Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.

Coexistence of antiferromagnetism and unconventional superconductivity in a quasi-one-dimensional flat-band system:Creutz lattice

We study the coexistence of antiferromagnetism and unconventional superconductivity on the Creutz lattice which shows strictly flat bands in the noninteracting regime.The famous renormalized mean-field theory is used to deal with strong electron-electron repulsive Hubbard interaction in the effective low-energy t-J model,the superfluid weight of the unconventional superconducting state has been calculated via the linear response theory.An unconventional superconducting state with both spin-singlet and staggered spin-triplet pairs emerges beyond a critical antiferromagnetic coupling interaction,while antiferromagnetism accompanies this state.The superconducting state with only spin-singlet pairs is dominant with paramagnetic phase.The A phase is analogous to the pseudogap phase,which shows that electrons go to form pairs but do not cause a supercurrent.We also show the superfluid behavior of the unconventional superconducting state and its critical temperature.It is proven directly that the flat band can effectively raise the critical temperature of superconductivity.It is implementable to simulate and control strongly-correlated electrons'behavior on the Creutz lattice in the ultracold atoms experiment or other artificial structures.Our results may help the understanding of the interplay between unconventional superconductivity and magnetism.

An approximate analytical model for unconventional reservoir considering variable matrix blocks and simultaneous matrix depletion

In regard to unconventional oil reservoirs,the transient dual-porosity and triple-porosity models have been adopted to describe the fluid flow in the complex fracture network.It has been proven to cause inaccurate production evaluations because of the absence of matrix-macrofracture communication.In addition,most of the existing models are solved analytically based on Laplace transform and numerical inversion.Hence,an approximate analytical solution is derived directly in real-time space considering variable matrix blocks and simultaneous matrix depletion.To simplify the derivation,the simultaneous matrix depletion is divided into two parts:one part feeding the macrofractures and the other part feeding the microfractures.Then,a series of partial differential equations(PDEs)describing the transient flow and boundary conditions are constructed and solved analytically by integration.Finally,a relationship between oil rate and production time in real-time space is obtained.The new model is verified against classical analytical models.When the microfracture system and matrix-macrofracture communication is neglected,the result of the new model agrees with those obtained with the dual-porosity and triple-porosity model,respectively.Certainly,the new model also has an excellent agreement with the numerical model.The model is then applied to two actual tight oil wells completed in western Canada sedimentary basin.After identifying the flow regime,the solution suitably matches the field production data,and the model parameters are determined.Through these output parameters,we can accurately forecast the production and even estimate the petrophysical properties.

Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

Orientation and Decision-Making for Soccer Based on Sports Analytics and AI:A Systematic Review

Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings gamechanging approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action(OODA) loop.In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decisionmaking models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.

Conventional Geothermal Systems and Unconventional Geothermal Developments: An Overview

This paper provides an overview of conventional geothermal systems and unconventional geothermal developments as a common reference is needed for discussions between energy professionals. Conventional geothermal systems have the heat, permeability and fluid, requiring only drilling down to °C, normal heat flow or decaying radiogenic granite as heat sources, and used in district heating. Medium-temperature (MT) 100°C - 190°C, and high-temperature (HT) 190°C - 374°C resources are mostly at plate boundaries, with volcanic intrusive heat source, used mostly for electricity generation. Single well capacities are °C - 500°C) and a range of depths (1 m to 20 Km), but lack permeability or fluid, thus requiring stimulations for heat extraction by conduction. HVAC is 1 - 2 m deep and shallow geothermal down to 500 m in wells, both capturing °C, with °C are either advanced by geothermal developers at <7 Km depth (Enhanced Geothermal Systems (EGS), drilling below brittle-ductile transition zones and under geothermal fields), or by the Oil & Gas industry (Advanced Geothermal Systems, heat recovery from hydrocarbon wells or reservoirs, Superhot Rock Geothermal, and millimeter-wave drilling down to 20 Km). Their primary aim is electricity generation, relying on closed-loops, but EGS uses fractures for heat exchange with earthquake risks during fracking. Unconventional approaches could be everywhere, with shallow geothermal already functional. The deeper and hotter unconventional alternatives are still experimental, overcoming costs and technological challenges to become fully commercial. Meanwhile, the conventional geothermal resources remain the most proven opportunities for investments and development.

