The problem addressed in this work considers a washing machine production line, composed of several workstations arranged in a sequential order, and linked together by conveyors. Each individual workstation performs one operation in the product being produced, which can be from different types: processing (e.g., bearing insertion, seal insertion, or pulley screwing), quality control (e.g., visual inspection, vibration analysis, or functional tests inspection), or manual operation (e.g., cable and electronics assembly). The quality control stations (QCSs) are distributed along the production line to verify the product quality conformity. As an example, the functional tests station comprises 6 boxes to perform a fixed plan of functional tests to all washing machines produced in the production line, which lasts 6 minutes for each one. A simplified vision of the production line is illustrated in Figure 16.1.

The objective is the integration of the process and quality control levels, creating feedback control loops to allow the adaptation of production parameters, improving the product quality and the process performance—e.g., reducing the production time—correcting earlier deviations or quality problems, skipping unnecessary tests along the line, and customizing the final product.

An important assumption in this work is to maintain the existing low-level control on the shop floor, which already uses state-of-the-art industrial control based on programmable logic controllers (PLCs) running IEC 61131-3 control programs, and introduces the MAS solution at a higher control level to provide intelligence and adaptation.

16.2.2 Agent-Based Architecture

The designed agent-based system, illustrated in Figure 16.2, comprises a society of autonomous and cooperative agents representing the manufacturing components disposed along the production line. These agents may represent a physical resource (e.g., a processing station or a QCS), or a logic activity (e.g., an order).

Several types of agents were identified, according to the process to control and their specialization, namely Leitão & Rodrigues (2011):

• Product Type Agents (PTAs): representing the catalog of products that can be produced in the production line (one agent for each type of product). These agents contain the process and product knowledge required to produce the product.

• Product Agents (PAs): handling the production of product instances being produced along the production line (one agent for each washing machine). They possess the process plan to produce the product and interact with the agents responsible for process and quality control.

• Resource Agents (RAs): representing the resources disposed along the production line, namely processing stations, QCSs, and operators. Several specializations were considered according to the type of operations performed, namely machine agents (MAs), associated with processing machines, such as welding robots or screwing stations, and quality control agents (QCAs), associated with QCSs.

• Independent Meta Agents (IMAs): acting at a strategic level and taking advantage of their global perspective to provide global optimization to the production system. In contrast to PAs and RAs, which are placed at the operational execution level and are mandatory, IMAs are positioned in a higher strategic level and are not mandatory (i.e., the system can continue working without them, but will lose some optimization).

The GRACE agent-based solution follows the ADACOR principles (Leitão & Restivo, 2006), namely using a Petri nets methodology to specify the system behavior. In this way, the behavior of each individual agent is modeled by using Petri nets formalism (Murata, 1989), taking advantage of the well-founded mathematical theory that allows to design the control system behavior, but also validate the system specifications, supporting the design-implementation path. In this work, the modeling phase is illustrated by modeling the behavior of the RA agent. The Petri nets behavioral model is illustrated in Figure 16.3.

Briefly, after the initialization phase, the agent enters into two sub-behaviors running in parallel, regarding the management of the operation execution (represented by the place p₇) and waiting for monitoring requests or feedback suggestions (p₄).

The operation execution is started when the station detects the arrival of the pallet, represented by the transition t₈ and using a RFID (radio-frequency identification) reader. This activity (i.e., the timed transition t₉) can be expanded into a more refined Petri nets model containing details about the executed functions, as illustrated in Figure 16.4. During the execution of the operation activity, the agent may adjust the operation parameters by applying self-adaptation procedures according to its local knowledge, and triggers the execution of the operation by sending a command to the resource (i.e., the physical equipment or operator). At the end of the processing or testing operation, the gathered data is analyzed and the results are sent to the PAs and IMAs to be used in future adaptation procedures.

In parallel with this behavior, the agent may receive information of the execution of the previous operations, sent by QCAs after executing inspection tests, which will support the improvement of its performance in the future (e.g., by using self-learning procedures in the activity “adapts parameters” represented by the timed transition t₅). Also, the suggestions sent by IMA agents are stored in the local database for posterior usage.

