Search

As a new abstract computational model in evolutionary transfer optimization (ETO), single-objective to multi-objective optimization (SMO) is conducted at the macroscopic level rather than the intermediate level for specific algorithms or the microscopic level for specific operators; this method aims to develop systems with a profound grasp of evolutionary dynamic and learning mechanism similar to human intelligence via a “decomposition” style (in the abstract of the well-known “Transformer” article “Attention is All You Need”, they use “attention” instead). To the best of our knowledge, it is the first work of SMO for discrete cases because we extend our conference paper and inherit its originality status. In this paper, by implementing the abstract SMO in specialized memetic algorithms, key knowledge from single-objective problems/tasks to the multi-objective core problem/task can be transferred or “gathered” for permutation flow shop scheduling problems, which will reduce the notorious complexity in combinatorial spaces for multi-objective settings in a straight method; this is because single-objective tasks are easier to complete than their multi-objective versions. Extensive experimental studies and theoretical results on benchmarks (1) emphasize our decomposition root in mathematical programming, such as Lagrangian relaxation and column generation; (2) provide two “where to go” strategies for both SMO and ETO; and (3) contribute to the mission of building safe and beneficial artificial general intelligence for manufacturing via evolutionary computation.

To reduce logistics scheduling costs and energy consumption, this paper studies the slab allocation and hot-rolling scheduling integrated optimization problem that arises in practical iron and steel enterprises. In this problem, slabs are first allocated to orders and then sent to heating furnaces for heating; then, they are sent to a hot-rolling mill for rolling. A 0–1 integer programming model is established to minimize the attribute difference in the allocation cost between slabs and orders, the switching cost of hot-rolling processing, and waiting times after slabs reach rolling mills. Given the problem’s characteristics, an improved differential evolution algorithm using a real-number coding method is designed to solve it. Three different heuristic algorithms are proposed to improve the quality of solutions in the initial population. Multiple parent individuals participate in the mutation operation, which increases the population diversity and prevents the algorithm from falling into the local optimum prematurely. Experiments on 14 sets of real production data from a large domestic iron and steel plant show that our improved differential evolution algorithm generates significantly better solutions in a reasonable amount of time compared with CPLEX, the simulated artificial method, and the classical differential evolution algorithm, and it can be used by practitioners.

A novel mechanically tunable frequency selective surface (FSS) based on a sliding 3D-printed inserted dielectric is presented in this paper. This paper first introduces the working mechanism of the tunable FSS, which indicates that the variable capacitance is the key to tunability. Based on this, we design an all-metal bandpass FSS with a certain thickness and a matching cross-shaped inserted dielectric. By changing the insertion depth of the dielectric, the resonance frequency can be adjusted. To optimize the performance, an improved structure based on a hollow support and a tripole slot is proposed. A tunable range from 3.24 to 5.52 GHz (53%) and good angular stability is obtained in the simulation. To verify this idea, we fabricate a cross slot prototype by 3D printing and mechanical engraving. Measured results show that this prototype has a continuous tunable range of 3.61 to 5.89 GHz (34.4%).

Recently, R. M. H. Bilal et al. proposed a wideband microwave absorber based on metallic split-ring resonators and an E-shaped fractal structure. It is found that the reflection components of high-order modes are very large but have been neglected by the authors. Our results show that the actual absorptivity is much lower than the reported one if the reflection components of high-order modes are taken into consideration. The simulation results prove that the proposed structure is not an effective absorber.

Recently, the non-fullerene acceptors with fused rings enable high-efficiency organic solar cells but they are not ideal in terms of synthetic cost and yield. Here, Huang et al. report ‘less fused’ acceptors with non-covalent S⋅⋅⋅O interactions and solar cell efficiency of up to 13%.

