ITER Operation Research Articles

Hybrid Laplace-time domain model for coupled dynamic analysis of multibody mating system in topside float-over installations

The mating operation is the most critical phase during the topside float-over installation for jacket platforms, involving complex load transfer process and nonlinear couplings among the topside, float-over barge, jacket, and other buffering devices. It is very important and yet challenging to accurately and efficiently capture the coupled dynamics of the multibody mating system, as the time domain (TD) model requires a sufficiently small time interval to clearly capture the strong impacts on the buffering devices, resulting in a worse computational efficiency. This paper innovatively proposes a hybrid Laplace-time domain (HLTD) model to improve the computational efficiency in the coupled dynamic analysis while the computational accuracy is remained. The HLTD model computes the coupled dynamics by the time-domain iterative operations, mixing the Laplace-domain pole-residue operations for computing the motion responses in each iteration. Since the tedious differential and integral solutions in the TD model are replaced by the simple algebraic pole-residue calculations, the HLTD model has much higher computational efficiency with the same computational accuracy as the TD model. By comparing with the commercial software OrcaFlex, the proposed HLTD model shows satisfactory accuracy and superior efficiency in the heave-only mating analysis during the topside float-over installation of a jacket platform.

A De-Nesting Hybrid Reliability Analysis Method and Its Application in Marine Structure

In recent years, marine structures have been widely used in the world, making significant contributions to the utilization of marine resources. In the design of marine structures, there is a hybrid reliability problem arising from aleatory uncertainty and epistemic uncertainty. In many cases, epistemic uncertainty is estimated by interval parameters. Traditional methods for hybrid reliability analysis usually require a nested optimization framework, which will lead to too many calls to the limit state function (LSF) and result in poor computational efficiency. In response to this problem, this paper proposes a de-nesting hybrid reliability analysis method creatively. Firstly, it uses the p-box model to describe the epistemic uncertainty variables, and then the linear approximation (LA) model and the two-point adaptive nonlinear approximation (TANA) model are combined to approximate the upper and lower bounds of LSF with epistemic uncertainty. Based on the first-order reliability method (FORM), an iterative operation is used to obtain the interval of the non-probability hybrid reliability index. The traditional nested optimization structure is effectively eliminated by the above approximation method, which efficiently reduces the times of LSF calls and increases the calculation speed while preserving sufficient accuracy. Finally, one numerical example and two engineering examples are provided to show the greater effectiveness of this method than the traditional nested optimization method.

Density compensation with pellet fueling during ELM suppression with n = 4 RMP on metal-wall EAST tokamak

Pellet injection is the most promising fueling method to achieve a deep particle deposition for future fusion reactors. On metal-wall EAST tokamak, a full density compensation has been achieved by the pellet fueling during ELM suppression with n = 4 RMP which will be used in ITER’s operation. During the pellet injection, ELM suppression is terminated and small ELMs reappear. The plasma stored energy does not have a reduction with the pellet injection. Meanwhile, large sawtooth accompanied with RMP application is modified by the pellet injection. The amplitude of sawtooth crash decreases and high frequency small sawtooth crashes appear during the pellet fueling. The concentration of heavy impurities in the plasma core, such as tungsten and molybdenum, has an obvious reduction with the ELM reappearance and sawtooth modification. Although the same ELM behaviors also appears after divertor gas fueling, pellet fueling can modify the core plasma more significantly. All these experimental results will provide a good support to the ITER operation in the future.

Adaptive iterative learning unified operation control for high-speed train considering electrical structure model and temperature compensation

Adaptive iterative learning unified operation control for high-speed train considering electrical structure model and temperature compensation

A novel Fourier domain scheme for three‐dimensional magnetotelluric modelling in anisotropic media

SUMMARYThis study presents a novel algorithm that combines the Lorenz gauge equations with the Fourier domain technique to simulate magnetotelluric responses in three‐dimensional conductivity structures with general anisotropy. The method initially converts the Helmholtz equations governing vector potentials into one‐dimensional differential equations in the wave number domain via the horizontal two‐dimensional Fourier transform. Subsequently, a one‐dimensional finite element method employing quadratic interpolation is applied to obtain three five‐diagonal linear equation systems. Upon solving these equations, the spatial domain fields are obtained via the inverse Fourier transform. This process guarantees the computational efficiency, memory efficiency and high parallelization of the algorithm. Moreover, an anisotropic medium iteration operator guarantees stable convergence of the method. The correctness, competence and applicability of the algorithm are verified using some synthetic models. The results demonstrate that the new method is efficient and performs well in anisotropic undulating terrain and complex structures. Compared to other Fourier domain methods and the latest edge‐based finite element algorithm, the proposed method exhibits superior computing performance. Finally, the impact of the Euler angles on the magnetotelluric responses is analysed.

