Spectral purification improves monitoring accuracy of the comprehensive growth evaluation index for film-mulched winter wheat

In order to further improve the utility of unmanned aerial vehicle(UAV)remote-sensing for quickly and accurately monitoring the growth of winter wheat under film mulching, this study examined the treatments of ridge mulching,ridge–furrow full mulching, and flat cropping full mulching in winter wheat.Based on the fuzzy comprehensive evaluation (FCE) method, four agronomic parameters (leaf area index, above-ground biomass, plant height, and leaf chlorophyll content) were used to calculate the comprehensive growth evaluation index (CGEI) of the winter wheat, and 14 visible and near-infrared spectral indices were calculated using spectral purification technology to process the remote-sensing image data of winter wheat obtained by multispectral UAV.Four machine learning algorithms, partial least squares, support vector machines, random forests, and artificial neural network networks(ANN), were used to build the winter wheat growth monitoring model under film mulching, and accuracy evaluation and mapping of the spatial and temporal distribution of winter wheat growth status were carried out.The results showed that the CGEI of winter wheat under film mulching constructed using the FCE method could objectively and comprehensively evaluate the crop growth status.The accuracy of remote-sensing inversion of the CGEI based on the ANN model was higher than for the individual agronomic parameters, with a coefficient of determination of 0.75,a root mean square error of 8.40, and a mean absolute value error of 6.53.Spectral purification could eliminate the interference of background effects caused by mulching and soil, effectively improving the accuracy of the remotesensing inversion of winter wheat under film mulching, with the best inversion effect achieved on the ridge–furrow full mulching area after spectral purification.The results of this study provide a theoretical reference for the use of UAV remote-sensing to monitor the growth status of winter wheat with film mulching.

Research on a TOPSIS energy efficiency evaluation system for crude oil gathering and transportation systems based on a GA-BP neural network

As the main link of ground engineering,crude oil gathering and transportation systems require huge energy consumption and complex structures.It is necessary to establish an energy efficiency evaluation system for crude oil gathering and transportation systems and identify the energy efficiency gaps.In this paper,the energy efficiency evaluation system of the crude oil gathering and transportation system in an oilfield in western China is established.Combined with the big data analysis method,the GA-BP neural network is used to establish the energy efficiency index prediction model for crude oil gathering and transportation systems.The comprehensive energy consumption,gas consumption,power consumption,energy utilization rate,heat utilization rate,and power utilization rate of crude oil gathering and transportation systems are predicted.Considering the efficiency and unit consumption index of the crude oil gathering and transportation system,the energy efficiency evaluation system of the crude oil gathering and transportation system is established based on a game theory combined weighting method and TOPSIS evaluation method,and the subjective weight is determined by the triangular fuzzy analytic hierarchy process.The entropy weight method determines the objective weight,and the combined weight of game theory combines subjectivity with objectivity to comprehensively evaluate the comprehensive energy efficiency of crude oil gathering and transportation systems and their subsystems.Finally,the weak links in energy utilization are identified,and energy conservation and consumption reduction are improved.The above research provides technical support for the green,efficient and intelligent development of crude oil gathering and transportation systems.

Comprehensive Evaluation of Distributed PV Grid-Connected Based on Combined Weighting Weights and TOPSIS-RSR Method

To effectively quantify the impact of distributed photovoltaic(PV)access on the distribution network,this paper proposes a comprehensive evaluation method of distributed PV grid connection combining subjective and objective combination of assignment and technique for order preference by similarity to an ideal solution(TOPSIS)—rank sum ratio(RSR)(TOPSIS-RSR)method.Based on the traditional distribution network evaluation system,a comprehensive evaluation system has been constructed.It fully considers the new development requirements of distributed PV access on the environmental friendliness and absorptive capacity of the distribution grid and comprehensively reflects the impact of distributed PV grid connection.The analytic hierarchy process(AHP)was used to determine the subjective weights of the primary indicators,and the Spearman consistency test was combined to determine the weights of the secondary indicators based on three objective assignment methods.The subjective and objective combination weights of each assessment indicator were calculated through the principle of minimum entropy.Calculate the distance between the indicators to be evaluated and the positive and negative ideal solutions,the relative closeness ranking,and qualitative binning by TOPSIS-RSR method to obtain the comprehensive evaluation results of different scenarios.By setting up different PV grid-connected scenarios and utilizing the IEEE33 node simulation algorithm,the correctness and effectiveness of the proposed subject-object combination assignment and integrated assessment method are verified.

