Dynamic Adjustment Mechanism Research Articles

SRdetector: Sequence Reconstruction Method for Microservice Anomaly Detection

With the expansion of microservice-based applications over time, the number of microservices rises, resulting in an augmentation of the volume of performance metrics. Consequently, selecting the appropriate performance metrics for anomaly detection becomes a critical challenge. Since these performance metrics are typically strongly correlated with timestamps, they form time series data comprising timestamp–value pairs. To address this, we propose SRdetector, a feature-enhanced Transformer-based model that adopts a time series forecasting approach to detect anomalies in microservices. Furthermore, we integrate a dynamic weight adjustment mechanism into the original Transformer attention mechanism to assign weights to different performance and temporal features. This enables the model to dynamically learn the significance of various features at different time intervals, effectively serving as a feature selection method for microservice performance metrics. Finally, anomaly detection in microservices is conducted by evaluating the predicted performance metric data based on confidence intervals.

Adaptive Step RRT*-Based Method for Path Planning of Tea-Picking Robotic Arm.

The Adaptive Step RRT* (AS-RRT*) path planning algorithm for tea-picking robotic arms was proposed as a solution to the autonomy, safety, and efficiency problems inherent to tea-picking robots in tea plantations. The algorithm employs an accumulator-based sampling point selection strategy to enhance the efficiency of path planning and the quality of the resulting path. It combines fast connectivity and pruning optimization methods to identify collision-free paths in a shorter time and to reduce the computational burden. It also incorporates a dynamic step length adjustment mechanism following collision detection, ensuring that the robot arm can avoid obstacles in real time. Furthermore, the generated paths were optimized through the introduction of redundant node removal and curve smoothing techniques. In the robotic arm motion planning experiments, the depth vision sensor was employed to obtain three-dimensional information within the tea plantation as the data source. The experimental results demonstrate that the AS-RRT* algorithm reduces the path length by 14.18% and the path planning time is less than 1 s, indicating that the proposed method enhances the efficiency of path planning and obstacle avoidance performance of the tea-picking robot arm.

Quantitative evaluation study of lithium sustainable development policies in China based on the PMC index model

The sustainable development of lithium is essential for facilitating the low-carbon energy transition and ensuring sustainable economic growth. Understanding the effectiveness of China’s policies on lithium development is vital for advancing these goals. This study constructed a comprehensive policy evaluation system using content analysis and the PMC (Policy Modeling Consistency) index model. A total of 12 representative policies were analyzed, and their performance was visualized through PMC surface diagrams. The evaluation revealed that among the 12 policies, 2 were rated as “excellent,” 9 as “good,” 1 as “acceptable,” and none as “poor.” These results indicate that China’s policies for lithium’s sustainable development are generally well-designed and scientifically grounded. Despite their strengths, the policies exhibit areas for improvement, including low timeliness, insufficient long-term planning, and limited dynamic adjustment mechanisms. Regional policy coordination is also lacking, especially in non-major lithium-producing areas where policy quality tends to be lower. To address these issues, we recommend optimizing future policies by enhancing timeliness and flexibility, improving regional coordination, refining policy tools, and increasing public participation.

Multi-scale spatio-temporal transformer: A novel model reduction approach for day-ahead security-constrained unit commitment

Security-constrained unit commitment (SCUC) in large-scale power systems faces significant computational challenges, particularly with increasing renewable energy integration. This paper introduces a multi-scale spatio-temporal transformer (MSTT) model for efficient SCUC problem reduction through three key innovations: a multi-scale ST attention mechanism integrating both hierarchical temporal attention and electrical distance-based spatial attention to capture complex system dependencies, a physics-informed position encoding method incorporating power system domain knowledge including electrical distance, power flow sensitivity, and generator stability characteristics, and an adaptive reduction strategy with dynamic threshold adjustment mechanism that automatically balances computational efficiency and solution reliability based on system states and prediction confidence. Experimental results on IEEE test systems demonstrate that the MSTT model achieves up to 69.5 % computational time reduction while maintaining solution optimality (base-normalized cost (BNC) ≤ 0.05 %), significantly outperforming existing approaches.

