Ebook: Design Studies and Intelligence Engineering

The 2024 International Symposium on Design Studies and Intelligence Engineering (DSIE-2024) was held in Hangzhou, China on 21 and 22 December 2024. The conference provided a platform for professionals and researchers from industry and academia to present and discuss recent advances in the field of design studies and intelligence engineering.

The technologies applied in design studies vary from basic theories to more application-based systems. Intelligent engineering also plays a significant role in design science in areas such as computer-aided industrial design, human-factor design, and greenhouse design. Intelligent engineering technologies also include topics from both theoretical and application perspectives, such as computational technologies, sensing technologies, and video detection. This conference aims to promote cooperation between the industries and universities involved in these fields. Renowned professors from around the world were invited to speak on these topics in greater depth, and to discuss in-depth research directions with other participants.

We received 498 submissions online for the conference, all of which were reviewed by three or four independent experts. Based on the reviewers’ comments, we accepted 157 papers for publication in this book. We believe that this conference will foster cooperation among organizations and researchers involved in these converging fields.

DSIE 2024 was sponsored by Zhejiang Sci-Tech University, and co-sponsored by Chinese Mechanical Engineering Society-Industrial Design, Aurel Vlaicu University of Arad, Techno India College of Technology, Chinese Academy of Art, and Xiamen University of Technology.

We would like to thank all contributors for their efforts in submitting their manuscripts on time. We would also like to express our gratitude to the reviewers for their contribution and to Mr. Maarten Fröhlich of IOS Press for accepting this volume for publication, as well as his colleagues for their efforts during the publishing process of the volume.

Lakhmi C. Jain

Valentina Emilia Balas

Qun Wu

Fuqian Shi

Under the background of the rapid development of China’s new energy vehicle market, the increasingly fierce competition and the increasing influence of social media, based on the analysis of the matrix construction and operation practice of N automobile, this paper discusses the digital marketing of new energy vehicle enterprises through social media to get the market volume. Through data analysis and case analysis, this paper analyzes the construction method, content planning and interactive strategy of N automobile Jinhua company’s human matrix on the red book. A social media communication method based on key opinion selling (KOS) content and user-generated content (UGC) is proposed. This method can help improve the brand’s exposure and user participation on social media and then enhance the brand influence. It provides a useful reference for the digital marketing of new energy automobile enterprises on social media and also provides reference and inspiration for other industries to use social media platforms to enhance brand influence.

This study explores the effects of multisensory memory on memory for everyday objects, with a particular focus on memory for £1 coins. The study delves into the intersection of sensory anthropology, sensory history, and sensory sociology to examine how multisensory experiences affect memory persistence. The study used a dual-task paradigm and cross-modal stimuli to investigate the effectiveness of different sensory combinations in enhancing memory. Post-epidemic era, unlike offline experiences, this experiment utilised an online survey and a variety of media formats including text, images, video, audio and physical objects. The results showed that multisensory interactions significantly improved short-term memory recall over single-sensory modalities, while visual elements such as colours and shapes had a lasting effect on long-term memory. The study also highlights the potential of multisensory engagement in educational environments and museum experiences, gathering reliable data for future projects in which computers simulate human behaviour.

In order to solve the problems of metadata conversion speed and low information utilization of traditional resource integration methods, a data-driven optimization model of physical education curriculum content is proposed. In this paper, we construct a network sports teaching resources metadata set, combine the key attribute matching idea with the design of network sports teaching resources metadata program, and utilize the constructed resource rapid integration platform to integrate the network sports teaching resources metadata. The experimental results show that the information utilization rate of the network sports teaching resources rapid integration method based on key attribute matching is higher than that of the network sports teaching resources integration methods based on data mining technology, Internet of Things and big data technology, and the information utilization rate of the method increases significantly over time, reaching a maximum of 80.235%, which is highly usable.

An improved algorithm for traffic anomaly detection in large-scale networks has been proposed to solve the current problem of detecting massive data and categorizing inhomogeneous data traffic. The algorithm combines the FCM algorithm and GRNN, using the FCM algorithm to cluster the data traffic samples, and then using the GRNN to train the convolution of the sample points closest to the FCM cluster center and iteratively update them until a stable cluster center is obtained; MFOA is introduced to perform parameter tuning of the FCM-GRNN, and the global optimization-seeking property of the MFOA and the three-dimensional spatial search method are utilized to Iterative optimization to find the optimal Spread value; using KDDCUP99 dataset for the test, it is concluded that the detection rate of the proposed algorithm is 91.36%, and the false detection rate is 1.154%, and the proposed algorithm has a better ability to detect abnormal traffic.

