Search Documents

By Yannis Faitakis, Simon Bergeron

"This paper describes the implementation of model-based predictive control (MPC) on a vacuum heat exchange network at Alcan's Jonquière Complex. The plant produces alumina from bauxite ore using the Bayer Process.The MPC system was commissioned in 2000, by Alcan personnel and an Advanced Control Engineer from Matrikon. The application has achieved an uptime of about 97%.The benefits were:• Energy savings : 0.5% - live steam reduction• Reduced variation: standard deviation of key temperatures reduced by 50%• Plant throughput increase: via the automated use of surge tanks• Decreased supervision time: by plant operations• Faster and easier diagnosis of problems and plant constraintsThe benefits were higher than expected with a payback time around 12 months.The purpose of the vacuum heat exchange network is to recover energy from a hot stream (pregnant liquor) by transferring it to a cold stream (spent liquor). The system is very tightly coupled, and the main constraints of the multivariable control system are: • to control the many tank levels involved in the process (8 tanks)• to maximize the temperature of the heated streams (spent liquor)• to prevent cooled streams (pregnant liquor) from cooling to below a minimum temperatureThe system includes 9 manipulated, 14 controlled and 2 feedforward variables.The advanced control implementation runs under an expert system environment and provides added flexibility to the overall control strategy."

Jan 1, 2003

By V Chamberlain, M Appeah Owusu, M Aniawu-Asumakah, A Anyimadu, R Peattie

This is an integrated geology and plant improvement study arising from the heterogeneity seen in mineralogy and gold association at the Obuasi goldmine in Ghana. This heterogeneity comes from the two ore types mined, the one being a sulphide ore, mainly composed of gold-bearing arsenopyrites. This gold is refractory and exhibits a strong relationship between gold and As. The other is quartz veins, that are high grade and free milling. The installed circuit consists of comminution – Gravity -Flotation – BIOX – Leaching and Adsorption processes. The opportunity tested involved improved mass pull - related flotation recovery of Au in the Sulphide stream; while balancing the need for a minimum Sulphide grade for the Bio-oxidation process, occasioned by the removal of 25 to 30 % of the (quartz) stream through preconcentration by Ore sorting. The current circuit is then utilized for the sulphide route, while a smaller grind-gravity circuit is utilised for the quartz stream in a relatively inexpensive way, followed by a common leaching and adsorption circuit. Added advantages of the strategy includes faster recovery of gold from the quartz stream, with less consumption of reagents from saving on flotation and BIOX reagents for this stream. Screening and Ore sorting was successfully tested with laser technology, achieving over 98% separation of quarts (containing up to 40% of the gold). The plant schedule of Ore, the suggested circuit design for the Ore sorting, the results obtained from the different flotation regimes, as well as consequent financial modelling have been presented and discussed in this paper. This illustrates the opportunity that arises out of a detailed analysis of material versus installed circuits, even if the gains in pre-concentration do not necessarily involve rejection of gangue material. An added opportunity for future investigation, briefly discussed but not tested in this paper, would be to maintain current mass pulls but with increase in throughput (by the space created by the sorted material). This will of course require the mining ability. It could also add LOM value by altering the cut-off grade.

Nov 10, 2020

Certain information contained herein regarding Champion Minerals Inc., including management?s assessment of future plans and operations, may constitute forward-looking statements under applicable securities law and necessarily involve risks, including but not limited to risks associated with mining exploration, operating costs, production costs, volatility of share prices, currency fluctuations, imprecision of resource and reserve estimates, environmental risks and ability to access sufficient capital from internal and external sources. As a consequence, actual results may differ materially from those anticipated in any forward looking statements. Plans, intentions or expectations disclosed in any forward-looking statements or information should not be read as guarantees of future results or events, and will not necessarily be accurate indications of whether or when or by which such results or events will be achieved. Except as required by law, Champion Minerals Inc., expressly disclaims any intention and undertakes no obligation to update any forward looking statements or information as conditions change. The historical mineral resources mentioned are strictly historical in nature and are non-compliant to National Instrument 43-101 mineral resources and mineral reserves standards, and should therefore not be relied upon. A qualified person has not done sufficient work to upgrade or classify the historical mineral resources as current National Instrument NI-43-101 compliant.