Ethical Decision-Making Framework Based on Incremental ILP Considering Conflicts

Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical care.If the artificial agents cannot align with social values or make ethical decisions,they may not meet the expectations of humans.Traditionally,an ethical decision-making framework is constructed by rule-based or statistical approaches.In this paper,we propose an ethical decision-making framework based on incremental ILP(Inductive Logic Programming),which can overcome the brittleness of rule-based approaches and little interpretability of statistical approaches.As the current incremental ILP makes it difficult to solve conflicts,we propose a novel ethical decision-making framework considering conflicts in this paper,which adopts our proposed incremental ILP system.The framework consists of two processes:the learning process and the deduction process.The first process records bottom clauses with their score functions and learns rules guided by the entailment and the score function.The second process obtains an ethical decision based on the rules.In an ethical scenario about chatbots for teenagers’mental health,we verify that our framework can learn ethical rules and make ethical decisions.Besides,we extract incremental ILP from the framework and compare it with the state-of-the-art ILP systems based on ASP(Answer Set Programming)focusing on conflict resolution.The results of comparisons show that our proposed system can generate better-quality rules than most other systems.

Stroke Risk Assessment Decision-Making Using a Machine Learning Model:Logistic-AdaBoost

Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to objectively predict and identify strokes,this paper proposes a new stroke risk assessment decision-making model named Logistic-AdaBoost(Logistic-AB)based on machine learning.First,the categorical boosting(CatBoost)method is used to perform feature selection for all features of stroke,and 8 main features are selected to form a new index evaluation system to predict the risk of stroke.Second,the borderline synthetic minority oversampling technique(SMOTE)algorithm is applied to transform the unbalanced stroke dataset into a balanced dataset.Finally,the stroke risk assessment decision-makingmodel Logistic-AB is constructed,and the overall prediction performance of this new model is evaluated by comparing it with ten other similar models.The comparison results show that the new model proposed in this paper performs better than the two single algorithms(logistic regression and AdaBoost)on the four indicators of recall,precision,F1 score,and accuracy,and the overall performance of the proposed model is better than that of common machine learning algorithms.The Logistic-AB model presented in this paper can more accurately predict patients’stroke risk.

Hydrocarbon gas huff-n-puff optimization of multiple horizontal wells with complex fracture networks in the M unconventional reservoir

The oil production of the multi-fractured horizontal wells(MFHWs) declines quickly in unconventional oil reservoirs due to the fast depletion of natural energy. Gas injection has been acknowledged as an effective method to improve oil recovery factor from unconventional oil reservoirs. Hydrocarbon gas huff-n-puff becomes preferable when the CO_(2) source is limited. However, the impact of complex fracture networks and well interference on the EOR performance of multiple MFHWs is still unclear. The optimal gas huff-n-puff parameters are significant for enhancing oil recovery. This work aims to optimize the hydrocarbon gas injection and production parameters for multiple MFHWs with complex fracture networks in unconventional oil reservoirs. Firstly, the numerical model based on unstructured grids is developed to characterize the complex fracture networks and capture the dynamic fracture features.Secondly, the PVT phase behavior simulation was carried out to provide the fluid model for numerical simulation. Thirdly, the optimal parameters for hydrocarbon gas huff-n-puff were obtained. Finally, the dominant factors of hydrocarbon gas huff-n-puff under complex fracture networks are obtained by fuzzy mathematical method. Results reveal that the current pressure of hydrocarbon gas injection can achieve miscible displacement. The optimal injection and production parameters are obtained by single-factor analysis to analyze the effect of individual parameter. Gas injection time is the dominant factor of hydrocarbon gas huff-n-puff in unconventional oil reservoirs with complex fracture networks. This work can offer engineers guidance for hydrocarbon gas huff-n-puff of multiple MFHWs considering the complex fracture networks.