The Petri net model can be validated using a qualitative (structural and behavioral) and quantitative (performance/simulation) analysis, not only to prove that the model is free of errors, but also to test if it performs the desired specifications. As example, analysing the results from the analysis of the behavioral analysis (see (Leitão & Rodrigues, 2012) for more details), it is possible to verify that the model is bounded, safe (e.g., meaning that it is only possible to execute only one operation at each time), reversible, and is absent of deadlocks.

A similar procedure was applied to formally specify the dynamic behavior of the other agents belonging to the system.

16.2.3 Cooperation Patterns and Ontology

The overall control system for the entire production line emerges from the cooperation among the distributed autonomous agents, coordinating their actions according to the agents’ goals. Of particular importance are the cooperation patterns aiming the integration of process and quality control, closing the control loops and implementing self-adaptation procedures. Examples are the dynamic adaptation of the functional tests plan, the customization of the on-board electronic controller, and the generation of warnings in any point of the production line in case the desired quality is not possible to be achieved anymore.

Figure 16.5 illustrates one example of these interaction diagrams, showing the interaction among the agents during the process of adaptation of the functional tests plan. Note that near the end of the production line, a QCS is devoted to perform a set of functional tests to the produced washing machines. The knowledge of the historical production data allows to customize the plan of tests by removing unnecessary tests, adjusting others, or customizing the messages to the operators.

Along the production line, the PA is receiving feedback information related to the results of the execution of the processing and inspection operations, respectively from MAs and QCAs. When the PA arrives at the functional tests station, it executes a self-adaptation procedure to customize the plan of tests for this particular washing machine, correlating the historical production data of the washing machine. In parallel, the PA can request support from IMAs, which, based on their wider perspective, can provide advice on the execution of the self-adaptation procedure.

The interaction among individual agents is crucial in MAS applications, requiring that the agents must understand each other to share knowledge, and use a proper agent communication language and proper knowledge representation. Of special importance is the establishment of a common understanding among the agents, because the exchange of shared knowledge becomes difficult if each agent has its own knowledge structure representation. The solution is to use ontologies (Gruber, 1995) to define a common understanding among distributed entities, defining the vocabulary and the semantics of the knowledge used in the communication between distributed agents.

In this work, an ontology was designed and implemented considering the particularities of the home appliance domain and the integration of process and quality control levels. This ontology formalizes the structure of the knowledge, namely the concepts, the predicates (the relation between the concepts), and the terms (attributes of each concept) (Leitão et al., 2012). The GRACE ontology schema was edited and validated using the Protégé framework (Protégé, 2014), which supports the Web Ontology Language (OWL) (W3C, 2004) and has an easy connection with agent development frameworks, such as JADE.

At the end of the design phase, the MAS application is ready for being implemented and deployed using a proper MAS development framework.

The designed agent-based solution was implemented using the JADE framework (Bellifemine et al., 2007) and following the existing standards in the field, namely the FIPA (Foundation for Intelligent Physical Agents) specifications (FIPA, 2013) (note that JADE is FIPA compliant). Each one of the developed agent types, namely PTAs, PAs, RAs, and IMAs, is a simple Java class that extends the agent class provided by the JADE framework. Each one inherits the basic functionalities from JADE, such as the white and yellow pages services, and the encoding and parsing of ACL messages, and extends them with features that represent the specific behavior of the agent, as detailed in the previous section using the Petri nets models. Each agent is developed, using multi-threaded programming, over JADE’s behavior concept (Bellifemine et al., 2007), allowing the execution of several actions in parallel.