Prediction of performance and turbulence in ITER burning plasmas via nonlinear gyrokinetic profile prediction

Abstract Burning plasma performance, transport, and the effect of hydrogen isotope (H, D, D-T fuel mix) on confinement has been predicted for ITER baseline scenario (IBS) conditions using nonlinear gyrokinetic profile predictions. Accelerated by surrogate modeling (Rodriguez-Fernandez et al 2022 Nucl. Fusion 62 076036), high fidelity, nonlinear gyrokinetic simulations performed with the CGYRO code (Candy et al 2016 J. Comput. Phys. 324 73), were used to predict profiles of Ti , Te , and ne while including the effects of alpha heating, auxiliary power (NBI + ECH), collisional energy exchange, and radiation losses inside of r / a = 0.9. Predicted profiles and resulting energy confinement are found to produce fusion power and gain that are approximately consistent with mission goals ( P fusion = 500 MW at Q = 10) for the baseline scenario and exhibit energy confinement that is within 1σ of the H-mode energy confinement scaling. The power of the surrogate modeling technique is demonstrated through the prediction of alternative ITER scenarios with reduced computational cost. These scenarios include conditions with maximized fusion gain and an investigation of potential resonant magnetic perturbation (RMP) effects on performance with a minimal number of gyrokinetic profile iterations required (3–6). These predictions highlight the stiff ITG nature of the core turbulence predicted in the ITER baseline and demonstrate that Q > 17 conditions may be accessible by reducing auxiliary input power while operating in IBS conditions. Prediction of full kinetic profiles allowed for the projection of hydrogen isotope effects around ITER baseline conditions. The gyrokinetic fuel ion species was varied from H, D, and 50/50 D-T and kinetic profiles were predicted. Results indicate that a weak or negligible isotope effect will be observed to arise from core turbulence in IBS conditions. The resulting energy confinement, turbulence, and density peaking, and the implications for ITER operations will be discussed.

An active learning framework assisted development of corrosion risk assessment strategies for offshore pipelines

Aggressive fluids and prolonged service life result in an increasing internal corrosion risk of offshore pipelines, especially for perforation. A framework was constructed by active learning (AL) aimed at assessing the future corrosion risk of offshore pipelines and rapidly developing in-line inspection (ILI) strategies. Compared with Support Vector Regression (SVR), K-Nearest Neighbors (KNN) and Random Forest (RF), the Gradient Boosting Regression (GBR) model exhibits greater robustness and stability under both 10-fold cross-validation (CV) and bootstrap method. The RMSE and R2 are 1.48 and 0.83, respectively. Through the double iterative operation of input parameters and models, the AL framework can significantly reduce the demand for training samples, while maintaining accurate predictions. This study contributes to promoting the application of active learning methods in pipeline integrity management and planning, and providing assistance for the construction of intelligent and digital oilfields.

Development of ITER first wall heat load feedback control

Real-time monitoring and control of thermal loads on tungsten plasma-facing components is mandatory for ITER to avoid their overheating during plasma discharges. For the Start of Research Operations (SRO) phase, dedicated First Wall Heat Load Control (FWHLC) functions are included in the ITER Plasma Control System (PCS) to prevent the development of excessive plasma heat loads on the inertially cooled first wall (FW). In this work, we propose a FWHLC design with a model-based approach, which features a simplified thermal model for the FW armour. This control-oriented model simulates the thermal response of ITER FW to slow changes in plasma equilibrium and energy, which during ITER operation will be monitored by the real-time wide angle infrared camera system. This allows computationally efficient runs for rapid controller performance assessment but can also assist operation scenario design by pre-empting potential heat load issues. FWHLC is designed to react to measured and predicted FW temperatures overcoming predesigned limits with real-time variations of the plasma shape or auxiliary power references, aiming to reduce thermal loads before a premature plasma termination is required to protect the FW. The new scheme is tested in closed loop simulations, where perturbations to nominal ITER low current scenarios are introduced in the wall thermal model to trigger the response of FWHLC, supporting the effectiveness of the proposed policy.

