Autonomous Inspection for Industrial Assets

Autonomous Vehicle Inspection Platform

3.1.1 Autonomous Inspection and Maintenance

Remotely controlled and autonomous inspection and maintenance devices are used in different sectors for different purposes. For instance, the military uses unmanned aerial vehicles (UAVs) for inspection, and offshore oil and gas industries use underwater robots for maintenance.

The following presents autonomous or remotely controlled devices used in the inspection and maintenance of linear assets and explains their purpose (Seneviratne, Ciani, Catelani, & Galar, 2018):

  • 1. Railways
  • • Identification of obstacles and track irregularities using drones.
  • • Inspection of rail profile, cracks, irregularities, and missing components using an autonomous robot vehicle.
  • • Replacement of missing components, crack welding, etc. using an autonomous maintenance robot vehicle.
  • 2. Roads
  • • Identification of obstacles and damage using drones.
  • • Inspection of roadway, road alignment, road profile etc. using an autonomous robot vehicle.
  • • Repair of roadway (placement of asphalt/concrete), repair of pavement, maintenance of embankments, maintenance and cleaning of ditches, etc. using autonomous maintenance robot vehicle.
  • 3. Canals and Waterways
  • • Identification of debris, obstacles, and damages for the infrastructure through drones.
  • • Inspection of waterway, sidewalls, berm, gates, etc. using an autonomous robot vehicle, both land and water.
  • • Removal of debris and obstacles, repair of sidewalls, berm, etc. using an autonomous maintenance robot vehicle (both land and water).
  • 4. Power Lines
  • • Identification/inspection of power line damage, insulator defects, and tower damage using drones.
  • • Cleaning of insulators and repair of line damage using an autonomous drone robot vehicle.
  • Smarter Drones

UAVs have attractive features, such as flexibility, adaptability, and a range of payloads. Sensors include high-resolution digital and infrared cameras, light detection and ranging (LiDAR), geographic information systems (GIS), sonar sensors, and ultrasonic sensors; most can be adapted to a UAV platform. A close-up photograph of a structure on an offshore platform, difficult for inspectors to reach, will show maintenance personnel how much corrosion/erosion has built up and suggest the situation of welds and other structural elements.

Drones equipped with forward-looking infrared (FLIR) or ultraviolet sensors can detect hot spots or corona discharge on conductors and insulators, signaling a potential defect or weakness in the component. LiDAR can be integrated with drones to survey a proposed right-of-way, show the infrastructure situation when seismic conditions are changing, or monitor the encroachment of vegetation. There are many more potential uses, and the examples are only a small fraction of the possible applications.

At present, UAVs are remotely operated; the next phase of UAV technology will be to deploy “smarter” machines that can fly autonomously. This technology will allow UAVs to sense and avoid other objects in their path, recognize features or components through various sensors (including cameras) using complex software algorithms such as image processing algorithms, and achieve situational awareness. This advanced technology will foster calculated decision-making, such as initiating focused inspections, issuing work orders for repairs, and starting maintenance work with the same robot or another autonomous robot integrated in the system.

In any industry, safety and cost are two of the most significant drivers of operation and maintenance and, thus, are always of high importance. Many industrial work areas are hazardous, so measures must be taken to secure the safety of users. Health safety and environmental (HSE) indicators can mitigate the risks, but the situation remains challenging when new technologies are introduced.

For instance, working on energized high-voltage transmission lines, sometimes hundreds of feet up in the air, can make the consequences of a mistake deadly. According to the US Bureau of Labor Statistics, 15 linemen were fatally injured in 2013 as a result of “exposure to harmful substances or environments.”

Unmanned systems have the potential to greatly reduce the amount of risk exposure of the operational workforce. The safety of personnel involved in risky operational tasks can be ensured with this new technology (Seneviratne, Ciani, Catelani, & Galar, 2018). Autonomous Robots

Many different robots have been developed to handle various situations on linear assets, buildings, ship hulls, or other human-made structures. However, most are limited to special situations or applications. To execute the desired tasks, autonomous robots, as well as all other technical systems, have to fulfil certain requirements. The requirements and their importance and focus depend on the individual application or tasks, but we can formulate a general set of requirements as follows (Seneviratne, Ciani, Catelani, & Galar, 2018):

