Integrating Image Analysis and Machine Learning for Moisture Prediction and Appearance Quality Evaluation: A Case Study of Kiwifruit Drying Pretreatment.

The appearance of dried fruit clearly influences the consumer's perception of the quality of the product but is a subtle and nuanced characteristic that is difficult to quantitatively measure, especially online. This paper describes a method that combines several simple strategies to assess a suitable surrogate for the elusive quality using imaging, combined with multivariate statistics and machine learning. With such a convenient tool, this study also shows how one can vary the pretreatments and drying conditions to optimize the resultant product quality. Specifically, an image batch processing method was developed to extract color (hue, saturation, and value) and morphological (area, perimeter, and compactness) features. The accuracy of this method was verified using data from a case study experiment on the pretreatment of hot-air-dried kiwifruit slices. Based on the extracted image features, partial least squares and random forest models were developed to satisfactorily predict the moisture ratio (MR) during drying process. The MR of kiwifruit slices during drying could be accurately predicted from changes in appearance without using any weighing device. This study also explored determining the optimal drying strategy based on appearance quality using principal component analysis. Optimal drying was achieved at 60 °C with 4 mm thick slices under ultrasonic pretreatment. For the 70 °C, 6 mm sample groups, citric acid showed decent performance.

The Application of Artificial Intelligence and Big Data in the Food Industry.

Over the past few decades, the food industry has undergone revolutionary changes due to the impacts of globalization, technological advancements, and ever-evolving consumer demands. Artificial intelligence (AI) and big data have become pivotal in strengthening food safety, production, and marketing. With the continuous evolution of AI technology and big data analytics, the food industry is poised to embrace further changes and developmental opportunities. An increasing number of food enterprises will leverage AI and big data to enhance product quality, meet consumer needs, and propel the industry toward a more intelligent and sustainable future. This review delves into the applications of AI and big data in the food sector, examining their impacts on production, quality, safety, risk management, and consumer insights. Furthermore, the advent of Industry 4.0 applied to the food industry has brought to the fore technologies such as smart agriculture, robotic farming, drones, 3D printing, and digital twins; the food industry also faces challenges in smart production and sustainable development going forward. This review articulates the current state of AI and big data applications in the food industry, analyses the challenges encountered, and discusses viable solutions. Lastly, it outlines the future development trends in the food industry.

New insight into thermal hydrolysis of sewage sludge from solubilisation analysis.

Thermal hydrolysis, a sludge pre-treatment process prior to anaerobic digestion, is increasing in popularity in academia and industry due to the potential of biogas production enhancement. However, there is a limited understanding of the solubilisation mechanism, which significantly influences the biogas yield. This study evaluated the influence of flashing, reaction time, and temperature to understand the mechanism. It was found that while hydrolysis is the primary process (responsible for approximately 76-87% of sludge solubilisation), the sudden decompression via flashing at the end of the process, creating shear force to break the cell membrane, contributes a considerable percentage (approximately 24-13% depended on the treatment conditions) to the solubilisation of treated sludge. More importantly, the decompression helps significantly shorten the reaction time from 30 min to 10 min, which in turn reduces the sludge's colour, minimises energy consumption, and eliminates the formation of inhibitory compounds for anaerobic digestion. However, a considerable loss in volatile fatty acids (650 mg L⁻1 of acetic acid at 160 °C) during flash decompression should be considered.

The importance of outlier rejection and significant explanatory variable selection for pinot noir wine soft sensor development.

Sensory attributes are essential factors in determining the quality of wines. However, it can be challenging for consumers, even experts, to differentiate and quantify wines' sensory attributes for quality control. Soft sensors based on rapid chemical analysis offer a potential solution to overcome this challenge. However, the current limitation in developing soft sensors for wines is the need for a significant number of input parameters, at least 12, necessitating costly and time-consuming analyses. While such a comprehensive approach provides high accuracy in sensory quality mapping, the expensive and time-consuming studies required do not lend themselves to the industry's routine quality control activities. In this work, Box plots, Tucker-1 plots, and Principal Component Analysis (PCA) score plots were used to deal with output data (sensory attributes) to improve the model quality. More importantly, this work has identified that the number of analyses required to fully quantify by regression models and qualify by classification models can be significantly reduced. Based on regression models, only four key chemical parameters (total flavanols, total tannins, A520nmHCl, and pH) were required to accurately predict 35 sensory attributes of a wine with R2 values above 0.6 simultaneously. In addition, for classification models to accurately predict 35 sensory attributes of a wine at once with prediction accuracy above 70%, only four key chemical parameters (A280nmHCl, A520nmHCl, chemical age and pH) were required. These models with reduced chemical parameters complement each other in sensory quality mapping and provide acceptable accuracy. The application of the soft sensor based on these reduced sets of key chemical parameters translated to a potential reduction in analytical cost and labour cost of 56% for the regression model and 83% for the classification model, respectively, making these models suitable for routine quality control use.

