Intelligent Control System Research Articles

Modeling and Control of Drinking Water Supply Infrastructures Through Multi-Agent Systems for Sustainability

Traditionally, drinking water supply infrastructures have been designed to store as much water as possible and to do so during the energy cheap hours. This approach is unsustainable today. The use of digital systems capable of modeling the behavior of infrastructures and the creation of intelligent control systems can help to make drinking water supply systems more efficient and effective, while still meeting minimum service requirements. This work proposes the development of a control system, based on multi-agent systems (MAS), capable of generating an intelligent control over a drinking water infrastructure, based on the use of local interests of the agents and with an emergent behavior coherent with the needs. To validate the proposal, a simulator based on the infrastructures of a medium-sized Spanish city of 5000 inhabitants has been built and the control has been simulated using the MAS. The results show how the system can maintain the objectives set, handling unknown situations, and facilitating the development of future physical systems based on a just-in-time paradigm that guarantees sustainability, as it allows the generation of virtualizations of the infrastructures and their behavior, thus being able to study the best option for an infrastructure to resolve a supply situation.

Novel high-safety aeroengine performance predictive control method based on adaptive tracking weight

Increasing attention has been attracted to the dynamic performance and safety of advanced performance predictive control systems of the next-generation aeroengine. The latest research demonstrates that Subspace-based Improved Model Predictive Control (SIMPC) can overcome the difficulty in solving the predictive model in MPC/NMPC applications. However, applying constant design parameters cannot maintain consistent control effects in all states. Meanwhile, the designed system relies too much on sensor-measured data, and thus it is difficult to thoroughly validate the safety of the system because of its high complexity. This means that any potential hardware/software faults will endanger the engine. Therefore, this paper first presents a novel nonlinear mapping relationship to adaptively tune the tracking weight online with the change of Power Lever Angle (PLA) and real-time relative tracking error. Thus, without introducing additional design parameters, an Adaptive Tracking Weight-based SIMPC (ATW-SIMPC) controller is designed to improve the control performance in all operating states effectively. Then, a Primary/Backup Hybrid Control (PBHC) strategy with the ATW-SIMPC controller as the primary system and the traditional speed (Nf) controller as the backup system is proposed to ensure safety. The designed affiliated switching controller and the real-time monitor therein can be used to realize reasonable and smooth switching between primary/backup systems, so as to avoid bump transition. The PBHC system switches to the Nf controller when the ATW-SIMPC controller is wrong because of potential hardware/software faults; otherwise, the ATW-SIMPC controller keeps acting on the engine. The main results prove that the ATW-SIMPC controller with the optimal nonlinear mapping relationship, compared with the existing SIMPC controller, uplifts the dynamic control performance by 32% and reduces overshoots to an allowable limit, resulting in a better control effect in full state. The comparison results consistently indicate that the PBHC can guarantee engine safety in occurrence of hardware/software faults, such as sensor/onboard adaptive model faults. The approach proposed is applicable to the design of a model-based engine intelligent control system.

The application of Internet of Things technology in intelligent fire protection

The uncertainty of fire and the difficulty of accurate prevention greatly increase the difficulty of fire prevention and control. Therefore, it is necessary to actively introduce modern science and technology, adopt fire Internet of Things (IoT) technology, realize remote dynamic monitoring, and accurately obtain fire prevention and control data information. This paper carries out an in-depth analysis on fire prevention and control, focusing on the application of fire IoT in the field of fire prevention and control. In addition, it specifically introduces the key technologies of intelligent fire protection, Radio Frequency ID, and the construction of fire safety models. At the same time, it describes the problems faced by the IoT in intelligent fire protection, that is, the quality of transmitted information is not strong, the speed of message transmission needs to be improved, and the application platform that is more conducive to the transmission of information needs to be built. By overcoming these issues, the future intelligent fire control system will be more intelligent and bring more convenience to people.

