It is no doubt that the most important contributing cause of global efficiency of coal fired thermal systems is combustion efficiency. In this study, the relationship between the flame image obtained by a CCD camera and the excess air coefficient ({\lambda}) has been modelled. The model has been obtained with a three-stage approach: 1) Data collection and synchronization: Obtaining the flame images by means of a CCD camera mounted on a 10 cm diameter observation port, {\lambda} data has been coordinately measured and recorded by the flue gas analyzer. 2) Feature extraction: Gridding the flame image, it is divided into small pieces. The uniformity of each piece to the optimal flame image has been calculated by means of modelling with single and multivariable Gaussian, calculating of color probabilities and Gauss mixture approach. 3) Matching and testing: A multilayer artificial neural network (ANN) has been used for the matching of feature-{\lambda}.

Probing single molecules in their nanoenvironment can reveal site-specific phenomena that would be obscured by ensemble-averaging experiments on macroscopic populations of molecules. Particularly in the past decade, major technological breakthroughs in scanning probe microscopy (SPM) have led to unprecedented spatial resolution and versatility and enabled the interrogation of molecular conformation, bond order, molecular orbitals, charge states, spins, phonons, and intermolecular interactions. On page 452 of this issue, Peng et al. ([ 1 ][1]) use SPM to directly measure the triplet lifetime of an individual pentacene molecule and demonstrate its dependence on interactions with nearby oxygen molecules with atomic precision. In addition to allowing the local tuning and probing of spin-spin interactions between molecules, this study represents a notable advance in the single-molecule regime and provides insights into many macroscopic behaviors and related applications in catalysis, energy-conversion materials, or biological systems. Single-molecule studies have benefited from the high resolution achieved with well-defined functionalized probes, especially with carbon monoxide–terminated atomic force microscopy (AFM) tips ([ 2 ][2]). The versatility and applicability of AFM have also been enhanced by biasing the tip with gate voltages and supporting molecules on insulating substrates. In this configuration, the conductive AFM tip serves as an atomically controlled charge injector with single-charge sensitivity. Such electrical addressing of electronic states of single molecules ([ 3 ][3]) allows for the study of charge distribution and transport in single-molecule devices, organic electronics, and photovoltaics. Beyond steady-state spectroscopy, excited-state dynamics of single molecules can be measured by using an ultrashort and high-intensity electric (voltage) or optical (laser) pulse (the “pump”) to excite the sample. After a nonequilibrium state is generated, a second weaker pulse (the “probe”) monitors the change of the excited state. By varying the time delay between the two pulses, the temporal evolution of the excited state can be mapped out. Peng et al. used the electronic pump-probe approach in AFM to measure the lifetime of the excited triplet state of an individual pentacene molecule with atomic precision (see the figure). They observed strong quenching of the triplet lifetime by co-adsorbed molecular oxygen (O2). The electronic energy-transfer processes had an intriguing dependence on the arrangement of surrounding O2 molecules, which they controlled by atomic manipulation with the tip. Spin-relaxation measurements of single molecules in space with atomic resolution provide insights into their local interactions with each other, as well as with their nanoenvironment. Such information could be useful for spin-based quantum-information storage or quantum computing ([ 4 ][4]). Given the radiative relaxation of excited states, SPM-coupled optical spectroscopy provides a powerful tool to perform spatially and energy-resolved spectroscopic studies of single molecules. Specifically, site-resolved excitations of molecules can be induced by highly localized scanning tunnel microscopy (STM) current, and the resulting luminescence, which carries information that describes excited states, can be probed by integrated optical detection systems. This approach revealed redox state–dependent excitation of single molecules and intermolecular excitonic coupling interactions with atomic-scale spatial precision ([ 5 ][5], [ 6 ][6]). A study of electroluminescence demonstrated selective triplet formation by manipulating electron spin inside a molecule ([ 7 ][7]), which could provide a route to interrogate quantum spintronics and organic electronics at the single-molecule level. Besides tunneling electrons, the interaction of photons with molecules can provide valuable structural information and chemical identification through measurements of absorption, emission, or scattering of light. In particular, by confining laser light at the atomic-scale