Recent Patents on Engineering - Volume 18, Issue 1, 2024

Privacy leakage that occurs when many IoT devices are utilized for training centralized models, a new distributed learning framework known as federated learning was created, where devices train models together while keeping their private datasets local. In a federated learning setup, a central aggregator coordinates the efforts of several clients working together to solve machine learning issues. The privacy of each device's data is protected by this setup's decentralized training data. Federated learning reduces traditional centralized machine learning systems' systemic privacy issues and costs by emphasizing local processing and model transfer. Client information is stored locally and cannot be copied or shared. By utilizing a centralized server, federated learning enables each participant's device to collect data locally for training purposes before sending the resulting model to the server for aggregate and subsequent distribution. As a means of providing a comprehensive review and encouraging further research into the topic, we introduce the works of federated learning from five different vantage points: data partitioning, privacy method, machine learning model, communication architecture, and systems heterogeneity. Then, we organize the issues plaguing federated learning today and the potential avenues for a prospective study. Finally, we provide a brief overview of the features of existing federated knowledge and discuss how it is currently being used in the field.

Early detection and treatment of breast cancer are very necessary, and effective classification of breast tissue is helpful for the diagnosis of breast cancer; so, a classification method named FT_GA_GBDT is proposed. First, the correlations between the features and classification labels of breast tissue samples were determined, and features with higher correlation were analyzed statistically and combined by weight. Thus, feature transformation (FT) is realized. The datasets were then enhanced by calculating the mean and root mean square of the feature attributes of each adjacent odd- and even-row sample with both belonging to the same class. Finally, the genetic algorithm (GA) was used to search the optimal parameters of the gradient boosting decision tree (GBDT) model, and the optimal parameters were substituted into the GBDT to classify the breast tissue. In addition, the K-nearest-neighbor (KNN), support-vector-machine (SVM) and GBDT methods were also used to test the breast tissue classification. Results of 6-fold cross validation on three breast tissue datasets showed that the average Precision, Recall, and F1 score obtained by the FT_GA_GBDT method were better than those obtained by the KNN, SVM and GBDT methods. The results further show that the FT algorithm and searching for the optimal hyper-parameters by the GA were helpful in improving the performance of the breast tissue classification model, which is more obvious when the correlations between features and classification labels are generally not high.

Background: The safe and stable operation of large-capacity hydro-generators is of great significance to the power grid. However, due to the armature reaction and the stator slots of the hydroelectric generator, the torque ripple of the generator is usually large. Long time running under the condition of large torque ripple will cause damage to the generator components and even threaten the safety of the power grid. Objective: To study the factors affecting the torque ripple of the hydro-generator and reduce the torque ripple. Methods: A 24 MW bulb tubular hydro generator is taken as an example, a two-dimensional transient electromagnetic field model was established, and the correctness of the model was verified by experiments. The causes of armature reaction and cogging effect on motor torque are analyzed. The effects of these two factors on torque ripple are studied respectively. The torque ripple under different working conditions is calculated, and the main factors causing and increasing torque ripple during normal operation of hydro generator are determined. Results: The torque ripple increases approximately linearly with the increase of the 7th and 11th harmonic contents, while it increases nonlinearly with the increase of the 5th harmonic contents. When the excitation current increases from 720 A to 960 A, the torque ripple is increased by 11.4 kN•m. In addition, when the excitation current increases from 720A to 840A (Rated excitation current of the generator is 840A), the torque ripple increases greatly, the torque ripple increases by 6.6 kN•m. When the excitation current exceeds the rated excitation current, due to the influence of magnetic saturation, the increasing extent of torque ripple gradually decreases. When the excitation current increases from 840A to 960A, the torque ripple increases only by 4.8kN•m. Conclusion: Due to the armature reaction, the harmonic magnetic potential will be generated in the generator, which will affect its torque ripple. The torque ripple of the generator will increase obviously with the increase of harmonic content. When the generator is in no-load operation, the slot effect is the main cause of the torque ripple. In the actual operation of the generator, it usually needs to adjust the excitation current to make the generator meet the requirements of various working conditions.