Conceptual directions for the development of driverless agricultural mobile power units

BACKGROUND: Currently, major global developers and manufacturers in the field of mobile agricultural machinery are working on the development of agricultural robotic systems. Particular attention is paid to the development of universal driverless mobile power units (MPU) capable of performing various technological operations autonomously, without human intervention. In the future, this makes it possible to exclude the operator from the MPU control process and to reconsider approaches to the issue of increasing the efficiency of technological operations. The existing trend of productivity improvement by increasing the main parameters of the unit, such as operating width, operating velocities, load capacity, etc., may change to an alternative path consisting in the use of numerous autonomous small-sized units comparable in performance (a swarm of agricultural robots). Thus, the use of driverless control systems makes it possible to use conceptually new approaches to the development of agricultural MPUs. In this regard, it becomes relevant to conduct the study aimed at identifying promising conceptual directions for the development of driverless MPUs and evaluating the efficiency of their application. AIM: Identification of conceptual directions for the development of driverless driverless MPUs and a theoretical assessment of the efficiency of their application. METHODS: The study object was the MPU transformation in the context of the development of driverless control systems. The study was based on scientific publications on the development of robotic agricultural tools, informational data of manufacturers of agricultural tractors and control systems for agricultural machinery. In the course of the study, such methods as information analysis, synthesis, methods of performance analysis of agricultural units and analysis of present cost of performing technological operations, adapted for driverless MPUs by the VIM, were used. RESULTS: The prospects for the introduction of driverless MPUs, the existing digital and intelligent control systems of MPUs and the main factors hindering their development are analyzed. A classification of agricultural MPUs according to automation levels is proposed. The main directions of development are identified and conceptual models of driverless MPUs are proposed: universal driverless MPUs (driverless tractors) with keeping the existing traction class and power classification, universal (multifunctional) low-power driverless MPUs of the only traction class, separate power modules capable of being combined into a single driverless unit based on the coupled agricultural machine. The method is proposed and the equivalent number of driverless MPUs of each conceptual model for each traction class is calculated. An assessment of the impact of the use of the proposed conceptual models of driverless MPUs on the arable unit performance and the present cost of arable operations has been carried out. CONCLUSIONS: Conceptual models for the advancing of driverless MPUs have been developed and comparative calculations of the efficiency of their application as part of arable units, helping to assess the possible prospects for their use, have been made.

Research on establishment of digital-twin system for intelligent control of cutting tools sintering process driven by data-model combination

In the manufacturing process of tungsten cemented carbide cutting tools, the changes in temperature, pressure and vacuum during the sintering process of the cutting tools can have a significant impact on the quality of the cutting tools. This effect is particularly significant in the vacuum sintering stage, so this paper focuses on cutting tools sintering in the vacuum stage. The cutting tools sintering process is carried out in a closed space in a sintering furnace with a complex internal structure. Therefore, it is extremely difficult to accurately predict the heating condition of the cutting tools in the furnace and monitor the sintering quality of the cutting tools. In this study, a digital twin system for the sintering process of cemented carbide cutting tools is proposed, which combines monitoring rolling data analysis and sintering quality prediction model. Firstly, the radiative thermodynamic model of cutting tools sintering temperature was established in this system. The model predicts the time-varying state of the heat distribution at any location in the furnace during the vacuum phase. Subsequently, based on the convolutional neural network, the mapping relationship between the sintering parameters and the grain size in the vacuum stage is constructed, and a dynamic evaluation model of cutting tools sintering quality is proposed. The model enables real-time prediction of sintering quality in the vacuum stage. The system realizes the prediction of the time-varying state of the sintering quality of the cutting tools. The digital twin system realizes the adaptive temperature control of the vacuum stage of cutting tools sintering based on the fuzzy control algorithm. The application of this system has increased the yield rate of cemented carbide cutting tools manufacturing to 98.9%. This breaks through the problem of timing modulation of cutting tools sintering quality in the vacuum stage of cutting tools sintering.

Monitoring Energy and Power Quality of the Loads in a Microgrid Laboratory Using Smart Meters

Microgrids are local energy production and distribution networks that can operate independently when disconnected from the main power grid thanks to the integration of power generation systems, energy storage units and intelligent control systems. However, despite their advantages, the optimal energy management of real microgrids remains a subject that requires further investigation. Specifically, an effective management of microgrids requires managing a large number of electrical variables related to the power generated by the microgrid’s power supplies, the power consumed by the loads and the aspects of power quality. This study analyzes how we can monitor different variables, such as the active power, reactive power, power factor, total harmonic distortion and frequency in the loads of a microgrid, using high-precision power meters. Our empirical study, conducted using a functional microgrid comprising a hybrid wind–solar power system and several household appliances, demonstrates the feasibility of using low-cost and high-performance power meters with IoT functionality to collect valuable power quality and energy consumption data that can be used to control the microgrid operation.