  • 1. Velocity and mobility: Vehicle speed and dynamics (ability to move) are two main aspects of robot design. Depending on the dimension of the linear asset, it may have to reach a relatively high velocity for sufficiently fast navigation between inspection areas or similar points of action. Another requirement is related to the desired manipulation and positioning capabilities of the system. This includes the precision of its locomotion and trajectory, since some inspection sensors need to be moved in a smooth and continuous way over the surface. The robot may also need to move sideways or turn 360° to position sensors or tools. The system dynamics should be able to handle the various terrains and reach all positions of the asset.
  • 2. Payload: Depending on the application, the system must be able to carry payloads of different weights. For example, in the case of steel piping, a payload of 5 kg or more is mandatory to carry ultrasonic inspection sensors. This requires a much bigger robot than a system which just needs a simple camera with a weight of several hundred grams. In other words, the dimension, adhesion, and motion components of the robot need to be adapted for the application.
  • 3. Reliability and safety: A further important nonfunctional aspect is the robustness of the system.

If the autonomous robot fails frequently during one inspection task, it is not usable in practice.

The requirements of reliability and safety include robust hardware, optimal controllers, and methods to detect and handle hazardous situations and to recover from them.

  • 4. Usability: Velocity, maneuverability, and the capability of carrying a certain payload are important, but they are only the basis of the general operability of the system. To bring a robotic system into application, it has to be more powerful, more efficient, and less dangerous than common approaches, for example, in terms of inspection devices. This includes aspects of maintainability and a broad range of other tasks. Therefore, it must be able to carry different payloads (e.g., inspection sensors or tools) depending on the desired task, parts need to be easily replaceable, and the operation must be faster and less complicated than existing approaches. Aspects such as energy consumption, weight, or dimension of the system can be important as well. Based on the individual task, a robot developer has to decide which requirements have to be fulfilled and select a suitable locomotion and attraction principle.
  • Autonomous Inspections

Traditionally, electric power suppliers have inspected power lines for encroaching trees, damage to structures, and deterioration of insulators by having employees traverse the lines on foot and climb the poles. This is time consuming and arduous, with a considerable element of risk. Now the task is often carried out by crews in manned helicopters using binoculars and thermal imagers to detect the breakdown of insulators. This too is not without hazard.

Recently, trials have tested the use of UAVs to inspect power lines, with considerable success. UAVs offer lower costs, do not create a hazard for aircrews, can operate in more adverse weather conditions, and are less obtrusive to neighboring communities or animals. Hover flight is essential for the inspection task. The UAV carries an electro-optic and thermal imaging payload, the data from which are available in real time to the operator and recorded. The UAV is automatically guided along the power line within a limited volume of airspace close to the lines using a distance measuring device. An important requirement of UAVs deployed in this role is that they must be flown close to high-voltage power lines, i.e., within their electromagnetic fields, without adverse effects on their control system or payload performance.

Oil and gas supplying companies are interested in UAVs for inspection and exploration purposes. UAVs offer a less expensive means of surveying the land where pipelines are installed. They also offer a means of patrolling the pipes to look for disruptions or leaks caused by accidents such as landslides or lightning strikes or for damage caused by vehicles or falling trees. In certain areas of the world, sabotage is not uncommon, so they look for this as well.

UAVs could be used in road and railway inspections and for certain maintenance purposes by traffic infrastructure agencies. In addition to being less expensive to operate than manned aircraft, they are more covert and will avoid distracting drivers.

Irrigation projects, river authorities, and water boards could use UAVs to monitor canals, waterways, pipelines, and rivers. UAVs could be used to monitor reservoirs for pollution or damage or to monitor pipelines for security purposes.

However, the use of UAVs in many of these cases will depend on the approval of the relevant regulatory authorities (Seneviratne, Ciani, Catelani, & Galar, 2018). Autonomous Maintenance

Autonomous maintenance activities are mainly associated with robotic applications. Various industries, especially those dealing with high risk activities, are already using remotely operated robots for maintenance activities, for instance, marine repairs (repairs of ships offshore, offshore oil and gas platform maintenance, deep sea pipeline, and cable maintenance), oil refinery repairs, nuclear power plant repairs, etc. At the moment, because of the limited development of robots for maintenance purposes, complete maintenance cannot be performed in the abovementioned industries (Seneviratne, Ciani, Catelani, & Galar, 2018). Conceptual Framework

With autonomous inspection devices and autonomous maintenance robots, a dynamic asset maintenance and management plan can be deployed with the help of big data technologies and available analytics. Right now, industries are using the devices separately for inspection and maintenance; the two have not yet been integrated. By integrating the two operations with the available Information and Communication Technologies (ICT), the asset maintenance and management process can be automated. The possible architecture for the ICT framework is shown in Figure 3.1. Moreover, the incorporation of artificial intelligence (AI) tools can make the whole process dynamic and autonomous (Seneviratne, Ciani, Catelani, & Galar, 2018).