Background: At present, the tree whitewashing in China is mainly based on the traditional manual whitewashing method, which has the shortcomings of high labor intensity, low efficiency, excessive wastage of paint, danger to human health, and poor adaptability to the strong seasonality of tree whitewashing. Objective: To reduce the sunburn and water evaporation of trees, prevent the invasion of diseases and pests, and to enhance the disease resistance of trees, the tree trunk coating mainly uses a traditional manual method. However, this mainstream manual whitewashing approach is labor- intensive and inefficient. To resolve the issue, an automatic spraying device for tree coating based on multisprinkler cooperative operation is designed. It can meet the requirements of tree whitening and replace manual operation. To some extent, this machine can reduce labor intensity and promote the healthy growth of trees. Methods: Through literature review and field research, the technical requirements and research status of tree whitewashing have been explored. The three-dimensional Software Solidworks has been used to model the rack assembly, device moving assembly, up and down moving assembly, nozzle moving support assembly, and spraying assembly, and then the three-dimensional assembly of the whole machine has been carried out. According to the simulation optimization results, the initial three-dimensional model is modified, and then the engineering drawing is drawn through the threedimensional model for prototype processing, manufacturing, and assembly. The schematic diagram and PCB pattern of the circuit board of the electronic control system have been drawn, the program of the controller k60dn512 single chip microcomputer has been written, simulation and debugging have been conducted, and the control system has been designed. Laboratory and field tests on the prototype have been conducted, and the device has been improved according to the test data. Results: Experiments show that the device can accurately spray trees with a trunk circumference of 50-125cm. When the trunk circumference is greater than 125 cm, repeated spraying can meet the spraying requirements. The trunk circumference is in the range of 50-80 cm, and the opening and closing angle is in the range of 80-100°. The spraying effect is good, and the average spraying coverage can reach 97.73%. The trunk perimeter is in the range of 80-125 cm, and the opening and closing angle is in the range of 100-120°. The spraying effect is the best, and the average spraying coverage can reach 98.06%. During the experiment, the spraying efficiency of the device can reach 100 trees/hour, which is significantly higher than the efficiency of manual operation. Conclusion: The device improves the efficiency and quality of tree spraying, reduces the labor intensity of operation, and realizes the high-efficiency spraying for tree coating.

Background: Proportional-integral-differential (PID) controller is widely used in the engineering field because of its simple structure, high control accuracy, and easy operation. Different patented PID control technologies have their own advantages, disadvantages, and application scenarios. Objective: By analyzing and discussing the improved PID control techniques in the electrohydraulic servo system, some valuable conclusions have been drawn to predict the future research and development of PID control techniques. Methods: The improved PID control techniques applied to electro-hydraulic servo systems are classified into three categories: PID parameter tuning technology, PID parameter online adjustment strategy and compound control strategy combined with PID algorithm. Results: By comparing the principles and characteristics of the above techniques, the advantages, disadvantages and application scenarios of each are analyzed, and the further development of PID control technology is discussed. Conclusion: Based on the characteristics of electro-hydraulic servo systems, the further combination of the three types of technology can make up for the shortcomings of PID algorithms to form a control strategy with high control accuracy, high robustness, and fast response speed.

High-speed motorized spindle is the core component of high-speed machining machine tools, and thermal error is the main factor affecting the machining accuracy of the motorized spindle. Reducing thermal error has become the most important research topic in the case of motorized spindles. The development status of the cooling strategy of the motorized spindle is explored, and the methods to improve the cooling efficiency of the motorized spindle are discussed. Some representative research results of the cooling strategy of motorized spindles at home and abroad are reviewed. Based on summarizing the related research results on cooling strategies for the core components, such as the stator, rotor and bearing of the motorized spindle, this paper analyzes the advantages and disadvantages of various cooling strategies and their applicable working conditions, and the future development direction of motorized spindle cooling strategies is discussed. The combination of various channel structures and the cooling strategy of the stator outer ring of the motorized spindle will improve the cooling efficiency of the motorized spindle, and research on the motorized spindle core cooling will become more and more important. In addition, the cooling system of the motorized spindle bearing, stator, and rotor can be improved at the same time, and the heating problem of the motorized spindle can be solved.