It is a common method of product appearance design that transmission materials form specific visual effects through photolithography process. Designers face two major challenges in the design process:first, it is difficult to accurately grasp the relationship between microstructure and macro dynamic visual effects; second, the proofing process is time-consuming, high cost and low design efficiency. Therefore, based on the gray-scale lithography process and the computer-aided industrial design technology, the optical simulation model of transmission grating is established, and the dynamic visual effect simulation technology of transmission material CMF design is developed. The visual effect of transmission grating texture is simulated, and the dynamic image is output to help the designer quickly evaluate the design scheme before the actual proofing and reduce invalid proofing. In addition, the paper puts forward the method of unit texture design, summarizes the creative process of constructing texture from unit, and provides a creative path for designers. Through the practical application verification, the simulation system is true and reliable, improves the designer’s work efficiency, and provides a new creative boundary for CMF design.

In order to solve the problem that the traditional methods for assessing micro plastic pollution are not accurate, the research on toxic effects of micro plastic pollution on aquatic organisms and dynamic assessment methods has been proposed. In this paper, stereomicroscope and Fourier transform infrared spectrometer were used to identify the apparent characteristics and polymer composition of microplastics, and pollution risk index, pollution load index and ecological risk index were used to assess the ecological risk of microplastics pollution in the study area. The experimental results showed that the detection rate of micro plastic pollution in surface water was 20%∼100%, the highest detection value was 420ng/L, and the predicted ineffective concentration (PNEC) derived from chronic toxicity data such as development, reproduction and behavior was 1.36 × 10^-6 mg/L; The risk quotient calculated based on chronic toxicity is 0.03-36.76.

Efficient and timely monitoring of plant diseases in large-scale farms is critical for maintaining crop health and minimizing economic losses. Current manual inspection and static image-based methods are limited by scalability and real-time detection capabilities. This paper presents a conceptual framework for a UAV-based multi-sensor fusion system aimed at enhancing plant disease detection in large-scale agricultural environments. The system integrates aerial imaging and environmental sensor data (e.g., temperature, humidity, light) using multi-modal data fusion techniques to improve the accuracy of disease prediction. The proposed architecture also leverages optimized flight path planning to ensure comprehensive coverage of the monitoring area. The framework is evaluated using theoretical analysis and existing data from plant disease datasets, and simulated sensor data is employed to demonstrate the potential improvements in disease detection efficiency. This design framework sets the stage for future development and deployment of UAV-based smart farming systems, offering improved scalability, real-time response, and accurate plant disease monitoring.

This study focuses on the application of Augmented Reality (AR) technology in LiuGou Village, located in Yanqing District, Beijing, as part of China’s rural revitalization efforts. The objective is to promote the sustainable development of local cultural heritage and the rural economy. By conducting field research and interviews, the study analyzes the potential of AR technology to enhance rural tourism and agriculture. It proposes a virtual interactive tourism experience project based on AR and the design of a mobile platform. This platform, which is AR-centric, aims to offer immersive cultural experiences, optimize the agricultural supply chain, and improve the overall tourist experience, thereby promoting rural tourism and the sale of agricultural products. The study seeks to leverage the advantages of the “Internet +” strategy, integrating modern technological elements into traditional culture to boost the economic returns of tourism and agriculture, while also providing a reference and solution for other rural revitalization projects.

In this paper, we propose FGITNet, an innovative Two-Stream Gated Network designed for accurate violence detection in surveillance videos. Leveraging both Inflated 3D ConvNet and Transformer architectures, FGITNet extracts spatiotemporal features by processing RGB and Optical Flow frames simultaneously. A key contribution of our model is a novel background suppression mechanism that effectively filters out non-motion elements, enhancing motion feature detection while maintaining computational efficiency. This two-stream approach achieves state-of-the-art performance on the RWF-2000 and Hockey datasets, surpassing existing methods by 4% on RWF-2000, reaching an accuracy of 93.75%. Our method demonstrates significant potential for real-time applications in intelligent security systems, contributing to the field of design and intelligent engineering.