May 1, 2011

The stability of paste fill bulkheads forms an integral part of a successful paste fill system. Bulkheads are constructed at the draw points of open stopes to contain paste fill while the initial pour cures and forms a consolidated plug. Mobilization of uncured paste fill as a result of a bulkhead failure can lead to significant consequences, including endangering the safety of personnel, property damage and production losses and delays. The loading conditions in the paste fill and the resultant lateral loads on the bulkheads are complex and are dependent on many factors. This paper presents a case study of several paste fill bulkhead failures; the results of an in-situ pressure monitoring program to ascertain the pressure loads, and the subsequent paste fill bulkhead evaluation.

May 1, 2007

By C. Steve

ABSTRACT: In this paper, the stability evaluation and bifurcation criteria are presented for the Jinping arch dam structure. The bifurcation models in failure status of the arch dam are derived from the uniqueness of the controlling equation of dam behaviours, and the relative phenomena between positive definition of dam structural tangent stiffness and bifurcation are given in the paper. Then the structural collapse criteria for arch dam are discussed based on the energy mode. A stability criterion of dam based on the connection of yield zones is proposed according to the implementation of elasto-plastic FEM (finite element method) numerical analysis. In accordance with this judging method, nonlinear FEM analysis is used for Jinping arch dam. The failure process of the Jinping dam was simulated and yield zones were found under the overloading condition. Keywords: Stability evaluation, bifurcation, failure process, Jinping arch dam ZUSAMMENFASSUNG: In der Verliegenden Arbeit wird ein integrater geomechanisch Modellversuch fuer Jinping Bogenstaumauer Vorgesstellt. Die Bogenstaumauer liegt aut der komplizerten felsformationen. Der Zerstoerungsmechanismus, die Stabilitaetsfaktoren und die Interaktion zwischen der Bogenstaumauer und den Seiltichen. In der Vorliegenden Arbeit wird eine dreidimensionale finite element analyse fuer die seitlichen. Gestein sauflager mittels dem Bruchmodell Vorgestellt, da fuer Jiniping Bogenstaumauer angewandet wird. Ein Bruch mechanismus model einschliesslich der statistischen parameter der Gesteinfes tigkeit wird entauckeit. RÉSUMÉ: Das ce documènt a été faite une analyse d’elemt limité de trois dimensions dn fondement de construction de roche faisant appel au modéle de l’endommagemnet à fracture, analyse appliquée an fondement du bar ragevoute de Jinping. Ce documènt décrit le test de modéle géomecanique intégral pour le barrage-voûte de Jinping L’ampleur du modéle en question constitute l’une de plus importantes en China. Ils correspondent par faitement anx calculs des résultats.

Jan 1, 2003

By Martin Hertzberg

The concept of limit burning velocities is used to formulate a quantitative theory of flammability limits. Competing processes dissipate power from a combustion wave and quench propagation at some characteristically low limit velocity. There are four competing processes and one complication: (a) Free, buoyant convection, (b) conductive-convective wall losses, (c) radiation, (d) selective, diffusional demixing (the complication), and (e) flow gradient effects (flame stretch). These complexities are unraveled by creating an idealization that is initially freed from these competing processes. The ideal serves as a standard, and its burning velocity (Su), ideal is a unique function of the initial thermodynamic variables of state. By adding each process individually, it is possible to evaluate their significance, quantitatively, in terms of a limit velocity (Su)a , b , c , or e , and to explore the nature of their cooperative interactions. The larger the limit velocity, the more significant the process. The apparently diverse observations of flammability behavior are readily unified within this simple, conceptual framework.

Jan 1, 1976

By A. S. Choudhary

Most of the coal reserves in India are of drift origin and have very poor washability characteristics and a high level of near gravity materials. At least 30 new coal wash plants are expected to be set up in the next 5years.In such a scenario, adequate sampling followed by sink float test work for washability analysis becomes very critical for designing these new plants. For coal sampling purpose, stipulations of different standards are sometimes formidable and on the border of ?impracticality?; sometimes are self contradictory in terms of gross sample weight vis-a-vis minimum number of particles required in each size fraction and in each relative density fraction and also the minimum mass in the latter. Validation of the generated data is another important aspect of washability analysis. These issues can easily be addressed by using straight forward mathematical relationships, well known RR plots and by using simple MS Excel tool, etc.

