In digital manufacturing, data-driven methods are promising to revolutionize various decision-making processes. However, the relationships between variables in high-dimensional data of data-driven decision-making methods are only correlations. Important causal relationships and knowledge between process variables are not considered. Therefore, existing data-driven systems are unstable, which could result in unreliable and dangerous decisions. To establish a stable decision-making model for complex processes with high-dimensional data, a causal-based decision-making framework that combined causal relationships and knowledge between key manufacturing variables was proposed. The causal relationships between state, decision, and objective data were established in the form of a direct acyclic graph formed by breaking an unexcepted loop between variables using a shadow objective variable. Then, causal knowledge of high-dimensional states was introduced to the neural network, forming a stable decision-making model. Compared with data-driven methods used in robotics and manufacturing scenarios, the proposed framework provided better and more stable decisions, particularly in noised environments.

Mechanism models often have limited performance due to incompleteness, while neural networks are acknowledged to lack interpretability and extrapolation stability. Augmenting incomplete mechanism models with neural networks can achieve accurate prediction and naturally inherit mechanism models' interpretability and extrapolation stability. According to the original purpose of establishing mechanism models augmented with neural networks (MMANNs), their effectiveness depends on the accuracy of mechanism models. However, since the directly labeled data of the mechanism model or residuals are inaccessible, this effectiveness criterion is difficult to meet in practice. To overcome this challenge, we introduce two heuristic constraints for MMANNs, and propose a mutual information (MI) guided multiobjective learning framework. In this framework, except for minimizing the end-to-end error and the norm of residuals, the MI of the mechanism model and labeled data is maximized, while the MI of the residuals and labeled data is minimized. Compared with the other seven methods, the verification results of the three cases show that all four MMANNs trained under the proposed framework can learn more accurate mechanism parameters and have better extrapolation stability.

The state prediction of key components in manufacturing systems tends to be risk-sensitive tasks, where prediction accuracy and stability are the two key indicators. The physics-informed neural networks (PINNs), which integrate the advantages of both data-driven models and physics models, are deemed as an effective approach and research trends for stable prediction; however, the potential advantages of PINN are limited for the situations with inaccurate physics models or noisy data, where the balancing of the weights of the data-driven model and physics model is very important for improving the performance of PINN, and it is also a challenge urgently to be addressed. This article proposed a kind of PINN with weighted losses (PNNN-WLs) by uncertainty evaluation for accurate and stable prediction of manufacturing systems, where a novel weight allocation strategy based on uncertainty evaluation by quantifying the variance of prediction errors is proposed, and an improved PINN framework is established for accurate and stable prediction. The proposed approach is verified with open datasets on tool wear prediction, and experimental results show that the prediction accuracy and stability could be obviously improved over existing methods.

Transfer learning has received much attention recently and has been proven to be effective in a wide range of applications, whereas studies on regression problems are still scarce. In this article, we focus on the transfer learning problem for regression under the situations of conditional shift where the source and target domains share the same marginal distribution while having different conditional probability distributions. We propose a new framework called transfer learning based on fuzzy residual (ResTL) which learns the target model by preserving the distribution properties of the source data in a model-agnostic way. First, we formulate the target model by adding fuzzy residual to a model-agnostic source model and reuse the antecedent parameters of the source fuzzy system. Then two methods for bias computation are provided for different considerations, which refer to two ResTL methods called ResTLLSand ResTLRD. Finally, we conduct a series of experiments both on a toy example and several real-world datasets to verify the effectiveness of the proposed method.

Cross conditions prediction is a prevalent problem in manufacturing area, where tool wear prediction is a typical one. Existing data-driven methods for tool wear prediction mainly focus on cutting conditions with small variations, which encounters much difficulty under cross conditions with large variations, and the essential is the difference of both marginal distribution and conditional distribution of the data under cross conditions. To address this issue, this article proposes a meta-invariant feature space (MIFS) learning method, where invariant feature space is constructed for paired tasks to close marginal distribution, whose nature law under cross conditions is learned by meta-learning, i.e., MIFS, which can be adapted to achieve accurate tool wear prediction under cross conditions with a small number of new samples. Experimental results provided positive confirmation on the feasibility and accuracy of the proposed method, which can also be readily extended to regression and classification problems in other fields.