Sensory Evaluation of Freeze-Dried Facial Mask and Analysis of User Profile

To thoroughly understand market opportunity of freeze-dried facial mask and deeply get insight of consumers’usage behavior and needs,evaluate sensory feelings of 10 screened commercial freeze-dried facial mask products,group test products according to the differences of sensory attributions via Principal Component Analysis(PCA)and Agglomerative Hierarchical Clustering(AHC),pick up the representative products.Freeze-dried facial mask users evaluate satisfaction degree of picked up products and participate survey of usage behavior/cognition.Analyze consumer data by AHC to get consumer segmentations and their profile.The test results show that,sensory data and consumer data,which is from consumers test of screened representative products by performing PCA and AHC on sensory data,can be verified mutually.It is helpful to understand the needs of consumer segmentations and reason to buy by combining sensory data and consumer test.

Measurement and Evaluation of the Business Environment in Large and Medium-Sized Cities in China

The comprehensive development level of the business environment reflects the quality of a region’s economic development,and a good business environment will give a city a strong vitality.This paper uses the entropy method to measure and evaluate the business environment of 106 large and medium-sized cities in China from 2017 to 2021.The results show that:From the spatial point of view,the business environment index of China’s cities shows a gradually decreasing pattern from east to west and from south to north.The balance of the business environment of large and medium-sized cities in China is divided into four levels according to the standard deviation of the ranking of each subindex.The greater the standard deviation,the more unbalanced the overall development of the business environment in the region.Finally,this paper put forward countermeasures and suggestions to further optimize the business environment.

Identification and evaluation of shale oil micromigration and its petroleum geological significance

Taking the Lower Permian Fengcheng Formation shale in Mahu Sag of Junggar Basin,NW China,as an example,core observation,test analysis,geological analysis and numerical simulation were applied to identify the shale oil micro-migration phenomenon.The hydrocarbon micro-migration in shale oil was quantitatively evaluated and verified by a self-created hydrocarbon expulsion potential method,and the petroleum geological significance of shale oil micro-migration evaluation was determined.Results show that significant micro-migration can be recognized between the organic-rich lamina and organic-poor lamina.The organic-rich lamina has strong hydrocarbon generation ability.The heavy components of hydrocarbon preferentially retained by kerogen swelling or adsorption,while the light components of hydrocarbon were migrated and accumulated to the interbedded felsic or carbonate organic-poor laminae as free oil.About 69% of the Fengcheng Formation shale samples in Well MY1 exhibit hydrocarbon charging phenomenon,while 31% of those exhibit hydrocarbon expulsion phenomenon.The reliability of the micro-migration evaluation results was verified by combining the group components based on the geochromatography effect,two-dimension nuclear magnetic resonance analysis,and the geochemical behavior of inorganic manganese elements in the process of hydrocarbon migration.Micro-migration is a bridge connecting the hydrocarbon accumulation elements in shale formations,which reflects the whole process of shale oil generation,expulsion and accumulation,and controls the content and composition of shale oil.The identification and evaluation of shale oil micro-migration will provide new perspectives for dynamically differential enrichment mechanism of shale oil and establishing a“multi-peak model in oil generation”of shale.

Comparative evaluation of commercial Douchi by different molds:biogenic amines,non-volatile and volatile compounds

To provide new insights into the development and utilization of Douchi artificial starters,three common strains(Aspergillus oryzae,Mucor racemosus,and Rhizopus oligosporus)were used to study their influence on the fermentation of Douchi.The results showed that the biogenic amine contents of the three types of Douchi were all within the safe range and far lower than those of traditional fermented Douchi.Aspergillus-type Douchi produced more free amino acids than the other two types of Douchi,and its umami taste was more prominent in sensory evaluation(P<0.01),while Mucor-type and Rhizopus-type Douchi produced more esters and pyrazines,making the aroma,sauce,and Douchi flavor more abundant.According to the Pearson and PLS analyses results,sweetness was significantly negatively correlated with phenylalanine,cysteine,and acetic acid(P<0.05),bitterness was significantly negatively correlated with malic acid(P<0.05),the sour taste was significantly positively correlated with citric acid and most free amino acids(P<0.05),while astringency was significantly negatively correlated with glucose(P<0.001).Thirteen volatile compounds such as furfuryl alcohol,phenethyl alcohol,and benzaldehyde caused the flavor difference of three types of Douchi.This study provides theoretical basis for the selection of starting strains for commercial Douchi production.