Design and Simulation of a Multi-Channel Biomass Hot Air Furnace with an Intelligent Temperature Control System

Timely and effective drying of agricultural products is crucial for ensuring the quality and yield of grains. Biomass drying enhances energy utilization and reduces energy pressure. To this end, a novel multi-channel circulating biomass hot air furnace was designed to provide precise control of the heat source for grain drying, thereby improving the efficiency and quality of the drying process. The combustion process utilizes a multi-channel combined air supply to ensure complete combustion of biomass pellet fuel. During the heat exchange process, heat exchange plates isolate hot and cold areas, discharging combustion exhaust, while ensuring a pure air output. Using rapeseed as the drying subject, a temperature controller based on adaptive fuzzy PID was designed, targeting the biomass hot air furnace’s heat exchange system for modeling and verifying the model with the step response method. Model simulations were conducted in Matlab’s Simulink module using both adaptive fuzzy PID and traditional PID controllers, for a given signal. The settling times for the conventional PID and fuzzy PID were 445 s and 364 s, respectively, with overshoots of 20.1% and 6.3%, showing that the fuzzy PID controller performed better in terms of control performance. The validation tests showed that both control methods could maintain the temperature within ±5 °C. Compared to traditional PID control, the adaptive fuzzy PID control achieved a precision of ±3 °C. At the target temperature of 90 °C, the error was reduced to 3.7%, with a stabilization time of 1014 s. The use of fuzzy PID control exhibited better dynamic response characteristics, meeting the drying needs of rapeseed. This study provides a theoretical basis for the structural design and control system design of biomass hot air furnaces.

Research on intelligent control system of permanent magnet motor for high-speed flywheel energy storage system based on deep learning

With the continuous development of society, more and more people pay attention to energy issues, and the realization of energy storage has become a hot research direction today. Despite advancements, the control system of the high-speed flywheel energy storage system’s permanent magnet motor still encounters issues in effectively regulating the magnetic suspension bearing and motor speed. In addressing this issue, a technical solution involves the implementation of an intelligent control system for the high-speed flywheel energy storage system’s permanent magnet motor, utilizing deep learning principles. This innovative approach employs deep neural networks to model, optimize, and regulate the flywheel energy storage system. The essence of flywheel energy storage lies in the conversion of electrical energy into mechanical energy, followed by its reconversion into electrical energy during output. It has the advantages of high energy density, high power density, long cycle life, fast charging and discharging, maintenance-free and environmental protection. A permanent magnet motor is a motor that uses permanent magnets to generate a magnetic field. It has the characteristics of high efficiency, high power density, and low rotor loss. It remains the most widely utilized motor in flywheel energy storage systems. An intelligent control system is characterized by its use of artificial intelligence technology to adapt, self-learn, and self-organize complex systems. This system is distinguished by its robust nonlinear processing capabilities and resilience to faults. The high-speed flywheel energy storage system permanent magnet motor intelligent control system based on deep learning can improve the performance, efficiency and reliability of the flywheel energy storage system, reduce costs and risks, and is suitable for electric vehicles, rail transit, power grid frequency regulation and other fields. In this paper, the convolutional neural network and PSO algorithm are used to obtain the PSNN neural network structure to predict the speed of the motor, so as to achieve its control. And the reliability of the structure is verified by experiments.

An intelligent continuous bladder irrigation monitoring and control system: Development and preliminary assessment

Abstract Objectives: To design an intelligent continuous bladder irrigation monitoring and control system and preliminarily assess its sensitivity of the early warning of flushing anomalies. Methods: According to the principle of bladder irrigation, an intelligent continuous bladder irrigation monitoring and control system was designed. The Amesim fluid simulation software was used to establish a parameterized simulation model for the bladder perfusion process and simulate the dynamic changes of bladder pressure and volume under different perfusion speeds to assess the sensitivity of the early warning of flushing anomalies. Results: The intelligent system consisted of 3 parts: the monitoring part (a flushing fluid inlet flow monitoring device, a flushing fluid outlet flow monitoring device, and a flushing fluid outlet color recognition sensor), the transition part (a control motherboard), and the regulation part (an alarm device, an electric control device for flushing fluid input speed, and a squeezing device for flushing waste fluid line). The data of the parameterized simulation model for the bladder perfusion process suggested that the sensitivity of the system was acceptable. Conclusion: The intelligent bladder irrigation system can automatically detect, report, and resolve signal abnormalities, thereby achieving the closed-loop management of bladder irrigation. The intelligent system might be used in clinical settings to reduce the burdens of nurses and promote patients’ recovery.

