GB2530300A - Monitoring an environmental condition - Google Patents
Monitoring an environmental condition Download PDFInfo
- Publication number
- GB2530300A GB2530300A GB1416511.2A GB201416511A GB2530300A GB 2530300 A GB2530300 A GB 2530300A GB 201416511 A GB201416511 A GB 201416511A GB 2530300 A GB2530300 A GB 2530300A
- Authority
- GB
- United Kingdom
- Prior art keywords
- environmental condition
- processor
- analysis
- environmental
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000007613 environmental effect Effects 0.000 title claims abstract description 120
- 238000012544 monitoring process Methods 0.000 title claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 50
- 230000009471 action Effects 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 27
- 241000251468 Actinopterygii Species 0.000 claims abstract description 14
- 230000007797 corrosion Effects 0.000 claims abstract description 14
- 238000005260 corrosion Methods 0.000 claims abstract description 14
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000003909 pattern recognition Methods 0.000 claims abstract description 7
- 239000004215 Carbon black (E152) Substances 0.000 claims abstract description 6
- 229930195733 hydrocarbon Natural products 0.000 claims abstract description 6
- 150000002430 hydrocarbons Chemical class 0.000 claims abstract description 6
- 238000012805 post-processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 4
- 239000000446 fuel Substances 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 34
- 238000012806 monitoring device Methods 0.000 description 32
- 238000009434 installation Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000008901 benefit Effects 0.000 description 4
- 238000003306 harvesting Methods 0.000 description 4
- 241000195493 Cryptophyta Species 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 208000010824 fish disease Diseases 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009372 pisciculture Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/10—Locating fluid leaks, intrusions or movements
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/001—Survey of boreholes or wells for underwater installation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Emergency Management (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Emergency Alarm Devices (AREA)
Abstract
A device and method for monitoring an environmental condition. The device is provided with a sensor arranged to collect environmental data S1. A processor is configured to analyse the collected environmental data using a combination of pattern recognition and artificial intelligence S2 to obtain an environmental condition value. The processor is further arranged to take a further action S3 in the event that the environmental condition value exceeds a predetermined environmental condition value. This allows an environmental condition to be monitored without the need for human intervention or periodic checking. The sensor may be some form of camera, with preprocessing to remove noise. The environment may be an abandoned hydrocarbon well, underwater, and the device monitors for corrosion, leakage, damage, oil drops in water, gas bubbles in water, or fish. The device may have a transmitter, floating on the surface of the water.
Description
MONITORING AN ENVIRONMENTAL CONDITION
TECHNICAL FIELD
The invention relates to the field of monitoring an environmental condition, for example in an inhospitable or remote location.
BACKGROUND
There are many circumstances in wftch it is desirable to monitor environmental conditions. In some cases the monitoring must take place in a hazardous! inhospitable or hard to access location.
Consider the case where a subsea well is abandoned. The well operator has a duty (typically a legal requirement) to monitor the abandoned well to ensure that it is safe and not creating any environmental hazards. A small amount of hydrocarbon leakage from an abandoned well may be within acceptable limits, but if the amount of leakage exceeds a pre-determined level then the operator must take action to make the abandoned well safe.
An abandoned well is typically left without any power or communications. In order to monitor it, the operator must periodically perform a visual inspection, for example by using a remote underwater vehicle. It can be many months or even years between inspectons and the well may, in the intervening period between inspections, start to leak. This environmental hazard will not be detected until the next inspection.
Another exemplary case where environmental monitoring is required is fish farming. In this case, certain conditions may be monitored such as a pattern of shoaling of the fish, a number of fish, a health of the fish and so on. Any of these factors must be periodically checked to ensure that the fish farm is operating as required. Again, this requires a periodic visual inspection, and problems could arise in periods between periodic visual inspections.
A further example is a wind farm. A wind farm consists of multiple wind turbines used for generating electricity. These may be located in a remote and inaccessible region but it is important to quickly detect any potential problems such as corrosion, cracking, damage and so on.
