TECHNICAL FIELD

Embodiments presented herein relate in general to detection of failure of industrial equipment in a process environment and in particular to a mobile communications device for detection of failure of industrial equipment in a process environment.

BACKGROUND

Process control is extensively used in industry and enables mass production of continuous processes such as oil refining, paper manufacturing, chemicals, power plants and many other industries. Process control enables automation, with which a small staff of operating personnel can operate a complex process from a central control room.

Today's industry strives to improve performance and profitability while maintaining and improving safety. The challenges include unremitting pressure to reduce costs, shorter product lifecycles, maximise the use of the asset base and plant availability; and pressure to reduce spurious alarms.

It is important that the process control system, for example, maintains a desired state of operation; that the industrial equipment monitored and controlled by the process control system is operating at a specific

temperature or airflow, that the industrial site comprising the industrial equipment is monitored so that no unauthorised access occurs and so on. However, occasionally the desired state is not maintained, e.g. in case of failure in a temperature or airflow regulating component, or in case of improper handling, or triggering of the access control system. When the desired state is not maintained an alarm is usually sent to, or generated by, a computer server that monitors the process control system. The alarm must in most cases be attended to by maintenance engineers in order to overcome the reason for the alarm. However, once a desired state has been identified by the computer server, the event causing the alarm may already have caused damages to the industrial equipment, the site itself, or any personnel located at the site of the industrial equipment.

User studies conducted in process plants have indicated that plant

maintenance engineers are using smell to identify industrial equipment in need for service. Some industrial equipment, e.g., engines, may, in

comparison to normal wear, even smell differently when they reach high levels of wear.

Experienced maintenance engineers may therefore be able use smell to detect industrial equipment that is in need of service before the industrial equipment has any major breakdowns.

However, it typically takes lots of training and experience to be able to use the human smell sensory organ to detect possible problems in industrial equipment before a problem affects the process. Normally it is only the most experienced maintenance engineers that are able to detect defects in the industrial equipment by use of smell.

Additionally, human beings cannot store smell readings from different scans and compare them. Therefore maintenance engineers have to judge every smell subjectively. There is hence no data to back up their conclusions.

Further, maintenance engineers can catch a cold, leaving them unable to use their sense of smell for a long period of time.

The human smell sensory organ does not work equally well for every human being. Some maintenance engineers could, for example, be missing important information because of their poor sense of smell.

Hence, there is a need for an improved detection of failure of industrial equipment.

SUMMARY

An object of embodiments herein is to provide improved detection of failure of industrial equipment. The inventors of the enclosed embodiments have through a combination of practical experimentation and theoretical derivation discovered that hardware smell sensors may be used to detect the state of industrial equipment. By using handheld devices with smell sensor-hardware it may be possible to perform automated readings in the process plant as the

maintenance engineers move around in the process environment. A

particular object is therefore to provide improved detection of failure of industrial equipment using a handheld device, such as a mobile

communications device, comprising a smell sensor. According to a first aspect there is presented a mobile communications device for detection of failure of industrial equipment in a process environment. The mobile communications device comprises a smell sensor. The smell sensor is arranged to detect an airborne chemical compound and to transduce the airborne chemical compound into an electrical signal representing smell data. The mobile communications device further comprises a processing unit. The processing unit is arranged to classify the smell data into at least one smell class from a group of smell classes, each one of the smell classes in the group of smell classes being associated with a malfunction of a part of the industrial equipment, the processing unit thereby being arranged to detect at least one upcoming malfunction in the process environment. The processing unit is further being arranged to, based on the detected at least one upcoming malfunction, identify a control action in the process environment for control of said part the industrial equipment so as to mitigate or stop said at least one upcoming malfunction. The processing unit is further being arranged to provide an indicator of said at least one upcoming malfunction and/or said control action to a user interface of the mobile communications device.

Advantageously the mobile communications device enables avoidance of certain unexpected breakdowns. In some cases it will even be possible to detect and repair malfunctions before they become critical to the process. Therefore production will increase. Advantageously the mobile communications device enables maintenance engineers to rely on technology rather than on their own smell sensory organ. This will make their jobs easier as they can take maintenance related decisions based on examined data instead of having to make their own subjective decision. This will most likely decrease production downtime, therefore increasing productivity.

According to embodiments the mobile communications device further comprises a transmitter arranged to transmit the smell data to other devices in the process environment. Advantageously the mobile communications device thereby enables data to be gathered jointly from all the plant maintenance engineers and saved for future reference instead of relying on the plant maintenance engineers' own notes or memories.