The Spherical q-Linear Diophantine Fuzzy Multiple-Criteria Group Decision-Making Based on Differential Measure

Spherical q-linearDiophantine fuzzy sets(Sq-LDFSs)provedmore effective for handling uncertainty and vagueness in multi-criteria decision-making(MADM).It does not only cover the data in two variable parameters but is also beneficial for three parametric data.By Pythagorean fuzzy sets,the difference is calculated only between two parameters(membership and non-membership).According to human thoughts,fuzzy data can be found in three parameters(membership uncertainty,and non-membership).So,to make a compromise decision,comparing Sq-LDFSs is essential.Existing measures of different fuzzy sets do,however,can have several flaws that can lead to counterintuitive results.For instance,they treat any increase or decrease in the membership degree as the same as the non-membership degree because the uncertainty does not change,even though each parameter has a different implication.In the Sq-LDFSs comparison,this research develops the differentialmeasure(DFM).Themain goal of the DFM is to cover the unfair arguments that come from treating different types of FSs opposing criteria equally.Due to their relative positions in the attribute space and the similarity of their membership and non-membership degrees,two Sq-LDFSs formthis preference connectionwhen the uncertainty remains same in both sets.According to the degree of superiority or inferiority,two Sq-LDFSs are shown as identical,equivalent,superior,or inferior over one another.The suggested DFM’s fundamental characteristics are provided.Based on the newly developed DFM,a unique approach tomultiple criterion group decision-making is offered.Our suggestedmethod verifies the novel way of calculating the expert weights for Sq-LDFSS as in PFSs.Our proposed technique in three parameters is applied to evaluate solid-state drives and choose the optimum photovoltaic cell in two applications by taking uncertainty parameter zero.The method’s applicability and validity shown by the findings are contrasted with those obtained using various other existing approaches.To assess its stability and usefulness,a sensitivity analysis is done.

A NovelMethod for Determining Tourism Carrying Capacity in a Decision-Making Context Using q−Rung Orthopair Fuzzy Hypersoft Environment

Tourism is a popular activity that allows individuals to escape their daily routines and explore new destinations for various reasons,including leisure,pleasure,or business.A recent study has proposed a unique mathematical concept called a q−Rung orthopair fuzzy hypersoft set(q−ROFHS)to enhance the formal representation of human thought processes and evaluate tourism carrying capacity.This approach can capture the imprecision and ambiguity often present in human perception.With the advanced mathematical tools in this field,the study has also incorporated the Einstein aggregation operator and score function into the q−ROFHS values to supportmultiattribute decision-making algorithms.By implementing this technique,effective plans can be developed for social and economic development while avoiding detrimental effects such as overcrowding or environmental damage caused by tourism.A case study of selected tourism carrying capacity will demonstrate the proposed methodology.

UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience

Autonomous umanned aerial vehicle(UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decisionmaking policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control methods.Moreover, we construct the UAV maneuvering decision-making model based on Markov decision processes(MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

Geological characteristics of unconventional tight oil reservoir (10^(9) t): A case study of Upper Cretaceous Qingshankou Formation, northern Songliao Basin, NE China

The Daqing exploration area in the northern Songliao Basin has great potential for unconventional oil and gas resources,among which the total resources of tight oil alone exceed 109 t and is regarded as an important resource base of Daqing oilfield.After years of exploration in the Qijia area,Songliao Basin,NE China,tight oil has been found in the Upper Cretaceous Qingshankou Formation.To work out tight oil’s geological characteristics,taking tight oil in Gaotaizi oil layers of the Upper Cretaceous Qingshankou Formation in northern Songliao Basin as an example,this paper systematically analyzed the geological characteristics of unconventional tight oil in Gao3 and Gao4 layers of the Qijia area,based on the data of the geological survey,well drilling journey,well logging,and test.It is that three sets of hydrocarbon source rocks(K2qn1,K2qn2+3,and K2n1)develop in the examined area,and exhibit excellent type I and II kerogens,high organic matter abundance,and moderate maturity.The reservoir is generally composed of thin-bedded mudstone,siltstone,and sandstone,and presents poor porosity(average 8.5 vol.%)and air permeability(average 4 mD).The main reservoir space primarily includes intergranular pores,secondary soluble pores,and intergranular soluble pores.Three types of orifice throats were identified,namely fine throat,extra-fine throat,and micro-fine throat.The siltstone is generally oil-bearing,the reservoirs with slime and calcium become worse oil-bearing,and the mudstone has no obvious oil-bearing characteristics.The brittleness indices of the sandstone in the tight oil reservoir range from 40%to 60%,and those of the mudstone range from 40%to 45%,indicating a better brittleness of the tight oil reservoir.Based on the study of typical core hole data,this paper gives a comprehensive evaluation of the properties of the tight oil and establishes a tight oil single well composite bar chart as well as the initial evaluation system with the core of properties in the tight oil reservoir.This study has theoretical guiding significance and practical application value for tight oil exploration and evaluation in the Qijia area.