SPM junction and taking advantage of plasmon-enhanced Raman scattering, tip-enhanced Raman spectroscopy can overcome the diffraction limit of conventional optical spectroscopy and thereby achieve submolecular chemical spatial resolution ([ 8 ][8]). Such capability provides in-depth insights into single-molecule chemistry and site-specific chemical effects at the spatial limit ([ 9 ][9]). ![Figure][10] Atomically addressing excited single molecules The effect of nearby oxygen molecules on the lifetimes (τ) of triplet states T x , T y , and T z or T1 decaying to the singlet state S of individual pentacene molecules has been probed on an insulating salt surface. GRAPHIC: V. ALTOUNIAN/ SCIENCE Most excited states induced by photon absorption are incredibly short-lived (on the order of picoseconds to femtoseconds), so time-resolved optical STM techniques have been developed with ultrafast lasers. For example, pump-probe terahertz laser pulses were used to induce state-selective ultrafast STM tunneling currents through a single molecule. This approach allowed the molecular orbital structure and vibrations to be measured directly on the femtosecond time scale ([ 10 ][11]). Optical STM further showed the capability to explore photon and field-driven tunneling with angstrom-scale spatial resolution and attosecond temporal resolution. This experimental platform can be used to study quasiparticle dynamics in superconductor and two-dimensional materials with exceptional resolutions ([ 11 ][12]). Single-molecule studies could open avenues to access extremely transient states and chemical heterogeneity, suc h as the vibration of atoms within a molecule, the precession of a spin, ultrashort-lived complex reaction intermediates, and some key stochastic processes of reactions in chemistry and biology. For example, the study of Peng et al. relates to the reactivity of electronic excited states of organic molecules to O2 (and thus air). These processes can affect various natural photochemical and photophysical processes undergoing excitation by sunligh that can lead to transformation, degradation, or aging ([ 12 ][13]). The insightful descriptions of molecular conformation, dynamics, and function provided by spatially resolved single-molecule studies could inform complex and emergent behaviors of populations of molecules or even cells. 1. [↵][14]1. J. Peng et al ., Science 373, 452 (2021). [OpenUrl][15][Abstract/FREE Full Text][16] 2. [↵][17]1. L. Gross, 2. F. Mohn, 3. N. Moll, 4. P. Liljeroth, 5. G. Meyer , Science 325, 1110 (2009). [OpenUrl][18][Abstract/FREE Full Text][19] 3. [↵][20]1. S. Fatayer et al ., Nat. Nanotechnol. 13, 376 (2018). [OpenUrl][21][CrossRef][22][PubMed][23] 4. [↵][24]1. M. N. Leuenberger, 2. D. Loss , Nature 410, 789 (2001). [OpenUrl][25][CrossRef][26][PubMed][27] 5. [↵][28]1. Y. Zhang et al ., Nature 531, 623 (2016). [OpenUrl][29][CrossRef][30][PubMed][31] 6. [↵][32]1. B. Doppagne et al ., Science 361, 251 (2018). [OpenUrl][33][Abstract/FREE Full Text][34] 7. [↵][35]1. K. Kimura et al ., Nature 570, 210 (2019). [OpenUrl][36][CrossRef][37][PubMed][38] 8. [↵][39]1. J. Lee, 2. K. T. Crampton, 3. N. Tallarida, 4. V. A. Apkarian , Nature 568, 78 (2019). [OpenUrl][40][CrossRef][41][PubMed][42] 9. [↵][43]1. S. Mahapatra, 2. L. Li, 3. J. F. Schultz, 4. N. Jiang , J. Chem. Phys. 153, 010902 (2020). [OpenUrl][44] 10. [↵][45]1. T. L. Cocker, 2. D. Peller, 3. P. Yu, 4. J. Repp, 5. R. Huber , Nature 539, 263 (2016). [OpenUrl][46][CrossRef][47][PubMed][48] 11. [↵][49]1. M. Garg, 2. K. Kern , Science 367, 411 (2020). [OpenUrl][50][Abstract/FREE Full Text][51] 12. [↵][52]1. P. R. Ogilby , Chem. Soc. Rev. 39, 3181 (2010). [OpenUrl][53][CrossRef][54][PubMed][55] Acknowledgments: We acknowledge support from the National Science Foundation (CHE-1944796). [1]: #ref-1 [2]: #ref-2 [3]: #ref-3 [4]: #ref-4 [5]: #ref-5 [6]: #ref-6 [7]: #ref-7 [8]: #ref-8 [9]: #ref-9 [10]: pending:yes [11]: #ref-10 [12]: #ref-11 [13]: #ref-12 [14]: #xref-ref-1-1 "View reference 1 in text" [15]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DPeng%26rft.auinit1%253DJ.%26rft.volume%253D373%26rft.issue%253D6553%26rft.spage%253D452%26rft.epage%253D456%26rft.atitle%253DAtomically%2Bresolved%2Bsingle-molecule%2Btriplet%2Bquenching%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.abh1155%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [16]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNzMvNjU1My80NTIiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzMvNjU1My8zOTIuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [17]: #xref-ref-2-1 "View reference 2 in text" [18]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DGross%26rft.auinit1%253DL.%26rft.volume%253D325%26rft.issue%253D5944%26rft.spage%253D1110%26rft.epage%253D1114%26rft.atitle%253DThe%2BChemical%2BStructure%2Bof%2Ba%2BMolecule%2BResolved%2Bby%2BAtomic%2BForce%2BMicroscopy%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.1176210%26rft_id%253Dinfo%253Apmid%252F19713523%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [19]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEzOiIzMjUvNTk0NC8xMTEwIjtzOjQ6ImF0b20iO3M6MjI6Ii9zY2kvMzczLzY1NTMvMzkyLmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [20]: #xref-ref-3-1 "View reference 3 in text" [21]: {openurl}?query=rft.jtitle%253DNat.