It will be appreciated that there are many circumstances where an environmental condition must be periodically monitored.
SUMMARY
It is an object to provide ways of monitoring one or more environmental conditions.
According to a first aspect, there is provided a device arranged to monitor an environmental condition. The device is provided with a sensor arranged to collect environmental data. A processor is configured to analyse the collected environmental data using a combination of pattern recognition and artificial intelligence to obtain an environmental condition value. The processor is further arranged to take a further action in the event that the environmental condition value exceeds a predetermined environmental condition value. An advantage of this device is that an environmental condition can be monitored without the need for human intervention or periodic checking. This reduces costs in monitoring the environmental condition and also increases the likelihood that any problems will be detected more quickly than is normally possible using periodic checks.
The sensor is optionally a camera arranged to obtain an image of a predetermined region. In this case, the processor is arranged to perform pre-processing on the image to remove noise. The processor is further arranged to perform an analysis of the image to determine a pattern that can be related to the environmental condition being monitored. The processor then performs a post-processing action to confirm the result of the analysis in order to minimize false decisions. The processor is arranged to determine the further action to be taken based on the analysis and the post-processing results. As a further option, the processor is arranged to perform pre-processing to improve lighting conditions.
As an option, the device further comprises a case base (in other words, an experience based database) usable by the processor when performing any of the analysis and the post-processing. The case base comprises data related to the environmental condition and the environmental condition value. The case base therefore contains information specific to the type of environmental condition being monitored and the conditions under which the environmental condition is monitored. For example, the environmental condition being monitored may be the presence of an oil leak from an abandoned well.
The case base will include information about the type of well, the depth of water, the murkiness of water and so on, so that it is specifically tailored to the conditions.
As an option, the processor is arranged to perform analysis of a pluralty of images obtained over a time period. This allows longer term environmental conditions, such as corrosion, to be monitored where the time period is long. Where the time period is short, it allows the presence of moving features, such as bubbles, to be detected.
The processor is optionally arranged to identify a feature in the plurality of images and to further determine a change to the feature in different images. Again, this allows movement to be detected in the short term, and growth to be detected in the long term.
The processor is optionally arranged to determine any of a rate of movement of the object and a direction of movement of the feature. For example, it may be known that gas bubbles move vertically upwards and within a certain range of velocities. Detection of movement in other directions or at velocities outside the range can therefore be discounted as coming from gas bubbles.
Optional examples of the feature include oil drops in water, gas bubbles in water, corrosion, fish, and damage.
The processor is optionally further arranged determine the further action to be taken based on any of a time of day and a date.
The device is optionally provided with a power source. Optional examples of the power source include any of wired power (where the device is connected to a remote facility such as a surface facility), a battery, a fuel cell and a rechargeable battery. The rechargeable battery may be connected to an energy harvesting device, such as a power generating turbine.
As an option, the device is configured to operate below a surface of water. Such a device may comprise a releasable float. The releasable float comprises a transmitter and is releasable when a precondition is met. As an option, the precondition comprises any of a predetermined further action and a predetermined level of available power in a power source. This allows the float to be released when battery power is running low, alerting a user to the fact that the device battery must be changed, or when an unwanted environmental condition is detected by the environmental condition value exceeding an environmental condition threshold.
As an option, the device is configured to monitor an environmental condition associated with an abandoned hydrocarbon well. Environmental conditions may include any of corrosion, damage, oil leaks, gas leaks and so on.
According to a second aspect, there is provided a method of monitoring an environmental condition. Environmental data is collected. The collected environmental data is analysed using a combination of pattern recognition and artificial intelligence to obtain an environmental condition value. A further action is taken in the event that the environmental condition value exceeds a predetermined environmental condition value.
As an option, the environmental data comprises an image of a predetermined region.
In this case, the method further comprises performing pre-processing on the image to remove image noise. An analysis of the image is performed to determine a pattern that may indicate an unwanted environmental condition (for example, an oil leak): A post-processing action is performed to confirm the result of the analysis in order to minimize false decisions. Not all patterns arise from unwanted environmental conditions, and the post-processing action uses artificial intelligence and case based reasoning (based on previously obtained data) to confirm that the pattern does indeed arise from an unwanted environmental condition. A further action to be taken is determined based on the analysis and the post-processing action.
