This PDF file contains the front matter associated with SPIE Proceedings Volume 12289, including the Title Page, Copyright information, Table of Contents, and Conference Committee Page.

This paper taking CNKI as the data source and ‘intelligent manufacturing technology’ as the retrieval subject word, using scientific metrology method and CiteSpace 5.8 R3 software carries out co-occurrence network visual analysis of literature authors, institutions and keywords. A total of 2687 related literatures were included. Li Fangyuan, Zang Jiyuan, Yang Shuzi, Zhou Ji and Yao Xifan are the main authors; Instrumentation Technology and Economy Institute, P. R. China, Chinese Academy of engineering, Huazhong University of science and technology, Zhejiang University and Tsinghua University are the main research institutions; Intelligent manufacturing and manufacturing industry are the most central research hotspots; The Symposium and made in China are relatively new research frontiers. Visual atlas analysis can intuitively and quickly show the development trend, research hotspots and cutting-edge contents of intelligent manufacturing technology research from 1992 to 2022, and provide reference data and development direction for further research.

Wall climbing robots, also known as wall moving robots, are also known abroad as extreme work robots because vertical wall work is beyond human limits. Despite its superior performance, there has been little research on the subject. This paper introduces a vacuum adsorption structure for a one-footed multi-suction wall climbing robot and establishes a onefooted multi-suction model. Using a four-legged wall crawler as a carrier, the basic conditions to be met by this structure are analysed for both the three-legged and four-legged suction states of the wall crawler. The feasibility of attaching the robot to the structure to move on a vertical wall is verified. The deformation of the body is simulated by ansys for the two adsorption states with load forces ranging from 500N to 700N to verify the feasibility of the structure and to derive a range of feasibility.

In order to complete the automatic press-fitting and detecting process on the assembly line of the enterprise, a rapid press-fitting and detection assembly line is proposed. According to enterprise requirements and working conditions, the structure of the entire automatic press-fitting and detecting device is designed through SolidWorks, and the structural scheme and working principle of key mechanisms are analyzed. The static analysis and kinematic simulation analysis are carried out on the key parts of the conveying-reversing mechanism in the device. The results show that the assembly line can realize automatic press-assembly and detecting process, and can arrange the products of middle cover and explosionproof plug from loose state to orderly state, carry out press-fitting and detect the press-assembly effect, and finally distribute the good products. The key components in the conveying-reversing mechanism can meet the strength requirements, and the handling process is relatively stable, which verifies the feasibility of the scheme and provides reference for the overall scheme design of the assembly line.

The dynamic characteristics of boiler temperature in chemical process are complex, but the boiler temperature is related to the product quality and process safety. In the actual production process, adjusting the production process parameters is a large disturbance to the temperature control system, and a single PID control does not have the ability to resist this disturbance. The cascade feed-forward control proposed in this paper selects the temperature of the boiler as the main control object, and the reactant flow as the secondary control object. The cascade control system is established, which has better ability to deal with disturbance.

In order to improve deficiencies in manual cleaning and lubrication of aero-engine fan blades, such as high working intensity, uneven lubrication, cleaning and lubrication toxic materials, the cleaning and lubrication system of aero-engine fan blades is designed. The system structure, hardware and software control scheme design are completed based on the maintenance work card standard. The cleaning operation can be realized through a combination of mechanical cleaning, ultrasonic cleaning, and the lubrication operation can be completed through industrial robots. The data exchange among the touch screen, mobile robot, PLC, industrial robot and PC five-terminal equipment is realized by using Modbus protocol, and the design of human-computer interface is completed with HMI touch screen. The system can realize automatic cleaning and lubrication operation flow, and avoid direct human contact with cleaning and lubricating toxic solvents. The engine blade cleaning efficiency is 60 s/pc, the lubrication efficiency is 55 s/pc, and the overall operation efficiency is 3.39 times higher than that of manual work. Through actual verification, the system is proved to be able to achieve stable and efficient operation, and has high engineering application value.