The communication between the distributed agents is asynchronous and done over the Ethernet network using the TCP/IP protocol. The messages exchanged by the agents are encoded using the FIPA-ACL communication language, being their content formatted according to the FIPA-SL0 language. The meaning of the message content is standardized according to the designed GRACE ontology. The integration of the GRACE ontology, edited in Protégé, in the MAS solution was performed by using the OntologyBeanGenerator plug-in, which allows to automatically generate the Java classes from the Protégé tool, following the FIPA specifications. The main generated class represents the vocabulary and main ontological objects (i.e., concepts and predicates) defined in the ontology. The second group of generated Java classes specify the structure and semantics of each ontological object defined in the ontology.

The integration of legacy systems, and particularly the interaction with physical devices hosted in the production line, assumes a critical role when deploying this kind of system into industrial environments. As an example, QCAs are associated with quality control functions, namely the adaptation procedures allowing the improvement of the QCS behavior and consequently the whole system behavior. The interconnection between the QCA and the QCS, illustrated in Figure 16.6, comprises the intelligent part (the agent) and the physical part (the hardware device responsible for the inspection tasks), which in this work also embodies a measurement system developed in LabView™.

Basically, the QCS application receives the data from the QCA, performs the inspection test and sends back the diagnosis result to the QCA. The approach used to perform this data exchange between QCA and QCS relies on opening two TCP/IP sockets: one for the communication from the QCA to the QCS and the other for the communication from the QCS to the QCA. The exchanged messages are described in XML (eXtensible Markup Language) to simplify the common understanding.

Several GUIs (graphical user interfaces) were developed using the Swing toolkit, allowing easy interaction between users and agents.

16.3.2 Installation in the Factory Plant

The installation of the agent-based solution in the Naples factory required the distribution of a plethora of agents by 8 computers disposed along the production line, and interconnected by TCP/IP over an Ethernet network, as illustrated in Figure 16.7.

Each individual agent is customized according to its particularities, namely role, knowledge, skills, and embedded algorithms, by interpreting an XML file during the startup phase.

Particularly, the algorithms embedded in each agent aim to apply proper self-adaptation mechanisms, based on data mining and learning techniques, according to the scope of the agent. The following algorithms were implemented:

• The RAs perform, in a continuous and individual manner, an analysis of the performance index of the processing/inspection station along the time, to detect trends or degradation in its behavior. This allows to detect deviations in advance and to trigger the implementation of corrective measures (e.g., the automatic calibration of the tool wear or the light source, or to request external maintenance intervention) to mitigate the detected deviation.

• The PAs perform, in a continuous and individual manner, an analysis of the evolution of the quality indexes of each washing machine along the production line, being detected deviations to the expected values specified for that model. This allows to detect, in real time and at any point of the production line, when the desired quality is not possible to be achieved anymore and consequently decide to stop the production of the washing machine to save time and money (because scraps can be reduced).

• Near the end of the production line, the PAs apply an algorithm to adapt the plan of functional tests to be performed in every washing machine according to their production historical data, allowing to correlate the data properly. This permits us to save on inspection time and execute more efficient inspection tests.

• The PAs apply, at the end of the production line, a method to customize the parameters of the electronic controller installed in each washing machine to control its behavior, based on the historical production data. This data can be related to the information of the previous operations of the washing machine and the information of other washing machines from the same model. For this purpose, the calculated customized parameters (e.g., the flow rate parameter) are written in the EEPROM (Electrically Erasable Programmable Read Only Memory) of the onboard controller.

• The PTAs, based on the data supplied by PAs at the end of the washing machine production, perform an adaptation of the process plan for each machine model, mainly adapting the parameters of individual operations.

• The IMAs perform, in the background and continuously, an analysis of historical and real-time data, applying data-mining techniques to generate warnings and guidelines to be proposed to PAs and RAs. As an example, IMAs can complement PAs with their wider scope to detect if the desired quality of a washing machine being produced is at risk: a yellow warning is generated if the achievement of the desired quality is at risk, and a red warning is generated when it is no longer possible to achieve the desired quality (even if the remaining operations will be performed with a performance of 100%). Figure 16.8 illustrates a screenshot of the IMA, showing two washing machines marked with a yellow color and one with red.