Sep 1, 2012

By F Gervilla, J Laukkanen

The Kevitsa Ni-Cu-PGE deposit in northern Finland contains disseminated Ni-Cu-Fe sulfides, and platinum-group minerals (PGM). The 2.05 Ga-old ultramafic-mafic, funnel-shaped intrusion is intruded into a volcanosedimentary sequence. The major ore minerals are pentlandite, hexagonal pyrrhotite and troilite, chalcopyrite, cubanite and magnetite. Pyrrhotite and pentlandite are replaced by pyrite, millerite and heazelwoodite near the surface. Nickeline, maucherite and gersdorffite are locally abundant. A pilot feed sample of 575 t of the main orebody at Kevitsa had average grades 0.45 per cent Cu, 0.36 per cent Ni, 1.85 per cent S, 0.33 g/t Pt, 0.34 g/t Pd and 0.19 g/t Au, with 0.06 per cent Ni contained in silicates. Higher PGE contents (2 - 27 ppm) occur in a vertical N-S bearing fault zone. The PGM (n = 6022) mapped in specimens of four drill holes, consist of sperrylite 34.7 vol per cent, braggite and cooperite 18.5 vol per cent, geversite 17.2 vol per cent, moncheite 14.7 vol per cent, merenskyite 6.7 vol per cent, stibiopalladinite 4.3 vol per cent, sobolevskite 1.9 vol per cent, kotulskite 0.7 vol per cent, michenerite 0.6 vol per cent, keithconnite 0.3 vol per cent, rustenburgite 0.1 vol per cent, melonite, froodite, laurite together 0.1 vol per cent and only a few grains of sudburyite, irarsite, vysotskite, erlichmanite, hongishiite, Pt-Cu-alloys, three undefined Pd and Pt bismuthinides and antimonides and a Pd-Cu-bearing Pt-Ni-Fe sulfide. Most of the PGM, 62 per cent, are enclosed in silicates, 29 per cent are intergrown with sulfides, nine per cent are within sulfides. A portion of the PGE occurs in solid solution in sulfides and arsenides. Ni flotation yielded smelter-grade concentrates averaging 12.2 per cent nickel. The average sulfide Ni recovery is 78.8 per cent and total Ni recovery is 65.3 per cent. The average Pt is 10 g/t at 55 per cent recovery, Pd 7.7 g/t at 38 per cent recovery and Au 1.6 g/t at ten per cent recovery. Cu concentrates averaged 28.6 per cent Cu with an average recovery of 78 per cent and further 11 per cent in the nickel concentrate. The copper concentrate contains 4 g/t Au at 24 per cent recovery. The average Fe to MgO ratio 17.9 is well above the targeted minimum of 4.5. The pilot results show that the previously used TETA (triethylene tetramine) can be avoided and good quality, smelter-grade concentrates can be produced from the Kevitsa ore at economical levels of recovery by conventional flotation methods.

Jan 1, 2008

By R. H. Lien

The Bureau of Mines investigated nitrous oxide (N20) stability when used as a solvent for organic removal from metal powder surfaces. Both supercritical and subcritical conditions were studied. This investigation was prompted by the occurrence of a violent reaction when supercritical N20 was being used to deoil a metal powder grinding waste sample that contained 20 to 25 wt pct cutting oil. Tests were conducted to determine the cause of the reaction and to define stability limits. Test data showed that the waste's oil fraction reacted violently with N20 acting as an oxidizer; the metal powder acted as a promoter to reduce the ignition temperature. Although the data were scattered, this temperature appeared to reach a minimum at a certain pressure (dependent on vessel and sample size). The minimum ignition temperature for a 0.64-g sample in a 72-cm3 vessel was 360° C at 200 psig. As the sample size increased, the ignition temperature decreased. For example, when the sample size was increased to 10 g, a reaction occurred at 240° C and 600 psig. Because of the variability of ignition temperature with pressure and sample size, safe operating conditions were not established. Overall, this research showed that extreme caution should be exercised when using N20 in an organic or organic-metal system.

