Predictive maintenance and its applications in civil engineering structures:A review

Structural health monitoring and performance prediction are crucial for smart disaster mitigation and intelligent management of structures throughout their lifespan.Recent advancements in predictive maintenance strategies within the industrial manufacturing industry have inspired similar innovations in civil engineering,aiming to improve structural performance evaluation,damage diagnosis,and capacity prediction.This review delves into the framework of predictive maintenance and examines various existing solutions,focusing on critical areas such as data acquisition,condition monitoring,damage prognosis,and maintenance planning.Results from real-world applications of predictive maintenance in civil engineering,covering high-rise structures,deep foundation pits,and other infrastructure,are presented.The challenges of implementing predictive maintenance in civil engineering structures under current technology,such as model interpretability of data-driven methods and standards for predictive maintenance,are explored.Future research prospects within this area are also discussed.

An Efficient IIoT-Based Smart Sensor Node for Predictive Maintenance of Induction Motors

Predictive maintenance is a vital aspect of the industrial sector,and the use of Industrial Internet of Things(IIoT)sensor nodes is becoming increasingly popular for detecting motor faults and monitoring motor conditions.An integrated approach for acquiring,processing,and wirelessly transmitting a large amount of data in predictive maintenance applications remains a significant challenge.This study presents an IIoT-based sensor node for industrial motors.The sensor node is designed to acquire vibration data on the radial and axial axes of the motor and utilizes a hybrid approach for efficient data processing via edge and cloud platforms.The initial step of signal processing is performed on the node at the edge,reducing the burden on a centralized cloud for processing data from multiple sensors.The proposed architecture utilizes the lightweight Message Queue Telemetry Transport(MQTT)communication protocol for seamless data transmission from the node to the local and main brokers.The broker’s bridging allows for data backup in case of connection loss.The proposed sensor node is rigorously tested on a motor testbed in a laboratory setup and an industrial setting in a rice industry for validation,ensuring its performance and accuracy in real-world industrial environments.The data analysis and results from both testbed and industrial motors were discussed using vibration analysis for identifying faults.The proposed sensor node is a significant step towards improving the efficiency and reliability of industrial motors through realtime monitoring and early fault detection,ultimately leading to minimized unscheduled downtime and cost savings.

An Ordinal Multi-Dimensional Classification(OMDC)for Predictive Maintenance

Predictive Maintenance is a type of condition-based maintenance that assesses the equipment's states and estimates its failure probability and when maintenance should be performed.Although machine learning techniques have been frequently implemented in this area,the existing studies disregard to the nat-ural order between the target attribute values of the historical sensor data.Thus,these methods cause losing the inherent order of the data that positively affects the prediction performances.To deal with this problem,a novel approach,named Ordinal Multi-dimensional Classification(OMDC),is proposed for estimating the conditions of a hydraulic system's four components by taking into the natural order of class values.To demonstrate the prediction ability of the proposed approach,eleven different multi-dimensional classification algorithms(traditional Binary Relevance(BR),Classifier Chain(CC),Bayesian Classifier Chain(BCC),Monte Carlo Classifier Chain(MCC),Probabilistic Classifier Chain(PCC),Clas-sifier Dependency Network(CDN),Classifier Trellis(CT),Classifier Dependency Trellis(CDT),Label Powerset(LP),Pruned Sets(PS),and Random k-Labelsets(RAKEL))were implemented using the Ordinal Class Classifier(OCC)algorithm.Besides,seven different classification algorithms(Multilayer Perceptron(MLP),Support Vector Machine(SVM),k-Nearest Neighbour(kNN),Decision Tree(C4.5),Bagging,Random Forest(RF),and Adaptive Boosting(AdaBoost))were chosen as base learners for the OCC algorithm.The experimental results present that the proposed OMDC approach using binary relevance multi-dimensional classification methods predicts the conditions of a hydraulic system's multiple components with high accuracy.Also,it is clearly seen from the results that the OMDC models that utilize ensemble-based classification algorithms give more reliable prediction performances with an average Hamming score of 0.853 than the others that use traditional algorithms as base learners.