Application of Three-Dimensional Digital Photogrammetry to Quantify the Surface Roughness of Milk Powder.

The surface appearance of milk powders is a crucial quality property since the roughness of the milk powder determines its functional properties, and especially the purchaser perception of the milk powder. Unfortunately, powder produced from similar spray dryers, or even the same dryer but in different seasons, produces powder with a wide variety of surface roughness. To date, professional panelists are used to quantify this subtle visual metric, which is time-consuming and subjective. Consequently, developing a fast, robust, and repeatable surface appearance classification method is essential. This study proposes a three-dimensional digital photogrammetry technique for quantifying the surface roughness of milk powders. A contour slice analysis and frequency analysis of the deviations were performed on the three-dimensional models to classify the surface roughness of milk powder samples. The result shows that the contours for smooth-surface samples are more circular than those for rough-surface samples, and the smooth-surface samples had a low standard deviation; thus, milk powder samples with the smoother surface have lower Q (the energy of the signal) values. Lastly, the performance of the nonlinear support vector machine (SVM) model demonstrated that the technique proposed in this study is a practicable alternative technique for classifying the surface roughness of milk powders.

Assessing and Quantifying the Surface Texture of Milk Powder Using Image Processing.

Milk powders produced from similar spray dryers have different visual appearances, while the surface appearance of the powder is a key quality attribute because the smoothness of the milk powder also affects flowability and handling properties. Traditionally quantifying this nuanced visual metric was undertaken using sensory panelists, which is both subjective and time consuming. Therefore, it is advantageous to develop an on-line quick and robust appearance assessment tool. The aim of this work is to develop a classification model which can classify the milk powder samples into different surface smoothness groups. This work proposes a strategy for quantifying the relative roughness of commercial milk powder from 3D images. Photogrammetry equipment together with the software RealityCapture were used to build 3D models of milk powder samples, and a surface normal analysis which compares the area of the triangle formed by the 3 adjacent surface normals or compares the angle between the adjacent surface normals was used to quantify the surface smoothness of the milk powder samples. It was found that the area of the triangle of the smooth-surface milk powder cone is smaller than the area of the triangle of the rough-surface milk powder cone, and the angle between the adjacent surface normals of the rough-surface milk powder cone is larger than the angle between the adjacent surface normals of the smooth-surface milk powder cone, which proved that the proposed area metrics and angle metrics can be used as tools to quantify the smoothness of milk powder samples. Finally, the result of the support vector machine (SVM) classifier proved that image processing can be used as a preliminary tool for classifying milk powder into different surface texture groups.

Mechanisms, status, and challenges of thermal hydrolysis and advanced thermal hydrolysis processes in sewage sludge treatment.

Sewage sludge management has garnered interest in both academia and industry due to the challenges of overpopulation and its potential as a bioenergy source. Thermal hydrolysis is a promising technology for sludge pre-treatment prior to anaerobic digestion to enhance biogas production. However, the technology is facing two main problems; the dark colour of sludge can affect UV disinfection and the formation of methanogenesis inhibitors such as free ammonia and refractory compounds have a significant impact on methane production in anaerobic digestion processes. Advanced thermal hydrolysis, which is an oxidative thermal hydrolysis process, has been introduced to overcome these challenges. This study provides a comprehensive review of the mechanisms and reactions which occur during the hydrothermal hydrolysis and advanced thermal hydrolysis processes. Technical and implementation challenges of both technologies are discussed. Additionally, the prospects of the technologies are assessed through their technology readiness levels. An assessment of the relevant literature is also provided to illuminate the aspects in which research gaps exist and areas where additional studies could be performed.

Enhancing biogas production from caribbean pelagic Sargassum utilising hydrothermal pretreatment and anaerobic co-digestion with food waste.