As an option, the method further comprising using a case base when performing any of the analysis and the post-processing, the case base comprising data related to the environmental condition and the environmental condition value.
The method optionally comprises performing an analysis of a plurality of images obtained over a time period. As a further option, the method comprises identifying a feature in the plurality of images and further determining a change to the feature in different images. The method may also further comprise determining a rate of movement of the feature and/or a direction of movement of the feature. Examples of moving features detected in this way include oil drops in water, gas bubbles in water, corrosion, fish, and damage.
The further action to be taken is optionally determined based on any of a time of day and a date.
As an option, the environmental condition is monitored below a surface of water. In this case, the method further comprising determining that a precondition is met and, as a result, releasing a float, the releasable float comprising a transmitter. An advantage of the releasable float is that when the environmental condition is monitored in a remote region, it may not be practical to connect the device directly to a surface facility.
However, radio wave communications travel poorly through water so cannot be used directly when an unwanted environmental condition is detected (or the device detects a fault or runs low on power). The float therefore transmits at the surface of the water, allowing a remote user to detect the presence of the unwanted environmental condition or low power/fault at the device.
Examples of the precondition include any of a predetermined further action (such as when an unwanted environmental condition is detected) and a predetermined level of available power in a power source.
As an option, the environmental condition is associated with an abandoned hydrocarbon well. Examples of such environmental conditions include damage, corrosion, oil leaks and gas leaks.
According to a third aspect, there is provided a computer program, comprising computer readable code which, when run on a computer device, causes the computer device to perform the method as described above in the second aspect.
According to a fourth aspect, there is provided a computer program product comprising a computer readable medium and a computer program as described above in the third aspect, wherein the computer program is stored on the computer readable medium.
BRIEF DESCRIPTION OF THE DRAWINGS
Figure 1 illustrates schematically in a block diagram an exemplary monitoring device in a subsea location; Figure 2 illustrates schematically in a block diagram an exemplary monitohng device; Figure 3 illustrates schematically in a block diagram a monitoring device in a subsea location in a second exemplary embodiment; Figure 4 illustrates schematically in a block diagram a monitoring device according to a second exemplary embodiment; Figure 5 illustrates schematically in a block diagram an exemplary system of databases; Figure 6 is a flow diagram illustrating exemplary steps; Figure 7 is a flow diagram illustrating further exemplary steps; Figure 8 is a flow diagram illustrating steps according to a second exemplary embodiment; and Figure 9 illustrates schematically in a block diagram an exemplary monitoring device.
DETAILED DESCRIPTION
Figure 1 shows an exemplary installation 1. The installation in this example is an abandoned subsea well, but it will be appreciated by the skilled person that it could be any type of installation (such as part of a fish farm, a wind turbine and so on). A monitoring device 2 is located in proximity to the installation 1. The monitoring device 2 is connected to a surface facility 3 (such as a shore based installation or an oil rig).
The monitoring device is provided with at least one sensor to collect environmental data. A processor is arranged to analyse collected environmental information using a combination of pattern recognition and artificial intelligence to obtain an environmental condition value. The processor is further arranged to take a further action in the event that the environmental condition value exceeds a predetermined environmental condition value.
Figure 2 shows an exemplary monitoring device that can be used in the example where the installation is an abandoned subsea well. In this case the monitoring device is provided with a light 4 to illuminate a region of the installation. A camera S is provided to capture still or moving images. The light is controlled by a processor 6. The processor 6 is also arranged to receive images from the camera 5. A source of power 7 is provided. This may be any suitable local power supply, such as a batter or a fuel cell, or it may be a connection to a remote power supply, such as a power supply provided from the surface facility 3. An in/out device B is operatively connected to the processor 6, which allows the monitoring device 2 to exchange data with the surface facility 3. In this instance, the monitoring device 2 may simply collect data and all analysis of the data is performed at the surface facility 3.
