Industrial robots are regarded as the essential instruments for advanced industry upgrading. The kinematic parameters of an industrial robot should be calibrated precisely to guarantee its absolute positioning accuracy, which can be implemented via an evolutionary computing (EC) algorithm. However, existing calibrators are mostly based on an EC algorithm with a homogeneous learning scheme, which may lead to performance loss due to limited searching ability. On the other hand, the existing hybrid algorithm schemes based on multiple EC algorithms mostly work by training different base-models with different EC algorithms and then building the ensemble for performance gain, which leads to high computational and storage costs. Motivated by these discoveries, this paper proposes a novel Hybrid-of-Evolutionary-Schemes (HOEs) model with three-fold ideas: a) aggregating the principle of six different EC algorithms’ learning schemes to build a hybrid evolution scheme, where the learning scheme of each EC algorithm is adopted to make the swarm evolve in sequence, thereby building an expert ensemble where each expert’s learning is taken based on previous results for establishing high calibration accuracy; b) establishing a memory system that consists of diversified and highly efficient individuals in a specific population during the update process of each expert for obtaining the solution diversity; c) designing a punishment system to dismiss the experts with poor calibration performance to achieve high computational efficiency. The convergence of the HOEs model is rigorously proved in theory. To validate its performance, a large dataset HSR-C has been established and published for industrial robot calibration. Empirical studies on HSR-C demonstrate that the proposed HOEs model outperforms several state-of-the-art algorithms (including both sole algorithms and HOEs model’s variants) in terms of calibration accuracy, which strongly supports its potential in addressing calibration issues for industrial robots.

Industrial robots, as the fundamental component for intelligent manufacturing, have attracted considerable attention from both academia and industry. Since its absolute positioning accuracy can suffer from collision, wear, elastic, or inelastic deformation during its operation, a data-driven calibration (DDC) model has become a trending technique. It utilizes abundant data to decrease the difficulty in building complex system models, making it an economic and efficient approach to robot calibration. This paper conducts a comprehensive survey of the state-of-the-art DDC models with the following six-fold efforts: a) Summarizing the DDC modeling methods; b) Categorizing the latest progress of DDC optimization algorithms; c) Investigating the publicly available datasets and several typical metrics; d) Evaluating several widely adopted DDC models to demonstrate their calibration performance; e) Introducing the applications of the current DDC models; f) Discussing the progressing trend of DDC models. This paper strives to present a systematic and thorough overview of the existing DDC models from modeling to kinematic parameter optimization, thereby providing some guidance for research in this field.

Calibration technology has become an essential part of the task of improving robot precision. However, existing calibration schemes suffer from accuracy loss in actual working conditions due to the ignorance of the target robot's constrained workspace. In response to this challenge, this study proposes a novel robot calibrator with three-fold ideas: 1) optimizing the measurement configuration via the measurement configurations selection (MCS) for suppressing the measurement noises, 2) developing the alternation-direction-method-of-multipliers with multiplanar constraints (AMPC) algorithm for superior calibration accuracy and mitigatory long-tail convergence, with its convergence being theoretically proved, and 3) building the MCS-AMPC-based robot calibrator for efficient kinematic parameters calibration. For validating its performance, the HRS-P dataset that contains 2400 samples collected from different working spaces of an HRS-JR680 industrial robot has been established and publicly released. Empirical studies conclusively affirm that, compared to the Levenberg–Marquardt algorithm (the most accurate among several state-of-the-art algorithms), the proposed AMPC algorithm reduces the mean error by 10.34%. After denoising the calibration data with MCS and then employing the AMPC algorithm to identify the robot's kinematic parameters, the calibration accuracy can be further improved. Moreover, building an ensemble to address the issue of various local optimal solutions can also contribute to better calibration accuracy. The empirical results highlight the superiority and scalability of the MCS-AMPC calibrator for industrial robot-related applications.