%2BNanotechnol.%26rft.volume%253D13%26rft.spage%253D376%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41565-018-0087-1%26rft_id%253Dinfo%253Apmid%252F29662243%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [22]: /lookup/external-ref?access_num=10.1038/s41565-018-0087-1&link_type=DOI [23]: /lookup/external-ref?access_num=29662243&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [24]: #xref-ref-4-1 "View reference 4 in text" [25]: {openurl}?query=rft.jtitle%253DNature%26rft.stitle%253DNature%26rft.aulast%253DLeuenberger%26rft.auinit1%253DM.%2BN.%26rft.volume%253D410%26rft.issue%253D6830%26rft.spage%253D789%26rft.epage%253D793%26rft.atitle%253DQuantum%2Bcomputing%2Bin%2Bmolecular%2Bmagnets.%26rft_id%253Dinfo%253Adoi%252F10.1038%252F35071024%26rft_id%253Dinfo%253Apmid%252F11298441%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [26]: /lookup/external-ref?access_num=10.1038/35071024&link_type=DOI [27]: /lookup/external-ref?access_num=11298441&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [28]: #xref-ref-5-1 "View reference 5 in text" [29]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D531%26rft.spage%253D623%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnature17428%26rft_id%253Dinfo%253Apmid%252F27029277%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [30]: /lookup/external-ref?access_num=10.1038/nature17428&link_type=DOI [31]: /lookup/external-ref?access_num=27029277&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [32]: #xref-ref-6-1 "View reference 6 in text" [33]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DDoppagne%26rft.auinit1%253DB.%26rft.volume%253D361%26rft.issue%253D6399%26rft.spage%253D251%26rft.epage%253D255%26rft.atitle%253DElectrofluorochromism%2Bat%2Bthe%2Bsingle-molecule%2Blevel%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aat1603%26rft_id%253Dinfo%253Apmid%252F30026221%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [34]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNjEvNjM5OS8yNTEiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzMvNjU1My8zOTIuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [35]: #xref-ref-7-1 "View reference 7 in text" [36]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D570%26rft.spage%253D210%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41586-019-1284-2%26rft_id%253Dinfo%253Apmid%252F31168096%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [37]: /lookup/external-ref?access_num=10.1038/s41586-019-1284-2&link_type=DOI [38]: /lookup/external-ref?access_num=31168096&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [39]: #xref-ref-8-1 "View reference 8 in text" [40]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D568%26rft.spage%253D78%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41586-019-1059-9%26rft_id%253Dinfo%253Apmid%252F30944493%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [41]: /lookup/external-ref?access_num=10.1038/s41586-019-1059-9&link_type=DOI [42]: /lookup/external-ref?access_num=30944493&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [43]: #xref-ref-9-1 "View reference 9 in text" [44]: {openurl}?query=rft.jtitle%253DJ.%2BChem.%2BPhys.%26rft.volume%253D153%26rft.spage%253D010902%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [45]: #xref-ref-10-1 "View reference 10 in text" [46]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D539%26rft.spage%253D263%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnature19816%26rft_id%253Dinfo%253Apmid%252F27830788%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [47]: /lookup/external-ref?access_num=10.1038/nature19816&link_type=DOI [48]: /lookup/external-ref?access_num=27830788&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom [49]: #xref-ref-11-1 "View reference 11 in text" [50]: {openurl}?query=rft.jtitle%253DScience%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aaz1098%26rft_id%253Dinfo%253Apmid%252F31727858%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [51]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNjcvNjQ3Ni80MTEiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzMvNjU1My8zOTIuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [52]: #xref-ref-12-1 "View reference 12 in text" [53]: {openurl}?query=rft.stitle%253DChem%2BSoc%2BRev%26rft.aulast%253DOgilby%26rft.auinit1%253DP.%2BR.%26rft.volume%253D39%26rft.issue%253D8%26rft.spage%253D3181%26rft.epage%253D3209%26rft.atitle%253DSinglet%2Boxygen%253A%2Bthere%2Bis%2Bindeed%2Bsomething%2Bnew%2Bunder%2Bthe%2Bsun.%26rft_id%253Dinfo%253Adoi%252F10.1039%252Fb926014p%26rft_id%253Dinfo%253Apmid%252F20571680%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [54]: /lookup/external-ref?access_num=10.1039/b926014p&link_type=DOI [55]: /lookup/external-ref?access_num=20571680&link_type=MED&atom=%2Fsci%2F373%2F6553%2F392.atom

