‐blown air

Yang,

Zhang,

Yang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

A modern chaos detection strategy for imaging measurements is proposed in this work to quantify the thermal mixing state quality in a metallurgical reactor stirred by top‐blown air. Specifically, the improved C‐C algorithm is proposed to reconstruct the phase space of the nonlinear time series of the bubble characteristics under thermal conditions. Moreover, a chaos decision tree algorithm is introduced to extract the chaotic mixing characteristics of the thermal two‐phase mixing system for the first time. Experimental and calculated results show that all the possible mixing states of the mixing system are visualized by reconstructing the phase space with the help of the visualization technique of the thermal gas–liquid two‐phase flow. It is found that the attractor of the nonlinear time series of bubbles exhibited more serious variations while the chosen working condition was optimal. Furthermore, the obtained parameter represents the chaotic characteristics of the thermal gas–liquid two‐phase mixing system which has chaotic characteristics under various experimental conditions. Hence, the new strategy would be helpful and effective in beneficial exploration for understanding the nonlinear intensification mechanism of metallurgical thermal processes.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic chaos of imaging measurements for characterizing gas–liquid nonlinear flow behaviour in a metallurgical reactor stirred by top‐blown air

Yang,

Zhang,

Yang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Mixing is one of the most common operations in process engineering that is used to combine materials and promote heat and mass transfer (Blower et al, 2020;Wang et al, 2023;Yang et al, 2023b). Solid-liquid mixing is one of the operations that are general and extensive (Delacroix et al, 2021) and commonly seen in chemical and metallurgical industries.…”

Section: Introductionmentioning

confidence: 99%

Measurement of solid–liquid mixing quality by using a uniform design method based on image analysis

Yang

Wang

et al. 2023

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

Solid–liquid mixing has been a common industrial process operation. The measurement of solid–liquid mixing quality can help improve the efficiency of related industrial processes, but there is still a lack of an intuitive, accurate, and simple measurement method. As an important indicator to evaluate the solid–liquid mixing quality, the degree of solid suspension and the uniformity of solid distribution are directly related to mass transfer and reaction efficiency. Therefore, it is necessary to study the solid suspension and distribution in a solid–liquid system. In this work, the solid suspension and distribution of a solid–liquid system composed of glass beads–water stirred by the impeller are studied experimentally via digital image processing combined with statistical analysis. Specifically, images of solid–liquid mixing are first obtained using a camera and digitally processed. The area ratio of the solid in the image is proposed to reflect the degree of solid suspension, and the modified L2-star discrepancy (MD) is then used to quantify the uniformity of the solid distribution. Then, the solid–liquid mixing quality can be characterized by combining the area ratio and solid distribution. The feasibility of this method was proved by qualitative analysis of the solid–liquid mixing state and comparison with known studies. In addition, the effects of various stirring factors on the solid distribution were studied and discussed by using the proposed method. The results show that the method proposed in this paper can measure the quality of the solid–liquid mixing state more directly and is effective and accurate. Furthermore, it was used to find the best experimental parameters in this work. This method is also simpler and cheaper than many other methods. It is of great significance to improve the efficiency of chemical and metallurgical and other industrial processes.

show abstract

“…Currently, the artificial neural network methodologies garner substantial interest globally, spurring the evolution of diverse research trajectories. For instance, the widely used intelligent algorithms consist of support vector machine (SVM) 12 , particle swarm optimization (PSO) 13 , random forest (RF) 14 , relevance vector machine (RVM) 15 , and other machine learning algorithms 16 – 19 . Such advancements facilitate the effective integration of intelligent algorithms within the engineering domain (i.e., chemical engineering or metallurgical engineering), resulting in innovative avenues for industrial research.…”

Section: Introductionmentioning

confidence: 99%

Quality control prediction of electrolytic copper using novel hybrid nonlinear analysis algorithm

Su,

Ye,

Yang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Traditional linear regression and neural network models demonstrate suboptimal fit and lower predictive accuracy while the quality of electrolytic copper is estimated. A more dependable and accurate model is essential for these challenges. Notably, the maximum information coefficient was employed initially to discern the non-linear correlation between the nineteen factors influencing electrolytic copper quality and the five quality control indicators. Additionally, the random forest algorithm elucidated the primary factors governing electrolytic copper quality. A hybrid model, integrating particle swarm optimization with least square support vector machine, was devised to predict electrolytic copper quality based on the nineteen factors. Concurrently, a hybrid model combining random forest and relevance vector machine was developed, focusing on primary control factors. The outcomes indicate that the random forest algorithm identified five principal factors governing electrolytic copper quality, corroborated by the non-linear correlation analysis via the maximum information coefficient. The predictive accuracy of the relevance vector machine model, when accounting for all nineteen factors, was comparable to the particle swarm optimization—least square support vector machine model, and surpassed both the conventional linear regression and neural network models. The predictive error for the random forest-relevance vector machine hybrid model was notably less than the sole relevance vector machine model, with the error index being under 5%. The intricate non-linear variation pattern of electrolytic copper quality, influenced by numerous factors, was unveiled. The advanced random forest-relevance vector machine hybrid model circumvents the deficiencies seen in conventional models. The findings furnish valuable insights for electrolytic copper quality management.

show abstract

Identifying Flow Patterns in a Narrow Channel via Feature Extraction of Conductivity Measurements with a Support Vector Machine

Cited by 15 publications

References 35 publications

Dynamic chaos of imaging measurements for characterizing gas–liquid nonlinear flow behaviour in a metallurgical reactor stirred by top‐blown air

Dynamic chaos of imaging measurements for characterizing gas–liquid nonlinear flow behaviour in a metallurgical reactor stirred by top‐blown air

Measurement of solid–liquid mixing quality by using a uniform design method based on image analysis

Quality control prediction of electrolytic copper using novel hybrid nonlinear analysis algorithm

Contact Info

Product

Resources

About