Comprehensive Evaluation of Flower Border Application Value of New and Superior Plants in Hefei Area

An analytic hierarchy process(AHP)was employed to assess the applicability of 18 new and superior varieties of flowers in Hefei City flower border applications.A total of 12 indicators were selected from three distinct aspects of adaptability,ornamental characteristics and use traits,in order to establish a comprehensive evaluation model.The results demonstrate that grade I(J≥2.685)exhibits excellent application value,encompassing six species of plants,such asHydrangeamacrophylla‘Endless Summer’;grade II(2.684≤J≤2.420)is also of notable application value,encompassing five species of plants,such asCallistemonrigidus;grade III(2.419≤J≤2.615)is of average application value,including five species of plants,such asCrocosmiacrocosmiflora;grade IV(J≤2.16)is of relatively poor application value.The evaluation results may be utilized as a theoretical reference for the promotion of new and superior varieties in the flower border of Hefei.

Machine learning in metal-ion battery research: Advancing material prediction, characterization, and status evaluation

Metal-ion batteries(MIBs),including alkali metal-ion(Li^(+),Na^(+),and K^(3)),multi-valent metal-ion(Zn^(2+),Mg^(2+),and Al^(3+)),metal-air,and metal-sulfur batteries,play an indispensable role in electrochemical energy storage.However,the performance of MIBs is significantly influenced by numerous variables,resulting in multi-dimensional and long-term challenges in the field of battery research and performance enhancement.Machine learning(ML),with its capability to solve intricate tasks and perform robust data processing,is now catalyzing a revolutionary transformation in the development of MIB materials and devices.In this review,we summarize the utilization of ML algorithms that have expedited research on MIBs over the past five years.We present an extensive overview of existing algorithms,elucidating their details,advantages,and limitations in various applications,which encompass electrode screening,material property prediction,electrolyte formulation design,electrode material characterization,manufacturing parameter optimization,and real-time battery status monitoring.Finally,we propose potential solutions and future directions for the application of ML in advancing MIB development.

A stability evaluation method for deep-seated toppling in the upper Lancang river,Southwestern China

Deep-seated toppling in the upper reaches of the Lancang River,southwest China involves deformations exceeding 100 m in depth.The slope deformation is initiated by river downcutting and evolves distinctive characteristics with a depth of river incision.In this study,we propose a system for evaluating the stability of deep-seated toppled slopes in different evolutionary stages.This system contains identification criteria for each evolutionary stage and provides the corresponding stability evaluation methods.Based on the mechanical and kinematic analysis of slope blocks,the specific stage of slope movement can be identified in the field through outcrop mapping,in situ tests,surface displacement monitoring,and adit and borehole explorations.The stability evaluation methods are established based on the limiting equilibrium theory and the strain compatibility between the undisturbed zone and the toppled zone.Finally,several sample slopes in different evolution stages have been investigated to verify the applicability and accuracy of the proposed stability evaluation system.The results indicate that intense tectonic activity and rapid river incision lead to a maximum principal stress ratio exceeding 10 near the slope surface,thus triggering widespread toppling deformations along the river valley.When considering the losses of joint cohesion during the further rotation process,the safety factor of the slope drops by 7%e28%.The self-stabilization of toppling deformation can be recognized by the layer symmetry configuration after the free rotation of the deflected layers.Intensely toppled rock blocks mainly suffer sliding failures beyond the layer symmetry condition.The factor of safety of the K73 rockslide decreased from 1.17 to 0.87 by considering the development of the potential sliding surface and the toesaturated zone.

PARE:Privacy-Preserving Data Reliability Evaluation for Spatial Crowdsourcing in Internet of Things

The proliferation of intelligent,connected Internet of Things(IoT)devices facilitates data collection.However,task workers may be reluctant to participate in data collection due to privacy concerns,and task requesters may be concerned about the validity of the collected data.Hence,it is vital to evaluate the quality of the data collected by the task workers while protecting privacy in spatial crowdsourcing(SC)data collection tasks with IoT.To this end,this paper proposes a privacy-preserving data reliability evaluation for SC in IoT,named PARE.First,we design a data uploading format using blockchain and Paillier homomorphic cryptosystem,providing unchangeable and traceable data while overcoming privacy concerns.Secondly,based on the uploaded data,we propose a method to determine the approximate correct value region without knowing the exact value.Finally,we offer a data filtering mechanism based on the Paillier cryptosystem using this value region.The evaluation and analysis results show that PARE outperforms the existing solution in terms of performance and privacy protection.