Pavement performance model for road maintenance and repair planning: a review of predictive techniques

This paper provides a review of predictive analytics for roads,identifying gaps and limitations in current methodologies.It explores the implications of these limitations on accuracy and application,while also discussing how advanced predictive analytics can address these challenges.The article acknowledges the transformative shift brought about by technological advancements and increased computational capabilities.The degradation of pavement surfaces due to increased road users has resulted in safety and comfort issues.Researchers have conducted studies to assess pavement condition and predict future changes in pavement structure.Pavement Management Systems are crucial in developing prediction performance models that estimate pavement condition and degradation severity over time.Machine learning algorithms,artificial neural networks,and regression models have been used,with strengths and weaknesses.Researchers generally agree on their accuracy in estimating pavement condition considering factors like traffic,pavement age,and weather conditions.However,it is important to carefully select an appropriate prediction model to achieve a high-quality prediction performance system.Understanding the strengths and weaknesses of each model enables informed decisions for implementing prediction models that suit specific needs.The advancement of prediction models,coupled with innovative technologies,will contribute to improved pavement management and the overall safety and comfort of road users.

Development of a Framework for Equipment Health Management in the Mining Industries in Zambia

The Zambian mining industry is crucial to the national economy but struggles with inconsistent equipment maintenance practices. This study developed an Equipment Maintenance Management Framework (EMMF) tailored to the industry’s needs. Using surveys, interviews, and on-site visits at eight major mining companies, we identified significant variations in maintenance strategies, CMMS usage, and reliability engineering. The EMMF prioritizes predictive maintenance, efficient CMMS implementation, ongoing training, and robust reliability engineering to shift from reactive to proactive maintenance. We recommend adopting continuous improvement practices and data-driven decision-making based on performance metrics, with a phased EMMF implementation aligning maintenance with strategic business objectives. This framework is poised to enhance operational efficiency, equipment reliability, and safety, fostering sustainable growth in the Zambian mining sector.

Construction and verification of a model for predicting fall risk in patients with maintenance hemodialysis

Objective:To construct a risk prediction model for fall in patients with maintenance hemodialysis(MHD)and to verify the prediction effect of the model.Methods:From June 2020 to December 2020,307 patients who underwent MHD in a tertiary hospital in Chengdu were divided into a fall group(32 cases)and a non-fall group(275 cases).Logistic regression analysis model was used to establish the influencing factors of the subjects.Hosmer–Lemeshow and receiver operating characteristic(ROC)curve were used to test the goodness of fit and predictive effect of the model,and 104 patients were again included in the application research of the model.Results:The risk factors for fall were history of falls in the past year(OR=3.951),dialysis-related hypotension(OR=6.949),time up and go(TUG)test(OR=4.630),serum albumin(OR=0.661),frailty(OR=7.770),and fasting blood glucose(OR=1.141).Hosmer–Lemeshow test was P=0.475;the area under the ROC curve was 0.907;the Youden index was 0.642;the sensitivity was 0.843;and the specificity was 0.799.Conclusions:The risk prediction model constructed in this study has a good effect and can provide references for clinical screening of fall risks in patients with MHD.

Research on Machine Tool Fault Diagnosis and Maintenance Optimization in Intelligent Manufacturing Environments

In the context of intelligent manufacturing,machine tools,as core equipment,directly influence production efficiency and product quality through their operational reliability.Traditional maintenance methods for machine tools,often characterized by low efficiency and high costs,fail to meet the demands of modern manufacturing industries.Therefore,leveraging intelligent manufacturing technologies,this paper proposes a solution optimized for the diagnosis and maintenance of machine tool faults.Initially,the paper introduces sensor-based data acquisition technologies combined with big data analytics and machine learning algorithms to achieve intelligent fault diagnosis of machine tools.Subsequently,it discusses predictive maintenance strategies by establishing an optimized model for maintenance strategy and resource allocation,thereby enhancing maintenance efficiency and reducing costs.Lastly,the paper explores the architectural design,integration,and testing evaluation methods of intelligent manufacturing systems.The study indicates that optimization of machine tool fault diagnosis and maintenance in an intelligent manufacturing environment not only enhances equipment reliability but also significantly reduces maintenance costs,offering broad application prospects.