Since linear assets have a common behavior and architecture across their length, the implementation of the concept may reduce costs, ensuring more effective operation and maintenance. The proposed framework is shown in Figure 3.2 (Seneviratne, Ciani, Catelani, & Galar, 2018).

  • 3.1.2 Maintenance as a Combination of Intelligent IT Systems and Strategies
  • Introduction

Industries are searching for technological solutions to improve their performance in business. The growth of ICT has helped organizations in using advanced solutions, such as eMaintenance, to manage their processes effectively, in this case their maintenance activities. eMaintenance can be seen as a tool for integrating companies’ production and maintenance operations through information technological solutions. Due to the rapid technological development, the research topic of eMaintenance is changing and redirecting its focal point constantly. This section identifies and describes the key components of eMaintenance.

A number of academic reviews on eMaintenance describing the development and implementation of eMaintenance systems have been published over the past decade. For example, the basic ideas of eMaintenance have been presented, and Maintenance Management (MM) has been described as composed of the pillar of IT, Maintenance Engineering (ME), and relationship management. Another classification is that MM consists of optimization, models, maintenance techniques, scheduling, and IT. eMaintenance

Proposed ICT infrastructure for the autonomous inspection and maintenance of linear assets (Seneviratne et ah, 2018)

FIGURE 3.1 Proposed ICT infrastructure for the autonomous inspection and maintenance of linear assets (Seneviratne et ah, 2018).

Proposed conceptual framework for autonomous inspection and maintenance of linear assets (Seneviratne et al„ 2018)

FIGURE 3.2 Proposed conceptual framework for autonomous inspection and maintenance of linear assets (Seneviratne et al„ 2018).

defines the strategic vision, organization, service and data architecture, and IT infrastructure. However, a number of joint academic and industrial papers providing an updated view on eMaintenance systems or parts of them within the context of industrial applications have been published recently (Metso, Baglee, & Marttonen-Arola, 2018). eMaintenance Concept

Karim et al., 2010, one of the first articles to explain eMaintenance examined a distributed intelligent and integrated system. This system integrated the control, maintenance, and technical management activities of a shop-floor organization with an intelligent system, now known as eMaintenance. eMaintenance allows the integration of production and maintenance operation systems. The importance of the maintenance function should be acknowledged, as it can impact the production operations and business process by ensuring system safety and by decreasing the costs of operations during the lifetime of systems.

eMaintenance as a system should be connected to other systems to assist in the collection, analysis, and definition of maintenance tasks which take advantage of the idea of “right data to right person at right time.” The “strength” of eMaintenance is based on various data sources, and it utilizes different tools and techniques (Lee, Ni, Djurdjanovic, Qiu, & Liao, 2006).

eMaintenance can be described as an “intelligent maintenance center” because it collects data from a number of different sources and provides relevant data to be used in the development of maintenance tasks. It supports the use of data collection and transfer to remote use through a number of Internet-enabled technologies. eMaintenance technologies can be used with other maintenance strategies to share and exchange information, such as elntelligence. elntelligence is a term that covers eMaintenance but also other data and ICT-related aspects of business (Metso, Baglee, & Marttonen-Arola, 2018). Dam

The aim of eMaintenance is to connect maintenance and production data with an intelligent system to analyze a number of manufacturing parameters. In effect, it creates a “smart factory” environment. However, to be useful, eMaintenance solutions need to be integrated with other information systems which allow transferring data between different environments. It is important that all systems in the eMaintenance network can exchange information in an efficient and usable way. This is depicted in Figure 3.3 (Metso, Baglee, & Marttonen-Arola, 2018).

Figure 3.3 shows that eMaintenance includes monitoring, collection, recording, and distribution of real-time data and decision/performance support information. eMaintenance improves the performance of the maintenance process through effective data collection and distribution. Data are converted into information and generated to knowledge that is valuable in the decision-making process. Computerized maintenance management systems (CMMS) allow users to use maintenance data. These systems often contain work order control, labor management, equipment management, material control and purchase, and performance report modules. Enterprise resource planning (ERP) systems have been used in MM to collect, store, and analyze manufacturing data. However, eMaintenance is a much wider concept than the relatively narrow modules suggested in ERPs. eMaintenance solutions must have access to different data sources. The integration of different systems can be challenging. Data quality must be taken into consideration, and interconnectivity is also important for eMaintenance solutions, because data are transferred between heterogeneous environments. All systems must be able to interact in an efficient and usable way in eMaintenance solutions.