Jan 1, 2011

By Catia Casagrande

O processo de pelotização foi desenvolvido com a finalidade de aproveitar as partículas finas e ultrafinas geradas nas operações de exploração e tratamento do minério de ferro. Os principais minérios que alimentam as usinas de Pelotização de Tubarão/Vitória/ES são provenientes das minas Brucutu, Fábrica Nova, Alegria, Conceição e Cauê. Os estudos de caracterização mineralógica e testes tecnológicos são realizados para auxiliar o processamento de minérios. Entretanto, alguns minérios possuem grande variabilidade de participação de minerais em sua composição, gerando necessidade de ajustes no processamento dos mesmos. Ter a previsibilidade mineralógica dos minérios é muito importante para atuar no processo com antecedência, realizando ajustes operacionais caso necessário, a fim de ganhar qualidade e reduzir custos. O método de cálculo normativo mineralógico é uma técnica nova que utiliza os resultados de análise química como base para quantificar minerais presentes no minério de ferro. O objetivo principal deste trabalho foi avaliar a aplicabilidade da metodologia de cálculo mineralógico normativo por meio de correlação com a microscopia ótica. As amostras analisadas foram pellet feed das minas de Fábrica Nova, Alegria e Brucutu. O estudo mostrou que existem diferenças entre as técnicas, entretanto os resultados foram promissores e satisfatórios.

Aug 17, 2017

By Owen Matthews

Introduction For the past year and a half, the mill of Cochenour Willans Gold Mines, Limited, McKenzie Island, Ontario has been roasting arsenopyrite-gold concentrates, prior to cyanidation, by means of a roaster employing techniques that are new and novel. The roaster is known as the Dorrco 'fluo-solids reactor', and the technique as 'fluidization'. The reactor has demonstrated its ability to roast a flotation concentrate containing arsenopyrite, pyrite, stibnite, small quantities of other sulphides, and some lime silicates and carbonates, yielding a calcine consisting mainly of porous iron oxide, plus the gold values. This calcine is readily amenable to cyanidation. Bulk shipments of concentrates to a distant custom smelter, as practised prior to this installation, has thus been eliminated, with appreciable savings in smelting charges, freight costs, and interest losses during shipment and smelting. This is the pioneer installation of fluo-solids roasting at a Canadian mill and up to the present performance results have not been published. It is the purpose of this paper to present the information now available for the benefit of other millmen who may be confronted with identical or similar problems to those encountered and solved at Cochenour Willans.

Jan 1, 1949

By George L. Gates

[When clays e.re mixe~ "Jith "~later to nake mud fluids f'ol' use in :irilling ','Iells "for oil and gar: h;:r vue :;'0 tary me thee. t 18 liquid mij~ tUl"es have certair.. phypicr..l characteri.",t.ics that vary ",dth t e Qlldlltit.y find]

Jan 1, 1941

By SANDEEP KUMAR JENA

This paper reviews the recovery of potassium from different rocks and mineral sources. Global demand for potassium is rising steadily due to the growth of agricultural production. Fertilizer manufacture consumes the majority of the world’s potassium production, with other uses including those in the pharmaceutical, glass, ceramic, food and detergent industries. The availability of soluble potash (K2O) minerals, such as sylvite, kainite and carnalite, in countries like Canada, the United States, Israel and Russia makes them major potash producers, whereas agriculture-based countries like Liberia, Somalia, Central African Republic, Thailand, Indonesia, Malaysia and India meet their potassium requirements through imports only. In these countries, the huge availability of potassium-bearing rocks/minerals like nepheline syenite, feldspar, mica and glauconitic sandstone, containing around 4 to 17 percent K2O, brings up the prospect of commercial production of potassium. Potassium recovery from minerals/rocks is complicated due to the uniform distribution of potassium throughout the crystal structure. Different physico-chemical separation methods like bioleaching, chemical leaching, flotation and roast-leaching have been discussed for the successful recovery of potash values from these rocks/minerals. Although seawater is vastly available, the recovery of potassium from seawater using chemical precipitation, solvent extraction, membrane separation and ion-exchange methods is not cost-effective due to low concentration of potassium.

By Paulo F. T. Sachs

ERP systems have been widely implemented nowadays in several industries. However, ERP was originally designed to fit former MRP and MRP II users, and most of the ERP research has been focused on discrete manufacturing . On the other hand, process industries ? and mining in particular ? present many peculiar characteristics, which are difficult to comply with ERP systems standard functionalities. Again, very limited research has been developed covering enterprise management systems in mining. The objective of this paper is to identify, through an explanatory study that includes a case study methodology, how ERP systems manage the functional areas of the mining industry, and how they fit into the mineral value chain IT requirements. A secondary objective is to identify the gaps between ERP?s functional capabilities and the mining industry business requirements, and to point out the perceived benefits they generate to the companies.