In a second embodiment, shown in Figure 3, the monitoring device 2 is not connected to a surface facility but is still located in proximity to the installation 1. The monitoring device is connected to a local power source 9. For example, the monitoring device may contain a battery that is connected to a power source 9 that harvests electrical power from subsea currents. The monitoring device is also provided with a float 10.
The float 10 is releasable, and configured to be released when an unwanted environmental condition is detected by the processor when an environmental condition value exceeds a predetermined environmental condition value. In addition, the float 10 may be released when the local source of power 9 (such as the battery) falls below a pre-determined level, informing the operator of the monitoring device 2 that the battery requires changing.
The device according to the second embodiment is provided with a light 4, a camera 5, a processor 6, a float 10, a battery 11 and a database 12 that is usable by the processor to determine when an unwanted situation has arisen.
Consider the case where the monitoring device is monitoring an abandoned well. The camera may be used to detect the presence of gas bubbles or oil droplets rising up from the well. In this case, images caught by the camera can be analysed to detect patters such as the presence of gas bubbles/oil drops in water, the direction of movement of the gas bubbles/oil drops, the amount of gas/oil and so on. As described below, filter must be applied to minimize the likelihood of false positive detections.
If the amount of gas bubbles/oil bubbles exceeds a predetermined threshold then, in the case of the first embodiment, a signal is sent to the surface facility 3 alerting a user that the abandoned well is potentially leaking. This allows the operator to investigate further, for example by sending a remote underwater vehicle to perform an inspection.
An advantage of this over periodic checks is that the unwanted environmental condition is detected much earlier. A further advantage of this is that periodic checks are not required; the operator need only intervene when an unwanted condition is detected by the monitoring device 2.
Considering the float of the second embodiment, this is particularly useful in the case where the installation 1 is in such as remote location that it is impractical to connect the monitoring device 2 to a surface facility 3. In this case the monitoring device 2 makes the determination that an environmental condition value has exceeded a predetermined threshold. When this determination is made, the float 10 is released. The float 10 may be formed from any suitable material to ensure that it floats to the surface of the water.
The float contains a power source and a transmitter and transmits information to the operator of the monitoring device 2. This information may include captured images, results of analysis, information identifying the installation, information identifying the monitoring device, geographical coordinates of the installation and so on. As mentioned above, the float may also be released when the monitoring device 2 is running low on power or detects a fault, even if the environmental condition has not exceeded the predetermined environmental condition threshold.
Figure 5 illustrates an exemplary system for analysing images that can be embodied with one or more databases in either hardware or software. It will be appreciate that the units shown in Figure 5 are functional modules.
An image acquisition function 13 is provided for acquiring images from the camera 5.
Images may be still or moving images. Information about the images (such as time, location, quality etc.) may be passed to a decision function 14.
A pre-processing function 15 is provided to clean' the image. The pre-processing function may use information obtained from a database about the local conditions to apply specific types of image cleaning to the acquired images. For example, information about light conditions, water depth, water murkiness, camera noise and so on may be used. The pre-processing function 15 cleans the image recognising and compensating for irrelevant objects such as fish or algae, and removes moire effects from the image. Any type of pre-processing may be used that removes or reduces unwanted noise' that is not relevant to the environmental condition being monitored.
For example, if the pre-processing function 15 is arranged to detect an oil leak, movement of objects in the image may be horizontal or vertical. Droplets from an oil leak will move substantially vertically upwards in water, whereas algae in the water will move substantially horizontally. Any movement that is substantially horizontal or verticaly downwards can therefore be ignored for the purpose of detecting an oil leak.
It will be appreciated that the information used by the pre-processing function is specific to the nature of the environmental condition being monitored and the local conditions.
An analysis function 16 is used to determine an unwanted environmental condition.
The analysis function 16 is configured to look for a specific environmental condition.
