Advanced Control for Applications最新文献

In intelligent vehicles, road environment perception technology is a key component of autonomous driving assistance systems. This component is the foundation for vehicle decision-making and control, and is a guarantee of safety during the driving of the vehicle. The existing environment perception technology mainly targets well-lit environments and requires visible light imaging equipment. Therefore, in low visibility environments, this technology cannot make good judgments about the external environment. Many existing perception systems mainly rely on sensors. Under low visibility conditions, these sensors weaken their effectiveness due to signal transmission, reflection, or absorption, resulting in incomplete or distorted data collection. Reduced visibility often affects the sensing range of various sensors, hindering the system's ability to detect and recognize distant objects, thereby limiting the necessary advance warning and response time for safe navigation. In response to this issue, this study proposed a combined method of infrared imaging and polarized imaging to collect feature data on road conditions in low visibility environments. Then, the obtained images were denoised and enhanced. The processed images were input into the system for recognition, and the images were analyzed and recognized using a low visibility road situation semantic segmentation algorithm based on deep learning. The research outcomes denoted that the pixel accuracy, average pixel accuracy, and average intersection ratio of the variable weight combination model in polarized degree images were 91.2%, 89.1%, and 71.6%, respectively. Those in infrared images were 83.6%, 90.6%, and 62.1%, respectively. The various indicators of the variable weight combination model were higher than those of the U-shaped neural network model, indicating its performance is relatively excellent. The research results indicated that infrared imaging helps to acquire information at night or in low light conditions, while polarized imaging can provide better adaptation to cluttered light and reflections, enabling the system to provide more robust environmental sensing in complex weather conditions. It fills a critical gap in perception for autonomous driving systems in adverse weather conditions.

In recent years, high-performance quartz-crystal oscillators (XOs) for integrated circuits have been receiving considerable attention due to their featuring low voltage and high-frequency stability. However, recent studies tend to focus solely on the impact of temperature as a single factor on crystal oscillator circuits, overlooking the circuit structure of the crystal oscillator itself. In this paper, a novel four-parameter crystal model of XOs is detailed demonstrated, and analyzed to interpret typical XO oscillation characteristics at room temperature. The relationship between the RLC circuit and the oscillation was investigated. Meanwhile, the study delves into the various factors that influence oscillation behavior, paving the way for a comprehensive understanding of XOs' performance characteristics. temperature sweep simulations were induced to verify the theory and found that the parameter drift and thermal perturbation are close to the theory we proposed, which can be applied in temperature-compatible XOs. The significance of this study lies not only in its contribution to the design and implementation of compact footprint XOs in the oscillator circuit platform but also in its provision of experimental evidence for fabricating wide temperature range compensated XO devices. The results show that the capacitance in the equivalent model of a crystal oscillator plays a dominant role in shaping the output waveform and exhibits relatively good temperature stability characteristics and serve as a valuable resource for engineers and researchers working on improving the performance and reliability of XOs, ultimately enabling the development of more advanced and efficient integrated circuits.

Agricultural machinery industry clusters have great potential to solve key technological problems in China, and it is crucial to accurately identify the stage of cluster evolution. Based on the location entropy method, this paper finds that the location quotient coefficient is greater than 1.2 and the average annual growth rate is 1.11%, which indicates that the agricultural machinery industry in Shandong Province has a high degree of agglomeration, but the agglomeration speed is slow. Using the Groundings agglomeration—Economic network—Social network—Service system model, it is found that the agricultural machinery industry cluster in Shandong province is in the growth stage, in which the service system has the most significant influence on its development level. The weights of service system, social network, economic network, and basic resource aggregation derived from the Analytic Hierarchy Process model are 0.410, 0.321, 0.151, and 0.118, respectively, where agglomeration degree of the agricultural machinery industry, raw material production of agricultural machinery enterprises, exchange of tacit knowledge and intermediary service level are the four indicators with the greatest weights in the influences on sustainable development of the agricultural machinery industry. Because of the strong fuzzy nature between the indicators, this paper applies the Fuzzy Comprehensive Evaluation method to quantify the stage of evolution of Shandong Province's agricultural machinery industry cluster.

With the continuous development and maturation of the era of intelligent manufacturing, there is a perpetual emergence of new information technology, control technology, and material technology, which are constantly accelerating 3D printing technology to advance to an unprecedented level. To achieve the safety perception interaction ability of auxiliary medical service robots, this study develops a direct write hybrid 3D printing auxiliary medical service robot system, enabling it to achieve temperature sensing function. Moreover, combined with linear interpolation algorithms, 3D printing technology has been improved to achieve improvement of system control accuracy. The results indicate that the apparent viscosity of the printing material Ag-TPU is still greater than 2000 Pa s at a rate of 87 s⁻¹. The change in resistance during 20% stretching is within 1.2 Ω, and the change is around 3 Ω during 30% stretching. When the preset temperature is 39.2°C, the absolute deviation is the smallest, about 0.03. When the preset temperature is 41.7°C, the maximum value is approximately 0.17. The absolute error of real-time temperature collection for auxiliary medical service robots is less than 0.2°C at temperatures ranging from 38 to 42°C. Over the past 30 days of overall operation, the system has had 970 users, 3270 interactions, and 99.4% availability. This system improves the perception and interaction ability of auxiliary medical service robots, which has certain practical potential in the field of medical services.

In an era of significant energy consumption by commercial building HVAC systems, this study introduces a Deep Reinforcement Learning (DRL) approach to optimize these systems in multi-zone commercial buildings, targeting reduced energy usage and enhanced user comfort. The research begins with the development of an energy consumption model for multi-zone HVAC systems, considering the complexity and uncertainty of system parameters. This model informs the creation of a novel DRL-based optimization algorithm, which incorporates multi-stage training and a multi-agent attention mechanism, enhancing stability and scalability. Comparative analysis against traditional control methods shows the proposed algorithm's effectiveness in reducing energy consumption while maintaining indoor comfort. The study presents an innovative DRL strategy for energy management in commercial HVAC systems, offering substantial potential for sustainable practices in building management.