In order to solve the problem of low accuracy of industrial structure optimization of digital economy in Active Distribution Network (ADN), the research on industrial structure optimization and development model of digital economy based on data driven was proposed. This paper analyzes the components of the total operating cost of ADN, and takes the minimum total operating cost of ADN as the objective function, comprehensively considers various constraints, and establishes an economic optimal scheduling model of ADN based on the Elite Strategy Cuckoo Search (ESCS). The Cuckoo Search (CS) algorithm is improved by using the dynamic setting of bird egg detection probability and elite strategy to improve the optimization performance of the algorithm. The IEEE33 bus distribution system is used for simulation analysis. The experimental results show that: in terms of the number of convergence iterations, the number of iterations of the ESCS algorithm is 52, which is far less than the other three optimization algorithms. From the perspective of the optimal solution, the solution accuracy of the ESCS algorithm is also higher than the other three optimization algorithms. It can be seen that the ESCS algorithm can effectively reduce the number of iterations and improve the calculation accuracy.

In order to solve the problem of high computing and storage costs of traditional algorithms and low accuracy of recommendation results, the research on cross-border e-commerce platform optimization and data-driven strategies in the ASEAN digital economy has been proposed. This paper first studies the information personalization algorithm of the artificial intelligence cross-border e-commerce shopping guide platform through big data technology, so that big data technology can be realized on the Hadoop platform. Then, it decomposes tasks into multiple tasks through Map, and uses Reduce to gather the decomposed multi task processing results together to obtain the final processing results. Finally, two MapReduce and one map are used to parallelize the user preference acquisition algorithm in the platform. According to user preferences, the products that match user preferences are obtained through association rule mining and recommended to users. The experimental results show that the proposed algorithm has the best effect among other algorithms when the click rate of recommended product information is 17.92%, indicating that the proposed algorithm recommendation results are more consistent with user needs.

In order to solve the problem of low seismic performance of multi-story assembled steel frame energy dissipating structural connections, the study of the seismic performance of buckling restrained bracing in assembled steel frame structures based on finite element analysis is proposed. This paper puts forward the anti-buckling braced steel frame modular assembly structural system, the design requirements of anti-buckling bracing in modular structure and the structural system design method, the nonlinear finite element analysis based on the test, analyzes the structural internal force process, the internal force distribution and redistribution law, improves the internal configuration, optimizes the structural design, and establishes the pre-embedded and welded connections by using the means of indoor physical simulation. Using indoor physical simulation, two different small-scale specimens were built with pre-installed parts and welded connections to compare the hysteresis curves, skeleton curves, stiffness curves, ductility and energy dissipation parameters and other seismic performance indexes of the two structures. The experimental results show that, under the same displacement, the pre-installed specimen has greater cut-line stiffness, but the ductility coefficient is smaller; the energy dissipation coefficient and the equivalent viscous damping coefficient of the pre-installed specimen are about 0.81 times that of the welded specimen, which indicates that the buckling restraint brace has superior seismic performance by using the welded connection.

In order to solve the problem of low efficiency of integrated processing of intelligent operation and maintenance management model of coal mine mechanical and electrical equipment, which leads to long response time of fault identification, the whole process operation and maintenance management system of mechanical and electrical equipment based on two-dimensional code mobile interconnection is proposed. This paper adopts a multi-level approach to improve the efficiency of comprehensive processing, establish a multi-level RFID coal mine electromechanical equipment intelligent operation and maintenance management model, and finally adopt the adaptive auxiliary adjustment to realize the operation and maintenance management. Experimental results show that: compared with the traditional method, the designed RFID technology of coal mine mechanical and electrical equipment intelligent operation and maintenance management method ultimately results in the fault identification response time is better controlled in 0.5s or less, indicating that in the RFID technology with the assistance and support of the designed coal mine mechanical and electrical equipment intelligent operation and maintenance management method is more efficient, and the practical application of the value of the higher significance of innovation.

In order to solve the problem of poor performance stability of traditional wind turbines, a data-driven approach to optimize the performance and life prediction of wind turbines is proposed. Firstly, sensors are installed to collect the operating data of wind turbines; secondly, according to the working principle and operating characteristics of wind turbines, corresponding mathematical models are established, and multi-objective power generation optimization algorithms are designed; finally, the control system structure of the turbine is clarified, and the wind speed section is divided into full wind speed sections, and multi-objective power generation optimization is implemented in the full wind speed section. The experimental results show that: the closer the smoothing factor is to 0, the smoother the output power of the wind turbine is, and the better the multi-objective power generation optimization control effect is; the closer the smoothing factor is to 1, the greater the fluctuation of the output power, and the worse the multi-objective power generation optimization control effect is.