For example, the analysis function 16 may determine that bubbles of a certain size, shape and/or colour, and travelling upwards in water, are likely to be oH bubbles. A certain number of bubbles in a given image area may exceed the environmental condition value, in which case further action must be taken. This example applies specifically to monitoring for an oil leakage in an abandoned well. It will be appreciated that other conditions may be monitored. For example, the analysis function l6may be configured to look for the presence of a particular fish disease or shoaling pattern in the fish contained in a fish farm. It may be configured to determine cracks that may arise from metal fatigue in the blade of a wind turbine. Any environmental condition that can be detected visually by the camera 5 may be monitored.
The analysis function l6may also be configured to look for longer term changes. For example, the growth of algae or shellfish on a subsea installation may take months, in which case the analysis function l6may compare images obtained months apart. A similar technique may be used to detect corrosion. Note that, depending on the environmental being monitored, the analysis function 16 may analyse a series of moving images, or may compare still images taken at different times. Analysis of moving images is appropriate for detecting, for example, bubbles. Analysis of still images taken at different times is appropriate for detecting, for example, corrosion.
It will also be appreciated that the analysis function 16 may be arranged to detect more than one environmental condition. For example, the analysis function 16 may be configured to detect an oil leak from an abandoned well, and may also be configured to detect corrosion at the abandoned well. The presence of either of these stuations may trigger further action.
The results obtained from the analysis function 16 are passed to the decsion function 14.
A post-processing function 17 is provided that uses case based reasoning and artificial intelligence to check the results of the analysis function 16. The post-processing function 17 is used to reduce the incidence of false positives from the analysis function.
For example artificial intelligence analysis may show that what appears to be an environmental condition value exceeding the predetermined threshold arises from another cause. The post processing function 17 uses data obtained from other sources to determine if the environmental condition value has been encountered before and the circumstances under which the apparent environmental condition resulted from an unwanted situation.
By way of example, where the analysis function 16 is configured to detect eakage of oil droplets, it may detect upwards moving objects in an image. Without the post-processing function 17, this would be a positive determination of a leakage and further action may be taken. However, the post-processing function 17 may determine that, based on past experience and case based reasoning, the detection of upwards-moving objects in the image may be more likely to arise from pollution or fish than from leakage.
The results obtained from the post-processing function 17 are passed to the decision function 14.
An action function 18 is also provided. When the analysis function 16 has detected an unwanted environmental condition (because the environmental condition value has exceeded a predetermined threshold), and the post-processing function has determined, using artificial intelligence and case based reasoning, that the environmental condition value is unlikely to be a false positive, the decision function 14 passes the results to the action function 14. The action function 14 initiates an action.
This may simply be, in the first specific embodiment, sending a signal to the surface facility 3 to alert a human operative. In the second specific embodiment, the action may be to pass relevant information to a computer readable medium in the form of a memory contained in the float 10 and release the float 10 so that it can alert a human operative.
Note that the battery life of the monitoring device may be critical, especially where the monitoring device is not connected to an external source of power such as the surface facility 3 or an energy harvesting device 9. Depending on the type of environmental condition being monitored, the camera 5 need not continuously monitor the installation 1. For example, the monitoring device may operate in sleep mode and wake up' periodically (for example daily) and monitor the installation for a short period of time before reverting to a sleep mode. In this way battery power may be conserved for a very long period before the battery requires recharging or replacing.
It will also be appreciated that while the above description focuses on using a camera 5 to detect conditions in an image, other types of sensor may be used aong with the camera. For example, pressure sensors, chemical sensors, radiation sensors, acoustic sensors and so on may all provide useful information relating to one or more environmental conditions. The monitor device may be fitted with any suitable sensors to detect an environmental condition, and a similar process as that described above and shown in Figure 5 can be used to clean the data, interpret it, and use artificial intelligence and case based reasoning to determine whether or not to take any action.
Figure 6 is a flow diagram illustrating exemplary steps in which the following numbering corresponds to that of the figure.
Si. A sensor is used to collect environmental data.