Complex product design generally involves multiple subdisciplines or subsystems. In this study, taking the two-stage planetary gear transmission system as an example, a multi-objective optimization model for multidisciplinary design is established and solved by collaborative optimization method. The goal of the optimization is to simultaneously minimize volume and maximize efficiency. In the model, the sequential quadratic programming (SQP) method is used for individual disciplinary optimization, and an improved wolf pack algorithm is developed as the optimizer at system level for the CO method. It is shown that the proposed method can realize the requirement of miniaturization of the part while ensuring the transmission efficiency almost undamaged, and obtains accurate and efficient optimization results.

To improve the production efficiency of children's furniture enterprises, the fuzzy cluster analysis method is used to classify the solid wood parts into groups according to the similarity of processing technology in children's furniture, thereby shortening the production cycle. This paper takes solid wood children's furniture as the research object, selects 3 pieces of solid wood children's furniture with different functions as samples, and divides them into 113 pieces and 50 kinds of solid wood parts. According to the processing technology of the parts, the part-process binary association matrix of solid wood parts is constructed. By establishing the fuzzy similarity matrix and the fuzzy equivalent matrix and solving them, the threshold λ and the corresponding number of parts groups are obtained. Children's furniture enterprises can select different thresholds λ based on the results of fuzzy cluster analysis, combined with actual production conditions and needs, and obtain suitable parts grouping production methods. On the basis of this, it can establish a corresponding production unit, reduce the ineffective transportation of parts between processing machines, grow large quantities of production and improve production efficiency.

Aiming at the problem of overheating in the grinding zone during the process of high-efficient and high-speed grinding of rails, a cryogenic gas-liquid two-phase spray cooling mode was proposed with the development trend of green processing, which mixed cryogenic compressed gas with small amount of liquid to achieve enhanced heat transfer in the grinding zone. A grinding experimental platform was established and high speed grinding experiments of rail materials were carried out. The results show that the grinding force, temperature and surface quality obtained by cryogenic gas-liquid two-phase cooling are better than that of cryogenic cold air cooling.

In order to build China into a manufacturing power and adapt to the development goal of the new era, a large number of high-end intelligent manufacturing talents and advanced intelligent manufacturing technology are needed. Transforming traditional manufacturing equipment and adding modern control methods such as artificial intelligence technology are also the main direction of intelligent manufacturing development. The application of neural algorithm and fuzzy control technology in the construction of machine manufacturing platform and artificial intelligence system, and the application of neural algorithm and artificial intelligence technology in the actual manufacturing of equipment, Combine the theoretical explanation of artificial intelligence technology and application with specific engineering practice and virtual simulation technology. The intelligent manufacturing experimental platform takes the small excavator as the main body. Through the transformation of each arm and hydraulic system of the excavator, the artificial intelligence technology is introduced into the intelligent manufacturing experimental platform. The experimental platform can not only control and dynamic test in real time, but also complete the control task through simulation combined with specific experimental cases. It can completely solve the problem that students cannot understand due to the lack of experimental equipment in traditional courses.

Cardiovascular disease is detrimental to people’s health and economy of the family and government. To reduce the cardiovascular mortality rate, this article designs a novel wearable micro-intelligent electrocardiogram equipment. The device can be 105cm3 with a small size. Meanwhile, it can collect five-lead electrocardiograph (ECG) data and analyze and diagnose ECG data using pattern recognition support vector machine (SVM) algorithm, the cardiovascular disease therefore could be found early. This paper is meaningful and conducive to the research of relevant equipment for the cardiovascular disease.

In this paper, the causes of condensation in switchgear are introduced firstly, and then some methods of anticondensation in switchgear are summarized. Finally, the research status of super-hydrophobic materials and the application prospect of super-hydrophobic materials in anti-condensation field of switchgear are emphatically introduced.

The connecting nut between phase B drain valve and gas tank of 51DK circuit breaker of high voltage shunt reactor of No. 1 bus in a substation was broken and failed. In order to find out the cause of fracture, the fractured brass connecting nut was comprehensively detected and analyzed by means of appearance morphology analysis, chemical composition analysis, microstructure detection and fracture micro area analysis. The results show that the chemical composition of brass nut is unqualified, the content of Cu element is low, and the content of Pb, Fe and impurity elements is high, which is easy to produce stress corrosion tendency, and the overheating structure is formed due to improper forging process, resulting in poor strength and toughness of the nut; Under the combined action of sulfide and stress, the stress corrosion cracking of externally threaded pipe occurs at the stress concentration part of the bottom of the first circle of thread, and gradually expands, so that the effective bearing area decreases, and finally breaks under the action of internal working pressure.