In order to solve the problems of low efficiency and inaccurate fault diagnosis in the operation and maintenance management of substations, a whole-process supervision method of automation equipment operation and maintenance based on digital twin is proposed. The system realizes panoramic perception and real-time monitoring by constructing high-precision virtual mapping of substations; introduces machine learning algorithms to give the system the ability of intelligent analysis and decision-making optimization; and applies human-computer interaction technology to enhance the experience of human-machine collaborative operation. The experimental results show that in the anomaly detection experiment, the algorithm achieves 95.2% precision and 97.1% recall on the test set, which indicates that the algorithm is able to effectively detect anomalies in the operation of the substation. The algorithm achieves 92.4% fault localization accuracy and 88.6% fault type identification accuracy on the test set.

This study delved into the mitigating effects of calligraphy practice on anxiety and its underlying neural mechanisms. Participants were subjected to Velten self-representation induction to evoke negative emotions, during which their calligraphy practice was combined with EEG data collection and spectral analysis to assess their pre- and post-anxiety states. The findings revealed a notable surge in beta-band (13-30 Hz) power following anxiety induction, with an average increase of 65.74%. Conversely, a marked reduction in beta-band power, averaging a 38.18% decrease, was observed after participants engaged in calligraphy practice.Subjective evaluations using the State Anxiety Inventory (SAI) scale corroborated these results, showing a significant escalation in scores post-anxiety induction (from 42.5 to 60.4), and a substantial decline after calligraphy practice (to 32.1), further underscoring the efficacy of calligraphy in anxiety reduction. Notably, higher affective potency scores were associated with regular and clerical scripts, indicating that these calligraphic styles may exert a more pronounced positive impact on emotional regulation. The study’s findings suggest that calligraphy practice can effectively alleviate anxiety by significantly diminishing beta-band power, a mechanism that parallels the focused attention and reduced external distraction observed in meditation. By doing so, calligraphy may harness a similar psychological mechanism to meditation. This research offers a neuroscientific foundation for the therapeutic use of calligraphy in emotional regulation, potentially paving the way for novel emotion-healing strategies in the realm of mental health.

When analyzing perceptual evaluations in industrial design, issues like limited data scope, high costs, inaccuracy, and underuse of unstructured data are common. This study introduces a novel sentiment analysis approach. Focusing on ceramic tea sets, it aims to build a model predicting their shape’s perceptual imagery. The process involves converting user reviews into quantifiable scores using sentiment analysis and identifying key design elements like handles, spouts, mouths, bellies, and lids. Quantification Theory I then maps these scores to design elements. Validated with ceramic teapot design optimizations, this method accurately captures user feelings and predicts their perceptual evaluations, aiding in design improvements and practical applications.

In order to solve the problem that the connection between the host-side equipment and the client-side equipment is not close, which leads to the unclear display of industrial heritage, the research on digital protection and virtual display technology of industrial heritage is proposed. In this paper, on the basis of B/S architecture, the host-side platform equipment and client-side platform equipment are connected on demand. Then the virtual reality is used to determine the location of the user role, and establish the human-computer interaction mode, and then through the way of perfecting the database storage system, to realize the construction of the system software execution environment. The experimental results show that during the whole experimental process, the mean value of the contact tightness index between the host-side equipment and the client-side equipment of the experimental group is relatively high, while the mean value of the control group is relatively low. From the perspective of limit value, the experimental group, the ϖ. The maximum value of the indicator amounted to 35.5%, compared to the control group ϖ. Compared with the maximum value of 18.9%, it has increased by 16.6%.

In order to solve the problem that conventional monitoring methods are easily affected by the calibration of monitoring area, difficult to resist the interference of monitoring identification, and the monitoring completion rate is low, the online monitoring method based on the data center of industrial IoT equipment operation state is proposed. In this paper, we first extract the abnormal state monitoring characteristics of networked node equipment; then construct the communication abnormality online monitoring framework of industrial IoT node equipment; finally design the communication abnormality online monitoring algorithm of industrial IoT node equipment to realize the communication abnormality online monitoring. Experimental results show that: in the same communication environment, the methods in this paper can normally complete the communication anomaly online monitoring task completion rate of more than 95%, without the influence of signal interference; PSO algorithm based on the communication network traffic anomalies in the intelligent monitoring method and based on the regional residuals of the airport communication data anomalies monitoring method method can not be normal in the signal interference to complete the anomalies in the online monitoring task.

