Lina Bertling Tjernberg

An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings

Gearbox has proven to be a major contributor toward downtime in wind turbines. The majority of failures in the gearbox originate from the gearbox bearings. An early indication of possible wear and tear in the gearbox bearings may be used for effective predictive maintenance, thereby reducing the overall cost of maintenance. This paper introduces a self-evolving maintenance scheduler framework for maintenance management of wind turbines. Furthermore, an artificial neural network (ANN)-based condition monitoring approach using data from supervisory control and data acquisition system is proposed. The ANN-based condition monitoring approach is applied to gearbox bearings with real data from onshore wind turbines, rated 2 MW, and located in the south of Sweden. The results demonstrate that the proposed ANN-based condition monitoring approach is capable of indicating severe damage in the components being monitored in advance.

A Model for the Optimization of the Maintenance Support Organization for Offshore Wind Farms

Maintenance of offshore wind power plants is known to be extensive and costly. This paper presents a model for optimizing the maintenance support organization of an offshore wind farm: the location of maintenance accommodation, the number of technicians, the choice of transfer vessels, and the use of a helicopter. The model includes an analysis of a transportation strategy using alternative transportation means, a queuing model of maintenance activities, and an economic model of the maintenance support organization. An example based on a generic 100 wind turbine 5-MW wind farm is used to demonstrate the application of the model. The results show the benefit of the production losses of the different options, which enables the identification of an optimal maintenance support organization based on the reliability, logistic costs, and electricity price. The most cost-efficient maintenance support organization in the case study consists of an offshore accommodation with technicians on service 24 hours a day, 7 days a week. The solution suggests transportation by use of a crew transfer vessel equipped with a motion compensated access system.

A New Approach for Benefit Evaluation of Multiterminal VSC–HVDC Using A Proposed Mixed AC/DC Optimal Power Flow

In this paper, an extended optimal power-flow (OPF) model incorporating a detailed model of a voltage-source converter-based-multiterminal high-voltage direct current system (VSC-MTDC) is proposed, hereafter referred to as the mixed ac/dc OPF (M-OPF) model. A cost-benefit analysis approach using the M-OPF model as the calculation engine is proposed to determine the preferred VSC-MTDC alternative to be installed in an existing ac transmission system. In this approach, the operational benefits of VSC-MTDC systems are evaluated against their investment costs to derive the benefit-to-cost ratios (BCR) which reflect the cost-effectiveness of the alternatives. A case study has been carried out using a modified Nordic 32-bus system. The results of the study show that VSC-MTDC systems might lead to a reduction in total operation cost, and the reduction of the total system transmission loss depends to a large extent on the VSC-MTDC configuration. The results from sensitivity analyses show that if the VSC loss could be reduced to a third of the original level, the total benefit from the system would be increased by about 70%. A suggestion for the placement and configuration of a VSC-MTDC system is made based on calculated BCRs.

On the analysis of the dc dynamics of multi-terminal VSC-HVDC systems using small signal modeling

In this paper, an analysis of the dc dynamics of multiterminal VSC-HVDC systems using the small signal modeling method is presented. Usually, the VSC controllers are designed under the consideration that they operate independently of each other. However, the possible interactions among them and the dc grid should be studied, especially in multi-terminal topologies. In this paper, three VSC-HVDC systems are modeled and, after linearization, the eigenvalues of the system are calculated for different loading conditions. The results from this analysis are compared to those obtained from more detailed models using PSCAD. It is shown that the operating point, the gains of the direct-voltage controller and the cable dynamics have an impact on the system performance.

Effects of plug-in electric vehicle charge scheduling on the day-ahead electricity market price

With the advent of plug-in electric vehicles (EV), it becomes increasingly important to study the impact of charge scheduling of a large number of EVs on the day-ahead electricity market price. In this paper, two scheduling models are proposed-joint scheduling model and aggregator scheduling model. They are used to study the effects of scheduling of EV charging on the day-ahead market price of electricity at various penetration levels of the EVs. Results from studies on an IEEE 30-bus test system show that, at lower penetration of EVs, a simple scheduling method using fixed-period charging during low demand periods can be used, without a large increase in market price. But at higher penetration levels, the opposite holds true, requiring advanced scheduling methods such as proposed in this paper. Between the two, joint scheduling model results in a lower increase in electricity price and is further tested on a simplified Nordic day-ahead market model. An overall conclusion is that the Nordic day-ahead market can accommodate large penetration of EVs without a significant increase in market price.

