Efficient and effective maintenance is crucial for all kind of industries. In the case of capital intensive investment industries such as petrochemicals, steel industry or power generation plants it is even more relevant and has an important impact in the operation costs during the long life cycle of their production means.
Besides the traditional maintenance problems of any industrial installation, this kind of facilities presents other additional challenging characteristics:
- Huge number of elements to inspect. Pipes, valves, switches, pumps, vessels, motors, vibrating machinery, chillers, ovens, etc.
- Multiple inspection technologies to be used: visual inspection (leaks, corrosion, paint condition, insulation condition, misalignments,...), thickness measurement (corrosion) mainly using Ultrasonic tests, vibration measurement, ultrasonic test, radiography, thermography, eddy current, noise analysis, gas sensors, etc.
- Extensive production facilities. This kind of plants spreads out for thousands of square meters, conducting pipes account for several tenths of kilometres and it is not infrequent to find several chimneys of high height.
- Risky working conditions for maintenance personnel due to the presence of hazardous materials (in case of inhalation or contact), high voltage elements and wires, need to work at height, etc.
The (almost infinite) range of maintenance activities in industry is not affordable individually due to its diversity, the specific features of each industry and the different maintenance policies in the companies.
However, MAINBOT has identified and proposes grouping some of the most relevant activities and provide a common solution to them. The selection criterion has been the relevance of the task in terms of economical impact, the general application and the feasibility to achieve a solution in the timeframe of the project.
The industrial objectives are summarized according to the type of operation and the nature of the equipment to inspect/maintain:
- To provide a means to help measuring several physical parameters in multiple points by autonomous robots able to navigate and climb structures, handling sensors or special non destructive testing equipment.
- To develop a surveillance robotic system able to detect leakages of fluids using vision system in the range of thermal and visible or/and gas sensors.
- Robotized non destructive testing of surface deterioration of equipment in extensive plants and detection of broken elements.
- Robotized non destructive testing of internal deterioration in pipes and walls of tanks, chimneys etc., from outside the element to be inspected.
- Ground robots able to navigate in large industrial plants handling sensors and manipulator for inspection and maintenance, and overcoming obstacles and terrain conditions.
- Robots able to climb vertical (or almost) industrial equipment handling sensors and manipulator for inspection and maintenance.
These industrial objectives will be validated in a real industrial scenario, a thermal solar plant that has been chosen for two main reasons: Representativeness and Impact.
To answer to the challenges described in the previous section, the project has identified a set of scientific and technological objectives in the following areas:
- Autonomous ground navigation: Robots must be able to autonomously navigate in a rather structured environment in a safe way for human beings, for the facilities and safeguarding themselves. To achieve such a degree of autonomy it is necessary to address some challenging topics:
- Smart combination of topological and metric maps. The large scale areas the robot should move in, introduces an additional complexity to the problem. Managing metric maps for such huge areas is not computationally affordable; however topological reasoning is not accurate enough for the requirements of maintenance applications. Therefore MAINBOT proposes a smart combination of both approaches.
- Local navigation strategies adapted to inspection and maintenance activities. In a traditional navigational problem, the robot controller has to plan the path to be followed based on the objective of achieving a target position in a map. However in the maintenance scenario the task itself (inspection) has to be used to close the navigational control loop. For instance, when inspecting a pipe using an ultrasonic sensor, inspecting the surface of a reflecting mirror, or any other inspection application, to obtain good quality sensor readings it is necessary the robot moved following specific patterns (angle, distance, velocity,…).
- Accurate localization in extensive areas. DGPS technology combined with maps provides a coarse localization mechanism. However, as the robot needs to operate in a deterministic distance of the element to be inspected (especially true for some inspection technologies), we need to introduce additional localization mechanisms that provide a more accurate position of the robot. The approach will be to combine widely used laser scanners with visual based localization mechanism that use natural or/and artificial landmarks in the surroundings to minimize positioning error.