Bearing bush spring is very important to the economic and stable operation of steam turbine. The supporting spring of turbine rotor bearing bush of 330MW unit in a thermal power plant broke during operation, resulting in unit shutdown. In order to find out the cause of spring fracture, this paper adopts macro morphology observation, fracture SEM detection, microstructure detection and chemical composition detection. The results show that the spring has original crack defects. In addition, the spring squeezes and wears with the inner wall of the mounting hole during operation, resulting in the damage of the outer surface of the steel wire. Moreover, this position is where the maximum shear stress is borne, so the crack source is initiated on the surface of the steel wire. Under the cyclic variable load caused by the vibration of steam turbine bearing bush, the crack continues to expand in the form of fatigue, and the effective bearing area of spring continues to decrease until fracture occurs.

The high-temperature fastening bolt of the high-pressure main steam valve of the steam turbine of 330MW unit in a thermal power plant breaks during operation. In this paper, the causes of bolt fracture are analyzed by means of macro morphology observation, fracture SEM detection, microstructure detection, mechanical property detection and chemical composition detection. The results show that during the long-term high-temperature service, the matrix structure of the fastening bolt of the high-pressure main throttle valve is aging and carbide particles are gradually precipitated. With the increase of operation time, the carbide particles continue to aggregate and grow up and distribute along the grain boundary, and a large number of creep holes and creep cracks are formed on the grain boundary. A large number of coarse carbides and creep cracks lead to the decline of mechanical properties of bolts, especially the deterioration of impact toughness and tensile strength; The accumulation of creep cracks becomes the crack source. Under the impact load formed during the action of high-pressure main throttle valve, the stress concentration part of the bottom of the first thread of the bolt external thread cracks, and the cracks continue to expand, resulting in the brittle fracture of the bolt.

Low-cost ceramic membranes supported by fly-ash-based substrates were fabricated. The membrane pore sizes were abated significantly after coating new layers on the substrates. The effect of substrate pore size on the composite membrane pore size distribution was investigated. The fabricated membranes were tested in transport membrane condenser for water and heat recovery from flue gas. Experimental results indicate that heat flux recovered by the prepared membrane was 9.2%-10.8% lower than that recovered by commercial membrane. The findings from the recovery test provide guidelines for developing low-cost membranes for gas dehydration.

EEG signals are closely related to mood changes, and the study of EEG signals can accurately reflect the changes of human emotions. In this paper, EEG signals were classified and recognized. Video emotion inducing materials were selected to induce subjects to produce happy, neutral and sad emotions, and EEG signals were collected at the same time. Wavelet packet transform, power spectral density and approximate entropy features were extracted, and then emotion classification was carried out by using width learning classification method, and then the classification results were analyzed and compared. The results show that the performance of differential entropy in single feature classification is up to 78.3%, while the accuracy of differential entropy and wavelet packet transform for feature fusion is up to 81.5%.

With the rapid development of modern industry, enterprises have an increasing demand for data monitoring and automated control of multiple production outlets and production lines. This paper first analyses the structure of the production line, completes the control system model design, establishes the network framework of the system, designs the human-machine interaction interface, gives the SFC flow chart of the workstations and the communication scheme of the PLC between each station, and finally realises the real-time interaction of the monitoring data in the industrial cloud platform. The research contributes new ideas to related research in this field.

