Adaptive feedback schemes are promising for quantum-enhanced measurements yet are complicated to design. Machine learning can autonomously generate algorithms in a classical setting. Here we adapt machine learning for quantum information and use our framework to generate autonomous adaptive feedback schemes for quantum measurement. In particular, our approach replaces guesswork in quantum measurement by a logical, fully automatic, programable routine. We show that our method yields schemes that outperform the best known adaptive scheme for interferometric phase estimation.

Machine learning for precise quantum measurement.

Integrated production planning and control system for a panelized home prefabrication facility using simulation and RFID

Quantum-enhanced metrology infers an unknown quantity with accuracy beyond the standard quantum limit (SQL). Feedback-based metrological techniques are promising for beating the SQL but devising the feedback procedures is difficult and inefficient. Here we introduce an efficient self-learning swarm-intelligence algorithm for devising feedback-based quantum metrological procedures. Our algorithm can be trained with simulated or real-world trials and accommodates experimental imperfections, losses, and decoherence.

Efficient Algorithm for Optimizing Adaptive Quantum Metrology Processes

Condition monitoring of electrical machines is recognised as being crucially important to reliable and economical plant operation, particularly in large installations. Choice of monitoring parameters is discussed. Practically viable condition monitoring schemes are proposed.

Condition Monitoring of Electrical Machines

This paper proposes a competent method for broken bars fault identification in line-start and inverter-fed industrial induction motors. The basis of the proposed method is to determine different frequency bands of the faulty motor current and extract a proper intrinsic mode function (IMF) developed by empirical mode decomposition (EMD). It is analytically proved that two specific IMFs, IMF2 in line-start mode and IMF3 in inverter-fed mode, can be used for precise prediction of the behavior of a faulty induction motor. The precision of the method is shown at different operating points, including different loads, fault, and reference speeds. The results indicate that the motor asymmetry is remarkably reduced at distributed broken bars. In addition, the proposed method is capable of determining the operating point of the faulty motor even at no/light loads. Finally, the Filippetti criterion is used, and a new aspect is analytically developed to justify the variations of IMF3 with speed in an inverter-fed induction motor. The analytical results are verified by experiments.

EMD-Based Analysis of Industrial Induction Motors With Broken Rotor Bars for Identification of Operating Point at Different Supply Modes

The performance of two stochastic search methods, particle swarm optimisation (PSO) and simulated annealing (SA), when used for fault identification of induction machine stator and rotor winding faults, is evaluated in this paper. The proposed condition monitoring technique uses time domain terminal data in conjunction with the optimization algorithm to indicate the presence of a fault and provide information about its nature and location. The technique is demonstrated using experimental data from a laboratory machine.

https://www.staff.ncl.ac.uk/damian.giaouris/pdf/Papers/PID886208.pdf

Comparison of particle swarm and simulated annealing algorithms for induction motor fault identification

This paper introduces a control scheme to improve efficiency as well as both the input and output current ripples of multiphase interleaved buck converter (IBC), which is suitable for applications that require a wide range of output voltage. The number of phases is dynamically changed throughout the entire range of the output voltage in order to obtain the optimum efficiency and the lowest output ripple possible. The paper demonstrates the proposed approach on a single converter of a fast DC charger module which usually consists of multiple converters connected in input-parallel output parallel (IPOP) configuration. Simulation results show that the proposed technique significantly reduces the output current ripple when compared with the conventional phase-shedding technique while maintaining satisfactory high efficiency across the entire range of the output voltage.

/pdf/current-ripple-minimisation-based-on-phase-shedding-of-dc-dc-4v3bc8ivnt.pdf

Current Ripple Minimisation Based on Phase-Shedding of DC-DC Interleaved Converters for EV Charging System

Under the umbrella of the Computational Intelligence (CI) the performance of a two algorithms: Particle swarm Optimization (PSO) and Bacterial Foraging Optimization (BFO), when used for inter-turn short circuit stator winding fault of induction machine, is investigated in this paper. The proposed condition monitoring technique uses time domain terminal data in conjunction with the optimization algorithm and an induction machine model to indicate the presence of a fault and provide information about its nature and location. The proposed technique is evaluated using experimental data obtained from a 1.5 kW wound rotor three-phase induction machine. PSO and BFO are shown to be effective in identifying the type and location of the fault without the need for prior knowledge of various fault signatures.

/pdf/inter-turn-short-circuit-stator-fault-identification-for-1qkxc8eyo5.pdf

Inter-turn short circuit stator fault identification for induction machines using computational intelligence algorithms

This paper presents an adaptive proportional resonant (PR) controller for single phase grid connected inverter that adapts its control parameters to grid impedance variations. Forth order band bass filter is designed and then integrated with the adaptive scheme for on-line detection of any variations in the resonance frequency. The estimated frequency is then processed by statistical signal processing operation to identify the variations in the grid impedance. For the on-line tuning of the PR parameters, a look-up table technique is utilized and its parameters are linked with the estimated impedance values. Simulation results based on MATLAB environment clearly verify the effectiveness of the proposed control scheme for 2 kW grid connected inverter system.

/pdf/an-adaptive-proportional-resonant-controller-for-single-8jyipjaudd.pdf

An adaptive proportional resonant controller for single phase PV grid connected inverter based on band-pass filter technique

/pdf/solid-state-transformer-an-overview-of-circuit-ino8oiu6cy.pdf

Salaheddine Ethni

Papers

Comparison of particle swarm and simulated annealing algorithms for induction motor fault identification

Current Ripple Minimisation Based on Phase-Shedding of DC-DC Interleaved Converters for EV Charging System

Inter-turn short circuit stator fault identification for induction machines using computational intelligence algorithms

An adaptive proportional resonant controller for single phase PV grid connected inverter based on band-pass filter technique

Solid State Transformer: An Overview of Circuit Configurations and Applications