An approach for self evolving neural network based algorithm for fault prognosis in wind turbine

In recent years Supervisory Control and Data Acquisition (SCADA) system has been used to monitor the condition of wind turbine components. SCADA being an integral part of wind turbines comes at no extra cost and measures an array of signals. This paper proposes to use artificial neural networks (ANN) algorithm for analysis of SCADA data for condition monitoring of components. The first step to build an ANN model is to create the training data set. Here an automated process to decide the training data set has been presented. The approach reduces the number of samples in the training data set compared to the conventional method of hand picking the data set. Further the approach describes how the ANN model could be kept in tune with the changes in the operating conditions of the wind turbine by updating the ANN model. The fault prognosis obtained from the model can be used to optimize the maintenance scheduling activity.

Remote switching of multiple smart meters and steps to check the effect on the grid's power quality

The traditional electrical grid is transitioning into the Smart Grid (SG) and the introduction of Smart Meter (SM) is a first stage towards Smart Grid. The SM can offer new functionalities such as remote reading, automatic event reporting and the possibility of remote switching by the Distribution System Operator (DSO). The DSO can send remote signal to the breaker of the SM to disconnect or connect customers. This could be used when customers are moving or do not have a contract. DSO is currently applying this technique regularly for customers but one by one which do not affect the grids power quality remarkably. But this technique has never been applied for multiple customers at a time in a single neighborhood and the possible effect on the grids power quality is still unknown. This condition is studied in this paper through test scenarios which have already been planned to test. This paper presents necessary steps of remote SM switching for a large number of customers. Power quality standards and steps for measuring power quality during the tests are outlined. Possible risks of the test as well as the probability of occurring risk and also the consequences of those risks are studied in this paper.

Self Evolving Neural Network Based Algorithm for Fault Prognosis in Wind Turbines : A Case Study

Asset management of wind turbines has gained increased importance in recent years. High maintenance cost and longer downtimes of wind turbines have led to research in methods to optimize maintenance activities. Condition monitoring systems have proven to be a useful tool towards aiding maintenance management of wind turbines. Methods using Supervisory Control and Data Acquisition (SCADA) system along with artificial intelligence (AI) methods have been developed to monitor the condition of wind turbine components. Various researchers have presented different artificial neural network (ANN) based models for condition monitoring of components in a wind turbine. This paper presents an application of the approach to decide and update the training data set needed to create an accurate ANN model. A case study with SCADA data from a real wind turbine has been presented. The results show that due to a major maintenance activity, like replacement of component, the ANN model has to be re-trained. The results show that application of the proposed approach makes it possible to update and re-train the ANN model.

Cost efficient maintenance strategies for wind power systems using LCC

Maintenance costs for wind power plants are a significant part of the total life cycle cost, especially for offshore wind power plants, situated at remote sites. In order to decrease the cost of maintenance, monitoring systems have been used to estimate the condition of critical components in wind turbines. This paper proposes Life Cycle Cost analysis (LCC) approach for maintenance management of wind turbines. The LCC approach for maintenance management presented in this paper is an extension on previous work by J. Nilsson and L. Bertling, where a comparison has been made with this previous work and the same is extended with new data and models. Case studies are presented based on data from three different wind turbines rated 3 and 6MW. Three different scenarios have been studied and the effect of condition monitoring system (CMS) has been analysed. For any chosen value the CMS proves to be a profitable option.

Cost-benefit analysis of a Multi-Terminal VSCHVDC system using a proposed Mixed ac/dc Optimal Power Flow

This paper presents a cost-benefit analysis of the Multi-Terminal Voltage Source Converter based HVDC (VSC-MTDC) using a proposed Mixed ac/dc Optimal Power Flow (M-OPF). In this analysis, the operational benefits of VSC-MTDC systems are evaluated and compared with their corresponding investment costs to derive the benefit-to-cost ratios (BCR) for selected candidates of VSC-MTDC systems in the transmission expansion planning. Case studies using a modified Nordic 32-bus system have been carried out. The results have shown that the embedded VSC-MTDC system might bring out a reduction in total operation cost depending on its configuration and location. The proposed M-OPF model incorporates a detailed model of a VSC-MTDC, and is suitable to the operation and planning analysis of the ac transmission grid with the embedded VSC-MTDC system.