Towards trustworthy multi-modal motion prediction:Holistic evaluation and interpretability of outputs

Predicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning.This task is very complex,as the behaviour of road agents depends on many factors and the number of possible future trajectories can be consid-erable(multi-modal).Most prior approaches proposed to address multi-modal motion prediction are based on complex machine learning systems that have limited interpret-ability.Moreover,the metrics used in current benchmarks do not evaluate all aspects of the problem,such as the diversity and admissibility of the output.The authors aim to advance towards the design of trustworthy motion prediction systems,based on some of the re-quirements for the design of Trustworthy Artificial Intelligence.The focus is on evaluation criteria,robustness,and interpretability of outputs.First,the evaluation metrics are comprehensively analysed,the main gaps of current benchmarks are identified,and a new holistic evaluation framework is proposed.Then,a method for the assessment of spatial and temporal robustness is introduced by simulating noise in the perception system.To enhance the interpretability of the outputs and generate more balanced results in the proposed evaluation framework,an intent prediction layer that can be attached to multi-modal motion prediction models is proposed.The effectiveness of this approach is assessed through a survey that explores different elements in the visualisation of the multi-modal trajectories and intentions.The proposed approach and findings make a significant contribution to the development of trustworthy motion prediction systems for autono-mous vehicles,advancing the field towards greater safety and reliability.

Full-domain collaborative deployment method of multiple interference sources and evaluation of its deployment effect

This paper realizes the full-domain collaborative deployment of multiple interference sources of the global satellite navigation system(GNSS)and evaluates the deployment effect to enhance the ability to disturb the attacker and the capability to defend the GNSS during navigation countermeasures.Key evaluation indicators for the jamming effect of GNSS suppressive and deceptive jamming sources are first created,their evaluation models are built,and their detection procedures are sorted out,as the basis for determining the deployment principles.The principles for collaboratively deploying multi-jamming sources are developed to obtain the deployment structures(including the required number,structures in demand,and corresponding positions)of three single interference sources required by collaboratively deploying.Accordingly,simulation and hardware-in-loop testing results are presented to determine a rational configuration of the collaborative deployment of multi-jamming sources in the set situation and further realize the full-domain deployment of an interference network from ground,air to space.Varied evaluation indices for the deployment effect are finally developed to evaluate the deployment effect of the proposed configuration and further verify its reliability and rationality.

Failure evaluation and control factor analysis of slope block instability along traffic corridor in Southeastern Tibet

The instability of slope blocks occurred frequently along traffic corridor in Southeastern Tibet(TCST),which was primarily controlled by the rock mass structures.A rapid method evaluating the control effects of rock mass structures was proposed through field statistics of the slopes and rock mass structures along TCST,which combined the stereographic projection method,modified M-JCS model,and limit equilibrium theory.The instabilities of slope blocks along TCST were then evaluated rapidly,and the different control factors of instability were analyzed.Results showed that the probabilities of toppling(5.31%),planar(16.15%),and wedge(35.37%)failure of slope blocks along TCST increased sequentially.These instability modes were respectively controlled by the anti-dip joint,the joint parallel to slope surface with a dip angle smaller than the slope angle(singlejoint),and two groups of joints inclined out of the slope(double-joints).Regarding the control effects on slope block instability,the stabilization ability of doublejoints(72.7%),anti-dip joint(67.4%),and single-joint(57.6%)decreased sequentially,resulting in different probabilities of slope block instability.Additionally,nearby regional faults significantly influenced the joints,leading to spatial heterogeneity and segmental clustering in the stabilization ability provided by joints to the slope blocks.Consequently,the stability of slope blocks gradually weakened as they approached the fault zones.This paper can provide guidance and assistance for investigating the development characteristics of rock mass structures and the stability of slope blocks.

Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm:A case study of Baihetan Reservoir Area

Landslide hazard susceptibility evaluation takes on critical significance in early warning and disaster prevention and reduction.In order to solve the problems of poor effectiveness of landslide data and complex calculation of weights for multiple evaluation factors in the existing landslide susceptibility evaluation models,in this study,a method of landslide hazard susceptibility evaluation is proposed by combining SBAS-InSAR(Small Baseline Subsets-Interferometric Synthetic Aperture Radar)and SSA-BP(Sparrow Search Algorithm-Back Propagation)neural network algorithm.The SBAS-InSAR technology is adopted to identify potential landslide hazards in the study area,update the cataloging data of landslide hazards,and 11 evaluation factors are chosen for constructing the SSA-BP model for training and validation.Baihetan Reservoir area is selected as a case study for validation.As indicated by the results,the application of SBAS-InSAR technology,combined with both ascending and descending orbit data,effectively addresses the incomplete identification of landslide hazards caused by geometric distortion of single orbit SAR data(e.g.,shadow,overlay,and perspective contraction)in deep canyon areas,thereby enabling the acquisition of up-to-date landslide hazard data.Moreover,in comparison to the conventional BP(Back Propagation)algorithm,the accuracy of the model constructed by the SSA-BP algorithm exhibits a significant increase,with mean squared error and mean absolute error reduced by 0.0142 and 0.0607,respectively.Additionally,during the process of susceptibility evaluation,the SSA-BP model effectively circumvents the issue of considerable manual interventions in calculating the weight of evaluation factors.The area under the curve of this model reaches 0.909,surpassing BP(0.835),random forest(0.792),and the information value method(0.699).The risk of landslide occurrence in the Baihetan Reservoir area is positively correlated with slope,surface temperature,and deformation rate,while it is negatively correlated with fault distance and normalized difference vegetation index.Geological lithology exerts minimal influence on the occurrence of landslides,with the risk being low in forest land and high in grassland.The method proposed in this study provides a useful reference for disaster prevention and mitigation departments to perform landslide hazard susceptibility evaluations in deep canyon areas under complex geological conditions.

Lunar In Situ Large-Scale Construction:Quantitative Evaluation of Regolith Solidification Techniques

Lunar habitat construction is crucial for successful lunar exploration missions.Due to the limitations of transportation conditions,extensive global research has been conducted on lunar in situ material processing techniques in recent years.The aim of this paper is to provide a comprehensive review,precise classification,and quantitative evaluation of these approaches,focusing specifically on four main approaches:reaction solidification(RS),sintering/melting(SM),bonding solidification(BS),and confinement formation(CF).Eight key indicators have been identified for the construction of low-cost and highperformance systems to assess the feasibility of these methods:in situ material ratio,curing temperature,curing time,implementation conditions,compressive strength,tensile strength,curing dimensions,and environmental adaptability.The scoring thresholds are determined by comparing the construction requirements with the actual capabilities.Among the evaluated methods,regolith bagging has emerged as a promising option due to its high in situ material ratio,low time requirement,lack of hightemperature requirements,and minimal shortcomings,with only the compressive strength falling below the neutral score.The compressive strength still maintains a value of 2–3 MPa.The proposed construction scheme utilizing regolith bags offers numerous advantages,including rapid and large-scale construction,ensured tensile strength,and reduced reliance on equipment and energy.In this study,guidelines for evaluating regolith solidification techniques are provided,and directions for improvement are offered.The proposed lunar habitat design based on regolith bags is a practical reference for future research.

I-DCGAN and TOPSIS-IFP:A simulation generation model for radiographic flaw detection images in light alloy castings and an algorithm for quality evaluation of generated images

The intelligent detection technology driven by X-ray images and deep learning represents the forefront of advanced techniques and development trends in flaw detection and automated evaluation of light alloy castings.However,the efficacy of deep learning models hinges upon a substantial abundance of flaw samples.The existing research on X-ray image augmentation for flaw detection suffers from shortcomings such as poor diversity of flaw samples and low reliability of quality evaluation.To this end,a novel approach was put forward,which involves the creation of the Interpolation-Deep Convolutional Generative Adversarial Network(I-DCGAN)for flaw detection image generation and a comprehensive evaluation algorithm named TOPSIS-IFP.I-DCGAN enables the generation of high-resolution,diverse simulated images with multiple appearances,achieving an improvement in sample diversity and quality while maintaining a relatively lower computational complexity.TOPSIS-IFP facilitates multi-dimensional quality evaluation,including aspects such as diversity,authenticity,image distribution difference,and image distortion degree.The results indicate that the X-ray radiographic images of magnesium and aluminum alloy castings achieve optimal performance when trained up to the 800th and 600th epochs,respectively.The TOPSIS-IFP value reaches 78.7%and 73.8%similarity to the ideal solution,respectively.Compared to single index evaluation,the TOPSIS-IFP algorithm achieves higher-quality simulated images at the optimal training epoch.This approach successfully mitigates the issue of unreliable quality associated with single index evaluation.The image generation and comprehensive quality evaluation method developed in this paper provides a novel approach for image augmentation in flaw recognition,holding significant importance for enhancing the robustness of subsequent flaw recognition networks.