An absorptive/transmissive frequency selective surface (ATFSS) with absorption bands at both sides of a passband is presented. Equivalent circuits of the ATFSS that consists of a lossy frequency selective surface (FSS) and a lossless FSS were modeled. To improve the rejection at an undesired band, a transmission zero was introduced and controlled by loading the lossless FSS with four-legged loaded slots. The parasitic passband was suppressed when the cross structure in the lossless FSS was loaded with resistance. In order to expand the absorption band, loaded dipoles were utilized for the lossy FSS design. An ATFSS with wide absorption bands was realized after three ATFSSs with different performances were investigated. The proposed ATFSS was fabricated and measured. The measurement results showed that a passband at around 5 GHz with a minimum insertion loss of 0.92 dB was obtained. Within an ultrawide band from 2.8 to 11.4 GHz with |S11|

This paper presents an active frequency selective surface (AFSS) with a wide reconfigurable passband. The tuning mechanism was investigated with an equivalent circuit which consists of a parallel L-C resonant circuit and a series L-C resonant circuit. A cross-loop slot was selected as a unit cell, and varactor diodes were added across the slot to tune the passband. The effects of various bias configurations on the transmission coefficients were studied. The simulation results showed that a reconfigurable passband ranged from 2.92 to 5.74 GHz was obtained with a variable capacitance from 0.8 to 0.1 pF. A prototype of the proposed AFSS was fabricated and measured. The measurement results showed that the passband was altered from 2.94 to 5.66 GHz if the biasing voltage of varactor diodes was increased from 4 to 18V. The measurement and simulation results agree well with each other.

Recently, due to the growth in machine learning and data mining, for scheduling applications in China’s industrial intelligence, we are quite fortunate to witness a paradigm of evolutionary scheduling via learning, which includes a new tool of evolutionary transfer optimization (ETO). As a new subset in ETO, single-objective to multi-objective/many-objective optimization (SMO) acts as a powerful, abstract and general framework with wide industrial applications like shop scheduling and vehicle routing. In this paper, we focus on the general mechanism of selection that selects or gathers elite and high potential solutions towards gathering/transferring strength from single-objective problems, or gathering/transferring storms of knowledge from solved tasks. Extensive studies in vehicle routing problems with time windows (VRPTW) on well-studied benchmarks validate the great universality of the SMO framework. Our investigations (1) contribute to a deep understanding of SMO, (2) enrich the classical and fundamental theory of building blocks for genetic algorithms and memetic algorithms, and (3) provide a completive and potential solution for VRPTW.

In this paper, we present a novel support vector machine learning method for multi-label classification in the steelmaking process. The steelmaking process involves complicated physicochemical reactions. The end-point temperature is the key to the steelmaking process. According to the initial furnace condition information, the end-point temperature can be predicted using a data-driven method. Based on the setting value of the temperature before tapping, multi-scale predicted errors of the end-point temperature can be calculated and divided into different ranges. The quality evaluation problem can be attributed to the multi-label classification problem of molten steel quality. To solve the classification problem, considering that it is difficult to capture nonlinear relationships between the input and output in linear models, we propose a novel support vector machine with robust low-rank learning, which has the characteristics of class imbalance without label correlations; a low-rank constraint is used to deal with high-order label correlations in low-dimensional space. Furthermore, we derive an accelerated proximal gradient algorithm and then extend it to handle the nonlinear multi-label classifiers. To validate the proposed model, experiments are conducted with real data from a practical steelmaking problem. The results show that the proposed model can effectively solve the multi-label classification problem in industrial production. To evaluate the proposed approach as a general classification approach, we test it on multi-label classification benchmark datasets. The results illustrate that the proposed approach performs better than other state-of-the-art approaches across different scenarios.

In this study, a frequency-selective rasorber with a tunable passband and two absorptive bands is presented. It is designed using two active FSSs, an absorptive FSS realized with tripole elements, and a lossless bandpass FSS achieved with ring slots. Both active FSSs embedded with varactors realize the shift of transmission frequency bands by controlling the bias voltage of the feed network. The working principle is briefly investigated according to an equivalent circuit model. A prototype is fabricated and measured to verify the simulated results, which show that a passband is tuned from 3 to 4.78 GHz between two absorptive bands, and the maximum band of |S11|

