Backward Prediction Model Research Articles

Two-Direction Prediction Method of Drilling Fluid Based on OS-ELM for Water Well Drilling

In this study, a drilling fluid prediction method based on an online sequential extreme learning machine (OS-ELM) is proposed, which is prepared for water well drilling on the muddy clay formation of Tarim Basin, Qinghai Province. First, we investigated the mechanism linking mix ratio to fluid performance, allowing us to employ an OS-ELM algorithm derived from the extreme learning machine. Particularly, the proposed prediction method is bidirectional to identify an appropriate slurry formulation. The forward prediction model is established to predict the fluid performance, where the mud additive contents are inputs, and the drilling fluid properties parameters are outputs. Correspondingly, the backward prediction model is established to modify the slurry formula, where differences in the drilling fluid properties are inputs and percentages of slurry additives amount are output. The simulation results show that the two-direction OS-ELM prediction model can better predict the drilling fluid properties in water well drilling.

An Improved Sequential Recommendation Algorithm based on Short‐Sequence Enhancement and Temporal Self‐Attention Mechanism

Sequential recommendation algorithm can predict the next action of a user by modeling the user’s interaction sequence with an item. However, most sequential recommendation models only consider the absolute positions of items in the sequence, ignoring the time interval information between items, and cannot effectively mine user preference changes. In addition, existing models perform poorly on sparse data sets, which make a poor prediction effect for short sequences. To address the above problems, an improved sequential recommendation algorithm based on short‐sequence enhancement and temporal self‐attention mechanism is proposed in this paper. In the proposed algorithm, a backward prediction model is trained first, to predict the prior items in the user sequence. Then, the reverse prediction model is used to generate a batch of pseudo‐historical items before the initial items of the short sequence, to achieve the goal of enhancing the short sequence. Finally, the absolute position information and time interval information of the user sequence are modeled, and a time‐aware self‐attention model is adopted to predict the user’s next action and generate a recommendation list. Various experiments are conducted on two public data sets. The experimental results show that the method proposed in this paper has excellent performance on both dense and sparse data sets, and its effect is better than that of the state of the art.

Development of a Long-Term Bridge Element Performance Model Using Elman Neural Networks

A reliable deterioration model is essential in bridge asset management. Most deterioration modeling requires a large amount of well-distributed condition rating data along with all bridge ages to calculate the probability of condition rating deterioration. This means that the model can only function properly when a full set of data is available. To overcome this shortcoming, an improved artificial intelligence (AI)-based model is presented in this study to effectively predict long-term deterioration of bridge elements. The model has four major components: (1) categorizing bridge element condition ratings; (2) using the neural network-based backward prediction model (BPM) to generate unavailable historical condition ratings for applicable bridge elements; (3) training by an Elman neural network (ENN) for identifying historical deterioration patterns; and (4) using the ENN to predict long-term performance. The model has been tested using bridge inspection records that demonstrate satisfactory results. This study primarily focuses on the establishment of a new methodology to address the research problems identified. A series of case studies, hence, need to follow to ensure the method is appropriately developed and validated.

Prediction of Long-Term Bridge Performance: Integrated Deterioration Approach with Case Studies

AbstractA bridge-deterioration approach is to predict the condition ratings and the deterioration pattern of bridge elements for determining optimal maintenance strategies and estimating future funding requirements. To effectively predict long-term bridge performance, an advanced integrated deterioration approach has been developed that incorporates a time-based model, a state-based model with the Elman neural network (ENN) and a backward prediction model (BPM). The proposed approach involves the categorization of the selected inspection records by bridge components, material types, traffic volume, and the construction era. The primary advantage of such categorization is to group similar components together, thereby identifying the common deterioration patterns. A selection process embedded in the proposed approach offers the ability to automatically select the most appropriate model for predicting future bridge condition ratings. To demonstrate the advantage of the proposed approach in predicting long-te...