基于生成对抗网络模型的小样本PM_(2.5)预测

针对目前数据驱动的方法在小样本下PM_(2.5)预测准确率较低的问题,提出一种基于生成对抗性网络(GAN)模型PME-GAN,用于在线预测PM_(2.5)浓度值。在生成器中加入长短期记忆网络(LSTM)并用于提取输入数据的时序特征,在判别器中加入多层感知机网络(MLP),通过生成器对PM_(2.5)浓度值进行预测。与LSTM、GRU、CNN-LSTM和CNN-GRU 4种模型进行对比实验,结果表明,该方法在小样本数据集上具有更高的预测准确率,对保定测试集的后25%数据开始预测,预测效果很好。

Reliability-based Maintenance Optimization under Imperfect Predictive Maintenance

The reliability-based maintenance optimization model has been focused by the engineers and scholars but it has never been solved effectively to formulate the effect of a maintenance action on the optimization model. In existing works, the system reliability was assumed to be increased to 1 after a predictive maintenance. However, it is very difficult in the most practical systems. Therefore, a new reliability-based maintenance optimization model under imperfect predictive maintenance (PM) is proposed in this paper. In the model, the system reliability is only restored to R i (0<R i <1, i∈N, N is natural number set) after the ith PM. The system uptimes and the corresponding probability in two cases whether there is an unexpected fault in one cycle are derived respectively and the system expected uptime model is given. To formulate the system expected downtime, the probability of each imperfect PM number in one cycle is calculated. Then, the system expected total time model is obtained. The total expected long-term operation cost is composed of the expected maintenance cost, the expected loss due to the downtime and the expected additional cost due to the occurrence of an unexpected failure. They are modeled respectively in this work. Jointing the system expected total time and long-term operation cost in one cycle, the expected long-term operation cost per time could be computed. Then, the proposed maintenance optimization model is formulated where the objective function is to minimize the expected long-term operation cost per time. The results of numerical example show that the proposed model could scheme the optimal maintenance actions for the considered system when the required parameters are given and the optimal solution of the proposed model is sensitive to the parameters of effective age model and insensitive to other parameters. The proposed model effectively solves the problem of evaluating the effect of an imperfect PM on the system reliability and presents a more practical optimization method for the reliability-based maintenance strategy than the existing works.

A Risk-Averse Remaining Useful Life Estimation for Predictive Maintenance

Remaining useful life(RUL)prediction is an advanced technique for system maintenance scheduling.Most of existing RUL prediction methods are only interested in the precision of RUL estimation;the adverse impact of overestimated RUL on maintenance scheduling is not of concern.In this work,an RUL estimation method with risk-averse adaptation is developed which can reduce the over-estimation rate while maintaining a reasonable under-estimation level.The proposed method includes a module of degradation feature selection to obtain crucial features which reflect system degradation trends.Then,the latent structure between the degradation features and the RUL labels is modeled by a support vector regression(SVR)model and a long short-term memory(LSTM)network,respectively.To enhance the prediction robustness and increase its marginal utility,the SVR model and the LSTM model are integrated to generate a hybrid model via three connection parameters.By designing a cost function with penalty mechanism,the three parameters are determined using a modified grey wolf optimization algorithm.In addition,a cost metric is proposed to measure the benefit of such a risk-averse predictive maintenance method.Verification is done using an aero-engine data set from NASA.The results show the feasibility and effectiveness of the proposed RUL estimation method and the predictive maintenance strategy.

Clinical study of predicting the occurrence and development of coronary heart disease by FT3 level in maintenance hemodialysis patients

Objective:To investigate the clinical significance of FT3 level in predicting the occurrence and development of coronary heart disease in maintenance hemodialysis patients.Methods:95 Patients who underwent maintenance hemodialysis in our hospital from January 2016 to December 2017 were selected as subjects. According to whether has coronary heart disease was divided into coronary heart disease group and non coronary heart disease group, the difference of FT3 level and related laboratory indexes was observed. ROC curve analysis and COX multiple factor risk regression were used to analyze the predictive value of FT3 level on the occurrence and development of heart disease in MHD patients.Results:The concentration of FT3, Hb and ALB in CHD group was lower than that of non-CHD group (P<0.05), and the content of TG, TC, LDL-C, Hcy and Hs-CRP were significantly higher than that of non-CHD group (P<0.05). FT3 was positively correlated with Hb and ALB (T=0.821, 0.809,P<0.05), and was negatively correlated with TG, TC, LDL-C, Hcy and Hs-CRP (T=- 0.814, - 0.843, - 0.904, - 0.806, - 0.912,P<0.05). The ROC curve analysis showed that the area of AUC of FT3 was the highest, 0.864 (95%, CI:0.803~0.935), the sensitivity and specificity was 86.5% and 89.3% respectively. The area of combined diagnosis of AUC was 0.904 (95%CI:0.867~0.976), the sensitivity and specificity was 85.6% and 94.5%, respectively. After analyzing the COX risk regression model and correcting the above laboratory indicators, FT3 is an independent risk factor (HR: 0.58, 95%, CI: 0.41~0.72,P<0.05) for the adverse prognosis of MHD patients with coronary heart disease.Conclusion:It is of high clinical value to predict the development of coronary heart disease in MHD patients by FT3 level, and its mechanism may be related to the reduction of thyroxine synthesis, inflammatory reaction and atherosclerosis.