An Intelligent Maneuver Decision-Making Approach for Air Combat Based on Deep Reinforcement Learning and Transformer Networks

The traditional maneuver decision-making approaches are highly dependent on accurate and complete situation information, and their decision-making quality becomes poor when opponent information is occasionally missing in complex electromagnetic environments. In order to solve this problem, an autonomous maneuver decision-making approach is developed based on deep reinforcement learning (DRL) architecture. Meanwhile, a Transformer network is integrated into the actor and critic networks, which can find the potential dependency relationships among the time series trajectory data. By using these relationships, the information loss is partially compensated, which leads to maneuvering decisions being more accurate. The issues of limited experience samples, low sampling efficiency, and poor stability in the agent training state appear when the Transformer network is introduced into DRL. To address these issues, the measures of designing an effective decision-making reward, a prioritized sampling method, and a dynamic learning rate adjustment mechanism are proposed. Numerous simulation results show that the proposed approach outperforms the traditional DRL algorithms, with a higher win rate in the case of opponent information loss.

Three-point adaptive preview steady-state compensation driver model based on articulated heavy vehicle

This article proposes a three-point adaptive preview steady-state compensation driver model based on articulated heavy vehicles (AHVs). Although AHVs have extremely high road transportation efficiency, they have poor driving stability and high accident risk during high-speed transportation due to their large weight, high center of mass and multi-body characteristics. However, there are few studies on intelligent driving control of AHVs. In order to improve the active safety performance of AHVs, a three-point adaptive preview driver model is designed in this article. Based on the driver model, a sliding mode steady-state compensation controller is added. The three-point adaptive preview driver is different from other driver models. Its characteristic is that the preview distance can be automatically adjusted according to the vehicle speed and road curvature. A driver model with three-point preview weighted deviation, preview time, current vehicle speed and vehicle state as input and front wheel angle as output is established. Considering the trailer state, the front wheel angle is compensated and corrected by sliding mode steady-state compensation controller. The simulation results show that the model can reasonably judge the relationship between the target path and the vehicle position, adapt to the dynamic adjustment mechanism of the preview distance, and has good tracking accuracy. The front wheel compensation angle provided by the sliding mode controller under high speed and extreme conditions can ensure that the AHVs can track the target trajectory while maintaining driving stability.

Research on the Value Creation Mechanism of Green-Driven Products in the Internet+ Era

In order to improve the value of green-driven products, this paper studies the value creation mechanism of green-driven products in the Internet+ era. Under the framework of the classic Cournot output game, based on the bounded rationality assumption of the participants, this paper constructs a novel Cournot duopoly investment game model, and analyzes the dynamic adjustment mechanism of the participants' investment. The decision variable of participating enterprises is to select the optimal investment amount, and each production enterprise makes investment decisions in the next period according to the observed marginal profit of the current period to maximize the profit. Through calculation and analysis, it can be known that three boundary equilibriums and one interior point equilibrium of the discrete dynamic model system are obtained in this paper. The experimental analysis shows that the value creation mechanism of green-driven products proposed in this paper can effectively promote the value of green-driven products.

A Three-Party Dynamic Pricing Mechanism for Customized Data Products Based on the Stackelberg Game and Bargaining Model

In the era of big data, breaking down data silos to enable efficient data transactions has become essential, with the fairness and transparency of pricing mechanisms being paramount. This study addresses these challenges by introducing a novel tripartite pricing model for customized data products that integrates the Stackelberg and bargaining game frameworks. By designing distinct utility functions for buyers, sellers, and the platform, the model effectively aligns the varying objectives of each participant. A dynamic adjustment mechanism further enhances this model by adaptively recalibrating the guidance price and pricing range based on real-time updates to buyer budgets and seller offers, thus ensuring fairness and responsiveness throughout the negotiation process. Experimental simulations comprising 100 transaction rounds across diverse buyer–seller profiles validate the model’s effectiveness, achieving a transaction success rate of 92.70% with an average of 6.86 bargaining rounds. These findings underscore the model’s capacity to optimize transaction outcomes, promote pricing equity, and enhance bargaining efficiency. The proposed model has broad applications in sectors such as finance, healthcare, and e-commerce, where precise data pricing mechanisms are essential to maximize transactional value.

