Reliability Evaluation Model Research Articles

Research on the HHO improved BP neural network fault prediction algorithm for distribution networks based on weather factors

Abstract Weather factors have a substantial impact on the operation and maintenance of the distribution network, but the current system fault prediction platform mainly focuses on the operating characteristics of the system, that is, the internal parameters, and rarely considers the external parameters. Firstly, by studying the fault data of the distribution network in a city in northern China caused by weather factors, this paper obtains the main weather factors affecting the reliability of power supply in this area. Then, the Harris Hawks optimization (HHO) improved BP neural network algorithm is used to establish the main reliability evaluation models suitable for this region, and based on this, the fault probability of this region is predicted under the target weather. Finally, the prediction results are compared with the actual fault data caused by weather factors in this area. The results show that both the PSO-BP algorithm and HHO-BP neural network algorithm achieve better prediction accuracy than the BP neural network algorithm, and the HHO-BP algorithm has better convergence speed.

Evaluation method of software reliability index

Abstract Software reliability refers to the ability of software not to cause system failure under specified conditions and within the specified time. With the increasing demand for equipment systems for software systems, the software system has become an important part of determining the success or failure of combat force system missions. The reliability assessment of the software system is becoming more and more important. Aiming at the problem of software reliability evaluation, this paper discusses the choice of reliability evaluation model. The model parameters are determined. On this basis, according to the selected reliability evaluation model, the model parameters are estimated through the collected data. Finally, the reliability evaluation analysis is carried out.

A Model and Data Hybrid-Driven Method for Operational Reliability Evaluation of Power Systems Considering Endogenous Uncertainty

A Model and Data Hybrid-Driven Method for Operational Reliability Evaluation of Power Systems Considering Endogenous Uncertainty

Reliability modeling and warranty optimization for products with self-healing under a dynamic shock environment

As modern products evolve in intelligence, self-healing mechanisms have been gaining prominence in the field of reliability. In actual operation, the performance of a product is inevitably influenced by external environments and user interactions. However, existing warranty studies often overlook these factors, leading to oversimplifications in product reliability modeling. This paper offers a comprehensive and realistic view of the product failure process by integrating the dynamic shock environment, inherent self-healing property, and post-sale consumer utilization. The constructed reliability evaluation model accounts for fatal and non-fatal shocks with a dynamic time-varying failure threshold. We introduce the concept of self-healing trigger/delay time, considering a generalized self-healing process. The approximate product reliability is derived, and its accuracy is validated using Monte Carlo simulations. Then, derived from real-world practices, we propose a novel two-stage warranty policy which combines lemon law principles with preventive maintenance. By minimizing the expected cost rate throughout the warranty service period, a preventive maintenance schedule optimization model is developed from the manufacturer's perspective. Finally, a numerical case is presented to reveal the influences of different factors on product reliability and demonstrate the existence of the optimal solution.

Reliability evaluation in the zero‐failure Weibull case based on double‐modified hierarchical Bayes

AbstractHierarchical Bayes, or E‐Bayes, is frequently used to estimate the failure probability when solving a zero‐failure reliability evaluation model; however, the accuracy of the reliability estimation using these methods is not very good in practice. Due to this, a novel double‐modified hierarchical Bayes (DMH‐Bayes) is proposed for Weibull characteristic data in this study to enhance failure probability estimation and improve reliability point estimation accuracy. Meanwhile, in order to guarantee the preservation of the assessment findings' consistency and confidence level, the parametric Bootstrap method (P‐Bootstrap) and the L‐moment estimation method based on point estimation are introduced to obtain reliability confidence interval estimates. Based on Monte–Carlo simulation testing and analysis of a gyroscope bearing, the new model is confirmed to have better applicability and robustness while improving the accuracy of reliability assessment.