A spatial multiplexing (SM) array and a beamforming (BF) array with similar antenna size working at 28 GHz are designed and fabricated. In the SM array, a 4 × 4 MIMO system is realized with each port composed of a four-element subarray. In the BF array, the whole 16 elements are used to formulate a high-gain array. The measured S-parameters are in agreement with the simulated results. For both arrays, the channel capacities are computed by the measured channel matrix and signal-to-noise ratio (SNR) in an office room. Results show that capacity of the SM system is larger than that of the BF system, although the gain of BF array is about 5 dB larger than that of the SM array. However, the capacity of the SM array depends heavily on SNR; specifically, for the 1 dBm transmit power, communication distance R=25 cm, the ergodic capacity of the SM system is 2.76 times that of the BF system, and if R=250 cm, the capacity gain is reduced to 1.45. Furthermore, compared with the BF array, the SM array has a more robust performance over antenna misalignment, because of the wider beamwidth.

The characteristics of a novel antipodal Vivaldi antenna array mounted on a dielectric cone are presented. By employing antipodal Vivaldi antenna element, the antenna array shows ultrawide bandwidth and end-fire radiation characteristics. Our simulations show that the cone curvature has an obvious influence on the performance of the conformal antenna, in terms of both the bandwidth and the radiation patterns. The thickness and permittivity of the dielectric cone have an effect on the bandwidth of the conformal antenna. Measurement results of both single antenna and conformal antenna array show a good agreement with the simulated results. The measured conformal antenna can achieve a −10 dB S11 with bandwidth of 2.2–12 GHz and demonstrate a typical end-fire radiation beam. These findings provide useful guidelines and insights for the design of wideband end-fire antennas mounted on a dielectric cone.

The colocated dual-polarized dipole (DPD) and dual-polarized loop (DPL) MIMO channel performances are compared. Computation results show that, for the ideal electric and magnetic dipoles, the dual-polarized MIMO systems have identical channel capacity. But the contour plots of the capacity gain of the realistic DPD and DPL are different, due to the difference in antenna patterns. The cumulative distribution function (CDF) of the capacity gain in the two-mirror (TM) channel shows that, for small distance, the capacity gain obtained by the DPD is obviously smaller than that of the DPL, but, with the increase of the distance, the difference gets smaller. A DPL with low mutual coupling is fabricated. Measured results show that high MIMO capacities can be obtained by this DPL in both the anechoic chamber (AC) and the realistic office room. The capacity gain of the DPL antenna is 1.5–1.99, which basically coincides with the theoretical and numerical results. Furthermore, the capacity of the virtual DPL antenna with no mutual couplings is also investigated. It is shown that, in the AC, the mutual coupling will generally decrease the dual-polarized MIMO capacity; however, in the office room, the effect of mutual coupling is not always negative.

Purpose: The effect of hearing aids (HAs) and educational counseling (EC) or their combination on tinnitus is ambiguous. This study aimed to investigate whether the combined use of HAs and EC is more effective than EC alone on tinnitus relief. Method: A total of 72 adults with chronic, bothersome tinnitus and coexisting sensorineural hearing loss completed at least 1-month and 3-month follow-up. After receiving EC and HA prescriptions, 21 participants selected to purchase HAs (i.e., the HA + EC group), whereas the remaining 51 refused to use HAs despite recommendations (i.e., the EC group). Tinnitus severity was measured by Tinnitus Handicap Inventory (THI), Tinnitus Evaluation Questionnaire (TEQ), and Visual Analog Scale (VAS) for loudness. The primary outcome measure was THI, and tinnitus relief was defined as a 20-point or more reduction in THI. A generalized linear mixed model was used to confirm that the heterogeneity in baseline characteristics between groups did not interfere with the results. Results: The THI, TEQ, and VAS scores decreased significantly after treat- ments, and both groups yielded a similar trend of reduction. There were no sig- nificant differences in the incidence of tinnitus relief and time-to-event curves between the two groups. In addition, the length of follow-up did not affect treat- ment effectiveness. Conclusion: There was insufficient evidence to support the superiority of the combined use of HA and EC for tinnitus over EC with no device. [ABSTRACT FROM AUTHOR]