- Autonomous climbing robots: Climbing robots have to face the following challenging requisites to navigate in vertical structures:
- Robots have to reach the entire surface of the vertical structures.
- Self planning of paths depending of simple geometrically description of the structure and information from environmental sensors.
- Orientation based on landmarks.
- Mobile manipulation for maintenance and inspection activities in order to assist in cleaning or replacing parts, to manipulate inspection devices, to inspect highly occluded components, etc. The challenge is twofold:
- Real time coordination of manipulator´s end-effector and mobile platform based on sensor information and inspection task strategy.
- Safe manipulation of inspection devices and actuators that require physical contact with the inspected part/infrastructure.
- Sensor fusion: The robot must be equipped with highly reliable sensors to perceive its surroundings, not only for navigation but for inspection and manipulation. The use of robots for maintenance allows using multiple sensing technologies at the same time. However to exploit the information provided by each of these technologies in a more efficient way we propose introducing the concept of sensor fusion. We will introduce a smart engine to dynamically adapt the fusion process according to the working conditions and environmental parameters (lighting conditions, velocity, etc.); i.e. context aware sensor fusion.
A high level task planner will be developed in order to plan robot actions for autonomous inspection and maintenance missions. This task planner will resolve specified tasks (defined by maintenance operators through Human Robot interface) and plan the resulting motions and sub-tasks for the robot. The plan generated will contain a sequence of actions (e.g. movement, picking up items, manipulating items) with assigned resources (e.g. sensors, gripper). A hierarchical planning approach will be considered, where a high level task is decomposed in a sequence of subtasks that will be managed by second level planners (manipulator, mobile base, inspection system) to produce primitive actions (i.e. non decomposable).
The scientific and technological objectives of MAINBOT are addressed through 7 work packages to be developed during 36 months.
A summary description of the WP activities is as follows:
WP1 Project management (TEKNIKER)
The aim of this WP is ensuring the project meets its goals and overall objectives. It includes and implements all management activities.
WP2 User requirements and scenario definition [TORRESOL]
Deep analysis of requirements and definition of the real working scenario for validation, including the definition of metrics. The requirement definition will be based not only at task level, but mainly in terms of Reliability, Availability, Maintainability and Safety (RAMS) of the final solutions.
WP3 Basic technologies for mobile robotics in maintenance [IFF]
The WP is devoted to solving the technical challenges in terms of robot localization, navigation and sensor based manipulation. As well as the design of needed changes on the existing platforms that will be taken as starting point. It also includes the general system architecture and interoperation mechanism design.
WP4 Mobile robots for plant inspection and maintenance development [ROBOSOFT]
The aim of the project is not to develop robots from scratch, but to incorporate the needed changes to existing platforms (either on hardware and software) to make it possible their use in testing and maintenance. In this WP those modifications identified in the previous WP will be implemented.
WP5 Automatic Robotic based inspection and maintenance [TECNATOM]
Non-destructive testing systems have to be adapted in order to be possible autonomous robot based operation. It includes features like correlating real-time inspection results with mobile manipulator position (for later localization and repair), adapting velocity to inspection process, etc. However the main requirement is automatic data analysis and smart context aware fusion of different inspection techniques.
WP6 Scenario development and validation. Industrial demonstrator [TEKNIKER]
Mobile robots and manipulators programming and control integration. It includes creating a common framework that receives as input High level maintenance tasks, human commands and produces robot task plans, schedules them and provides the results of inspection/maintenance to plant level control systems.
In this WP all validation procedures are carried out according to the definition in WP2. The result is a set of robots working in a real industrial plant, performing inspection and maintenance activities. The demonstrator will be build up in one thermal solar power plant in the south of Spain.
WP7 Project Dissemination and exploitation(IFF)
The aim of this WP is to guarantee an effective dissemination of the project results, as well as the proper use and exploitation of the project results in accordance with the Consortium Agreement.