May 1, 2004

Large quantities of electrical and electronic equipments are discarded at the end-of-life (EOL) in different industries and house hold applications. Their disposal is creating a challenging environmental problem due to the presence of hazardous metals and non-metallic materials such as epoxy resins and plastics including brominated flame retardants etc particularly in printed circuit boards (PCBs). The recovery valuable metals and separation of hazardous materials from discarded PCBs will not only conserve the resources but also mitigate the environmental pollution. From a recycling point of view for a sustainable society, the studies have been carried out for the recovery of metal values from EOL-PCBs of DVD video players (DVD-PCBs) and vacuum cleaners (VC-PCBs) using physical beneficiation techniques. The concentration of the metals was found to be 43 wt.% and 30 wt.% in DVD-PCBs and VC-PCBs, respectively. Both the PCBs samples were ground in a hammer mill after cutting and their size analysis was carried out. The liberation of the metallic and non-metallic fractions was investigated under the microscope for different size fractions. Subsequently, froth flotation and pneumatic air separation studied were carried out to enrich the metallic constituents. The studies showed the enrichment of metals in coarser particles (-1000 +150 µm) and non-metals in the finer particles -150 µm following mechanical recycling process. A grade of 90 % with 75% recovery was achieved by froth flotation, but lower grade and recovery of 75% and 65% respectively were obtained by pneumatic separation with -1500 µm powders for DVD-PCBs. A grade of 86% metal was obtained by froth flotation with 76% recovery in the case of VC-PCBs. The lower grade of 65% with almost same recovery was achieved during pneumatic separation studies due to lower concentration of metals in VC-PCBs. The studies also showed that the froth flotation is an efficient process for enrichment of metals from both the samples. The process is environmental friendly as no chemicals are employed during entire processing. The higher recovery and grade of metal is expected to be obtained on a large scale beneficiation process.

Sep 1, 2012

By J Jackson, E Sellers

Blasting related indices were developed to quantify variation in rock strength and structure for each stope, and for each lift of each stope, as part of a Mine to Mill study at an underground open stope mine. The indices were derived from combinations of data from underground diamond drilling because the simplifying assumptions contained in the block model prevented sufficient differentiation in rock mass characteristics to enable adjustments to the blast design.Application of combinations of blasting related indices enabled the identification of stopes with a high potential for inconsistent and oversize fragmentation, underbreak and overbreak. The indices also fragmentation outcomes to deliver increased material flow within stopes, better digability and predict indicative mill throughput. The stopes with issuesCalibration of the results enabled adjustments to the blast design based on the rock mass conditions and accordingly improved the blast outcomes. This enabled improved productivity by reducing underbreak and overbreak, having a more appropriate fragmentation, which reduces unplanned rock handling and improves bogging. The reduction in recovery drilling creates huge opportunities to improve output by reducing production delays and decreasing the overall cost per tonne. By understanding the explosive performance and blast energy distribution in relation to rock mass blastability poor, performing designs in blind upholes and convex stopes were identified.The conclusion of the work is that value improvement, regarding increased revenue and reduced costs, can be achieved across the whole underground Mine to Mill process chain by developing stope based indices from the existing geological information to correctly tailor the blast design to the rock within, and surrounding, the stope.CITATION:Jackson, J and Sellers, E, 2017. Blasting related indices as the key to underground blasting improvements in a challenging rock mass, in Proceedings 13th AusIMM Underground Operators’ Conference 2017, pp 23–32 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Oct 16, 2017