Reliability evaluation technique with the integration of wind power fluctuation through considering frequency regulation and failure restoration

The adequacy of power system can be elevated with the increasing grid-connected capacity of wind farm, and meanwhile, the power system reliability is also affected by the intermittent power fluctuation of wind farm. However, the traditional reliability evaluation technique cannot take the power fluctuation into account. Therefore, for considering the positive and negative influence of wind energy on the power system reliability, this paper proposes a reliability evaluation technique through considering static frequency regulation and failure restoration process. A failure restoration strategy which can be integrated into the reliability evaluation model is presented through designing system load curtailment, system frequency restoration, and system load restoration strategies. A series reliability calculating models which depended on the different failure restoration conditions are established. Case studies for different systems are investigated, and the results verify that the proposed method can consider both aspects of the positive and negative influence of wind farm on the power system reliability.

Reliability evaluation of flexible manufacturing systems based on three-layer index system with time-varying weights

With the development of industrial manufacturing, flexible manufacturing system provides an effective way to improve the machining quality and efficiency, as well as reduce the manufacturing cost. Fflexible manufacturing system reliability has been one focus of recent studies. But a systematic, effective and executable reliability evaluation method has not yet proposed in existing researches. This work firstly presented a three-layer index system for flexible manufacturing system reliability evaluation, which is composed of the whole layer indexes, subsystem layer indexes and equipment layer indexes determined by system composition and running features analysis. Time-varying weights of each layer are calculated through the modelling of the reliability and reliability importance based on the classical two-state failure hypothesis. Then, considering multi-state failure modes of elements, a fuzzy evaluation model of flexible manufacturing system reliability is established based on fault grading and statistics, considering grade and number distributions of faults within a certain statistical period. Moreover, through a simulation case of a box-parts finishing flexible manufacturing system, the influence of failure rates and service time on the index weights distribution is firstly revealed, which can provide theoretical basis for the improvement of flexible manufacturing system reliability; then the effectiveness of the proposed method is verified through the comparison of results obtained by the previous model based on two-state failure and the proposed model based on multi-state failure.

Fuzzy reliability evaluation and machine learning-based fault prediction of wind turbines

The swift growth of the wind power industry necessitates comprehensive evaluation and efficient fault prediction of wind turbines. Given the challenges of integration and optimization of reliability evaluation and fault prediction models, a systematic method of reliability fuzzy evaluation and fault prediction based on the Supervisory Control and Data Acquisition (SCADA) data is proposed. A mid-to-long-term reliability fuzzy evaluation model is constructed using Fuzzy Comprehensive Evaluation (FCE). The mid-term evaluation results in ten failure modes reveal that the model's hazard ranking results match the situation better than the RPN method. And the long-term evaluation results of 5 years in the operating mode show that the model effectively gathers the evaluation information each year and provides a clear and accurate reflection of reliability. Meanwhile, fault prediction is studied using alarm logs because they are better at expressing the status of wind turbines than monitoring data. And the tree-based algorithms and unsupervised statistical learning methods are used to mine the mapping relationship between input variables and predefined tags. The fault prediction achieves both accuracy and recall of 0.784 and saves over 163k Euros based on local wind turbine maintenance expenditures. Overall, the reliability evaluation and fault prediction complement each other, which may either affect future wind farm management or prevent unnecessary maintenance costs.

Cluster-Based Toxicity Estimation of Osteoradionecrosis Via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification

PurposeGiven the limitations of extant models for normal tissue complication probability estimation for osteoradionecrosis (ORN) of the mandible, the purpose of this study was to enrich statistical inference by exploiting structural properties of data and provide a clinically reliable model for ORN risk evaluation through an unsupervised-learning analysis that incorporates the whole radiation dose distribution on the mandible. Materials and MethodsThe analysis was conducted on retrospective data of 1,259 head and neck cancer (HNC) patients treated at XXX between 2005 and 2015. During a minimum 12-month post-therapy follow-up period, 173 patients in this cohort (13.7%) developed ORN (grades I to IV). The (structural) clusters of mandibular dose-volume histograms (DVHs) for these patients were identified using the K-means clustering method. A soft-margin support vector machine (SVM) was used to determine the cluster borders and partition the dose-volume space. The risk of ORN for each dose-volume region was calculated based on incidence rates and other clinical risk factors. ResultsThe K-means clustering method identified six clusters among the DVHs. Based on the first five clusters, the dose-volume space was partitioned by the soft-margin SVM into distinct regions with different risk indices. The sixth cluster entirely overlapped with the others; the region of this cluster was determined by its envelopes. For each region, the ORN incidence rate per pre-radiation dental extraction status (a statistically significant, non-dose related risk factor for ORN) was reported as the corresponding risk index. ConclusionThis study presents an unsupervised-learning analysis of a large-scale data set to evaluate the risk of mandibular ORN among HNC patients. The results provide a visual risk-assessment tool for ORN (based on the whole DVH and pre-radiation dental extraction status) as well as a range of constraints for dose optimization under different risk levels.

Analysis of the Impacts of Students Back to School on the Volatility and Reliability of Travel Speed on Urban Road

How to effectively and accurately evaluate and analyze the volatility and reliability of travel speed on urban road before and after students back to school is a hot and key problem in urban road traffic congestion governance research. The Beijing 3rd Ring Road was taken as the research object and the impacts of the students back to school on the volatility and reliability of the travel speed of road sections were qualitatively and quantitatively analyzed based on the road section travel speed data during the weekday morning peak (7:00–8:59). The results showed that the travel speed of the Beijing 3rd Ring Road had cyclicity, time variability, large-scale volatility, and light congestion during the weekday morning peak, and the volatility and reliability indexes of the travel speed of road sections significantly decreased under the impact of the students back to school. The data showed that after the students back to school, the maximum reduction ratio of average travel speed was larger than 55%, and the maximum travel speed reliability reduction value was larger than 0.85 based on the evaluation model of travel speed reliability of car commuters. The research results provide data and theoretical support for urban road traffic congestion mitigation and governance.

An entropy weight variable fuzzy recognition and 1D-CNN deep learning method for general aviation fleet reliability evaluation

The reliability level of general aviation fleet system directly affects the economic benefits and safe operation of general aviation fleet. In order to effectively evaluate the reliability level of general aviation fleet, using the entropy weight variable fuzzy recognition and 1D-CNN depth learning reliability evaluation method. Firstly, taking the Cessna 172 general aviation fleet as the research object, refers to the maintenance statistical analysis of general aviation fleet reliability data, and classifies the fleet reliability evaluation indexes according to the ATA100 chapter standard. Combined with index importance analysis and Delphi expert investigation, 14 key items are extracted as reliability evaluation indexes of general aviation fleet. Secondly, using entropy weight method to obtain indexes weight objectively, and the evaluation level membership function is constructed based on variable fuzzy recognition method. Finally, a reliability evaluation model based on 1D-CNN deep learning method was established. Through training and testing the reliability data evaluation model of general aviation fleet, and comparing with the results of evaluation methods such as support vector machines. The results show that the recognition rate of the 1D-CNN deep learning method based on entropy weight variable fuzzy recognition can reach 91.95%, verifying the objective effectiveness of the evaluation method.

Reliability analysis and evaluation model for space phased‐mission system

AbstractA reliability analysis and evaluation model based on event chain and Bayesian information fusion is proposed for the characteristics of complex space phased‐mission systems (SPMSs), the implementation process of integrated reliability modeling is detailed, and the identification of weak links and reliability evaluation is carried out with the entry, descent, and landing process of Tianwen‐1 Mars Probe as an example. The application results show that the reliability analysis and evaluation model based on event chain and Bayesian information fusion has good engineering applicability, and the method can be extended and applied to the reliability modeling, analysis, and evaluation of complex SPMSs.