S2. A processor is configured to analyse the collected environmental data using a combination of pattern recognition and artificial intelligence. This allows the processor to obtain an environmental condition value, S3. In the event that the environmental condition value exceeds a predetermined environmental condition value, the processor is arranged to take a further action (for example, alerting a human user) Figure 7 is a flow diagram illustrating further exemplary steps where the sensor is a camera. The following numbering corresponds to that of the figure.
S4. The camera 5 collects an image or series of images.
S5. A pro-processing step is performed by a processor to remove noise from the collected image(s) and/or compensate for poor lighting.
S6. The processor performs an analysis on the processed image(s) to detect a pattern.
S7. If a pattern is detected that could relate to an unwanted environment condition, a post-processing analysis is performed using artificial intelligence and case based reasoning.
SB. If an unwanted environmental condition is met (because a detected environmental condition value exceeds a predetermined environmental condition value) then further action is taken (for example, a human user is alerted).
Figure 8 is a flow diagram illustrating steps according to the second exemplary embodiment. The following numbering corresponds to that of the figure.
S9. An underwater environmental condition is monitored by a monitoring device 2.
For example, the presence of an oil leak at an abandoned well may be monitored.
SlO. In the event that the environmental condition monitoring indicates a problem (when an environmental condition value exceeds a predetermined threshold) a float is released. Note that the float may also be released in the event that the monitoring device 2 detects a fault with the monitoring device 2 or its battery life (or other power source) falls below a predetermined threshold.
Si 1. The float reaches the surface of the water and begins transmitting. Information transmitted includes at least the identity of the device monitoring the environmental condition, and may additionally include information relating to a detected problem, the collected environmental data, the results of analysis, the geographical co-ordinates of the float and/or the monitoring device 2 and so on. This allows an alert to be sent to a human user who can determine the appropriate action to take.
Figure 9 shows an exemplary monitoring device 2. The monitoring device is provided with a processor 6. A source of power 7 is provided. This may be a power lead from a surface facility 3, a battery, a fuel cell and so on, and may be attached to an energy harvesting device. An in/out device 8 is provided. This may simply be a transmitter, a wired connection to a surface facility, or a connection to the float as described above.
A sensor 19 is provided (an example of a sensor is a camera 5) for collecting environmental data. The processor 6 may either perform the analysis described above, or may send the collected environmental data to via the in/out device 8 to the surface facility 3 for analysis.
A non-transient computer readable medium in the form of a memory 20 may be provided that is used to store a computer program 21 which, when executed by the processor 6, causes the processor 6 to behave as described above. Note that the computer program 21 may be provided from an external source 22 such as a carrier wave, a flash drive, a compact disk and so on.
It will be appreciated by the person of skill in the art that various modifications may be made to the above described embodiments without departing from the scope of the present invention as defined in the appended claims.
Claims (17)
- CLAIMS1. A device arranged to monitor an environmental condition, the device comprising: a sensor arranged to collect environmental data; a processor arranged to analyse the collected environmental data using a combination of pattern recognition and artificial intelligence to obtain an environmental condition value; the processor being further arranged to take a further action in the event that the environmental condition value exceeds a predetermined environmental condition value.
- 2. The device according to claim 1 wherein the sensor comprises a camera arranged to obtain an image of a predetermined region; the processor is arranged to perform pre-processing on the image to remove noise.the processor is further arranged to perform an analysis of the image to determine a pattern; the processor is arranged to perform a post-processing action to confirm the result of the analysis in order to minimize false decisions; and the processor is arranged determine the further action to be taken based on the analysis and the post-processing results.
- 3. The device according to claim 2, wherein the processor is arranged to perform pre-processing to improve lighting conditons.
- 4. The device according to claim 2 or 3, the device further comprising: a case base usable by the processor when performing any of the analysis and the post-processing, the case base comprising data related to the environmental condition and the environmental condition value.
- 5. The device according to any one of claims 2, 3 or 4, wherein the processor is arranged to perform analysis of a plurality of images obtained over a time period.