The recurring inundation of beaches in the tropical North Atlantic by pelagic Sargassum and the associated social, ecological and economic challenges, have aroused great interest in its potential use as a marine energy crop. However, to date, the seasonal availability and low experimental methane potential of these invasive brown seaweeds have hindered their commercial exploitation as feedstock for sustainable energy production. This novel study evaluated Caribbean pelagic Sargassum and the synergistic interactions of hydrothermal pretreatment and co-digestion with food waste at different mixture ratios, on biogas production enhancement and bio-fertiliser recovery. Batch testing revealed that hydrothermal pretreatment promoted the hydrolysis of organics in pelagic Sargassum and food waste, thus increasing methane recovery from mono-substrate digestion by 212.57% and 10.16%, respectively, in comparison to the untreated samples. Co-digestion of pelagic Sargassum and food waste redistributed metal elements and raised the buffering capacity of the digester, facilitating high organic loadings without pH control. Food waste also provided lipids to the seaweed feed which augmented the digestion performance. The maximum cumulative methane yield of 292.18 ± 8.70 mL/gVS was obtained from a blend of co-pretreated pelagic Sargassum and food waste at the weight ratio 25:75. Screening of the whole digestate from co-digestion indicated bio-fertiliser potential. However, the solid fraction necessitates arsenic remediation to meet international soil standard guidelines. The findings of this study are promising and suggest opportunity for the design, scale up and optimisation of biogas systems, equipped with hydrothermal pretreatment for utilisation of Sargassum seaweeds during influx.

Oxidative hydrothermal surface modification of activated carbon for sevoflurane removal.

The emission of waste anaesthetic gas is a growing contributor to global warming and remains a factor in atmospheric ozone depletion. Volatile anaesthetics in medical waste gases could be removed via adsorption using suitable activated carbon materials possessing an enhanced affinity to anaesthetic molecules. In this work, the effects of surface physical and chemical properties on sevoflurane adsorption were investigated by oxidative hydrothermal surface modification of a commercial activated carbon using only distilled water. The hydrothermal surface modification was carried out at different treatment temperatures (150-300 °C) for varying durations (10-30 min), and adsorption was conducted under fixed conditions (bed depth = 10 cm, inlet concentration = 528 mg/L, and flow rate = 3 L/min). The hydrothermal treatment generally increased the BET surface area of the activated carbons. At oxidation temperatures above 200 °C, the micropore volume of the samples diminished. The relative amount of surface oxygen was enriched as the treatment temperature increased. Treatment duration did not significantly affect the introduction of relative amount of surface oxygen, except at higher temperatures. There were no new types of functional groups introduced. However, disappearance and re-formation of oxygen functional groups containing C-O structures (as in hydroxyl and ether groups) occurred when treatment temperature was increased from 150 to 200 °C, and when treatments were conducted above 200 °C, respectively. The ester/acetal groups were enriched under the temperature range studied. The findings suggested that the re-formation of surface oxygen functionalities might lead to the development of functional groups that improve sevoflurane adsorption.

Effects of Morphology on the Bulk Density of Instant Whole Milk Powder.

The chemical and physical properties of instant whole milk powder (IWMP), such as morphology, protein content, and particle size, can affect its functionality and performance. Bulk density, which directly determines the packing cost and transportation cost of milk powder, is one of the most important functional properties of IWMP, and it is mainly affected by physical properties, e.g., morphology and particle size. This work quantified the relationship between morphology and bulk density of IWMP and developed a predictive model of bulk density for IWMP. To obtain milk powder samples with different particle size fractions, IWMP samples of four different brands were sieved into three different particle size range groups, before using the simplex-centroid design (SCD) method to remix the milk powder samples. The bulk densities of these remixed milk powder samples were then measured by tap testing, and the particles' shape factors were extracted by light microscopy and image processing. The number of variables was decreased by principal component analysis and partial least squares models and artificial neural network models were built to predict the bulk density of IWMP. It was found that different brands of IWMP have different morphology, and the bulk density trends versus the shape factor changes were similar for the different particle size range groups. Finally, prediction models for bulk density were developed by using the shape factors and particle size range fractions of the IWMP samples. The good results of these models proved that predicting the bulk density of IWMP by using shape factors and particle size range fractions is achievable and could be used as a model for online model-based process monitoring.

Enrichment of surface oxygen functionalities on activated carbon for adsorptive removal of sevoflurane.