Predictive Maintenance of Manned Spacecraft Through Remaining Useful Life Estimation Technique

Manned spacecraft pose challenges in terms of extremely high safety and reliability, and with the growth of system complexity and longer on-orbit operation time, the traditional management mode, such as monitoring the threshold of parameter passively, is difficult to meet the required safety standards. Predictive maintenance, which analyzes the system heath trend and estimates remaining useful life(RUL) to establish maintenance strategies ahead of time before failure occurs, is a new mode to approach maintenance tasks. Here, a predictive maintenance strategy for complex manned spacecraft is proposed based on the remaining useful life estimation technique. Firstly, a health index is established based on an abundance of telemetry data, reflecting the system's current health state. Secondly, we map the health index to the remaining useful life through system degradation modelling, taking into consideration both the system's stochastic deterioration and uncertainty. The maintenance and management strategies are then made based on the calculated distribution of RUL time. Finally, a case study on Chinese space station energy system predictive maintenance is presented.

A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm

In multi-component systems,the components are dependent,rather than degenerating independently,leading to changes inmaintenance schedules.In this situation,this study proposes a grouping dynamicmaintenance strategy.Considering the structure of multi-component systems,the maintenance strategy is determined according to the importance of the components.The strategy can minimize the expected depreciation cost of the system and divide the system into optimal groups that meet economic requirements.First,multi-component models are grouped.Then,a failure probability model of multi-component systems is established.The maintenance parameters in each maintenance cycle are updated according to the failure probability of the components.Second,the component importance indicator is introduced into the grouping model,and the optimization model,which aimed at a maximum economic profit,is established.A genetic algorithm is used to solve the non-deterministic polynomial(NP)-complete problem in the optimization model,and the optimal grouping is obtained through the initial grouping determined by random allocation.An 11-component series and parallel system is used to illustrate the effectiveness of the proposed strategy,and the influence of the system structure and the parameters on the maintenance strategy is discussed.

Optimization of extended warranty cost for multi-component systems with economic dependence based on group maintenance

During extended warranty(EW)period,maintenance events play a key role in controlling the product systems within normal operations.However,the modelling of failure process and maintenance optimization is complicated owing to the complex features of the product system,namely,components of the multi-component system are interdependent with each other in some form.For the purpose of optimizing the EW pricing decision of the multi-component system scientifically and rationally,taking the series multi-component system with economic dependence sold with EW policy as a research object,this paper optimizes the imperfect preventive maintenance(PM)strategy from the standpoint of EW cost.Taking into consideration adjusting the PM moments of the components in the system,a group maintenance model is developed,in which the system is repaired preventively in accordance with a specified PM base interval.In order to compare with the system EW cost before group maintenance,the system EW cost model before group maintenance is developed.Numerical example demonstrates that offering group maintenance programs can reduce EW cost of the system to a great extent,thereby reducing the EW price,which proves to be a win-win strategy to manufacturers and users.

A Hybrid Deep Learning Approach for PM2.5 Concentration Prediction in Smart Environmental Monitoring