Industrial robots inevitably incur kinematic errors in the advanced manufacturing and assembly processes, resulting in the severe reduction of the absolute positioning accuracy (APA). Kinematic calibration (KC) is well-known as a vital technique in APA-promoting tasks. However, existing KC models generally adopt a single distance-oriented Loss, e.g., an L₂ norm-oriented one that neglects the featured L_p norms. In response to this critical issue, this study presents an Adaptive p-norms-oriented Kinematic Calibration (ApKC) model on the basis of threefold ideas: 1) studying the effects of diversified L_p norms on the industrial robot calibration performance; 2) combining multiple L_p norms to obtain the aggregated loss with the hybrid effects by different norms; and 3) implementing the weight adaptation on the norm components of the aggregated loss, and rigorously prove its ensemble capability benefiting the calibration performance. Afterwards, a novel Newton interpolated Adaptive Differential Evolution (NADE) algorithm is further proposed to optimize the ApKC model. Empirical studies on an HRS JR680 industrial robot demonstrate that the achieved ApKC-NADE calibrator can significantly reduce the robot’s maximum positioning error from 4.610 to 0.856 mm. It can vigorously support the high-accuracy application of industrial robots.

Accurate photovoltaic (PV) power forecasting is crucial for effective smart grid management, given the intermittent nature of PV generation. To address these challenges, this paper proposes the Temporal Bottleneck-enhanced Bidirectional Temporal Convolutional Network with Multi-Head Attention and Autoregressive (TB-BTCGA) model. It introduces a temporal bottleneck structure and Deep Residual Shrinkage Network (DRSN) into the Temporal Convolutional Network (TCN), improving feature extraction and reducing redundancy. Additionally, the model transforms the traditional TCN into a bidirectional TCN (BiTCN), allowing it to capture both past and future dependencies while expanding the receptive field with fewer layers. The integration of an autoregressive (AR) model optimizes the linear extraction of features, while the inclusion of multi-head attention and the Bidirectional Gated Recurrent Unit (BiGRU) further strengthens the model’s ability to capture both short-term and long-term dependencies in the data. Experiments on complex datasets, including weather forecast data, station meteorological data, and power data, demonstrate that the proposed TB-BTCGA model outperforms several state-of-the-art deep learning models in prediction accuracy. Specifically, in single-step forecasting using data from three PV stations in Hebei, China, the model reduces Mean Absolute Error (MAE) by 38.53% and Root Mean Square Error (RMSE) by 33.12% and increases the coefficient of determination ($R^2$) by 7.01% compared to the baseline TCN model. Additionally, in multi-step forecasting, the model achieves a reduction of 54.26% in the best MAE and 52.64% in the best RMSE across various time horizons. These results underscore the TB-BTCGA model’s effectiveness and its strong potential for real-time photovoltaic power forecasting in smart grids.

Hyper-parameters play a critical role in neural networks; they significantly impact both training effectiveness and overall model performance. Proper hyper-parameter settings can accelerate model convergence and improve generalization. Among various hyper-parameters, the learning rate is particularly important. However, optimizing the learning rate typically requires extensive experimentation and tuning, as its setting is often dependent on specific tasks and datasets and therefore lacks universal rules or standards. Consequently, adjustments are generally made through trial and error, thereby making the selection of the learning rate complex and time-consuming. In an attempt to surmount this challenge, evolutionary computation algorithms can automatically adjust the hyper-parameter learning rate to improve training efficiency and model performance. In response to this, we propose a black widow optimization algorithm based on Lagrange interpolation (LIBWONN) to optimize the learning rate of ResNet18. Moreover, we evaluate LIBWONN’s effectiveness using 24 benchmark functions from CEC2017 and CEC2022 and compare it with nine advanced metaheuristic algorithms. The experimental results indicate that LIBWONN outperforms the other algorithms in convergence and stability. Additionally, experiments on publicly available datasets from six different fields demonstrate that LIBWONN improves the accuracy on both training and testing sets compared to the standard BWO, with gains of 6.99% and 4.48%, respectively.