Decision-Making and Management of Self-Care in Persons with Traumatic Spinal Cord Injuries: A Preliminary Study

Patients and physicians understand the importance of self-care following spinal cord injury (SCI), yet many individuals with SCI do not adhere to recommended self-care activities despite logistical supports. Neurobehavioral determinants of SCI self-care behavior, such as impulsivity, are not widely studied, yet understanding them could inform efforts to improve SCI self-care. We explored associations between impulsivity and self-care in an observational study of 35 US adults age 18 - 50 who had traumatic SCI with paraplegia at least six months before assessment. The primary outcome measure was self-reported self-care. In LASSO regression models that included all neurobehavioral measures and demographics as predictors of self-care, dispositional measures of greater impulsivity (negative urgency, lack of premeditation, lack of perseverance), and reduced mindfulness were associated with reduced self-care. Outcome (magnitude) sensitivity, a latent decision-making parameter derived from computationally modeling successive choices in a gambling task, was also associated with self-care behavior. These results are preliminary;more research is needed to demonstrate the utility of these findings in clinical settings. Information about associations between impulsivity and poor self-care in people with SCI could guide the development of interventions to improve SCI self-care and help patients with elevated risks related to self-care and secondary health conditions.

Research on Public Engineering Emergency Decision-Making Based on Multi-Granularity Language Information

To effectively deal with fuzzy and uncertain information in public engineering emergencies,an emergency decision-making method based on multi-granularity language information is proposed.Firstly,decision makers select the appropriate language phrase set according to their own situation,give the preference information of the weight of each key indicator,and then transform the multi-granularity language information through consistency.On this basis,the sequential optimization technology of the approximately ideal scheme is introduced to obtain the weight coefficient of each key indicator.Subsequently,the weighted average operator is used to aggregate the preference information of each alternative scheme with the relative importance of decision-makers and the weight of key indicators in sequence,and the comprehensive evaluation value of each scheme is obtained to determine the optimal scheme.Lastly,the effectiveness and practicability of the method are verified by taking the earthwork collapse accident in the construction of a reservoir as an example.

A Blind Spot in the Reframing of a Universe of Possibles: Towards a Suitable Model for Decision-Making Theory and A.I.

Bayesian inference model is an optimal processing of incomplete information that, more than other models, better captures the way in which any decision-maker learns and updates his degree of rational beliefs about possible states of nature, in order to make a better judgment while taking new evidence into account. Such a scientific model proposed for the general theory of decision-making, like all others in general, whether in statistics, economics, operations research, A.I., data science or applied mathematics, regardless of whether they are time-dependent, have in common a theoretical basis that is axiomatized by relying on related concepts of a universe of possibles, especially the so-called universe (or the world), the state of nature (or the state of the world), when formulated explicitly. The issue of where to stand as an observer or a decision-maker to reframe such a universe of possibles together with a partition structure of knowledge (i.e. semantic formalisms), including a copy of itself as it was initially while generalizing it, is not addressed. Memory being the substratum, whether human or artificial, wherein everything stands, to date, even the theoretical possibility of such an operation of self-inclusion is prohibited by pure mathematics. We make this blind spot come to light through a counter-example (namely Archimedes’ Eureka experiment) and explore novel theoretical foundations, fitting better with a quantum form than with fuzzy modeling, to deal with more than a reference universe of possibles. This could open up a new path of investigation for the general theory of decision-making, as well as for Artificial Intelligence, often considered as the science of the imitation of human abilities, while being also the science of knowledge representation and the science of concept formation and reasoning.

Crossing the Achilles Heel of Algorithms:Identifying the Developmental Dilemma of Artificial Intelligence-Assisted Judicial Decision-Making

In the developmental dilemma of artificial intelligence(AI)-assisted judicial decision-making,the technical architecture of AI determines its inherent lack of transparency and interpretability,which is challenging to fundamentally improve.This can be considered a true challenge in the realm of AI-assisted judicial decision-making.By examining the court’s acceptance,integration,and trade-offs of AI technology embedded in the judicial field,the exploration of potential conflicts,interactions,and even mutual shaping between the two will not only reshape their conceptual connotations and intellectual boundaries but also strengthen the cognition and re-interpretation of the basic principles and core values of the judicial trial system.