Non-destructive prediction of the total viable count (TVC) in Fujian oysters (Crassostrea angulata) based on the colorimetric sensor array

The total viable count (TVC) is a traditional method for evaluating seafood freshness. This study aimed to predict the TVC of Fujian oysters stored at 4℃ by using the colorimetric sensing array (CSA) technique combined with imaging and visible near-infrared (Vis-NIR) information channels. An optimal quantitative prediction model based on partial least squares (PLS) was established by combining feature variable selection with a data fusion strategy. All three data-fusion strategies showed better predictive performance than the individual datasets. The high-level fusion strategy performed the best, with a root mean square error of prediction (RMSEP) of 0.17, mean absolute error of prediction (MAEP) of 0.14, coefficient of determination of prediction (Rp2) of 0.9822, and residual prediction deviation (RPD) of 7.37. The experimental results showed that CSA combined with multiple detection channels could be effectively used to predict the TVC of Fujian oysters. In this study, a reliable and comprehensive evaluation model was established to achieve a rapid and accurate prediction of oyster freshness.

Construction of Reliability Evaluation Model of Cigarette Quality Supervision Measuring Instrument Based on Random Forest Algorithm

Abstract This paper combines the cigarette quality supervision measurement project, summarizes the key instruments for cigarette quality supervision, constructs the reliability evaluation model of cigarette quality supervision measurement instruments, adopts the random forest method and carries out model optimization so as to solve the weights of quality evaluation indexes of cigarette quality supervision measurement instruments. The QTM comprehensive test bench is selected to measure the quality and circumference of the traceability comparison stick of cigarette physical inspection equipment and combined with the Random Forest optimization algorithm to analyze the impact of measurement repeatability on the moisture content of cigarettes. Using the normalized deviation evaluation method, we can compare the consistency of the detection results of the evaluation model of this paper with the detection results of the parent company. It is analyzed that the maximum permissible error of cigarette circumference is ±0.05, and the maximum permissible deviation of comparison D max is ±0.06. The circumference deviation of sample A is 0.04<0.06, the sample is qualified, and it is consistent with the testing results of the parent company.

A Network-gene-mutation-based model for large network dynamic application reliability evaluation

Network evolution model (NEM) is a framework proposed recently for dynamic application reliability evaluation which integrates various factors that affect application failure. The existing component-based NEM relies on an exhaustive enumeration of all potential states of network components, which can lead to a computational bottleneck, especially when dealing with large networks. Therefore, to tackle this challenge, this paper presents a Network-gene-mutation-based NEM. The model introduces novel concepts of Network-cells and Network-genes inspired by the gene-cell-function model framework used in system biology to address complex disease problems. Network-cells are constructed according to the statistical classification of components. Network-genes are constructed by the average failure rate of components within a Network-cell. Dynamic network states are simulated by the Network-gene-mutation function of Network-cells instead of the failure and repair function of network components. Validation of our proposed model is performed through the comparison with benchmark models. The results demonstrate the validity of our proposed model in calculating dynamic application reliability. Besides, the comparison results with the component-based NEM also suggest that our proposed model reduces the time complexity of the algorithm from square order [Formula: see text] to constant order [Formula: see text] and improves the simulation efficiency by roughly 104. Applied to networks of varying scales, our proposed model proves to be an efficient method for calculating dynamic application reliability in large networks. In summary, this paper offers a promising solution to address the computational bottlenecks encountered in the component-based NEM when evaluating the reliability of dynamic applications.

Feeder Capacity Planning and Reliability Evaluation Model of Distribution Network Based on Support Vector Machine

Capacity planning and reliability evaluation models of the traditional distribution network feeder mainly use multi-option balance constraints for multi-objective solutions, which are prone to capacity constraints, resulting in lower reliability indicators for planning and evaluation. Therefore, a brand-new distribution network feeder capacity planning and reliability evaluation model based on a support vector machine is designed. By using support vector machines to design the reliability evaluation process of distribution network feeder capacity planning, we establish an optimization model for reliability evaluation of distribution network feeder capacity planning. The experimental results show that the designed feeder capacity planning and reliability evaluation model based on a support vector machine has good evaluation results, high-reliability indicators for planning and evaluation, reliability, and certain application values.