Compared with autoclave curing process, microwave can cure the composite with high quality, short time and low cost. However, the temperature distribution of the composite is uneven during microwave heating, which seriously hampers the industrial application of the microwave curing technology. In order to solve the problem, this paper presents a method for improving the temperature distribution of the composite during microwave curing using time-varying electromagnetic field. The method can achieve a real-time and automatic power adjustment of multiple microwave sources via LabVIEW program, and generate a large number of electromagnetic field modes in the high-performance microwave cavity. The temperature distribution is improved by the compensation effect between the heating patterns corresponding to different kinds of resonant states during microwave curing. Experimental results show that the time-varying electromagnetic field in the microwave cavity can effectively improve the temperature distribution of the composite. Compared with rotating tray adjustment, the method proposed can greatly improve the temperature distribution.

Complex structural parts are pervasive and playing an important role in the aircraft manufacturing area. In order to improve the machining efficiency, the cutting parameter optimization of complex structural parts during the machining has always been a problem in manufacturing industry. At present, the cutting parameters are usually optimized based on the final state of complex structural parts and remain unchanged during the machining process, which may not consider the cutting parameter optimization of workpiece in the intermediate machining process. Thus, a cutting parameter optimization method based on dynamic machining features for complex structural parts is proposed to improve the machining efficiency and guarantee the product quality during the machining process. The interim geometric state of each machining occasion is constructed in order to analyze the chatter stability. Then, the cutting parameters are optimized using a genetic algorithm within the limits of chatter stability.

Feature-based technologies are widely researched for manufacturing automation. However, in current feature models, features once defined remain constant throughout the whole manufacturing lifecycle. This static feature model is inflexible to support adaptive machining when facing frequent changes to manufacturing resources. This paper presents a new machining feature concept that facilitates responsive changes to the dynamics of machining features in 2.5/3D machining. Basic geometry information for feature construction of complex parts with various intersecting features is represented as a set of meta machining features (MMF). Optimum feature definition is generated adaptively by choosing optimum merging strategies of MMFs according to the capabilities of the selected machine tool, cutter, and cutting parameters. A composite function block for dynamic machining feature modelling is designed with Basic Machining Feature Function Block, Meta Machining Feature Extraction Function Block and Feature Interpreter Function Block. Once changes of the selected machining resources occur, they are informed as input events and machining features are then updated automatically and adaptively based on the event-driven model of function blocks. An example is provided to demonstrate the feasibility and benefits of the developed methodology.

The production of aircraft structure parts is featured by multiple varieties and small batches, which imposes significant challenges for the representation of process knowledge. Feature based method is an effective way as the process knowledge carrier. Although the parts are different from each other, they are composed of similar geometric features with similar machining processes. This paper introduces the concept of "dynamic machining feature" which is formed in the machining process and influenced by various real operations. In this paper, the process knowledge and interim geometric information are associated based on dynamic machining features. An ontology-based method has been adopted to represent relevant information of dynamic machining features. The proposed approach can speed up process decision and facilitate process optimization.

Small batch and multiple variety production mode and changing machining conditions call for dynamic inspection to guarantee machining quality. Dynamic inspection by considering real time monitoring information is a promising approach, but there is no available technology for integrating real time monitoring and inspection. To address this issue, this paper proposes a method of integrating monitoring and inspection based on intelligent software agents and manufacturing features. An agent-based approach is applied to develop an integrated framework, while manufacturing features are used as the information carrier to represent and connect monitoring and inspection information. Dynamic inspection is triggered according to the analysis results of real time monitoring. A prototype system has been developed to implement and validate the proposed method.