Design and implementation of facility intelligent carbon dioxide incubator control system based on POA optimized fuzzy PID

To solve the problem that traditional carbon dioxide incubators are difficult to accurately control the required carbon dioxide environment to the detriment of experimental cultivation, and given the difficulties of time lag, nonlinearity, time-varying, and poor adaptive ability of the incubator control system, this study designs a set of intelligent carbon dioxide incubator control system suitable for laboratory cultivation. The system is based on the POA (Pelican optimization algorithm) to optimize the fuzzy PID (Proportional Integral Derivative) control to regulate the opening degree of the solenoid valve to accurately control the carbon dioxide concentration in the incubator to the set range. In this study, the simulation and comparison tests of POA-based optimized fuzzy PID control, PID control, and fuzzy PID control are carried out by MATLAB/Simulink, and it is found that the overshooting amount of the system is reduced by 11.6%, the regulating time is shortened by 69.3 s, and the steady state error is reduced by 0.1% compared with that of the traditional fuzzy PID control. It can be obtained through practical tests that the accuracy, response, and stability of the optimized fuzzy PID control of the pelican algorithm are better than those of the fuzzy PID control method, and it has better robustness. Therefore, the carbon dioxide incubator control system has high practical application value.

Intelligent control of electric vehicle air conditioning system based on deep reinforcement learning

The existing AC system of EVs consumes a lot of energy in summer, resulting in reduced range. Additionally, the cabin temperature (Tcabin) fluctuates due to varying driving conditions. In this paper, an innovative cooling strategy is designed to address the above drawbacks using deep reinforcement learning algorithms. The primary objective of this strategy is to achieve high-precision temperature control while concurrently minimizing the energy consumption of the AC system. The strategy combines compressor speed (Ncompressor) and blower airflow (Bairflow) control to optimize the AC system's performance. The RL controller minimizes energy consumption by reducing Ncompressor while increasing Bairflow, thus ensuring a constant cooling capacity (Q). And it effectively reduces temperature fluctuations within the cabin. Finally, the RL control strategy was compared with on/off control and proportional integral differential (PID) control. The results showed that RL control performed well in the multi-objective optimization of the AC system. In terms of temperature control, it effectively reduces the amount of overshooting, and the minimum temperature fluctuation achieved through RL control is merely 0.07 °C, exhibiting an 84.4 % and 86.5 % decrease compared to traditional control methods. The average absolute temperature error stands at 0.06–0.07℃, maintaining a remarkable precision in preserving the target temperature. Furthermore, RL control not only ensures superior energy efficiency but also reduces energy consumption by up to 5.98 % and 7.65 % compared with traditional control methods.

An improved low‐carbon intelligent agriculture system with energy optimization principles using wireless IoT environment

AbstractA low‐carbon agricultural plan and intelligent agriculture control system are designed and completed with a green economy to foster the significant expansion of green resources and environmental assets. This research employs a fixed‐effect panel model to examine the farming cumulative energy savings in 11 cities and regions along the Yamuna Tributary Commercial Region, focusing on both static and dynamic factors. The directional linear equation and the Malmquist–Luenberger (ML) indicator are the key analytical tools. Unlike conventional techniques, regression analysis using cross‐sectional data is the primary tributary. Research has found that a 5.9% decrease in the literacy rate of the working force had a large impact on farming energy efficiency and that for each 1% rise in crop losses, farm energy efficiency would decrease by 0.487%. In addition to mitigating the detrimental effects of industrial design and mechanization on agricultural output, this effort aids in the advancement of smart city design. This activity paves the way for cutting‐edge technology by encouraging people to move to cities, educating the workforce, and giving money to the agricultural sector. The ability of proposed model gives the smart agriculture system with intelligent control principles and energy optimization principles in the deployed wireless‐IoT platform. On this research problem, this paper contributes to new knowledge by approaching agricultural energy efficiency from a green economy perspective, conducting regression analyses of panel data on the most important influencing factors using the advanced statistical analysis tool Eviews, and then drawing the conclusion from the evaluation of metrics that affect farming energy efficiency in our nation. Enhancing productivity while also fostering long‐term growth in the agricultural ecosystem is crucial. It contributes for smart and green technologies adaptation in agriculture filed.