Traditional “fail and fix” maintenance practices are changing into a perspective of “predict and prevent.” eMaintenance methodology has emerged due to the increase in Internet technologies, faster data transfer, and specific data analytics to collect and analyze large amounts of data quickly and effectively. Sensors enable the collection and delivery of data about the status of machines. These data are rarely used to support a continuous information flow throughout the entire maintenance process, because the infrastructures do not support data delivery, management, and analysis. A possible answer is to include smart machines in a remotely monitored network, where data are modeled and analyzed with embedded systems; this should allow a shift from predictive maintenance to intelligent prognostics, a systematic approach to monitor and predict potential machine failures continuously and to synchronize maintenance actions with production operation, maintenance resources, and spare parts.

However, data quality from different sources can be inadequate to support maintenance actions. Another issue is technical problems in transferring data from one system to another system. Relevant data are needed, and real-time data and data analysis can improve maintenance actions, but the existing body of knowledge has not yet succeeded in finding optimal solutions to these challenges (Metso, Baglee, & Marttonen-Arola, 2018).

eMaintenance data access (Wandt et al., 2012)

FIGURE 3.3 eMaintenance data access (Wandt et al., 2012). Advantages and Challenges of eMaintenance

The advantages and challenges of eMaintenance are presented in Table 3.1. It should be noted that the same main items can be seen as both advantages and challenges for eMaintenance; for example, in theme 3, inspection and monitoring are difficult if real-time, remote, and distributed monitoring and analysis devices have not been developed (Metso, Baglee, & Marttonen-Arola, 2018).

eMaintenance offers possibilities to improve the development of new ways of implementing maintenance. Maintenance expert centers can be organized easily because data can be shared easily over the Internet. Experts can log into the systems remotely and give their instructions to maintenance employees. Maintenance support can be improved, and real-time data should always be available. Maintenance documentation should always be updated and available because the users could log in to the systems anywhere with any equipment. This is naturally an issue of security because eMaintenance is used over the Internet, and the same security risks exist as in other Internet-based solutions. Transparency and access to maintenance information and services across the maintenance operation chain have also been seen as a benefit in eMaintenance.

The positive impact of eMaintenance can be divided into two levels. The first is the “maintenance micro-level,” where eMaintenance serves technicians, mechanics, and support engineers as a support to execute maintenance tasks. eMaintenance reduces the number of interfaces to information sources, improves fault diagnosis and knowledge sharing, and automates the procedures of technical administration. The second level is the “maintenance macro-level,” where eMaintenance supports managerial maintenance planning, preparation, and assessment. It enables information-driven maintenance and


Advantages and Challenges of eMaintenance

Potential Improvements


Theme 1: Developing New Maintenance Types and Strategies

Remote maintenance operations and decision-making; logging in anywhere and on any devices, manpower on the customer’s site can be reduced, the use of expertise is easy, new features can be added

Remote maintenance; security and reliability over the Internet, human resource training, maintenance agreements

Business process integration and cooperative/collaborative maintenance; easy to design and synchronize maintenance with production, maximizing process throughput

Business process integration and cooperative/collaborative maintenance; data transform mechanism, communication, data protocols, safe network; the maintenance processes must be stable and capable

Fast online maintenance; real-time remote monitoring, alerts, high-rate communication to experts, maintenance support system

Predictive maintenance; prognostics and health management systems

Predictive maintenance; difficult to integrate different techniques

Theme 2: Improving Maintenance Support and Tools

Fault/failure analysis; development in sensors, signal processing, ICT, etc.

Maintenance documentation; easy to fill out forms, remove bottlenecks between the plant floor and business system

Maintenance documentation; need to collect, record, and store information from different systems, multitasking, and multiuser operating environment

Theme 3: Improving the Maintenance Activities

Fault diagnosis/localization; e-diagnosis offers online fault diagnosis for experts

Inspection/monitoring; problems with distributed monitoring

Repair/rebuilding; reducing downtimes by direct interaction

Modification/improvement—Knowledge capitalization and management; how to realize the knowledge-based operation and maintenance of plants

Source: Modified from Crespo-Marquez, and lung (2008), Muller, Crespo-Marquez, and lung (2008).

support processes. In, for example, aviation maintenance, eMaintenance implementation enables a more efficient use of digital product information and design data over the whole life cycle (Metso, Baglee, & Marttonen-Arola, 2018).

< Prev   CONTENTS   Source   Next >