According to embodiments the mobile communications device further comprises further sensors, such as a global positioning system unit, a near- field communications unit, and/or a gyro. By combining the smell sensor with other sensors in the mobile communications device, it may be possible to determine where the mobile communications device is located and in what angle it is aligned. This information could aid the smell sensor since the smell sensor would be able to determine what process objects are close by and therefore what smells to search for in order to detect abnormalities

associated with a malfunction.

According to a second aspect there is presented a method for detection of failure of industrial equipment in a process environment. The method comprises detecting an airborne chemical compound and transducing the airborne chemical compound into an electrical signal representing smell data. The method further comprises classifying the smell data into at least one smell class from a group of smell classes, each one of the smell classes in the group of smell classes being associated with a malfunction of a part of the industrial equipment, thereby detecting at least one upcoming malfunction in the process environment. The method further comprises identifying, based on the detected at least one upcoming malfunction, a control action in the process environment for control of said part the industrial equipment so as to mitigate or stop said at least one upcoming malfunction. The method further comprises providing an indicator of said at least one upcoming malfunction and/or said control action to a user interface of a mobile communications device.

According to embodiments the method is performed in the mobile

communications device.

According to a third aspect there is presented a computer program for detection of failure of industrial equipment in a process environment. The computer program comprises computer program code which, when run on a mobile communications device, causes the mobile communications device to perform a method according to the second aspect.

According to a fourth aspect there is presented a computer program product comprising a computer program according to the third aspect and a computer readable means on which the computer program is stored.

It is to be noted that any feature of the first, second, third and fourth aspects may be applied to any other aspect, wherever appropriate. Likewise, any advantage of the first aspect may equally apply to the second, third, and/or fourth aspect, respectively, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the attached dependent claims as well as from the drawings.

Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the element, apparatus, component, means, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated. BRIEF DESCRIPTION OF THE DRA WINGS

Embodiments of the invention will now be described, by way of non-limiting examples, references being made to the accompanying drawings, in which:

Fig l schematically illustrates a process environment; Fig 2 is a schematic diagram showing functional modules of a mobile communications device;

Fig 3 schematically illustrates a computer program product; and Fig 4 is a flowchart of a method according to an embodiment.

DETAILED DESCRIPTION

The invention will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments of the invention are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Like numbers refer to like elements throughout the description.

Fig 1 schematically illustrates a process environment 1. The process environment 1 comprises a number n of industrial equipment (IE) 2a, 2b, 2c, 2n. The industrial equipment 2a-n may represent equipment for manufacturing, processing and/or refinement of raw materials or pre- processed material, heating, ventilation and/or air-conditioning (HVAC), power generation, or the like of an oil refining, paper manufacturing, chemicals, or power plant industrial environment. Typically each of the industrial equipment 2a-n emanates at least one particular smell during a state of malfunction. Each smell is defined by a particular airborne chemical compound. One airborne chemical compound emanated from the industrial equipment 2a is schematically illustrated by the cloud at reference numeral 3. The process environment 1 may be operated under supervision of a process controller (PC) 4. The process controller 4 may run an automation system application. The so-called System 8ooxA from the company ABB is one typical example of an automation system application. System 8ooxA aims at improving process availability while reducing the risk to overall plant operation by providing a common environment for production control, safety supervision, and production monitoring. Within this environment, System 8ooxA comprises a Safety Instrumented System (SIS) solution, complying with the IEC 61508 and IEC 61511 standards and covers safety loops comprising field instruments, central controllers and field actuators. With safety applications such as emergency shutdown systems, fire and gas systems, and burner management, System 8ooxA aims at delivering safe reliable operation of any industrial process.

The process environment 1 further comprises a database (DB) 5 operatively coupled to the process controller 4. The database 5 may hold data associated with the industrial equipment 2a-n.

The process environment 1 further comprises a mobile communications device (MCD) 6. The mobile communications device 6 is typically a mobile phone or a tablet computer. The mobile communications device may be operatively connected to the process controller 4 by means of a radio communications network. The mobile communications device 6 is typically carried by a plant maintenance engineer.

The embodiments disclosed herein relate detection of failure of industrial equipment, and more particularly to detection of failure of industrial equipment using a handheld device, such as a mobile communications device. As noted above, plant maintenance engineers may use smell to identify industrial equipment in need for service. As also noted above, hardware smell sensors may be used to detect the state of industrial equipment. Plant maintenance engineers may therefore be equipped with portable electronic devices, such as mobile communication devices, comprising a smell sensor. The smell sensor may be arranged to collect data as the plant maintenance engineers that carry the mobile devices walk around in the process plant. In order to obtain detection of failure of industrial equipment there is provided a mobile communications device comprising a smell sensor, a method, a computer program comprising code, for example in the form of a computer program product, that when run on a mobile communications device, causes the mobile communications device to perform the method.