Activated carbons have been reported to be useful for adsorptive removal of the volatile anaesthetic sevoflurane from a vapour stream. The surface functionalities on activated carbons could be modified through aqueous oxidation using oxidising solutions to enhance the sevoflurane adsorption. In this study, an attempt to oxidise the surface of a commercial activated carbon to improve its adsorption capacity for sevoflurane was conducted using 6 mol/L nitric acid, 2 mol/L ammonium persulfate, and 30 wt per cent (wt%) of hydrogen peroxide (H2O2). The adsorption tests at fixed conditions (bed depth: 10 cm, inlet concentration: 528 mg/L, and flow rate: 3 L/min) revealed that H2O2 oxidation gave desirable sevoflurane adsorption (0.510 ± 0.005 mg/m2). A parametric study was conducted with H2O2 to investigate the effect of oxidation conditions to the changes in surface oxygen functionalities by varying the concentration, oxidation duration, and temperature, and the Conductor-like Screening Model for Real Solvents (COSMO-RS) was applied to predict the interactions between oxygen functionalities and sevoflurane. The H2O2 oxidation incorporated varying degrees of both surface oxygen functionalities with hydrogen bond (HB) acceptor and HB donor characters under the studied conditions. Oxidised samples with enriched oxygen functionalities with HB acceptor character and fewer HB donor character exhibited better adsorption capacity for sevoflurane. The presence of a high amount of oxygen functional groups with HB donor character adversely affected the sevoflurane adsorption despite the enrichment of oxygen functional groups with HB acceptor character that have a higher tendency to adsorb sevoflurane.

Assessing the sustainability of phosphorus use in China: Flow patterns from 1980 to 2015.

Phosphorus is vital for living creatures and will run out in the next few hundred years. The imbalanced phosphate rock distribution and inefficient consumption make phosphorus management of great importance. As China has an undeniable influence on global phosphorus production and consumption, understanding its changing historical patterns is critical for phosphorus resource management and water quality improvement. However, most existing research focus on anthropogenic phosphorus flows in the agricultural sector for a specific year, making the evaluation of such changes difficult. Therefore, substance flow analysis and principal component analysis for phosphorus flows between 1980 and 2015 were performed to understand phosphorus consumption structure change and the build-up of legacy phosphorus in China. The results show that although China's phosphorus utilization efficiency has decreased over time, it is still higher than in most other countries. The research also demonstrates the effectiveness of combining multiyear substance flow analysis and principal component analysis to improve the transparency of identifying underlying consumption structure change during resource management.

An improved model for the kinetics of non-oxidative hydrothermal process.

Hydrothermal processing as a post-treatment technology for sludge has attracted great interest globally as it could reduce the amount of sludge considerably. This experimental study developed a comprehensive kinetic model of cellulose degradation via non-oxidative hydrothermal processing at various temperatures (ranges 180-260 °C). Values of activation energies and pre-exponential factors were determined using chemical oxygen demand (COD)-based lumped concentrations. In this study, a new reaction pathway between solid, soluble matter and gaseous products was proposed which not only enables prediction of solid phase degradation but also can predict the formation of various types of products (in liquid and gas phase) during the reaction time. The results show that the reaction rate of cellulose to liquid products (k1=2.7×109exp(-102810RT)) were fast compared to that of for liquid products to gaseous products (k2=4.4×103exp(-64629RT)). Moreover, the model infers that the major part of solid degradation leads to the formation of the gaseous product with the reaction rate constant of k3=5.7exp(-12905RT). The proposed model can provide an opportunity to predict the performance of the non-oxidative hydrothermal processing of organic solid waste.

Breakthrough analysis of continuous fixed-bed adsorption of sevoflurane using activated carbons.

The inhalational anaesthetic agent - sevoflurane is widely employed for the induction and maintenance of surgical anaesthesia. Sevoflurane possesses a high global warming potential that imposes negative impact to the environment. The only way to resolve the issue is to remove sevoflurane from the medical waste gas before it reaches the atmosphere. A continuous adsorption study with a fixed-bed column was conducted using two commercial granular activated carbons (E-GAC and H-GAC), to selectively remove sevoflurane. The effect of bed depth (Z, 5-15 cm), gas flow rate (Q, 0.5-6.0 L/min) and inlet sevoflurane concentration (C0, ∼55-700 mg/L) was investigated. E-GAC demonstrated ∼60% higher adsorption capacity than H-GAC under the same operating conditions. Varying the levels of Z, Q and C0 showed significant differences in the adsorption capacities of E-GAC, whereas only changing the C0 level had significant differences for H-GAC. Three breakthrough models (Adams-Bohart, Thomas, and Yoon-Nelson) and Bed-depth/service time (BDST) analysis were applied to predict the breakthrough characteristics of the adsorption tests and determine the characteristic parameters of the column. The Yoon-Nelson and Thomas model-predicted breakthrough curves were in good agreement with the experimental values. In the case of the Adams-Bohart model, a low correlation was observed. The predicted breakthrough time (tb) based on kinetic constant (kBDST) in BDST analysis showed satisfactory agreement with the measured values. The results suggest the possibility of designing, scaling up and optimising an adsorption system for removing sevoflurane with the aid of the models and BDST analysis.