As artificial intelligence and automation technology develop, the concept and application of intelligent manufacturing is recognized by more and more people, and the development trend of industrial enterprises' intelligence is gradually remarkable. In order to improve the industrial intelligence of an economy and indirectly promote its circular economy, this study uses fuzzy hierarchical analysis and feed-forward neural network algorithm to construct an evaluation model of the intelligence of an economy and multiple linear regression to build an analytical model to evaluate the effect and impact of industrial intelligence on circular economy. Based on China's provincial economic yearbooks from 2012 to 2022, the total absolute difference between the average absolute error values of the hybrid fuzzy hierarchical analysis and feedforward neural network algorithm model, the traditional hierarchical analysis model and the manual evaluation method designed in this study are 0.14 and 0.31, respectively. In the industrial intelligentization - industrial structure model, except for the proportion of output value of state-owned enterprises above the scale, all other indicators have a significant positive effect, indicating that industrial intelligence, information construction and urbanization are conducive to economic scale growth. In the industrial intelligentization - environmental bias technology progress model, the regression coefficients of the proportion of output value of state-owned enterprises above the scale, industrial intelligence score, and postal communication per capita are 3.846, 0.8510, and 0.0381, respectively, which can accelerate the industrial transformation of the economy. In the industrial intelligence-economic scale model, the percentage of output value of state-owned enterprises above the scale significantly effects the environmental bias toward technological progress and the regression coefficient is −34.72, indicating that the lower percentage of state-owned enterprises in the economic structure is more conducive to industrial intelligence. This study has some reference significance for auxiliary economies to carry out industrial intelligence and stimulate the development of circular economy.

The traditional manufacturing industry is facing the impact of Big Data, and all aspects of product research and development, process design, quality management, production and operation are urgently looking forward to the birth of innovative methods to cope with the challenges of big data in the industrial background. Although traditional manufacturing enterprises have initially established quality control information system, there are still many problems and limitations in the existing quality control system, which cannot meet the operation needs of manufacturing enterprises. This paper chooses the quality management of manufacturing enterprises as the research object, and uses advanced technologies such as computer, internet, big data and cloud computing to build a data system model of quality control of manufacturing enterprises. this paper optimizes the quality data processing process by establishing the quality monitoring model, and builds an intelligent quality supervision platform, and sets up the quality alarm rules for manufacturing enterprises. If the deviation between the actual value and the predicted value of the quality monitoring index is mapped between [0,1], the quality monitoring system can generate an outlier probability score. In this study, the traditional manual quality management is transformed into the management mode of the “internet + quality data” in order to realize the information, digital and intelligent quality management of manufacturing enterprises. This comprehensive research method combines modern digital technology and relevant theories of quality management to explore the optimization scheme of quality management of manufacturing enterprises, and also provides reference experience for the information construction of other similar enterprises.

In order to improve the monitoring effect of electronic communication power supply, this paper applies the intelligent communication signal processing method to the monitoring system, and deeply analyzes the basic principle of OTA. Moreover, from the perspective of improving linearity, a signal attenuation OTA is designed in this paper, and its linearity has been greatly improved. In addition, this paper designs a cross-coupled POTA that can not only ensure high linearity but also achieve tunable translinearity. The tunable POTA circuit has simple structure, wide linear input range, tunable translinearity and easy implementation, and can meet its performance requirements in FPAA arrays. Through data analysis, it can be seen that the intelligent-oriented electronic communication power monitoring system proposed in this paper has a good data monitoring effect. This study provides an effective approach for the development of electronic communication power monitoring technology, improves the signal processing efficiency of electronic communication power monitoring, and also provides some reference for the improvement of signal strength in electronic communication technology.

The environmental issues brought on by carbon emissions from transport have risen to prominence in recent years. More and more academics are using the multi-objective path optimization method to solve the multimodal optimization problem from the standpoint of sustainable development in order to address the environmental issues brought on by the transport process. The research proposes a two-stage method to handle multi-objective optimization convergence and simplify multimodal transport path optimization. In the first stage, a fuzzy C clustering model is established, and based on the clustering results, the multimodal transport network nodes are identified. In the second stage, a multimodal transport multi-objective path optimization model is established, and the optimal path is solved using a genetic algorithm. The research method was applied in the Bohai Rim region. Results indicated that the fuzzy C-clustering method and the genetic method were able to select the optimal node city, thus solving the actual site selection problem of multimodal transportation networks. Using the FCM model, the 86 city nodes were categorized into four types, leading to the establishment of the most proficient multimodal transportation network in the Bohai Rim region. Using a genetic algorithm for optimization, a stable state is reached after 25 iterations. In the validation experiment on path optimization, the cost was reduced by 47.12% compared to the minimum single objective time, and transportation carbon emissions saw a reduction of 28.23%. Similarly, compared to the lowest target for transportation carbon emissions, the cost was reduced by 39.48% and the time was reduced by 38.12%. Compared to the lowest target for transportation carbon emissions, the time was reduced by 32.02% and the carbon emissions were reduced by 19.23%. Notably, the transportation multi-objective path optimization model showed significant improvement compared to the single-target model. The research method has been proven to be superior, and can offer the most optimal transportation route guidance for participants in multimodal transportation. Furthermore, it can effectively tackle the issue of node selection convergence and multi-objective optimization, while also serving as a valuable source of data to support the theoretical advancement of multimodal transportation network path optimization.