Typical deterministic and stochastic bridge deterioration modelling incorporating backward prediction model

A backward prediction model (BPM) has been developed to generate the missing bridge condition ratings in past years, thereby ensuring adequate condition data as required in long-term performance modelling. The BPM establishes a correlation between the known condition ratings and the non-bridge factors, including climate condition, traffic volume and population growth. The aim of this study is to confirm the ability of BPM in improving the prediction accuracy using the existing bridge deterioration models. The prediction accuracies of typical deterministic and stochastic bridge deterioration models are compared when different sets of BPM-generated historical condition ratings are used as input. Comparisons indicate that the prediction error decreases as more historical condition ratings are made available. Notwithstanding the above findings, several limitations of the current deterministic and stochastic bridge deterioration models are also worth noting and further research is essential to improve the prediction accuracy of bridge deterioration modelling.

Minimising uncertainty in long‐term prediction of bridge element

PurposeSuccessful bridge management system (BMS) development requires a reliable bridge deterioration model, which is the most crucial component in a BMS. Historical condition ratings obtained from biennial bridge inspections are a major source for predicting future bridge deterioration in BMSs. However, historical condition ratings are very limited in most bridge agencies, thus posing a major barrier for predicting reliable future bridge performance. The purpose of this paper is to present a preliminary study as part of a long‐term research on the development of a reliable bridge deterioration model using advanced Artificial Intelligence (AI) techniques.Design/methodology/approachThis proposed study aims to develop a reliable deterioration model. The development work consists of two major Stages: stage 1 – generating unavailable bridge element condition rating records using the Backward Prediction Model (BPM). This helps to provide sufficient historical deterioration patterns for each element; and stage 2 – predicting long‐term condition ratings based on the outcome of Stage 1 using time delay neural networks (TDNNs).FindingsLong‐term prediction using proposed method can also be expressed in the same form of inspection records – element quantities of each bridge element can be predicted. The proposed AI‐based deterioration model does not ignore critical failure risks in small number of bridge elements in low condition states (CSs). This implies that the risk in long‐term predictions can be reduced.Originality/valueThe proposed methodology aims to utilise limited bridge inspection records over a short period to predict large datasets spanning over a much longer time period for a reliable, accurate and efficient long‐term bridge deterioration model. Typical uncertainty, due to the limitation of overall condition rating (OCR) method, can be minimised in long‐term predictions using limited inspection records.

Development of an Integrated Method for Probabilistic Bridge-Deterioration Modeling

Probabilistic deterioration models such as state-based and time-based models are only capable of predicting future bridge-condition ratings when a sufficient amount of condition data and reasonable data distribution are available. However, such are usually difficult to acquire from limited bridge-inspection records. As a result, these probabilistic models cannot guarantee reliable long-term prediction for each of the bridge elements concerned. To minimize this shortcoming, this paper proposes an advanced integrated method to construct workable transition probabilities for predicting long-term bridge performance. A selection process within this method automatically chooses a suitable prediction procedure for a given situation in terms of available inspection data. The backward prediction model (BPM) is also incorporated to effectively predict the bridge performance when sufficient inspection data are unavailable. Four different situations in regard to the available inspection data are predefined in this study to demonstrate the capabilities of the proposed integrated method. The outcomes show that the method can help develop an effective prediction model for various situations in terms of the quantity and distribution of available condition-rating data.

Refinement of Backward Prediction Method for Reliable Artificial Intelligence-Based Bridge Deterioration Modelling

A deterioration model is the most critical component of a Bridge Management System (BMS). Artificial Intelligence (AI)-based bridge deterioration model has recently been developed to minimise uncertainties in predicting long-term performance of bridge structural elements. This model contains two components: (1) using Neural Network-based Backward Prediction Model (BPM) to generate unavailable historical condition ratings; and (2) using Time Delay Neural Network (TDNN) to perform long-term performance prediction of bridge structural elements. However new problems have emerged in the process of TDNN prediction. In this study, the BPM-generated condition ratings are used together with the actual overall condition ratings. The incompatibility between the two sets of data produces unreliable prediction outcomes during the TDNN process. This research therefore aims to introduce a new data processing procedure for BPM outcomes, by removing meaningless condition ratings that cause poor training outcomes for long-term prediction using TDNN. Consequently, the outcome of this study can improve accuracy of the current AI-based bridge deterioration model.