Impurity behaviour in JET high-current baseline scenario for Deuterium, Tritium and Deuterium-Tritium plasmas

To support future ITER operation, experimental campaigns at the Joint European Torus (JET) with an ITER-like wall (tungsten divertor and beryllium main chamber) in pure deuterium (D), tritium (T) and Deuterium-Tritium (D-T) were performed. One of the most important challenges in recent years was the development of two main scenarios that investigated different approaches to achieve the high fusion power as well as good plasma confinement (Garzotti et al., 2023). The first one, so-called baseline scenario is relying on high plasma current (Ip≈3.5 MA), normalized beta βN < 2 and safety factor q95 ≈ 3 (Garzotti et al., 2023). On the other hand, the second one, so-called Hybrid scenario is operating at lower plasma current (flat-top Ip ≤ 2.6 MA) and density with respect to the baseline, higher normalized beta βN > 2 and safety factor q95 ≈ 4.8 (Hobirk et al., 2023).In this paper we focus on the impurity behaviour analysis for the baseline discharges at Ip = 3.5 MA and BT = 3.3 T with D, T and DT plasmas, in which the gas and power waveform were optimized to achieve the best possible performance. In particular, we study the impact of total heating power (Ptot + Palpha), flat-top gas flow and ELM (edge localized modes) frequency on mid-Z (Nickel (Ni), Copper (Cu)) and high-Z (Tungsten (W)) impurities. In addition, we compared the two best performing pulses of the baseline scenario (Ip = 3.5MA, BT = 3.3 T and Pin ≈ 35 MW) in D and DT in order to identify the causes responsible for the increase in radiation during the DT pulse, which led to an early plasma termination. All presented results rely on the data collected by the VUV as well as the bolometry system. Detailed analysis indicates that in the baseline scenario, higher radiation, which is most likely due to the tungsten (W), is observed for T and DT plasmas in comparison to D. Moreover, for the two best performing baseline pulses, tomographic reconstructions show that the radiated power density is mainly emitted from the low field side (LFS) of the plasma and W does not accumulate in the plasma center (Telesca et al., 2024).

Algorithm for optimization of cold‑rolled pipe rolling routes

The relevance of the work is justified by the need to refine the methodology for calculating cold rolling routes, associated with the expansion of factors that need to be taken into account in conducting such calculations. The aim of the work is to develop an algorithm for optimizing the routes of cold rolling of pipes using CRP and CRPR type mills, convenient for implementation in a software product. The paper analyzes the main parameters for optimizing the routes of cold rolling of pipes, factors limiting the field of optimal values of the geometric parameters of the billet‑pipe in each pass. Among the latter, the maximum possible reduction in the cross‑sectional area, the required reduction in the cross‑sectional area in the last pass, the requirement for the nature of the distribution of the reduction value in the cross‑sectional area, in the wall thickness and in the pipe diameter from pass to pass and other parameters are highlighted. The importance of minimizing the number of passes is noted. The main dependencies included in the method for calculating the deformation parameters of the cold rolling route using CRP and CRPR mills are analyzed and highlighted. An algorithm for calculating the route of cold rolling of pipes, with several iteration operations, has been developed. The proposed algorithm allows optimizing the rolling route of pipes made of any grades of steels and alloys, and allows optimizing most parameters, including those affecting the economic parameters of production. Depending on the grade of steel or alloy, some iteration operations can be excluded. The algorithm has been tested in the practice of calculating rolling routes for pipes made of carbon and stainless steels and alloys.