Nowadays,air pollution is a big environmental problem in develop-ing countries.In this problem,particulate matter 2.5(PM2.5)in the air is an air pollutant.When its concentration in the air is high in developing countries like Vietnam,it will harm everyone’s health.Accurate prediction of PM2.5 concentrations can help to make the correct decision in protecting the health of the citizen.This study develops a hybrid deep learning approach named PM25-CBL model for PM2.5 concentration prediction in Ho Chi Minh City,Vietnam.Firstly,this study analyzes the effects of variables on PM2.5 concentrations in Air Quality HCMC dataset.Only variables that affect the results will be selected for PM2.5 concentration prediction.Secondly,an efficient PM25-CBL model that integrates a convolutional neural network(CNN)andBidirectionalLongShort-TermMemory(Bi-LSTM)isdeveloped.This model consists of three following modules:CNN,Bi-LSTM,and Fully connected modules.Finally,this study conducts the experiment to compare the performance of our approach and several state-of-the-art deep learning models for time series prediction such as LSTM,Bi-LSTM,the combination of CNN and LSTM(CNN-LSTM),and ARIMA.The empirical results confirm that PM25-CBL model outperforms other methods for Air Quality HCMC dataset in terms of several metrics including Mean Squared Error(MSE),Root Mean Squared Error(RMSE),Mean Absolute Error(MAE),and Mean Absolute Percentage Error(MAPE).

Research on PM_(2.5) Concentration Prediction Algorithm Based on Temporal and Spatial Features

PM2.5 has a non-negligible impact on visibility and air quality as an important component of haze and can affect cloud formation and rainfall and thus change the climate,and it is an evaluation indicator of air pollution level.Achieving PM2.5 concentration prediction based on relevant historical data mining can effectively improve air pollution forecasting ability and guide air pollution prevention and control.The past methods neglected the impact caused by PM2.5 flow between cities when analyzing the impact of inter-city PM2.5 concentrations,making it difficult to further improve the prediction accuracy.However,factors including geographical information such as altitude and distance and meteorological information such as wind speed and wind direction affect the flow of PM2.5 between cities,leading to the change of PM2.5 concentration in cities.So a PM2.5 directed flow graph is constructed in this paper.Geographic and meteorological data is introduced into the graph structure to simulate the spatial PM2.5 flow transmission relationship between cities.The introduction of meteorological factors like wind direction depicts the unequal flow relationship of PM2.5 between cities.Based on this,a PM2.5 concentration prediction method integrating spatial-temporal factors is proposed in this paper.A spatial feature extraction method based on weight aggregation graph attention network(WGAT)is proposed to extract the spatial correlation features of PM2.5 in the flow graph,and a multi-step PM2.5 prediction method based on attention gate control loop unit(AGRU)is proposed.The PM2.5 concentration prediction model WGAT-AGRU with fused spatiotemporal features is constructed by combining the two methods to achieve multi-step PM2.5 concentration prediction.Finally,accuracy and validity experiments are conducted on the KnowAir dataset,and the results show that the WGAT-AGRU model proposed in the paper has good performance in terms of prediction accuracy and validates the effectiveness of the model.

Failure Prediction and Intelligent Maintenance of a Transportation Company’s Urban Fleet

The present work deals with intelligent vehicle fleet maintenance and prediction. We propose an approach based primarily on the history of failures data and on the geographical data system. The objective here is to predict the date of failures for a fleet of vehicles in order to allow the maintenance department to efficiently deploy the proper resources;we further provide specific details regarding the origins of failures, and finally, give recommendations. This study used the Société de transport de Montréal (STM)’s historical bus failure data as well as weather data from Environment Canada. We thank Facebook’s Prophet, Simple Feed-forward, and Beats algorithms (Uber), we proposed a set of computer codes that allow us to identify the 20% of buses that are responsible for the 80% of failures by mean of the failure history. Then, we deepened our study on the unreliable equipments identified during the diffusion of our computer code This allowed us to propose probable predictions of the dates of future failures. To ensure the validity of the proposed algorithm, we carried out simulations with more than 250,000 data. The results obtained are similar to the predicted theoretical values.

基于预知维修的小麦播种机运行监控系统设计

为了减少播种机故障频率,提升小麦播种机的播种效率和播种质量,基于预知维修对小麦播种机的运行监控系统进行了设计。系统的主要组成包括主控单片机、检测系统、显示监控系统、报警系统及电源。为了对播种机进行预知维修,将灰色模型和神经网络模型结合,建立了动态灰色神经网络模型,并进行了算法设计。为了验证小麦播种机监控系统性能和预知维修算法的有效性,对其进行了监测精度和趋势预测试验,结果表明:监测系统的监测精度较高,播种机可有效对数据趋势进行预测。