Manufacturing of aircraft structural parts has the characteristics of multi-varieties, complex structure, and small batch which result in high difficulty and workload of the processing planning. When the project leader is deciding the assignment of processing planning tasks, two main factors which affect the reliability of the processing plan need to be considered: the capability of the planners and the complexity of the structural parts. This paper proposes a fuzzy comprehensive evaluation method to evaluate these two factors. The reliability of processing plans is predicted by using the two impact factors and evaluated by using the machining results both based on the fuzzy comprehensive method. A project case study is taken to demonstrate the usability of the proposed method and the test results show that the proposed prediction method is feasible and practicable.

Due to the lack of efficiency communication and collaboration among each manufacturing department, it makes long lead-time and high cost for the manufacturing of aircraft structure parts which have the characteristics of multi-varieties, complexity structure, and small batch. In order to address these challenge issues, a feature-based and multi-agents-based manufacturing collaborative framework which includes process planning agent, NC programming agent, fixture designing agent, cost estimation agent and production management agent for aircraft structural parts is proposed, and the collaboration among each other is realized based on feature, the collaboration between fixture design and NC programming is described in detail. The prototype developed based on the framework has been utilized in a large aviation enterprise, and the result shows that the lead-time and cost are decreased.

Distributed, collaborative, and integrated product development with dynamic and reconfigurable manufacturing environments require more holistic information model to support its use throughout the product lifecycle. In this paper, a multiple dimensional in-process workpiece (MDIPW) is created based on dynamic feature information model (DFIM). The MDIPW is able to adjust its forms of expression through creating associations between feature-based models and manufacturing resources. These associations as representation of knowledge are embedded into the MDIPW, and make it more intelligent. The generated inprocess workpiece is a solid model which can be used for other purposes, such as inspection points generation.

NC machining time of a part depends on its geometry and process plan, NC program, and machine characteristics. Since the integration of geometry and process plan, NC program, and machine characteristics is difficult during NC machining time forecasting, existing commercial software tools and research systems do not fully consider these factors, and therefore the machining time forecasting accuracy is low. In order to address this challenging issue, this paper proposes a feature-based model for NC machining time estimation. Experiment results shown that the proposed approach is feasible and practical.

Because of the characteristics of large dimensions, complex structure and high machining accuracy in aircraft structural parts, iterations frequently happen in the parts design process, which increase the R&D time and costs substantially. In response to the situation, a cooperative design framework based on multi-agent for aircraft is proposed in this paper. Agent of detailed design, feature recognition, manufacturability analysis and etc. are included in the framework. According to the constraints upstream, new feature or structure will be constructed to confirm a new design scheme during the design process. Through the local feature recognition, machining features are recognized from the design feature model simultaneously, and then employed to analyze manufacturability and evaluate costs, in order to obtain an optimal design scheme. An original system has been developed and partially tested in an aviation enterprise. The result shows that the methodology is practicable.

Traditional design process modeling methods are analyzed and compared. A novel design process model based on synchronous mapping from weighted directed graph to design structure matrix (DSM) and polychromatic set is presented. In this model, the information related to design process analysis and reconfiguration is inherited from weighted directed graph to mixed DSM, and in the meantime the information concerned with task assignment and schedule is transferred from weighted directed graph to polychromatic set. The model integrates all information related, which makes it direct and convenient to operate in one model. It improves the efficiency and accuracy of concurrent design process planning and is suitable to be realized by computer. The algorithm based on the model is applied to design process planning for aircraft finish machining fixture. It proves that the algorithm is implemented rapidly and the result is rational.