Fig 2 schematically illustrates, in terms of a number of functional modules, the components of a mobile communications device 6. A processing unit 7 is provided using any combination of one or more of a suitable central processing unit (CPU), multiprocessor, microcontroller, digital signal processor (DSP), application specific integrated circuit (ASIC) etc., capable of executing software instructions stored in a computer program product 18 (as illustrated in Fig 3), e.g. in the form of a memory 11. Thus the processing unit 7 is thereby arranged to execute methods as herein disclosed. The memory 11 may also comprise persistent storage, which, for example, can be any single one or combination of magnetic memory, optical memory, solid state memory or even remotely mounted memory.

The mobile communications device 6 further comprises a smell sensor 8. The smell sensor 8 is arranged to detect an airborne chemical compound and to transduce the airborne chemical compound into an electrical signal representing smell data. In the literature, smell sensors are also termed electronic noses since the stages of the recognition process are similar to human olfaction. As will be further disclosed below, the operational steps performed by the smell sensor 8 and the processing unit 7 may comprise identification, comparison, quantification and other applications, including data storage and retrieval. The smell sensor 8 may comprise a head space sampling module, a chemosensor (also known as a chemoreceptor), a sensor array module, and/or a pattern recognition module, to generate signal patterns that are used for characterizing the airborne chemical compound into an electrical signal representing smell data. The sensor array may be arranged to react to volatile compounds contacting the sensor array. Commonly used smell sensors 8 include metal-oxide-semiconductor

(MOSFET) devices, conducting polymers devices, quartz crystal

microbalance devices, and surface acoustic wave devices. In MOSFET devices a transistor is used for amplifying or switching electronic signals. These work on the principle that molecules entering the sensor area will be charged either positively or negatively, which should have a direct effect on the electric field inside the MOSFET. Thus, introducing each additional charged particle will directly affect the transistor in a unique way, producing a change in the MOSFET signal that can then be interpreted by pattern recognition computer systems. Essentially, each detectable molecule will have its own unique signal for a computer system to interpret. In short, conducting polymers devices comprise organic polymers that conduct electricity. In short, quartz crystal microbalance (QCM) is a way of measuring mass per unit area by measuring the change in frequency of a quartz crystal resonator. This can be stored in a database, such as the memory 11 and/or the database 5, and used for future reference. Surface acoustic wave (SAW) devices belong to a class of micro- electromechanical systems (MEMS) which rely on the modulation of surface acoustic waves to sense a physical phenomenon. Some smell sensors combine multiple sensor types in a single device, for example polymer coated QCMs. The smell sensor 8 may be trained with qualified samples so as to build a database of reference. Then smell sensor 8 may recognize new samples by comparing volatile compounds fingerprint to those contained in its memory. The smell sensor 8 may thereby perform qualitative or quantitative analysis. When in contact with the volatile compounds, the smell sensor 8 experiences a change of electrical properties. Each smell sensor 8 is sensitive to all volatile molecules but each in their specific way. Sensor arrays that react to volatile compounds on contact may be used; the adsorption of volatile compounds on the sensor surface causes a physical change of the sensor. A specific response may be recorded by an electronic interface transforming the signal into a digital value.

The processing unit 7 is arranged to process signals it receives from the smell sensor 8 (as well as other sensors as disclosed below). The processing may comprise different steps of analysis, determination and provision of results and representations that may be interpreted by other devices and entities. The mobile communications device 6 may further comprise an input/output (I/O) interface 14 for receiving and providing information to a user interface. The mobile communications device 6 may also comprise one or more transmitters 9 and receivers 10, comprising analogue and digital components forming the functionalities of a transmitter and a receiver. The one or more transmitters 9 and receivers 10 may be provided with circuitry forming a suitable number of antennae to be used for radio communication with a communications network. The processing unit 7 controls the general operation of the mobile communications device 6, e.g. by sending control signals to the transmitter 9 and/or receiver 10 and receiving reports from the transmitter 9 and/or receiver 10 of its operation.

Fig 4 is flow chart illustrating embodiments of methods for detection of failure of industrial equipment in a process environment 1. The methods are performed in the mobile communications device 6. The methods are advantageously provided as computer programs 19. Fig 3 shows one example of a computer program product 18 comprising computer readable means 20. On this computer readable means 20, a computer program 19 can be stored, which computer program 19 can cause the processing unit 7 and thereto operatively coupled entities and devices to execute methods according to embodiments described herein. In the example of Fig 3, the computer program product 18 is illustrated as an optical disc, such as a CD (compact disc) or a DVD (digital versatile disc) or a Blu-Ray disc. The computer program product could also be embodied as a memory (RAM, ROM, EPROM, EEPROM) and more particularly as a non-volatile storage medium of a device in an external memory such as a USB (Universal Serial Bus) memory. Thus, while the computer program 19 is here schematically shown as a track on the depicted optical disk, the computer program 19 can be stored in any way which is suitable for the computer program product 18.