Recent advance progress of HL-3 experiments

Abstract Since the first plasma realized in 2020, a series of key systems on HL-3 (known as HL-2M before) tokamak have been equipped/upgraded, including in-vessel components (the first wall, lower divertor, and toroidal cryogenic/water-cooling/baking/glow discharge systems, etc.), auxiliary heating system of 11 MW, and 28 diagnostic systems (to measure the plasma density, electron temperature, radiation, magnetic field, etc.). Magnet field systems were commissioned firstly for divertor plasma discharges. During the 2nd experimental campaign of HL-3 tokamak, several great progresses have been achieved. Firstly, the successful operation with plasma current larger than 1 MA was achieved under a divertor configuration. Secondly, the advanced divertor concept with two distinct snowflake configurations was realized. It is found that the distribution of ion saturation current and heat flux on bottom plate becomes wide due to magnetic surface expansion, demonstrating the advantage of such configuration in the heat flux mitigation. In addition, using the combination of NBI, ECRH and LHCD, the standard sawtoothing high confinement mode of megampere plasma was firstly accessed on the HL-3. The successful commissioning of HL-3 is beneficial for the initial operation of ITER.

Overview of T and D–T results in JET with ITER-like wall

Abstract In 2021 JET exploited its unique capabilities to operate with T and D–T fuel with an ITER-like Be/W wall (JET-ILW). This second major JET D–T campaign (DTE2), after DTE1 in 1997, represented the culmination of a series of JET enhancements—new fusion diagnostics, new T injection capabilities, refurbishment of the T plant, increased auxiliary heating, in-vessel calibration of 14 MeV neutron yield monitors—as well as significant advances in plasma theory and modelling in the fusion community. DTE2 was complemented by a sequence of isotope physics campaigns encompassing operation in pure tritium at high T-NBI power. Carefully conducted for safe operation with tritium, the new T and D–T experiments used 1 kg of T (vs 100 g in DTE1), yielding the most fusion reactor relevant D–T plasmas to date and expanding our understanding of isotopes and D–T mixture physics. Furthermore, since the JET T and DTE2 campaigns occurred almost 25 years after the last major D–T tokamak experiment, it was also a strategic goal of the European fusion programme to refresh operational experience of a nuclear tokamak to prepare staff for ITER operation. The key physics results of the JET T and DTE2 experiments, carried out within the EUROfusion JET1 work package, are reported in this paper. Progress in the technological exploitation of JET D–T operations, development and validation of nuclear codes, neutronic tools and techniques for ITER operations carried out by EUROfusion (started within the Horizon 2020 Framework Programme and continuing under the Horizon Europe FP) are reported in (Litaudon et al Nucl. Fusion accepted), while JET experience on T and D–T operations is presented in (King et al Nucl. Fusion submitted).

EUROfusion contributions to ITER nuclear operation

ITER is of key importance in the European fusion roadmap as it aims to prove the scientific and technological feasibility of fusion as a future energy source. The EUROfusion consortium of labs within Europe is contributing to the preparation of ITER scientific exploitation and operation and aspires to exploit ITER outcomes in view of DEMO. The paper provides an overview of the major progress obtained recently, carried out in the frame of the new (initiated in 2021) EUROfusion work-package called ‘Preparation of ITER Operation’ (PrIO). The overview paper is directly supported by the eleven EUROfusion PrIO contributions given at the 29th Fusion Energy Conference (16–21 October 2023) London, UK [www.iaea.org/events/fec2023]. The paper covers the following topics: (i) development and validation of tools in support to ITER operation (plasma breakdown/burn-through with evolving plasma volume, new infra-red synthetic diagnostic for off-line analysis and wall monitoring using Artificial Intelligence techniques, synthetic diagnostics development, development and exploitation of multi-machine databases); (ii) R&D for the radio-frequency ITER neutral beam sources leading to long duration of negative deuterium/hydrogen ions current extraction at ELISE and participation in the neutral beam test facility with progress on the ITER source SPIDER, and, the commissioning of the 1 MV high voltage accelerator (MITICA) with lessons learned for ITER; (iii) validation of neutronic tools for ITER nuclear operation following the second JET deuterium–tritium experimental campaigns carried out in 2021 and in 2023 (neutron streaming and shutdown dose rate calculation, water activation and activated corrosion products with advanced fluid dynamic simulation; irradiation of several materials under 14.1 MeV neutron flux etc).