Background: Traditional rigid robots are difficult to adapt to complex unstructured environments due to their limited degree of freedom and lack of flexibility. Therefore, soft crawling robots are concerned widely by their powerful deformation ability, infinite number of degrees of freedom, and effective interaction with humans. Objective: This paper aims to report the recent progress of soft crawling robots and provide a reference for readers in this field. Methods: By reading and summarizing the patents and papers related to soft crawling robots in recent years, they are divided into three categories according to different driving methods. The structure, motion mechanism, characteristics, and applications of each class of robots are compared and analyzed. Results: The advantages and disadvantages of each driving method are analyzed, and the key issues in soft crawling robots are pointed out. Based on this, the future development direction of this research field is predicted. Conclusion: The study shows that according to the driving method, soft crawling robots are classified as pressure driven, motor-wire driven, and soft active material driven. In addition, the characteristics of each drive are summarized. In the future, soft crawling robots will have more potential applications in biomedicine, outdoor survey, rescue search, and inspection and maintenance of equipment.

Background: Capacitive micromachined ultrasonic transducers (CMUTs) is a promising component of mechanical-electrical-acoustical conversion, which shows valuable applications in non-distructive testing and obstacle detection fields. In order to study the influence of dimension parameters on the directivity of CMUTs, the three-dimensional multi-physics coupling model is proposed for CMUTs in this paper. Methods: The model combines multiple physical fields through finite element method (FEM), which is more efficient and accurate. The influence of dimension parameters on the transducer is studied from two aspects: the pitch between adjacent cells and cell number, respectively. Results: When increasing the pitch, the directivity becomes better if the pitch is less than half of the wavelength, the grating lobe and side lobe are aroused. However, the bandwidth at -3dB is reduced by up to 71.1% at the same time. When increasing the cell number, the better the direcitvity, while the change of the cell number has little effect on the bandwidth of the array. However, 5.4% frequency shift was caused due to the effective mass change of the transducer. Conclusion: In this study, a 3D model based on FEM is proposed for the influence of dimension parameter on CMUTs. The simulation results indicate that the directivity can be enhanced by changing the dimension. At the same time, it also introduces other performance issues, such as bandwidth decrease and frequency shift through this approach. Therefore, the simulation proposed the guidance of CMUTs performance optimization and patented technology application work in the future.

Background: Surface microtextured technology is an expansion and extension of biomimicry in the tribology field, promoting vigorous development in microtextured tribology. Through artificial means, tiny convex hulls, craters, or stripes of specific size and arrangement are processed on the friction surfaces to change the morphology and contact angle of the surfaces and improve the surface contact state or the lubrication effect. The function and properties of microtextured surfaces are determined by optimizing their geometrical parameters, but the microtextured geometrical parameters require a high-level machining quality. It is necessary to analyze and summarize the existing research on manufacturing microtextured surfaces. By summarizing the preparation methods of microtextured surfaces in the past decade, some valuable conclusions are drawn to predict the future development of technology for manufacturing microtextured surfaces and provide a reference for researchers in related fields. This paper summarizes the representative patents related to the methods of manufacturing microtextured surfaces, analyzes the properties of the microtextured surfaces produced by each method, and discusses the advantages and disadvantages of these methods. The existing problems are summarised through the analyses of patents related to microtextured preparation methods. The future development of new preparation methods has prospected. By cooperating with various processing technologies and optimizing the processing methods, the microtextured surfaces can meet various functional requirements, and the manufacturing precision is higher than before. The processing method needs further improvement according to the working conditions. More new technologies will be invented to create microtextured surfaces.

With the improvement of living standards and the acceleration of the pace of modern life, people pay more and more attention to health. All kinds of ball games are deeply loved by people. Most people like to go to all kinds of equipment halls for all kinds of sports. However, at present, there are few types of service machines, and there is still a lot of room for development. With the development of ball games, small simple serve machine, as important equipment for modern entertainment and sports, has research projects in various countries and occupies a large market share. The purpose of this study is to synthesize the existing pitching mechanism, summarize and analyze the advantages and disadvantages of various pitching mechanisms from a large number of documents and patents, and solve some problems with the existing pitching machine. This paper summarizes various patents and the latest research progress on ball-pitching machines. From the mechanical structure of the pitching machine to the functions it can realize, the advantages and disadvantages of the serving machine are analyzed. By summarizing the characteristics of a large number of pitching mechanisms, this paper analyzes some problems existing in the pitching machine and looks forward to the research and design of the pitching machine. Combined with relevant mechanical technology, this paper refers to the patents related to various ball automatic mechanical pitching devices and draws valuable conclusions through the summary and comparison of these patents.