Transmission reliability evaluation of wireless sensor networks considering channel capacity randomness and energy consumption failure

The reliable transmission of data packets is the basis of ensuring the Internet of Things applications. Therefore, how to ensure the transmission reliability of wireless sensor networks has already become a hotspot. However, the existing researches ignore the effects of multiple fault modes and random factors on transmission reliability. Firstly, in the node reliability modeling, few studies have considered the effects of random failure and energy consumption failure comprehensively. Secondly, in the link reliability modeling, existing studies ignore the effect of the channel capacity randomness, which can lead to the erroneous estimation of transmission reliability. To overcome the above shortcomings, we propose a more realistic transmission reliability model. Firstly, considering the comprehensive effects of two failure modes, we establish a new node reliability model to better characterize the node performance. Secondly, considering the channel capacity randomness, we propose an improved SNR-Capacity connection model by deriving the one-hop connectivity probability, which can better characterize the link reliability. Then, we propose a transmission reliability evaluation model, and give the corresponding exact and approximate algorithms for its solution. Finally, taking the military Internet as an example, the effectiveness of the proposed method is verified.

Evaluation model and algorithm optimization of intelligent manufacturing system on the basis of BP neural network

Intelligent manufacturing is a key direction for the development of the manufacturing industry. Since the level of intelligent manufacturing varies among enterprises, building a scientific and reliable evaluation model is the key to evaluate enterprises. The study optimizes the Back Propagation (BP) neural network based on the Firefly Algorithm (FA) and innovatively introduces the Sparrow Search Algorithm (SSA), which changes the search mechanism of the BP and improves the traditional BP affected by the local optimum. of the traditional BP. In the experimental results, the average error of the improved model is 1.34 % and 0.41 % under the optimal preset parameters, which is significantly better than other advanced algorithms. It is verified that the improved evaluation model in this study has lower error and better effect, which has better application value in the evaluation of intelligent manufacturing system.

Reliability-constrained planning of community integrated energy systems based on fault incidence matrix

Reliability is a prerequisite for community integrated energy systems to provide consumers with uninterrupted high-quality energy supply. However, it is still challenging to consider reliability in the planning of community integrated energy systems due to the complexity of energy conversion relationships. Conventional reliability-constrained planning methods usually form a bi-level optimization problem in which the planning scheme optimization and reliability index calculation are separated into two subproblems. In this paper, a novel reliability-constrained planning method for community integrated energy systems is proposed. First, the fault incidence matrices are employed to construct the analytic reliability evaluation model of community integrated energy system. Then, the reliability evaluation model is linearized and explicitly integrated into the planning model, forming a mixed-integer linear programming model. This model can be efficiently solved by mathematical optimization algorithms while effectively balancing the operation cost and reliability at the planning stage. Case studies are conducted based on a practical community integrated energy system in North China to verify the effectiveness of the proposed method.

A methodology to determine the target reliability of natural gas pipeline systems based on risk acceptance criteria of pipelines

The reliable operation of the natural gas pipeline system is directly related to natural gas supply security, and it is vital to determine the target reliability of the natural gas pipeline system when assessing whether the system is reliable. In this study, a methodology to determine the target reliability of natural gas pipeline system based on the risk acceptance criteria of pipelines is proposed, and the methodology consists of three parts. Firstly, the risk acceptance criteria of the natural gas pipelines are determined based on the existing standards. Secondly, the failure consequence model of natural gas pipelines considering the pipeline properties and surroundings is developed, and the corresponding allowable pipeline failure probabilities are calculated according to the risk theory. Finally, the evaluation model of the gas supply reliability for natural gas pipeline systems considering the unit’s failure and hydraulic characteristics is developed, and the target reliability of natural gas pipeline systems is calculated by employing the allowable pipeline failure probabilities. Furthermore, a real natural gas pipeline system is employed to determine its target reliability, and the target value is compared with the actual value of the gas supply reliability. Based on the compared results, the corresponding measure to improve the gas supply reliability is proposed.