The complex interrelationships between variables and units in a plant lead to challenging monitoring, and it is necessary to design distributed monitoring schemes. Among the steps of distributed data-driven fault detection methods, process decomposition is important to ensure monitoring performance. In this paper, a data-driven mutual information approach is used for process decomposition. Traditional canonical correlation analysis (CCA) focuses on global structural information but ignores local information which is also important for process monitoring. In the locality preserving canonical correlation analysis approach, local structure information is integrated into CCA to produce a new optimization objective involving both global and local structure information for better extraction of data features. In this paper, we propose a datadriven Distributed Locality Preserving Canonical Correlation Analysis (D-LPCCA) fault detection method for addressing plant-wide process fault detection that contains nonlinear correlations. In order to set a detection limit that can better distinguish between normal and abnormal values, a kernel density estimation method is used in this paper. Finally, the effectiveness of the method proposed in this paper is verified by the Tennessee Eastman simulation platform.

Machine tool accuracy is a key performance index of machine tools. The machine tool error index is divided into related geometric errors and position-independent geometric errors. These errors account for about 70% of the overall error of the machine tool. Accurate measurement of machine tool errors plays a vital role in improving machine tool accuracy. Use HTM50100 turning and milling compound machine tool as an example, this paper designs a convenient and fast method for measuring the geometric error of machine tools by using laser interferometer, ballbar, dial indicator and other tools, and validates the method. The results show that the method has high measurement accuracy, high speed and convenient use, and provides a theoretical basis and a practical method for the measurement method of geometric error of CNC machine tools.

Transient power angle stability and transient voltage stability are always the key problems in power system. In the exploration of power system stability, it is difficult to separate the correlation between voltage stability and power angle stability, because they are often coupled with each other. In order to identify the dominant instability mode and effectively optimize it, the coupling mechanism is analyzed according to the models of two stable forms, and the evaluation index of coupling strength is obtained quantitatively.

The no-wait flow shop scheduling problem (NWFSP) has been achieved a wide variety of researches by scholars as a typical NP-hard problem. In this paper, a construction block inspired variable neighborhood search heuristic algorithm (BBA-VNS) is proposed for solving NWFSP with the goal of maximum completion time. The core idea of BBA is to seek out the best match until all jobs are arranged in the process set. In the BBA, waiting time matrix and matching matrix between two jobs are constructed to obtain an approximate optimal scheduling sequence. In addition, the variable neighborhood search mechanism (VNS) is used to further improve the solution quality which based on block neighborhood structure and insert neighborhood structure. The results on a large-scale benchmark indicate that BBA-VNS is better than the most advanced heuristic algorithm.

In order to improve the detection efficiency and accuracy of spacecraft thermistor wire solder joint detection and defect identification, yolov5 neural network model is studied and optimized, ECA attention module is introduced, infrared thermal imager and microscope lens are used, temperature control fixture and optical fiber coupled semiconductor laser are used to realize the detection of micro holes in its solder joint Infrared image signal acquisition and quality detection of cracks and other defects.

The common desulfurization method of sintering flue gas is to use activated carbon for adsorption, but due to its many parameters, it is easy to fail, and the failure is difficult to analyze. This paper uses k-wheel recognition and key parameter similarity to fit the formula, quantitatively evaluate the abnormal characteristic parameters, and finally get the fault judgment. Finally, compared with the manual judgment case, the accuracy is 93.9%, which has high application significance

As main methods for the degradation of liquor-making industry wastewater, biochemical treatments are mature and stable. However, there are still many technical problems in the process of wastewater treatment, such as low utilization of organic resources, anaerobic stage release of toxic gases, defection of traditional flocculant, limitation of microbialflocculant, large yield of sludge and difficult processing technologies. The design of the research adopts the internal circulation anaerobic reactor, anaerobic anoxic oxic and membrane bioreactor technology to treat the winery wastewater produced by Qingbaijiang district wanyi wine factory in Chengdu. The test results show that the process has a favorable effect toward the removing of COD, BOD₅, SS and TN. The discharge wastewater index can reach the standard of water pollutants emission limits in fermented alcohol and liquor industry water pollutant discharge standards(GB27631-2011). In addition, the process have lots of advantages such as high volumetric load, strong capability of resisting impact, economical efficiency, running stability and less land requirement. The success of such combined technology will be beneficial to the sustainable development of the liquor-making industry.