Design and simulation of remote monitoring of the intelligent automatic control system in the production line

<p><span lang="EN-US">In this research, we will introduce implementation requirements of a remote wireless control and monitoring unit of industrial production lines automatically controlled using programmable logic controller (PLC). PLC is capable of collecting different types of data and converting them into electrical signals that can be controlled by the industrial network using supervisory control and data acquisition (SCADA) systems. SCADA will be installed in the main server inside the control unit. The PLC will be used as a decision maker of the received signals for the industrial lines that comes from a group of detectors (sensors/transducers). The output of the PLC processor will trigger the engines, according to a specific industrial process management program. The processed data could be transferred through wireless or wired method. The wireless approach will be shown in this study, along with two other ways to implement it.</span></p>

Dynamic Optimization-Based Intelligent Control System for Drilling Rate of Penetration (ROP): Simulation and Industrial Application

Dynamic Optimization-Based Intelligent Control System for Drilling Rate of Penetration (ROP): Simulation and Industrial Application

Preface

We are glad to welcome you to the proceedings of 2023 The 4th Asia Conference on Computers and Communications (ACCC 2023), which was held in Shanghai, China (virtual) during December 15-17, 2023. By following most of delegates’ willingness, the conference was entirely transferred as online conference instead of Shanghai, China as scheduled.ACCC 2023 welcomes contributions that involve computers and communications. All papers in this proceeding were subject to peer-review by conference committee members and international reviewers. Conference’s relevance and quality drive the selection of the papers included in the proceedings. The contributed papers presented in this volume cover a wide range of topics spanning sensor based electronic system design and circuit analysis, signal analysis and data transmission in future communication systems, modern intelligent system monitoring and security, and so on.The conference has lasted virtually for 3 days including the online testing, 2 keynote speeches, each with 40 minutes, 2 invited speeches, each with 30 minutes, as well as 3 oral sessions from December 15-17, 2023. All research presentations were split into 3 sessions with the theme below: Intelligent Detection and Image Analysis Based on Machine Vision, Next Generation Communication Systems and Information Security, Model based intelligent control system and simulation analysis. Each presenter has made 15-minute (including Q&A) oral presentation. The diverse interesting discussions give a generation of new ideas during conference. We are grateful that they share new research ideas with us.We are deeply grateful to committee members, and international reviewers, whose diligence and effort brought these proceedings successfully together. Their excellent professional advice enabled us to prepare this conference. Our special thanks go to our guest speakers for sharing their latest research results. We do hope these talks interest and inspire all of you.As you peruse these proceedings, we encourage you to explore the wealth of knowledge presented within. It is our hope that these research papers inspire further exploration and contribute to the ongoing development of computers and communications technologies. We look forward to future editions of ACCC, where the global community will continue to converge, share ideas, and shape the future of computing and communications.Thank you to all participants for making ACCC 2023 a memorable and intellectually stimulating event.ACCC 2023Organizing CommitteeList of Committees, Statement of Peer Review are available in this pdf.

The intersection of mechatronics and precision engineering: Synergies and future directions

The convergence of mechatronics and precision engineering has sparked significant interest due to its potential to revolutionize various industries, ranging from manufacturing to healthcare. This review explores the synergies between these two domains and outlines potential future directions for research and application. Mechatronics, an interdisciplinary field combining mechanical engineering, electrical engineering, computer science, and control engineering, focuses on the design and development of intelligent systems with integrated sensing, actuation, and control capabilities. Precision engineering, on the other hand, emphasizes the fabrication of high-accuracy components and systems, often at micro or nanoscales, to meet stringent performance requirements. The intersection of mechatronics and precision engineering offers numerous synergistic opportunities. One such opportunity lies in the development of precision actuators and sensors with embedded intelligent control systems, enabling precise motion control and feedback mechanisms in complex systems. Furthermore, advancements in microfabrication techniques allow for the integration of sensors and actuators directly onto precision components, leading to miniaturized and efficient mechatronic systems. In manufacturing, this synergy facilitates the creation of highly automated and flexible production processes capable of producing intricate and high-quality products with minimal human intervention. In healthcare, it enables the development of precision medical devices for diagnostics, surgery, and drug delivery, enhancing patient outcomes and reducing the invasiveness of procedures. Future directions in this interdisciplinary field include exploring novel materials and manufacturing techniques to further improve the precision and performance of mechatronic systems. Additionally, advancements in artificial intelligence and machine learning are poised to enhance the autonomy and adaptability of mechatronic systems, enabling them to learn from data and adapt to changing environments in real-time. the intersection of mechatronics and precision engineering holds great promise for addressing complex engineering challenges and driving innovation across various industries. By leveraging their complementary strengths, researchers and engineers can unlock new opportunities to create smarter, more efficient, and more precise systems with transformative impacts on society.