Phosphorus recovery through struvite crystallisation: Recent developments in the understanding of operational factors.

Phosphorus is an essential element for life and is predicted to deplete within the next 100 years. Struvite crystallization is a potential phosphorus recovery technique to mitigate this problem by producing a slow release fertilizer. However, complex wastewater composition and a large number of process variables result in process uncertainties, making the process difficult to predict and control. This paper reviews the research progress on struvite crystallization fundamentals to address this challenge. The influence of manipulated variables (e.g. seed material, magnesium dosage and pH) and sources of variation on phosphorus removal efficiency (e.g. organics and heavy metal concentration) and product purity were investigated. Recently developed models to describe, control and optimize those variables were also discussed. This review helps to identify potential challenges in different wastewater streams and provide valuable information for future phosphorus recovery unit design. It therefore paves the way for commercialization of struvite crystallization in the future.

Phosphorous recovery through struvite crystallization: Challenges for future design.

Phosphorous (P) is an essential element for living organisms and is predicted to be depleted within the next 100 years. Across the world, significant phosphorous losses due to its low utilization efficiency become one of the main reasons for water pollution. Struvite crystallization has been found to be a promising recovery technique to mitigate these problems, as the recovered precipitate can be used as a slow release fertilizer or raw material for chemical industry. Although this technique has been widely investigated over the past two decades, there are currently few real applications in industry. This paper addresses this issue by reviewing key aspects relevant to process design to pave the way for future application. It will help to narrow down struvite process design options and thus reduce the voluminous calculations for a detailed analysis. Struvite process development, research trend, product application and process economics are reviewed and a conceptual process design is provided. This analysis provides comprehensive information that is essential for future industrial struvite crystallization process design.

Effect of hydrodynamic mixing conditions on wet oxidation reactions in a stirred vessel reactor.

The aim of this study was to investigate the impact of mixing intensity and mixing flow patterns on solid waste degradation, and production of valuable intermediate by-products such as acetic acid. Total suspended solids generally decreased, soluble chemical oxygen demand, dissolved organic carbon, and acetic acid concentration generally increased with the progress of the reaction and increase in the mixing intensity. The results showed that axial-radial flow pattern (using pitch blade impeller) and medium impeller speed (500 rpm) resulted in a higher degree of solid degradation and production of acetic acid.

Side draw control design for a high purity multi-component distillation column.

Industrial methanol production involves a multi component feed containing methanol, water and trace levels of ethanol being refined to produce AA grade methanol at high product recovery. Due to practical constraints, the bottoms discharge of the column is primarily water with only trace of methanol impurities. As a result of these constraints, ethanol, which is a non-key middle boiling component gets "trapped" near the side draw of the column forming an ethanol bulge, which in turn results in non-linear, inverse, time and state varying behaviour of the side draw ethanol composition. In this work, we established that the existence of the ethanol bulge creates the complex process behaviour of the side draw ethanol composition and that this bulge needs to be explicitly controlled. This type of explicit composition bulge analysis and subsequent control has not been attempted on methanol distillation columns before. For this purpose a novel, robust and practical side draw control scheme to detect and remedy the excess ethanol bulge movement using override control is presented. The side draw controller, together with other regulatory controllers is shown to maintain on-specification operations of the column. Disturbance rejection tests carried out illustrate that the side draw control scheme will keep the column operating within commercial specification. It is also shown that a traditional DV control structure is unable to achieve this objective.

Rheological characterisation of biologically treated and non-treated putrescible food waste.

Food waste is gaining increasing attention worldwide due to growing concerns over its environmental and economic costs. Understanding the rheological behaviour of food waste is critical for effective processing so rheological measurements were carried out for different food waste compositions at 25, 35 and 45 °C. Food waste samples of various origins (carbohydrates, vegetables & fruits, and meat), anaerobically digested and diluted samples were used in this study. The results showed that food waste exhibits shear-thinning flow behaviour and viscosity of food waste is a function of temperature and composition. The composition of food waste affected the flow properties. Viscosity decreased at a given temperature as the proportion of carbohydrate increased. This may be due to the high water content of vegetable & fruits as the total solids fraction is likely to be a key controlling factor of the rheology. The Herschel-Bulkley model was used successfully to model food waste flow behaviour. Also, a higher strain was needed to break down the structure of the food waste as digestion time increased.