Research on Interaction Effect Between Rural Roads and Peasants' Income Based on Granger Causality Test

This study aims to address the lack of methods for adjusting the scale of online ride hailing capacity. Taking G city as an example, a dynamic monitoring index system for the scale of online ride hailing capacity is constructed by comprehensively considering factors such as order volume, driver labor hours and income levels, and the operation status of the taxi market. Pearson correlation analysis and stepwise linear regression methods are applied to screen the indicators, and key indicators and threshold standards for the dynamic adjustment mechanism of online ride hailing capacity are proposed, providing theoretical basis and decision support for the adjustment of urban online ride hailing capacity scale

Research on the Dynamic Adjustment Mechanism of Online Ride Hailing Capacity Scale

This study aims to address the lack of methods for adjusting the scale of online ride hailing capacity. Taking G city as an example, a dynamic monitoring index system for the scale of online ride hailing capacity is constructed by comprehensively considering factors such as order volume, driver labor hours and income levels, and the operation status of the taxi market. Pearson correlation analysis and stepwise linear regression methods are applied to screen the indicators, and key indicators and threshold standards for the dynamic adjustment mechanism of online ride hailing capacity are proposed, providing theoretical basis and decision support for the adjustment of urban online ride hailing capacity scale

The dynamic adjusted system of sea use fees: An empirical research on the sea use management in Zhejiang province

To prevent excessive exploitation of sea resources by developers, countries around the world have established systems for managing sea use. The system of sea use fees in China is continually improving, but it cannot reflect the full value of marine natural resources. Therefore, an optimization mechanism for dynamic adjustment which considered the value of marine natural resources and the adjustment coefficient of sea area fees was constructed in the study. This study explored the difference between marine resources zoning and the dynamic adjustment standard of sea use fees collection and took Zhejiang province as an example. The results showed that the comprehensive scores of coastal marine resources were generally higher than those of the open sea in Zhejiang province. Furthermore, the comprehensive scores of important ecological areas such as bays and islands were higher than those of other marine areas, and the comprehensive score of Ningbo sea area was significantly higher than those of other sea areas. On the basis, there are six classes of the adjustment range of the sea use fees standard were divided in Zhejiang province in the study. The overall increase of fee was 3.9–8.0 %. The results of study can assist decision-making by evaluating the value of marine resources and the adjustment of sea area usage royalties, which will help to improve the efficiency of sea area management.

Improved real-time [formula omitted] control for aero-engines based on the equilibrium manifold expansion model

This paper investigates the transient performance and disturbance rejection control problem for aero-engines based on the equilibrium manifold expansion (EME) model. Considering the operating characteristics of the aero-engine vary greatly during different flight states, it is difficult to ensure the performance of the aero-engine in different states using a single controller designed offline. To solve this problem, this paper proposes an improved real-time H∞ controller. Through driving the controller to match the changes in dynamic characteristics of the system, the stability and disturbance rejection performance of the system are guaranteed over a wide range effectively. In addition, a dynamic adjustment mechanism is designed for the disturbance rejection parameter in the proposed real-time H∞ controller, which further improves the transient performance of the system. The sufficient conditions to ensure the stability of the system under the designed method are also given. Finally, the effectiveness and superiority of the proposed method are verified through an aero-engine numerical simulation program and a hardware-in-the-loop (HIL) experiment.

Rolling bearing fault diagnosis method based on adaptive signal diagnosis network and its application

Aiming at the problems of fixed convolution kernel size and poor targeting of extracted features in the application of deep learning in fault diagnosis, this paper develops a fault diagnosis framework called adaptive signal diagnosis network (ASDN), in which the EEMD of multi-scale signal decomposition is improved in the adaptive preprocessing stage to adaptively capture the transient changes of signals. Meanwhile, SSA is improved to further extract fault trends and periodic components to optimize the signal representation. In the adaptive deep learning stage, an innovative temporal convolutional network (TCN) with a dynamic adjustment mechanism was developed to enable the neural network to adjust its convolutional kernel size according to different frequency components so as to accurately process signals of different frequencies. Validation on datasets from Case Western Reserve University and Xi'an Jiaotong University shows the superior performance of the proposed method, with diagnostic accuracies of 100% and 97.42% on these two public datasets, respectively.