We present Bayesian Controller Fusion (BCF): a hybrid control strategy that combines the strengths of traditional hand-crafted controllers and model-free deep reinforcement learning (RL). BCF thrives in the robotics domain, where reliable but suboptimal control priors exist for many tasks, but RL from scratch remains unsafe and data-inefficient. By fusing uncertainty-aware distributional outputs from each system, BCF arbitrates control between them, exploiting their respective strengths. We study BCF on two real-world robotics tasks involving navigation in a vast and long-horizon environment, and a complex reaching task that involves manipulability maximisation. For both these domains, there exist simple handcrafted controllers that can solve the task at hand in a risk-averse manner but do not necessarily exhibit the optimal solution given limitations in analytical modelling, controller miscalibration and task variation. As exploration is naturally guided by the prior in the early stages of training, BCF accelerates learning, while substantially improving beyond the performance of the control prior, as the policy gains more experience. More importantly, given the risk-aversity of the control prior, BCF ensures safe exploration and deployment, where the control prior naturally dominates the action distribution in states unknown to the policy. We additionally show BCF's applicability to the zero-shot sim-to-real setting and its ability to deal with out-of-distribution states in the real-world. BCF is a promising approach for combining the complementary strengths of deep RL and traditional robotic control, surpassing what either can achieve independently. The code and supplementary video material are made publicly available at https://krishanrana.github.io/bcf.