The mobile communications device 6 is thereby arranged for automatic smell data collection and analysis in real time in any process control system. In more detail, in a step S2 an airborne chemical compound 3 is detected and transduced into an electrical signal representing smell data. The airborne chemical compound 3 is detected and transduced into an electrical signal representing smell data by the smell sensor 8 of the mobile communications device 6.

The mobile communications device 6 is further enabled to detect upcoming malfunctions of industrial equipment 2a-n and also suggest possible solutions in advance to repair the industrial equipment 2a-n before the failure. In order to do so the smell data is, in a step S4, classified into at least one smell class from a group of smell classes. The classification is according to embodiments performed by the processing unit 7 of the mobile

communications device 6. Each one of the smell classes in the group of smell classes is associated with a malfunction of a part of the industrial equipment 2a-n. The processing unit 7 is thereby arranged to detect at least one upcoming malfunction in the process environment 1.

Further, in a step S6 a control action in the process environment 1 for control of the part the industrial equipment 2a-n is identified. According to embodiments the identification is performed by the processing unit 7. The control action is based on the detected at least one upcoming malfunction. The control action is for control of the part the industrial equipment 2a-n so as to mitigate or stop the at least one upcoming malfunction.

In a step S8 an indicator of the at least one upcoming malfunction and/or the control action is provided to a user interface which is part of the I/O interface 14 of the mobile communications device 6. According to embodiments the provision is performed by the processing unit 7. Hence the mobile

communications device 6 may function as an expert system, giving advice on what to do when errors are detected in the process environment 1. Even novice users, such as maintenance engineers not familiar with different smells of industrial equipment, will thus be able to detect malfunctions associated with airborne chemical compounds using the disclosed mobile communications device 6. As noted above the mobile communications device 6 may further comprise a transmitter 9. The transmitter 9 may be arranged to transmit the control action to a process controller 4 of the process environment 1. Thereby the process controller 4 of the process environment 1 may control the identified industrial equipment 2a-n so as to mitigate or stop the at least one upcoming malfunction before the at least one upcoming malfunction causes any damage.

Different kinds of sensors may be used to perform various levels of detailed troubleshooting. According to an embodiment the mobile communications device 6 further comprises a vibration sensor 16. For example, the smell sensor 8 may be utilized to identify a malfunction within the detection range of the smell sensor 8 and the vibration sensor 16 may be used to find exactly what process object of the industrial equipment 2a-n is not functioning as expected. Further, the smell sensor 8 may have different modes of operation.

Particularly, according to embodiments the smell sensor 8 has at least two modes of sensitivity. The different modes of sensitivity may be associated with different levels of resolution of the sensitivity. Alternatively, the different modes of sensitivity may be associated with different fractions of an available spectrum of airborne chemical compounds. Hence, in one of the at least two modes of sensitivity only a fraction of the available spectrum of airborne chemical compounds may considered when transducing the detected airborne chemical compound into the electrical signal. However, according to embodiments malfunctions relating to smoke should be detected in all modes, since smoke may be associated with a fire in the industrial equipment 2a-n. The smell sensor 8 may therefore be arranged to detect an airborne chemical compound representing smoke from fire in both the at least two modes of sensitivity.

The processing unit 7 may further be arranged to associate the smell data with a current location of the mobile communications device 6. For example, data from a global positioning system (GPS), gyros, a compass, blueprints and/or near-field communications units can provide location information. Thereby the mobile communications device 6 may be enabled to determine its exact position as well as the surrounding process objects. Classification of the smell data into said at least one smell class may be dependent on the current location of the mobile communications device 6. Depending on the current location of the mobile communications device 6, some airborne chemical compounds may be considered as being associated with a malfunction of an industrial equipment 2a-n whilst other airborne chemical compounds which otherwise would be considered as being associated with a malfunction of the same industrial equipment 2a-n are, for that particular location, not considered as being associated with a malfunction of the industrial equipment 2a-n, and vice versa. The different fractions of available spectrum of airborne chemical compounds may be determined by the current location of the mobile communications device 6. It may thus be possible to utilize further sensors which may be provided in the mobile communications device 6 in conjunction with the smell sensor 8. As noted above, the mobile communications device 6 may further comprise a GPS unit 13. The GPS unit 13 may be arranged to determine the current location of the mobile communications device 6. With information relating to the current location of the mobile communications device 6 it may be possible to limit the smell data processing to certain spectrums.