In order to solve the problem of high error rate of grid equipment fault prediction due to the existence of communication blind zones and poor smoothness of collected data in existing monitoring methods, a digital twin-based full-life cycle condition monitoring method for grid equipment is proposed. This paper divides the whole life cycle stage of power transmission and distribution equipment, and summarizes the characteristics of life cycle stage determination; based on this, we improve RFID technology to build a multi-antenna RFID communication framework; based on the construction of the communication framework, we combine the characteristics of different life cycle stages of the equipment, and adaptively adjust the collection interval of the operation data to obtain the operation data of power transmission and distribution equipment; we effectively combine the integration of the moving average autoregressive model and the support vector machine algorithm to predict the faults in advance, and we use the digital twin to predict the faults in advance, and then we use the digital twin to predict the faults in advance. The moving average autoregressive model and support vector machine algorithm are effectively combined to predict the faults of power transmission and distribution equipment in advance, thus realizing the intelligent monitoring of the whole life cycle of power transmission and distribution equipment. The experimental results show that compared with the comparison method, the error rate of fault prediction of transmission and distribution equipment obtained by the proposed method in this paper is lower, the lowest numerical value is 5%, which indicates that the fault prediction results of the proposed method are more accurate.

In order to solve the problems of poor compatibility, weak environmental adaptability and low discharge efficiency of traditional liquid metal diaphragm tank, the research on multi-objective parameter regulation of liquid metal structure optimization design was put forward. In this paper, the structural design of spherical metal diaphragm with a certain volume is carried out, and the arc length method is used for numerical simulation. By using the second generation genetic algorithm, the multi-objective optimization design of the spherical liquid metal diaphragm with this configuration was carried out with the objective of reducing the eccentric displacement and increasing the buckling load at the initial position, and the local optimal bottom radius, the fixed-point thickness of the diaphragm and the pre-flanging radius were obtained, which reduced the eccentric displacement of the diaphragm apex and increased the buckling load at the initial position. The experimental results show that the buckling load P_buckle is increased by 1.13% and the eccentric displacement T_xz is decreased by 36.07% compared with that before optimization, and the performance of membrane turnover after optimization is better.

In order to solve the problem of low drawing accuracy of complex scenes in virtual reality system, the research on improving the modeling accuracy of digital environment driven by intelligent technology is put forward. Firstly, the half-edge folding algorithm is used to simplify the complex three-dimensional geometric model, which reduces the computational overhead and improves the efficiency of model rendering. Then, in the process of drawing the level of detail of complex scenes, the preprocessing stage of selecting the level of detail is added, and the appropriate parallax measurement coefficient of the level of detail is selected for each frame of scene area through the calculation of projection value, which speeds up the real-time calculation. The experimental results show that the number of display triangles of the optimized method in this paper is increased, that is, the time complexity is improved. However, due to the improved preprocessing mechanism of LOD model selection, the total execution time of the algorithm is still less than that of SR-LOD method, which is 31.145s, that is, the complex scene can still be drawn relatively quickly.

In order to solve the voltage instability problem under the influence of the increasing proportion of new energy in the receiving power grid and DC power outside the region, the research on the influence and control of new energy access on the dynamic stability of the power grid is put forward. Firstly, based on the improved small signal analysis method, the dynamic voltage stability model of the new energy receiving power grid is established. Then, considering the uncertainty of wind power, photovoltaic and load, aiming at the minimum total planning cost, a new energy receiving power network planning model considering dynamic voltage stability is established and solved. Finally, the simulation results show that the proposed new energy receiving power grid planning model can improve the receiving power grid’s ability to accept future new energy and load uncertainty. The experimental results show that the configuration capacity of various types of equipment in the new energy receiving power grid has increased except for thermal power units, and the investment cost of scenario 2 has increased by 6.32% compared with scenario 1 in the planning period. Considering that the energy demand of wind power, photovoltaic output and load is uncertain, it will lead to the phenomenon of abandoning wind and light. In the second scenario, the energy storage system has a certain capacity margin, which can make full use of the efficient coordinated operation among energy storage, peak shaving units and controllable loads, reduce the energy purchase cost and improve the consumption of new energy. Therefore, the overall operating cost of the second scene is reduced by 51.42% compared with that of the first scene, and the overall wind rejection rate and light rejection rate are reduced by 62.76% and 64.01% respectively.