维持性血液透析尿毒症患者动静脉内瘘急性血栓形成的危险因素分析及Nomogram预测模型构建

目的探讨维持性血液透析(MHD)尿毒症患者动静脉内瘘急性血栓形成的危险因素及Nomogram预测模型构建。方法选择2020年12月至2022年12月于新乡医学院第三附属医院门诊行MHD治疗的418例尿毒症患者为研究对象。根据动静脉内瘘是否形成急性血栓将患者分为急性血栓组(n=32)与非急性血栓组(n=386)。应用单因素及多因素logistic回归分析影响行MHD的尿毒症患者动静脉内瘘急性血栓形成的影响因素;根据尿毒症患者动静脉内瘘急性血栓形成的独立危险因素建立Nomogram预测模型,并应用Bootstrap来验证Nomogram模型的有效性。结果急性血栓组患者合并糖尿病患、合并低血压、透析时穿刺失败占比、钙磷乘积、超敏C反应蛋白(hs-CRP)、总胆固醇(TC)、低密度脂蛋白胆固醇(LDL-C)水平均显著高于非急性血栓组(P<0.05);logistic回归分析显示,糖尿病、低血压、透析时穿刺失败、钙磷乘积升高、高水平hs-CRP、高水平LDL-C是影响行MHD的尿毒症患者动静脉内瘘急性血栓形成的独立危险因素(P<0.05);依据6个独立危险因素构建了Nomogram预测模型,该模型的一致性指数为0.893(95%置信区间:0.833~0.928);且其校正曲线和标准曲线拟合较好,曲线下面积为0.918。结论糖尿病、低血压、透析时穿刺失败、钙磷乘积升高、高水平hs-CRP和LDL-C是行MHD的尿毒症患者动静脉内瘘急性血栓形成的危险因素,依据独立危险因素构建的Nomogram模型预测行MHD的尿毒症患者动静脉内瘘急性血栓形成的效果较好,有助于临床急性血栓形成患者的早期筛查。

维持性血液透析患者甲状旁腺切除术后早期骨饥饿综合征风险预测模型的构建与验证

目的:甲状旁腺切除术(parathyroidectomy,PTX)是治疗难治性继发性甲状旁腺功能亢进(secondary hyperparathyroidism,SHPT)的有效方法,但PTX后极易出现骨饥饿综合征(hungry bone syndrome,HBS),严重威胁维持性血液透析(maintenance hemodialysis,MHD)患者的生命健康。目前已有研究分析PTX后并发HBS的风险因素,但风险预测模型的预测性能和临床适用性仍待进一步验证。本研究旨在构建MHD伴SHPT患者PTX后并发HBS的风险预测模型,并验证其预测效果。方法:回顾性收集2020年1月至2021年12月在长沙捷奥肾病医院行PTX的MHD伴SHPT的368例患者为训练集,按照是否发生HBS分为HBS组和non-HBS组,对2组的一般资料、手术相关信息、生化指标等进行比较,应用多因素logistic回归筛选HBS的影响因素,建立风险预测模型。采用受试者操作特征(receiver operator characteristic,ROC)曲线、决策曲线、校准曲线对模型进行评价。收集2022年1至12月在中南大学湘雅三医院行PTX的MHD伴SHPT的170例患者为验证集进行外部验证。结果:MHD伴SHPT患者PTX后HBS发生率为60.60%,logistic回归分析结果显示:术前骨骼受累(OR=3.908,95%CI 2.179~7.171)、术前血钙(OR=7.174,95%CI 2.291~24.015)、术前全段甲状旁腺激素(intact parathyroid hormone,i PTH)(OR=1.001,95%CI 1.001~1.001)、术前碱性磷酸酶(alkaline phosphatase,ALP)(OR=1.001,95%CI 1.000~1.001)、术后第1天血钙(OR=0.006,95%CI0.001~0.038)是MHD患者伴SHPT行PTX后并发HBS的独立危险因素(均P<0.01)。构建的风险预测模型在内部训练集和外部验证集中均表现出良好的预测结果,内部验证集的准确度为0.821,灵敏度为0.890,特异度为0.776,约登指数为0.666,曲线下面积(area under curve,AUC)为0.882(95%CI 0.845~0.919);外部验证集的准确度为0.800,灵敏度为0.806,特异度为0.799,约登指数为0.605,AUC为0.863(95%CI 0.795~0.932)。结论:术前骨骼受累、术前血钙、术前iPTH、术前ALP、术后第1天血钙水平是MHD伴SHPT患者行PTX后并发HBS的影响因素,基于上述因素构建的风险预测模型可靠。