Classification of the smell data into the at least one smell class may further be dependent on the location of the industrial equipment 2a-n in the process environment 1. In order to associate the location of the industrial equipment 2a-n with the current position of the mobile communications device 6, the mobile communications device 6 may comprise a near-field communications (NFC) unit 15 arranged to exchange information with at least one industrial equipment 2a-n in the process environment. The near-field communications unit may be a radio frequency identification (RFID) reader or tag.

Alternatively the positions of the industrial equipment 2a-n may be provided as map data originating from a blueprint of the process environment 1. The map data may be stored in the memory 11 and/or database 5 and compared with the positioning information of the GPS unit 13 in order to associate the location of the industrial equipment 2a-n with the current position of the mobile communications device 6.

In order to save power (such as the battery lifetime) of the mobile

communications device 6 the smell sensor 8 may only be activated during movement of the mobile communications device 6. Hence activation of the smell sensor 8 may be based on movement of the mobile communications device 6. The mobile communications device 6 may therefore further comprise a movement sensor arranged to detect the movement of the mobile communications device. The movement sensor may be a gyro 12. Activation of the smell sensor 8 may additionally or alternatively be based on the location of the mobile communications device 6; the smell sensor 8 may exclusively be activated when the mobile communications device 6 is located in the process environment 1, or even in a particular area of the process environment 1.

As noted above, according to embodiments the mobile communications device 6 further comprises a receiver 10. By automatically examining newly collected data with previously recorded data it may be possible for the processing unit 7 to determine if any industrial equipment 2a-n is showing any signs of failing. The receiver 10 may therefore be arranged to receive further smell data originating from at least one other mobile communications device. The processing unit 7 may then further be arranged to add the further smell data to one smell class from the group of smell classes.

The mobile communications device 6 may also, based on the collected information, suggest possible measures to correct the detected problems before they can affect the process environment 1. The receiver 10 may therefore be arranged to receive at least one control action associated with the further smell data. The processing unit 7 may then further be arranged to classify the further smell data based on the received at least one control action. Likewise, the mobile communications device 6 may further comprise a transmitter 9 arranged to transmit the smell data to other devices in the process environment. The other devices may be other mobile

communications devices, process controllers 4, databases 5, etc. The smell sensor 8 may be an integral part of the mobile communications device 6. Alternatively the smell sensor 8 is detachable from the mobile communications device 6.

A typical illustrative scenario where the disclosed embodiments may readily apply will be described next. In the illustrative scenario the disclosed mobile communications device 6 is carried by a maintenance engineer. At a first instance the maintenance engineer is present at a first location in the process environment 1 to perform a maintenance task of an industrial equipment, say industrial equipment 2b in the process environment 1 of Fig 1, for example changing filters in a water tank. Upon completing the maintenance task, the maintenance engineer is transported from the first location to a second location in the process environment 1. The mobile communications device 6 thus detects movement and activates the smell sensor 8. The mobile communications device 6 carried by the maintenance engineer is arranged to analyse the air in search of smells that would indicate any upcoming malfunctions or breakdowns. The smell sensor 8 thus is active and collects data as the maintenance engineer moves around. During the transport to the second location in the process environment 1 the maintenance engineer passes a third location. The third location may represent an engine hall which may comprise industrial equipment, say industrial equipment 2a in Fig 1. The smell sensor 8 is aware of its position as it utilizes data from GPS, gyros etc. As the maintenance engineer passes the third location the mobile

communications device 6 picks up a smell. The smell sensor 8 provides the processing unit 7 of the mobile communications device 6 with an electrical signal representing smell data for analysis. Alternatively the mobile communications device 6 may transmit the recorded smell to the process controller 4 for analysis. Only a fraction of the spectrum has to be analyzed as the processing unit 7 is aware of nearby process objects and therefore can exclude certain smells. The electrical signal representing the smell data may for example be compared with reference data from exactly the same location It is determined that the recorded smell should not be present in this part of the process environment 1. The collected data may be stored for future reference. A message is therefore provided to a user interface of the mobile communications device 6. For example, operators and maintenance engineers can access the data and plot its history. Based on this returned information the maintenance engineer can take appropriate actions. For example, the maintenance engineer may add a maintenance request for the industrial equipment 2a that was identified to be associated with the smell.

The invention has mainly been described above with reference to a few embodiments. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope of the invention, as defined by the appended patent claims.