According to the characteristics and difficulties of the aircraft tooling collaborative design as well as the state-of-the-art of some aircraft manufacturing enterprises, the necessity of realizing semantic collaboration of the aircraft tooling design is analyzed. By studying semantic collaboration and semantic information transferring in aircraft tooling design, a semantic collaboration implementation framework of aircraft tooling design is constructed. Based on this framework, the multi-agent-based semantic collaboration technology of aircraft tooling design is put forward. By mean of combining multi-agent technology with CAD, PDM and knowledge management technologies, this technology solves the issues in distributed semantic collaboration and semantic information transmission of aircraft tooling design. And the implementation process is introduced through a pilot system. This system has been partially tested in an aviation enterprise. By comparison, this system has the advantages of opening, real-time, intelligence and etc. Finally, further work is prospected.

In this paper, we propose CYBER, a CommunitY Based sEaRch engine, for information retrieval utilizing community feedback information in a DHT network. In CYBER, each user is associated with a set of user profiles that capture his/her interests. Likewise, a document is associated with a set of profiles - one for each indexed term. A document profile is updated by users who query on the term and consider the document as a relevant answer. Thus, the profile acts as a consolidation of users feedback from the same community, and reflects their interests. In this way, as one user finds a document to be relevant, another user in the same community issuing a similar query will benefit from the feedback provided by the earlier user. Hence, the search quality in terms of both precision and recall is improved. We conduct a comprehensive experimental study and the results show the effectiveness of our scheme.

Considering the characteristic and difficulty of airplane tooling design that the correlation is complicated and cooperation is difficult, the collaborative design framework for airplane tooling is constructed, and the key technologies, including the technology of collaboration between tooling design and airplane product design, the collaborative design technology of airplane tooling application model, the correlative design technology of airplane tooling structure, and the correlative design technology of airplane tooling semantic information are brought forward in this paper and the collaborative design for airplane tooling in different levels is realized. The software system based on those technologies is applied to an aviation manufacture enterprise and has many advantages such as little dependence on the network, controllable and correlative update.

In this paper, we propose SPRITE (selective progressive index tuning by examples), a scalable system for text retrieval in a structured P2P network. Under SPRITE, each peer is responsible for a certain number of terms. However, for each document, SPRITE learns from (past) queries to select only a small set of representative terms for indexing; and these terms are progressively refined with subsequent queries. We implemented the proposed strategy, and compare its retrieval effectiveness in terms of both precision and recall against a static scheme (without learning) and a centralized system (ideal). Our experimental results show that SPRITE is nearly as effective as the centralized system, and considerably outperforms the static scheme.

Concurrent engineering, collaborative design and network manufacturing have higher demands for parts library to share information in and among enterprises. Based on the study of the diverse parts library application status, a parts library application level model (PL-AIM) is put forward, which consists of geometry layer, system layer, neutral layer and network layer. The contents of different layers of the PL-ALM are expatriated. In order to upgrade parts libraries on different layers gradually, a solution is provided aiming at single geometry information, multi-view information, heterogeneous information and distributed information respectively. According to the PL-ALM, evaluation software is developed, which standardizes and advances the application level of parts library of enterprises

Web-based parts library is important to collaborative design, concurrent engineering and supply chain management system. As common resources, Web-based parts library should be integrated into different application systems of not only parts suppliers but also enterprises. Other than research of product design, the research of Web-based parts library pays more attention to previewing parts shape, acquiring features and attributes. The following progresses are achieved in this paper. A data description norm of parts in network is put forward, based on which parts information is described in XML. Accordingly, information integration of parts library not only accords with PLIB standard but also is realized on data dictionary. A hoops-based visualization method of part feature model is presented which realizes quick browse of parts geometric model and share of design intention by extracted feature tree. Parameterized design technology driven by remote data is brought forward. Geometric information and attributes are encapsulated with master parameters and local geometric models are driven by remote geometric parameters. The above achievements are used in China National 863 High-Tech Project. Besides, the achievements have been embodied in the international standard raised by China National Institute of Standardization and provided the technical foundation to propose the international standards with Chinese independent intellectual property right.

No abstract available.