Whole petroleum system and ordered distribution pattern of conventional and unconventional oil and gas reservoirs

The classical source-to-trap petroleum system concept only considers the migration and accumulation of conventional oil and gas in traps driven dominantly by buoyance in a basin,although revised and improved,even some new concepts as composite petroleum system,total petroleum system,total composite petroleum system,were proposed,but they do not account for the vast unconventional oil and gas reservoirs within the system,which is not formed and distributed in traps dominantly by buoyancedriven.Therefore,the petroleum system concept is no longer adequate in dealing with all the oil and gas accumulations in a basin where significant amount of the unconventional oil and gas resources are present in addition to the conventional oil and gas accumulations.This paper looked into and analyzed the distribution characteristics of conventional and unconventional oil/gas reservoirs and their differences and correlations in petroliferous basins in China and North America,and then proposed whole petroleum system(WPS)concept,the WPS is defined as a natural system that encompasses all the conventional and unconventional oil and gas,reservoirs and resources originated from organic matter in source rocks,the geological elements and processes involving the formation,evolution,and distribution of these oil and gas,reservoirs and resources.It is found in the WPS that there are three kinds of hydrocarbons dynamic fields,three kinds of original hydrocarbons,three kinds of reservoir rocks,and the coupling of these three essential elements lead to the basic ordered distribution model of shale oil/gas reservoirs contacting or interbeded with tight oil/gas reservoirs and separated conventional oil/gas reservoirs from source rocks upward,which is expressed as“S\T-C”.Abnormal conditions lead to other three special ordered distribution models:The first is that with shale oil/gas reservoirs separated from tight oil/gas reservoirs.The second is that with two direction ordered distributions from source upward and downward.The third is with lateral distribution from source outside.

Artificial intelligence promotes shared decision-making through recommending tests to febrile pediatric outpatients

BACKGROUND:To promote the shared decision-making(SDM)between patients and doctors in pediatric outpatient departments,this study was designed to validate artificial intelligence(AI)-initiated medical tests for children with fever.METHODS:We designed an AI model,named Xiaoyi,to suggest necessary tests for a febrile child before visiting a pediatric outpatient clinic.We calculated the sensitivity,specificity,and F1 score to evaluate the efficacy of Xiaoyi’s recommendations.The patients were divided into the rejection and acceptance groups.Then we analyzed the rejected examination items in order to obtain the corresponding reasons.RESULTS:We recruited a total of 11,867 children with fever who had used Xiaoyi in outpatient clinics.The recommended examinations given by Xiaoyi for 10,636(89.6%)patients were qualified.The average F1 score reached 0.94.A total of 58.4%of the patients accepted Xiaoyi’s suggestions(acceptance group),and 41.6%refused(rejection group).Imaging examinations were rejected by most patients(46.7%).The tests being time-consuming were rejected by 2,133 patients(43.2%),including rejecting pathogen studies in 1,347 patients(68.5%)and image studies in 732 patients(31.8%).The difficulty of sampling was the main reason for rejecting routine tests(41.9%).CONCLUSION:Our model has high accuracy and acceptability in recommending medical tests to febrile pediatric patients,and is worth promoting in facilitating SDM.

A multi-enterprise quality function deployment paradigm with unstructured decision-making in linguistic contexts

This paper presents an operational framework of unstructured decision-making approach involving quality function deployment(QFD)in an uncertain linguistic context.Firstly,QFD is extended to the multi-enterprise paradigm in a real-world manufacturing environment.Secondly,hesitant fuzzy linguistic term sets(HFLTSs),which facilitate the management and handling of information equivocality,are designed to construct a house of quality(HoQ)in the product planning process.The technique of computing with words is applied to bridge the gap between mechanisms of the human brain and machine processes with fuzzy linguistic term sets.Thirdly,a multi-enterprise QFD pattern is formulated as an unstructured decision-making problem for alternative infrastructure project selection in a manufacturing organization.The inter-relationships of cooperative partners are directly matched with a back propagation neural network(BPNN)to construct the multi-enterprise manufacturing network.The resilience of the manufacturing organization is considered by formulating an outranking method on the basis of HFLTSs to decide on infrastructure project alternatives.Finally,a real-world example,namely,the prototype manufacturing of an automatic transmission for a vehicle,is provided to illustrate the effectiveness of the proposed decision-making approach.