Dynamic simulation of ITER cryo-distribution system using Aspen HYSYS

The ITER cryogenic system consists of the Liquid Helium (LHe) plant, the Cryo-Distribution (CD) system, and the cryo-lines. The Auxiliary Cold Boxes (ACBs) dedicated to cooling the superconducting (SC) magnet system and the Cryoplant Termination Cold Box (CTCB) of the ITER CD system are in the factory acceptance phase. The internal components of ACBs, e.g., cryogenic valves, a cold compressor (CCp), heat exchangers, and a cold circulator (CCr), have been sized and assembled, ensuring their functionality. The interdependency of the functional parameters of one component over the others needs to be assessed, as their integrated performance under the dynamic heat load deposition from the SC magnets may impact the overall operation of the ITER cryogenic system. The ACBs are equipped with two helium baths having ∼ 1200 kg of He inventory and situated inside the Tokamak building. These baths act as a thermal buffer for the LHe plant, situated in the cryoplant building, allowing it to operate at a quasi-steady state despite heat load variation from the applications. Such a large helium inventory can challenge the secondary confinement system of ITER due to helium ingress accidental events and thus needs to be optimized. The integrated system-level simulation is therefore necessary for the safe and reliable operation of the cryogenic system under such demanding requirements. The present study summarizes the results obtained for ACBs dedicated to the magnet system, including CTCB for the enhanced ITER operation modes, and confirms the integrated performance of the system. The results show that the LHe baths inside the ACBs can be used as a thermal buffer with the proposed limit of initial filling and by keeping a constant opening of the respective J-T valves upstream of the LHe baths. The study outcome and the proposed recommendations would be beneficial to mitigate the pulsed heat load to the LHe plant while minimizing the helium inventory.

Ditching the Queue: Optimizing Coprocessor Utilization with Out-of-Order CPUs on Compact Systems on Chip

The growing demand for high-performance and energy-efficient processing in edge-oriented Systems-on-Chip is driving the adoption of dedicated integrated circuits that accelerate computationally intensive workloads. To minimize area and performance overhead, low-power, general-purpose CPUs are often tightly coupled with domain-specific coprocessors implementing custom instructions, thereby delivering higher throughput and reduced memory traffic. However, commonly used in-order CPUs are not optimized for instruction-level parallelism, leading to stalls in the instruction stream while waiting for long-latency coprocessor operations and under-utilization of the coprocessor while executing other instructions. This work investigates the benefits of replacing simple in-order cores with a more complex out-of-order architecture to dynamically schedule instructions for the main core and coprocessor, optimizing resource utilization and reducing execution time. To ensure generality, an in-depth analysis was carried out by offloading instructions to a custom dummy coprocessor capable of emulating iterative and pipelined operations with arbitrary latency. Various workloads simulating real-world applications were executed on two variants of an open-source microcontroller equipped with a recent out-of-order core and the state-of-the-art CV32E40X in-order core, respectively. Results from Register Transfer Level simulations show that the former configuration executes up to 60% more instructions per cycle, with a modest 12% system area overhead on a 65 nm CMOS technology node.

Simultaneous seismic data de‐aliasing and denoising with a fast adaptive method based on hybrid wavelet transform

AbstractMissing data and random noise are prevalent issues encountered during the processing of acquired seismic data. Interpolation and denoising represent economical solutions to address these limitations. Recovering regularly missing traces is challenging because of the spatial aliasing, and the extra difficulty is compounded by the presence of noise. Hence, developing an effective approach to realize denoising and anti‐aliasing is important. Projection onto convex sets is an effective method for recovering missing seismic data that is typically used for processing data with a good signal‐to‐noise ratio. The computational attractiveness of the projection onto convex sets reconstruction approach is compromised by its slow convergence rate. In this study, we aimed to efficiently implement simultaneous seismic data de‐aliasing and denoising. We combined a discrete wavelet transform with a seislet transform to construct a hybrid wavelet transform. A new fast adaptive method based on the fast projection onto convex sets method was proposed to recover the missing data and remove random noise. This approach adjusts the projection operator and iterative shrinkage threshold operator. The result is influenced by the threshold value. We enhanced the processing accuracy by adopting an optimal threshold strategy. Synthetic and field data tests indicate the effectiveness of the proposed method.

Automatic and User-Assisted Sphere-Mesh Construction.