By W. T. Sampson

Introduction The Kirkland Lake (Ontario) property of Wright-Hargreaves Mines, Limited, - consists of four claims. The two main shear zones or 'breaks' of the Kirkland Lake camp extend through three of these claims, for a distance of approximately 3,500 feet. These claims are on the northeast side of the original lake. The water in this section of the lake has now been replaced with mill tailings. The degree of success of any completed undertaking, especially in the mining industry, reflects the personnel involved. I state with pleasure that the successful deepening of No. 5 winze from 6,400 feet to 7,272 feet was largely due to the co-operation and skilled workmanship of Shaft Captain J. Myelde and his efficient 'leaders'. This winze was sunk at a time when it was most difficult to obtain experienced shaftmen, with the result that the crews did not wholly consist of experienced men (although their desire to learn shaft sinking soon gave good results). This condition added greatly to the responsibilities and duties of those in charge, whose first consideration was for the safety of those engaged in the work, and I take great pride in recording that the entire sinking programme was completed without a lost-time accident. Location of Winze Due to the information obtained through deep diamond-drill holes collared below the 6,000-foot level being of sufficient importance to warrant further exploration, it was decided to deepen the existing No. 5 winze rather than sink another winze. This decision meant that the sinking must be co-ordinated with and proceed simultaneously with operations in the winze, where mining was being carried on between the 3,900-foot and 5,100-foot horizons, inclusive.

Jan 1, 1948

By R. Webster

"Daniel Krige’s influence on soil science, and on soil survey in particular, has been profound. From the 1920s onwards soil surveyors made their maps by classifying the soils and drawing boundaries between the classes they recognized. By the 1960s many influential pedologists were convinced that if one knew to which class of soil a site belonged then one would be able to predict the soil’s properties there. At the same time, engineers began to realize that prediction from such maps was essentially a statistical matter and to apply classical sampling theory. Such methods, though sound, proved inefficient because they failed to take account of the spatial dependence within the classes.Matters changed dramatically in the 1970s when soil scientists learned of the work of Daniel Krige and Georges Matheron’s theory of regionalized variables. Statistical pedologists (pedometricians) first linked R.A. Fisher’s analysis of variance to regionalized variables via spatial hierarchical designs to estimate spatial components of variance. They then applied the mainstream geostatistical methods of spatial analysis and kriging to map plant nutrients, trace elements, pollutants, salt, and agricultural pests in soil, which has led to advances in modern precision agriculture. They were among the first Earth scientists to use nonlinear statistical estimation for modelling variograms and to make the programmed algorithms publicly available. More recently, pedometricians have turned to likelihood methods, specifically residual maximum likelihood (REML), to combine fixed effects, such as trend and external variables, with spatially correlated variables in linear mixed models for spatial prediction. They have also explored non stationary variances with wavelets and by spectral tempering, although it is not clear how the results should be used for prediction. This paper illustrates the most significant advances, with results from research projects."

Jan 1, 2015

By S. K. Dimitrov

?Ellatzite Med? is one of the biggest mining companies in Bulgaria, processing about 12,000,000 t of ore per year. Waste materials left after extraction of copper concentrate are deposited in tailings dam ?Benkovski 2?. The hydraulic structure is built according to the downstream method, through hydrocyclonization where the downstream batter and the body of the wall are formed by the separated coarse sand particles of the separated tailings. In connection with the prolonged concession of Ellatzite Med and the enlarged capacity of Benkovski 2, the tailings dam has expanded on to the surrounding terrain. To guarantee a normal hydrocyclonization and build up of a tailings wall during waste deposition from the ore mill, the technological scheme of the hydraulic transport system of Benkovski 2 has been changed.

Aug 1, 2013

By Jian Wang, Kun Li, Hao Wu, Juan Nan

In this paper, in order to solve the problems of low accuracy and slow speed of fire flame recognition, an extreme learning machine (ELM) method based on improved Harris hawks optimization (IHHO) is proposed for fire flame recognition. A novel Harris hawks optimization (HHO) is used to solve the problem of parameter selection of ELM. In order to solve the problem that the original HHO is prone to fall into local optimum, firstly circle mapping is used to initialize the population to solve the problem of uneven distribution and small range of the initial population. Then the formula of escaping energy of HHO is modified to make the population have a large range in the middle and late iterations while gradually decreasing in the whole iteration process. Thus, the exploitation stage in HHO is improved to make the search range smaller near the optimal solution to accelerate the convergence process. Finally, at the end of each iteration, a certain number of individuals are selected to perform Gaussian and Cauchy hybrid mutation to prevent the IHHO from falling into local optimization. Through three groups of experiments, the effectiveness of the proposed IHHO and IHHO-ELM is verified. In experiment 1, the convergence performance of IHHO is significantly better than that of the other remaining algorithms in the test results of six benchmark functions. In experiments 2 and 3 of real fire flame recognition case, IHHO-ELM outperforms other remaining algorithms on the whole and has significant advantages in some indexes.

Jan 17, 2023