FLAV: Federated Learning for Autonomous Vehicle privacy protection

Autonomous Vehicle Systems are committed to safer, more efficient and more convenient transportation on the roads of the future. However, concerns about vehicle data privacy and security remain significant. Federated Learning, as a decentralized machine learning approach, allows multiple devices or data sources to collaboratively train models without sharing raw data, providing essential privacy protection. In this paper, we propose a privacy-preserving framework for autonomous vehicles, named FLAV. First, we use a multi-chain parallel aggregation strategy to transmit model parameters and design a model parameter filtering mechanism, which reduces communication overhead by filtering out the local model parameters of certain vehicles, thereby alleviating bandwidth pressure. Second, we introduce a dynamic adjustment mechanism that automatically adjusts regularization strength by comparing each vehicle’s local parameters with the cumulative parameters of preceding vehicles in the chain. This mechanism balances local training with global consistency, ensuring the model’s adaptability to local data while improving coordination between vehicles in the chain. Experimental results demonstrate that our proposed method reduces communication costs while improving model accuracy and privacy protection level, effectively ensuring the security of autonomous driving data.

GWO-ANFIS-RD3PG: A reinforcement learning approach with dynamic adjustment and dual replay mechanism for building energy forecasting

Reliable prediction of building energy consumption is essential for effective and sustainable energy management. Traditional forecasting methods, however, face challenges when dealing with sudden changes in energy consumption. To address the above-mentioned issue, we introduce the GWO-ANFIS-RD3PG prediction model in this paper. This model aims to ensure global forecasting accuracy while minimizing prediction errors at sudden change points. A Grey Wolf Optimization (GWO) algorithm with the Adaptive Neuro-Fuzzy Inference System (ANFIS) is proposed to predict the energy consumption type and its fluctuation magnitude for the next time step. Within the Recurrent Dual Experience Replay Buffer DDPG (RD3PG) prediction module, we employ Long Short-Term Memory (LSTM), as the actor network in the Deep Deterministic Policy Gradient (DDPG), to account for long-term dependencies in time series data. Notably, we introduce an adaptive action modification mechanism that allows the agent to optimize actions based on the output of the aforementioned ANFIS, enabling real-time adjustments during sudden change. To further enhance the model’s performance, we adopt a dual experience replay mechanism to store data samples from sudden change points, capturing insight information during these anomalies. Experimental results on two real-world datasets demonstrate that this method reduces MAE by 5.81% and 13.47%, and RMSE by 5.69% and 15.21% compared to the state-of-art models, showing the significance of the proposed method for energy efficiency improvement in real-world building operations.

Enhancing point cloud registration with transformer: cultural heritage protection of the Terracotta Warriors

Point cloud registration technology, by precisely aligning repair components with the original artifacts, can accurately record the geometric shape of cultural heritage objects and generate three-dimensional models, thereby providing reliable data support for the digital preservation, virtual exhibition, and restoration of cultural relics. However, traditional point cloud registration methods face challenges when dealing with cultural heritage data, including complex morphological and structural variations, sparsity and irregularity, and cross-dataset generalization. To address these challenges, this paper introduces an innovative method called Enhancing Point Cloud Registration with Transformer (EPCRT). Firstly, we utilize local geometric perception for positional encoding and combine it with a dynamic adjustment mechanism based on local density information and geometric angle encoding, enhancing the flexibility and adaptability of positional encoding to better characterize the complex local morphology and structural variations of artifacts. Additionally, we introduce a convolutional-Transformer hybrid module to facilitate interactive learning of artifact point cloud features, effectively achieving local–global feature fusion and enhancing detail capture capabilities, thus effectively handling the sparsity and irregularity of artifact point cloud data. We conduct extensive evaluations on the 3DMatch, ModelNet, KITTI, and MVP-RG datasets, and validate our method on the Terracotta Warriors cultural heritage dataset. The results demonstrate that our method has significant performance advantages in handling the complexity of morphological and structural variations, sparsity and irregularity of relic data, and cross-dataset generalization.