Physics-informed neural networks (PINNs) are successful machine-learning methods for the solution and identification of partial differential equations (PDEs). We employ PINNs for solving the Reynolds-averaged Navier$\unicode{x2013}$Stokes (RANS) equations for incompressible turbulent flows without any specific model or assumption for turbulence, and by taking only the data on the domain boundaries. We first show the applicability of PINNs for solving the Navier$\unicode{x2013}$Stokes equations for laminar flows by solving the Falkner$\unicode{x2013}$Skan boundary layer. We then apply PINNs for the simulation of four turbulent-flow cases, i.e., zero-pressure-gradient boundary layer, adverse-pressure-gradient boundary layer, and turbulent flows over a NACA4412 airfoil and the periodic hill. Our results show the excellent applicability of PINNs for laminar flows with strong pressure gradients, where predictions with less than 1% error can be obtained. For turbulent flows, we also obtain very good accuracy on simulation results even for the Reynolds-stress components.

In this paper, we address the Perception--Constrained Model Predictive Control (PCMPC) and state estimation problems for quadrotors with cable suspended payloads using a single camera and Inertial Measurement Unit (IMU). We design a receding--horizon control strategy for cable suspended payloads directly formulated on the system manifold configuration space SE(3)xS^2. The approach considers the system dynamics, actuator limits and the camera's Field Of View (FOV) constraint to guarantee the payload's visibility during motion. The monocular camera, IMU, and vehicle's motor speeds are combined to provide estimation of the vehicle's states in 3D space, the payload's states, the cable's direction and velocity. The proposed control and state estimation solution runs in real-time at 500 Hz on a small quadrotor equipped with a limited computational unit. The approach is validated through experimental results considering a cable suspended payload trajectory tracking problem at different speeds.

Fuel optimization of diesel and petrol vehicles within industrial fleets is critical for mitigating costs and reducing emissions. This objective is achievable by acting on fuel-related factors, such as the driving behaviour style. In this study, we developed an Explainable Boosting Machine (EBM) model to predict fuel consumption of different types of industrial vehicles, using real-world data collected from 2020 to 2021. This Machine Learning model also explains the relationship between the input factors and fuel consumption, quantifying the individual contribution of each one of them. The explanations provided by the model are compared with domain knowledge in order to see if they are aligned. The results show that the 70% of the categories associated to the fuel-factors are similar to the previous literature. With the EBM algorithm, we estimate that optimizing driving behaviour decreases fuel consumption between 12% and 15% in a large fleet (more than 1000 vehicles).

Detecting abrupt changes in temporal behavior patterns is of interest in many industrial and security applications. Abrupt changes are often local and observable primarily through a well-aligned sensing action (e.g., a camera with a narrow field-of-view). Due to resource constraints, continuous monitoring of all of the sensors is impractical. We propose the bandit quickest changepoint detection framework as a means of balancing sensing cost with detection delay. In this framework, sensing actions (or sensors) are sequentially chosen, and only measurements corresponding to chosen actions are observed. We derive an information-theoretic lower bound on the detection delay for a general class of finitely parameterized probability distributions. We then propose a computationally efficient online sensing scheme, which seamlessly balances the need for exploration of different sensing options with exploitation of querying informative actions. We derive expected delay bounds for the proposed scheme and show that these bounds match our information-theoretic lower bounds at low false alarm rates, establishing optimality of the proposed method. We then perform a number of experiments on synthetic and real datasets demonstrating the efficacy of our proposed method.

Time-series forecasting plays an important role in many domains. Boosted by the advances in Deep Learning algorithms, it has for instance been used to predict wind power for eolic energy production, stock market fluctuations, or motor overheating. In some of these tasks, we are interested in predicting accurately some particular moments which often are underrepresented in the dataset, resulting in a problem known as imbalanced regression. In the literature, while recognized as a challenging problem, limited attention has been devoted on how to handle the problem in a practical setting. In this paper, we put forward a general approach to analyze time-series forecasting problems focusing on those underrepresented moments to reduce imbalances. Our approach has been developed based on a case study in a large industrial company, which we use to exemplify the approach.

Turbine maintenance is an expensive, high-risk task. According to a recent analysis from the news website, wind farm owners are expected to spend more than $40 billion on operations and maintenance over a decade. Another recent study finds by using drone-based inspection instead of traditional rope-based inspection, you can reduce the operational costs by 70% and further decrease revenue lost due to downtime by up to 90%. This blog post will present how drones, machine learning (ML), and Internet of Things (IoT) can be utilized on the edge and the cloud to make turbine maintenance safer and more cost effective. First, we trained the machine learning model on the cloud to detect hazards on the turbine blades, including corrosion, wear, and icing.

The energy consumption from crypto mining has been increasingly exponentially with the increasing adoption of crypto. This increasing becoming of concern as it should be. Large parts of the world suffer from energy deprivation due to unaffordability and inadequate energy generation. At the same time climate change goals will require the world to reduce net emission much of which is produced from electricity generation. Supporting the world's growth and generating the and while reducing emissions when large populations suffer from energy deficiency is a very difficult issue requires trillions is capital over the coming 2 decades.