Modelling Long-Term Bridge Deterioration at Structural Member Level Using Artificial Intelligence Techniques

Efficient use of public funds for structural integrity of bridge networks requires an effective bridge asset management technology. To achieve this, a reliable deterioration model is essential in any Bridge Management System (BMS). The deterioration rate is calculated based on historical condition ratings obtained from the structural element-level bridge inspections. Although most bridge authorities have previously conducted inspection and maintenance tasks, these past inspection records are incompatible with what are required by a typical BMS as input. Such incompatibility is a major cause for the deficiency of the current BMS outcomes. Artificial Intelligence (AI)-based bridge deterioration model has recently been developed to minimise uncertainties in predicting deterioration of structural bridge members (e.g. beams, piers etc). This model contains two components: (1) using Neural Network-based Backward Prediction Model (BPM) to generate unavailable historical condition ratings; and (2) using Time Delay Neural Network (TDNN) to perform long-term performance prediction of bridge structural members. However new problems have emerged in the process of TDNN prediction. This is because the BPM-generated condition ratings are used together with the actual condition ratings. The incompatibility between the two sets of data produces unreliable prediction outcomes during the TDNN process. This research is thus to develop a new process based on the existing method, thereby overcoming the abovementioned problems. To achieve this, the actual overall condition ratings are replaced by the BPM forward predicted condition ratings. Consequently, the outcome of this study can improve accuracy of long-term bridge deterioration prediction.

Improving the reliability of a Bridge Management System (BMS) using an ANN-based Backward Prediction Model (BPM)

The slow adoption of Bridge Management Systems (BMSs) and its impractical future prediction of the condition rating of bridges are attributed to the inconsistency between BMS inputs and bridge agencies' existing data for a BMS in terms of compatibility and the enormous number of bridge datasets that include historical structural information. Among these, historical bridge element condition ratings are some of the key pieces of information required for bridge asset prioritisation but in most cases only limited data is available. This study addresses the abovementioned difficulties faced by bridge management agencies by using limited historical bridge inspection records to model time-series element-level data. This paper presents an Artificial Neural Network (ANN) based prediction model, called the Backward Prediction Model (BPM), for generating historical bridge condition ratings using limited bridge inspection records. The BPM employs historical non-bridge datasets such as traffic volumes, populations and climates, to establish correlations with existing bridge condition ratings from very limited bridge inspection records. The resulting model predicts the missing historical condition ratings of individual bridge elements. The outcome of this study can contribute to reducing the uncertainty in predicting future bridge condition ratings and so improve the reliability of various BMS analysis outcomes.

Event detection by forward- and backward-prediction, illustrating the analysis for behaviors of black larder beetle Dermestes haemorrhoidalis Küster

There are several studies that estimate the emergent event from the time series of behavior in some organisms. However, they do not focus on the emergent event itself. Our aim is to detect the emergent event from the time series of individual’s behavior, focusing on the transition from predictable machinery behavior to purpose-oriented behavior and vice versa. We recorded the behavior of larvae and adults of black larder beetle. To detect the emergent event of the beetle, we defined a forward- and backward-prediction model. In the forward-prediction, the next state in the time series of behavior was interpreted by precedent behavior. In the backward-prediction, the previous state in the time series of behavior was interpreted by subsequent behavior. The time step with conspicuous peak of the co-intensity of errors in the forward- and backward-prediction was regarded as the timing at which the emergent event occurs. At the same time, the time series of states was estimated to determine whether noise was stationary or non-stationary. The attribute of noise was estimated using the Allan variance. The time series of the larvae’s velocity of walking showed stationary noise. But in the case of the adults, whole time series contained 1/ f noise. And, when time series was divided before and after the detected event, the noise changed from stationary to non-stationary and vice versa. These results suggest that development enables an individual to change the internal mechanism of walk considering the slight change of environment.