DBUP: Dynamic blockchain UTXO processing for storage efficiency optimization

In traditional blockchain systems, the Unsent Transaction Output (UTXO) dataset stores all generated UTXOs, which typically represent digital assets of the users. UTXOs can be used to track the output status of cryptocurrency transactions. However, with the development of blockchain networks, the UTXO dataset continuously increasing in scale. In the UTXO dataset, a large number of low-value UTXOs occupied huge storage space, making the blockchain dataset expanded. This impacts the running performance of the whole blockchain system. To address this issue, this paper proposes the Dynamic Blockchain UTXO Processing strategy (DBUP) for UTXO storage efficiency optimization. This strategy aims to rapidly consume the low-value UTXOs, effectively alleviating UTXO dataset expansion. Furthermore, Through improved simulated annealing (ISA) algorithm and a UTXO dynamic adjustment mechanism in DBUP, the strategy ensures that the transaction fee in the transaction process remain at a low level. The experimental evaluation indicates that our strategy can achieve the better performance against the Low Value First (LVF) and the First-In-First-Out (FIFO) strategies, enhancing the storage efficiency of blockchain systems.

Research on blind source separation of operation sounds of metro power transformer through an Adaptive Threshold REPET algorithm

PurposeThe safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system. Through voiceprint technology, the sounds emitted by the transformer can be monitored in real-time, thereby achieving real-time monitoring of the transformer’s operational status. However, the environment surrounding power transformers is filled with various interfering sounds that intertwine with both the normal operational voiceprints and faulty voiceprints of the transformer, severely impacting the accuracy and reliability of voiceprint identification. Therefore, effective preprocessing steps are required to identify and separate the sound signals of transformer operation, which is a prerequisite for subsequent analysis.Design/methodology/approachThis paper proposes an Adaptive Threshold Repeating Pattern Extraction Technique (REPET) algorithm to separate and denoise the transformer operation sound signals. By analyzing the Short-Time Fourier Transform (STFT) amplitude spectrum, the algorithm identifies and utilizes the repeating periodic structures within the signal to automatically adjust the threshold, effectively distinguishing and extracting stable background signals from transient foreground events. The REPET algorithm first calculates the autocorrelation matrix of the signal to determine the repeating period, then constructs a repeating segment model. Through comparison with the amplitude spectrum of the original signal, repeating patterns are extracted and a soft time-frequency mask is generated.FindingsAfter adaptive thresholding processing, the target signal is separated. Experiments conducted on mixed sounds to separate background sounds from foreground sounds using this algorithm and comparing the results with those obtained using the FastICA algorithm demonstrate that the Adaptive Threshold REPET method achieves good separation effects.Originality/valueA REPET method with adaptive threshold is proposed, which adopts the dynamic threshold adjustment mechanism, adaptively calculates the threshold for blind source separation and improves the adaptability and robustness of the algorithm to the statistical characteristics of the signal. It also lays the foundation for transformer fault detection based on acoustic fingerprinting.

Digitalisation of Administrative Discretion Legal Risks and Responses

In the context of the construction of a digital rule of law government, the digitisation of administrative penalties has been widely used in law enforcement practice, enhancing the efficiency and objectivity of administrative penalties. However, there are certain legal risks associated with digitised discretion: the algorithmic black box contradicts the principle of administrative openness, the procedural rights of the administrative relative are ignored, justice in individual cases is sometimes difficult to be achieved as well as the definition of the responsible subject is vague. For this reason, the risk-building programme should be improved through the construction of a transparency mechanism and a dynamic adjustment mechanism, the improvement of administrative procedures, and the clarification of the subject of responsibilityr.

The Setting and Dynamic Adjustment Mechanism of Law Majors Facing the Development of Regional New Economy

Digital services, including healthcare, among others, have recently seen a massive volume of complicated data that arrives rapidly due to a rapid increase in the number of smart devices, focusing on the needs of regional emerging economic development and industrial structure adjustment, this paper explores the dynamic adjustment of a major in which schools, governments, enterprises and international cooperation participate in the development of regional emerging economies. mechanism. Based on the concept of future-oriented development, formulate a development plan for the legal profession, build a community of government, school, enterprise and international cooperation, promote the vigorous implementation of engineering practice education, and cultivate high-quality, high-level, international graduates, and to form the school-running characteristics of law majors in local application-oriented undergraduate colleges.