Optimization and evaluation of a neural network based policy for real-time control of construction factory processes

This paper focuses on the development, optimization, and evaluation of an intelligent real-time control system for the fabrication of precast reinforced concrete components. The study addresses the unique challenges associated with real-time control in the construction manufacturing industry, including high customization, uncertain work demand, and limited stockpiling opportunities. A production system model is built based on a real construction manufacturing factory to simulate real-world precast reinforced concrete component fabrication, and acts as the basis for the development and validation of the control system. A review of alternative decision-making techniques is presented to identify the most suitable for the control of construction manufacturing factories. Ultimately, an artificial neural network approach trained using a reinforcement learning strategy is selected as a promising technique for effective real-time control. The controller is developed and validated, and its performance is optimized using sensitivity analysis, which takes into account both the structure of the artificial neural network and the parameters of the reinforcement learning algorithm. The ANN-based control policy is applied to the sequencing of precast reinforced concrete component production, while a rule-of-thumb policy is used as a benchmark for comparison. The study demonstrates that the optimized ANN-based control policy significantly outperforms the standard rule-of-thumb policy. The paper concludes by providing suggestions for further advancement of the ANN-based approach and potential avenues to increase the control policy's scope of application in construction manufacturing.

Application of digital technologies in the management of oil well pumping systems in oil extraction

In recent years, one of the trends in oil well production has been the continuous growth of interest in intelligent monitoring and control systems for mechanized well assets. This is attributed, on one hand, to the increasing number of oil fields worldwide reaching maturity and the development of new challenging reservoirs (in terms of viscosity, water cut, and sand production). On the other hand, it is driven by the necessity to enhance the economic efficiency of oil production, including cost reduction and minimizing losses. The emergence of «smart» oil production technologies, such as programmable drives for well pumps, also contributes significantly to addressing these issues. Their application allows for increased reliability and lifespan of pump equipment, reduced well downtime and failures, prevention of negative scenarios during oil production, and facilitates the visualization of parameters in a user-friendly manner. Despite the widespread use of digital technologies in the oil and gas industry, there is still significant potential for further digitization to expand operations for enhanced safety and productivity. This article presents the experience of creating and testing such a control station for screw pump units at an oil field.

Research on Intelligent Supervision System of Ore Pass

To prevent safety accidents caused by mining vehicles and personnel entering the operation area by mistakes, it is necessary to reduce the risk of the ore pass. However, the underground space of the mine is narrow, and factors such as dust and noise during the unloading process endanger the health of the personnel on duty in the ore pass. As such, the target detection technology based on deep learning is introduced into the underground monitoring system. The underground surveillance video samples are collected to establish a dataset for Yolov3 algorithm to identify minecarts. Through optimizing the Yolov3 model training process and algorithm, and using the dual-camera collaborative discrimination method, the influence of brightness on the recognition results when the loaders or trucks lights are turned on can be overcome. Four types of minecarts can be accurately identified from the underground surveillance video. On the basis of mining car recognition, an intelligent access control system for mine shafts based on Jetson Nano’s embedded development is developed. The on-site operation results show that the average accuracy of target vehicle recognition is within the range of 95%-100%. The system continuously recognizes the mine car 5 times from the detection program and sends the opening and closing command to complete a 90 ° rotation, which takes only 3 seconds，effectively meeting the needs of the mine for ore pass control.

Lightweight Vehicle Detection Based on Improved YOLOv5s.

A vehicle detection algorithm is an indispensable component of intelligent traffic management and control systems, influencing the efficiency and functionality of the system. In this paper, we propose a lightweight improvement method for the YOLOv5 algorithm based on integrated perceptual attention, with few parameters and high detection accuracy. First, we propose a lightweight module IPA with a Transformer encoder based on integrated perceptual attention, which leads to a reduction in the number of parameters while capturing global dependencies for richer contextual information. Second, we propose a lightweight and efficient multiscale spatial channel reconstruction (MSCCR) module that does not increase parameter and computational complexity and facilitates representative feature learning. Finally, we incorporate the IPA module and the MSCCR module into the YOLOv5s backbone network to reduce model parameters and improve accuracy. The test results show that, compared with the original model, the model parameters decrease by about 9%, the average accuracy (mAP@50) increases by 3.1%, and the FLOPS does not increase.