A sphere-mesh is a class of geometric proxies defined as the volume swept by spheres with linearly interpolated centers and radii, potentially striking a good balance between conciseness of representation, simplicity of spatial queries, and expressive power. We investigate the semiautomatic generation of sphere-meshes from standard triangular meshes. We improve one known automatic construction algorithm, based on iterative local coarsening operation, by introducing a mechanism to prevent operations that would result in spheres exceeding the target shape; then, we propose a 3-D interface designed to permit users to easily and intuitively modify the automatically generated sphere-meshes. The two phases, an improved automatic algorithm and a novel interactive tool, used in cascade, constitute a viable semiautomatic way to produce high-quality sphere-meshes. We test our method on several inputs tri-meshes, assess their quality, and finally exemplify the usability of our results by testing them in a few downstream applications.

Quantum rectangular MinRank attack on multi-layer UOV signature schemes

Recent rank-based attacks have reduced the security of Rainbow, which is one of the multi-layer UOV signatures, below the NIST security requirements by speeding up iterative kernel-finding operations using classical mathematics techniques. If quantum algorithms are applied to perform these iterative operations, the rank-based attacks may be more threatening to multi-layer UOV, including Rainbow. In this paper, we propose a quantum rectangular MinRank attack called the Q-rMinRank attack, the first quantum approach to key recovery attacks on multi-layer UOV signatures. Our attack is a general model applicable to multi-layer UOV signature schemes, and in this paper, we provide examples of its application to Rainbow and the Korean TTA standard, HiMQ. We design two quantum oracle circuits to find the kernel in consideration of the depth-width trade-off of quantum circuits. One is to reduce the width of the quantum circuits using qubits as a minimum, and the other is to reduce the depth using parallelization instead of using a lot of qubits. By designing quantum circuits to find kernels with fewer quantum resources and complexity by adding mathematical techniques, we achieve quadratic speedup for the MinRank attack to recover the private keys of multi-layer UOV signatures. We also estimate quantum resources for the designed quantum circuits and analyze quantum complexity based on them. The width-optimized circuit recovers the private keys of Rainbow parameter set V with only 1089 logical qubits. The depth-optimized circuit recovers the private keys of Rainbow parameter set V with a quantum complexity of 2174\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2^{174}$$\\end{document}, which is lower than the complexity of 2221\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2^{221}$$\\end{document} recovering the secret key of AES-192, which provides the same security level as parameter set III.

Electron cyclotron emission detection of neoclassical tearing modes for control for ITER.

Successful operation of ITER requires control of magnetic instabilities including neoclassical tearing modes (NTMs) that can degrade confinement and lead to disruption. Low latency detection by electron cyclotron emission (ECE) diagnostics has been demonstrated in a few current experiments. Using a synthetic diagnostic, we demonstrate low latency NTM detection for ITER with plasmas described by ITER IMAS database scenarios and with realistic limitations imposed on the instrumentation by these high temperature scenarios. 2/1 NTMs are detected 430ms after magnetic island seeding and before island locking. The radiometer configuration was optimized using simulation, and the smallest detectable island size was explored. Island sizes of ∼3cm are detectable at the 2/1 surface. The simulated signals incorporate recent physics models for island growth and rotation, which show early locking and continued island growth after locking and before disruption. This work determines limits for ITER ECE spatial resolution imposed by relativistic broadening of channels, which informs hardware design. Real-time detection is demonstrated in hardware that is required by ITER, including on an NI PXI-7853R FPGA system. Development of a synthetic diagnostic and details of the hardware will be discussed.

Surface temperature measurement from infrared synthetic diagnostic in preparation for ITER operations

The protection of ITER in-vessel components and the plasma-wall interaction studies will be based on a large network of infrared (IR) cameras covering 70% of the tokamak. The surface temperature measurement from IR images remains challenging due to the presence of metallic targets, with changes in surface thermo-radiative properties (emissivity) and the presence of multiple reflections. The paper provides an overview of major progress to improve the interpretation of IR image and to get more reliable surface temperature from IR synthetic diagnostics. The paper presents the latest development of (1) the forward model to include the modelling of the edge localised modes and a new advanced camera that is better adapted to experimental data (2) the inverse model to retrieve the emissivity of the targets and the surface temperature from a neural network trained exclusively from synthetic IR images. Promising results have been obtained both from simulated test images with an estimated emissivity better than 0.05 and a surface temperature better than 10%, and from WEST experimental images of ITER-like wide-angle to filter reflection patterns.