This paper comprehensively summarizes the problems related to the metering field handheld equipment technical specification, focusing on professional terms, model preparation, environment requirements (metering site climate environment, equipment mechanical performance, equipment hardware, communication interface, rfid reading and writing module, etc.), function requirements (general management function and business function), test project (specific test project of power metering field handheld equipment, specific inspection method, corresponding relationship between inspection items and inspection link) for reference.

Anticorrosion of distribution cabinet is the basis of ensuring the safe operation of distribution cabinet. In this paper, the corrosion mechanism of metals is described, and the advantages and disadvantages of various common anticorrosion methods are expounded. At the same time, the new technology of super hydrophobic anticorrosion coating is introduced, and the future development direction of super hydrophobic anticorrosion coating technology is prospected.

For the secondary voltage control model based on inverter of isolated island microgrid (MG) theory, a fault-tolerant controller is designed under the influence of external interference. The observer is used to reconstruct fault information and estimate interference in real time. Then, based on the observer signal, a controller based on the backstep method is established to realize fault tolerance and interference compensation, and ensure that the output voltage amplitude of the distributed power generation system stably tracks the given track. Simulation results verify the effectiveness of the proposed scheme.

The multi-purpose safety monitoring system is necessary to ensure the vehicle driving personnel's life and health. This paper analyzes the principle, structure, and design, and designs the automobile safety driving monitoring system based on the single-chip microcomputer, which is composed of four functional modules: alcohol detector, anti-fatigue device, expressway limiting device and reverse anti-collision device. Finally, the vehicle auxiliary safety driving monitoring system proposed in this paper was verified through an experimental platform.

Streaming data refers to a dynamic data set that grows infinitely over time. And the streaming data set of load lacks historical data due to difficult data collection or short running time. Therefore, it is very difficult to ensure the accuracy of streaming data forecasting results. To solve the problem, this paper proposes a quantile prediction model for streaming data based on the adversarial transfer bidirectional long short-term memory (ATLSTM) networks. The model can be divided into two parts. In the pre-training model based on domain adversarial network, the adversarial mechanism is introduced based on the bidirectional long short-term memory (Bi-LSTM) architecture to train. In this paper, streaming data is used as the target domain data. And data with high similarity to streaming data is used as source domain data. By minimizing the prediction loss and maximizing the domain classification loss, the model extracts the common features of the target domain and the source domain. In the migration training model based on parameter fine-tuning, a simple model is constructed by importing part of the network of the pre-training model. On this basis, the optimization training is carried out through the data of the target domain to extract the deep features. And the quantile fitting can not only solve the situation of outliers in the data, but also obtain the load forecasting curve under different confidence conditions. The experimental results show that the accuracy, efficiency, and stability of the proposed model are better than the traditional deep learning model.

With the development of wind energy industry, the application of floating wind turbine has been largely solved at the technical level. Since the floating wind turbine has six additional degrees of freedom, the dynamic response of its rotor and the wake characteristics also change accordingly. Compared with offshore bottom-fixed wind turbines, the wake of floating wind turbines has a different impact on the power output of downstream units. A Spar-type floating wind farm model is established, and simulation calculations are carried out under medium and low ambient wind speeds. By using scatter plots, box plots, etc., the time series data of the displacement of the rotor and the position of the center of the wake are compared and studied. The conclusions are as follows: Spar-type wind turbine has a wider range of motion of the rotor, and the wake is more dispersed. Meanwhile, the wake effect of Spar-type wind turbine has a wider range but a weaker degree of influence to the downstream units. Floating wind farms composed of Spar-type wind turbines have higher power output under the same external environment.

Hybrid HVDC circuit breaker is one of the key equipment of flexible DC system. The type test of the whole machine is an important means to ensure its safe, reliable and stable operation. Due to the special conditions of high voltage and high current coexistence, it is difficult to reproduce the breaking process completely, so it is necessary to propose the equivalence index of the breaking process. However, a complete equivalent index for reclosing is lacking. This paper analyzes the whole process of hybrid DC circuit breaker, divides the whole process into six stages, and systematically puts forward eight equivalent indexes. The equivalent index proposed in this paper can effectively equivalent the opening process of DC circuit breaker under the extreme condition of reclosing opening failure, which provides a reference for the equivalent open circuit of hybrid DC circuit breaker.