Study on thermal decomposition kinetics of azobenzene-4,4′-dicarboxylic acid by using compensation parameter method and nonlinear fitting evaluation

Recently,azobenzene-4,4'-dicarboxylic acid(ADCA)has been produced gradually for use as an organic synthesis or pharmaceutical intermediate due to its eminent performance.With large quantities put into application in the future,the thermal stability of this substance during storage,transportation,and use will become quite important.Thus,in this work,the thermal decomposition behavior,thermal decomposition kinetics,and thermal hazard of ADCA were investigated.Experiments were conducted by using a SENSYS evo DSC device.A combination of differential iso-conversion method,compensation parameter method,and nonlinear fitting evaluation were also used to analyze thermal kinetics and mechanism of ADCA decomposition.The results show that when conversion rate α increases,the activation energies of ADCA's first and main decomposition peaks fall.The amount of heat released during decomposition varies between 182.46 and 231.16 J·g^(-1).The proposed kinetic equation is based on the Avrami-Erofeev model,which is consistent with the decomposition progress.Applying the Frank-Kamenetskii model,a calculated self-accelerating decomposition temperature of 287.0℃is obtained.

Mitigation of polycyclic aromatic hydrocarbons(PAHs)in roasted beef patties by cold plasma treatment and products quality evaluation

The cold plasma(CP)technique was applied to alleviate the contamination of polycyclic aromatic hydrocarbon(PAH)in this investigation.Two different CP treatments methods were implemented in the production of beef patties,to investigate their inhibition and degradation capacity on PAHs.With 5 different cooking oils and fats addition,the inhibition mechanism of in-package cold plasma(ICP)pretreatment was explored from the aspect of raw patties fatty acids composition variation.The results of principal component analysis showed that the first two principal components accounted for more than 80%of the total variation in the original data,indicating that the content of saturated fatty acids was significantly positively correlated with the formation of PAHs.ICP pretreatment inhibited the formation of PAHs by changing the composition of fatty acids,which showed that the total amount of polyunsaturated fatty acids decreased and the total amount of monounsaturated fatty acids increased.Sensory discrimination tests demonstrated there were discernable differences between 2 CP treated samples and the controls,utilization of the ICP pretreatment in meat products processing was expected to achieve satisfying eating quality.In conclusion,CP treatment degraded PAHs through stepwise ring-opening oxidation in 2 reported pathways,the toxicity of PAHs contaminated products was alleviated after CP treatment.

Data-driven diagnosis of high temperature PEM fuel cells based on the electrochemical impedance spectroscopy: Robustness improvement and evaluation

Utilizing machine learning techniques for data-driven diagnosis of high temperature PEM fuel cells is beneficial and meaningful to the system durability. Nevertheless, ensuring the robustness of diagnosis remains a critical and challenging task in real application. To enhance the robustness of diagnosis and achieve a more thorough evaluation of diagnostic performance, a robust diagnostic procedure based on electrochemical impedance spectroscopy (EIS) and a new method for evaluation of the diagnosis robustness was proposed and investigated in this work. To improve the diagnosis robustness: (1) the degradation mechanism of different faults in the high temperature PEM fuel cell was first analyzed via the distribution of relaxation time of EIS to determine the equivalent circuit model (ECM) with better interpretability, simplicity and accuracy;(2) the feature extraction was implemented on the identified parameters of the ECM and extra attention was paid to distinguishing between the long-term normal degradation and other faults;(3) a Siamese Network was adopted to get features with higher robustness in a new embedding. The diagnosis was conducted using 6 classic classification algorithms—support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), and Naive Bayes employing a dataset comprising a total of 1935 collected EIS. To evaluate the robustness of trained models: (1) different levels of errors were added to the features for performance evaluation;(2) a robustness coefficient (Roubust_C) was defined for a quantified and explicit evaluation of the diagnosis robustness. The diagnostic models employing the proposed feature extraction method can not only achieve the higher performance of around 100% but also higher robustness for diagnosis models. Despite the initial performance being similar, the KNN demonstrated a superior robustness after feature selection and re-embedding by triplet-loss method, which suggests the necessity of robustness evaluation for the machine learning models and the effectiveness of the defined robustness coefficient. This work hopes to give new insights to the robust diagnosis of high temperature PEM fuel cells and more comprehensive performance evaluation of the data-driven method for diagnostic application.