Other self-adaptation mechanisms were implemented, tested, and successfully operated in the factory plant, namely the adaptation of individual processes based on the data captured, analyzed, and correlated from posterior workstations.

16.4.1 Qualitative Properties

The experimental tests showed that the installed agent-based system reaches several important qualitative properties:

• Modularity and flexibility: the use of the MAS principles simplifies the development of complex computational software applications by dividing the complex problem into simple ones. This allows achieving modularity because the system specifications are built for 4 types of agents (i.e., PTAs, PAs, RAs, and IMAs), each one exhibiting a proper behavior. For the installation in the Naples factory, several instances for each type of agent were created, each one using the same agent codification and inheriting its behavior but customized for its particularities according to an XML file.

• Distribution: due to the distributed architecture provided by the MAS system, the distribution of large-scale systems is easier because agents might be distributed by hardware computational resources according to the application needs (e.g., geographical dependency or processing capabilities). In the installed system, the agents were distributed by several PCs disposed along the production line.

• Runtime and on-the-fly reconfiguration: in such systems, agents can be removed, others can be added, or even some modifications can be performed in the behavior of the agents without the need to stop, re-program, and reinitialize the other components (i.e., the system can continue running without any perturbation). In the installed system, this is illustrated in several ways—for example, shutting down RA agents (e.g., the one associated with the A-Bearing station), adding new RA agents during operation (e.g., those associated with functional tests boxes), or changing the algorithms embedded in the RA associated with the Screwing Upper Counterweight station. These functionalities were successfully tested and validated (note that in a centralized implementation, this feature is not possible).

• Robustness: in case of an individual node breakdown, the system continues running without perturbation (in contrast to the traditional centralized structures where the system collapses). In the installed system, this is illustrated by shutting down some RAs (e.g., those related to the functional tests stations) or IMAs without affecting the global behavior of the system.

• Adaptation: the use of distributed control structures allows the runtime adaptation (i.e., applying local self-adaptive concepts to adapt the system behavior according to unplanned changes). In the installed system, this feature was illustrated by the adaptation of the parameters to execute the processing/inspection operations, to customize the sequence plan of the functional tests, and to customize the flow rate parameter of the onboard controller of each washing machine. Also observed in the installed system is the fast adaptation of the system to the change of washing machine models in the production sequence, and the introduction of new product models in the production line.

• Scalability: a main drawback of MAS solutions is usually associated with the agent middleware (in this case, JADE) and is related to possible delays or congestion in the communication infrastructure due to the growth of the exchanged messages (note that the increase of agents implies an increase of exchanged messages, not in a linear way, but in a more exponential manner). From the achieved experimental results, the increase from several agents to approximately 400 agents running simultaneously and having physical representation, namely connected to washing machines and workstations, some of them exhibiting weighted GUIs, didn’t provoke visible degradation at this level.

• Smooth migration: the use of the MAS technology allows the smooth migration from old technologies/systems to new ones. This is illustrated in the installed system with a consideration of 12 workstations from the entire production line to be controlled by the MAS solution. A slowly and smoothly integration of the remaining workstations along the production line can be performed gradually in time.

16.4.2 Quantitative Impact

The installed agent-based system brings some significant improvements in the factory plant, namely in terms of:

• Production efficiency, e.g., due to the adaptation of the process parameters, the adaptation of the functional tests for each washing machine and the customization of the onboard controller parameters, based on the production history. As an example, with this approach, the functional test time for each washing machine is reduced by approximately 20%, which implies an increase of the flow in the production line, or in alternative the possibility to save one testing box (and consequently save investment and energy).

• Cost reduction, because the earlier identification of defects or quality unconformities in the washing machines being produced can lead to a reduction of the scraps from 5% to 3%. Additionally, stopping, in advance, the production of washing machines that never reach the desired quality, contributes to reduce the waste costs and also save production time.

• Product quality, because most effective quality control procedures are performed along the production line (e.g., using customized testing plans in the functional tests area), and because the onboard controller of each individual washing machine is customized according to the production historical data.