- 6. The device according to claim 5 wherein the processor is arranged to identify a feature in the plurality of images and to further determine a change to the feature in different images.
- 7. The device according to claim 6 wherein the processor is arranged to determine any of a rate of movement of the object and a direction of movement of the feature.
- 8. The device according to any one of claims 6 or 7, wherein the feature comprises any of oil drops in water, gas bubbles in water, corrosion, fish, and damage.
- 9. The device according to any one of claims 2 to 8, wherein the processor is further arranged determine the further action to be taken based on any of a time of day and a date.
- 10. The device according to any one of claims 1 to 9, further comprising a power source.
- 11. The device according to claim 10, wherein the power source comprises any of wired power, a battery, a fuel cell and a rechargeable battery.
- 12. The device according to any one of claims 1 to 11, wherein the device is configured to operate below a surface of water, the device further comprising a releasable float, the releasable float comprising a transmitter and being releasable when a precondition is met.
- 13. The device according to claim 10, wherein the precondition comprises any of a predetermined further action and a predetermined level of available power in a power source.
- 14. The device according to any one of claims 1 to 13, configured to monitor an environmental condition associated with an abandoned hydrocarbon well.
- 15. The device according to claim 14, wherein the environmental condition comprises any of corrosion and leakage.
- 16. A method of monitoring an environmental condition, the method comprising: collecting environmental data; analysing the collected environmental data using a combination of pattern recognition and artificial intelligence to obtain an environmental condition value; taking a further action in the event that the environmental condition value exceeds a predetermined environmental condition value.
- 17. The method according to claim 15 wherein the environmental data comprises an image of a predetermined region, the method further comprising: performing pre-processing on the image to remove noise; performing an analysis of the image to determine a pattern; performing a post-processing action to confirm the result of the analysis in order to minimize false decisions; and determining the further action to be taken based on the analysis and the post-processing.19. The method according to claim 17, the method further comprising using a case base when performing any of the analysis and the post-processing, the case base comprising data related to the environmental condition and the environmental condition value.20. The method according to claim 18 or claim 19, further comprising performing an analysis of a plurality of images obtained over a time period.21. The method according to claim 20, further comprising identifying a feature in the plurality of images and to further determine a change to the feature in different images.22. The method according to claim 21, further comprising determining any of a rate of movement of the feature and a direction of movement of the feature.23. The method according to any one of claims 21 or 22, wherein the feature comprises any of oil drops in water, gas bubbles in water, corrosion, fish, and damage.24. The method according to any one of claims 17 to 23, further comprising determining the further action to be taken based on any of a time of day and a date.25. The method according to any one of claims 16 to 24, wherein the environmental condition is monitored below a surface of water, the method further comprising determining that a precondition is met and, as a result, releasing a float, the releasable float comprising a transmitter.26. The method according to claim 25, wherein the precondition comprises any of a predetermined further action and a predetermined level of available power in a power source.27. The method according to any one of claims 16 to 26, wherein the environmental condition is associated with an abandoned hydrocarbon well.28. The method according to claim 27, wherein the environmental condition comprises any of corrosion and leakage.29. A computer program, comprising computer readable code which, when run on a computer device, causes the computer device to perform the method as caimed in any of claims 16 to 28.30. A computer program product comprising a computer readable medium and a computer program according to claim 28, wherein the computer program is stored on the computer readable medium.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB1416511.2A GB2530300B (en) | 2014-09-18 | 2014-09-18 | Monitoring an environmental condition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB1416511.2A GB2530300B (en) | 2014-09-18 | 2014-09-18 | Monitoring an environmental condition |
Publications (3)
Publication Number | Publication Date |
---|---|
GB201416511D0 GB201416511D0 (en) | 2014-11-05 |
GB2530300A true GB2530300A (en) | 2016-03-23 |
GB2530300B GB2530300B (en) | 2021-06-30 |
Family
ID=51869119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
GB1416511.2A Active GB2530300B (en) | 2014-09-18 | 2014-09-18 | Monitoring an environmental condition |
Country Status (1)
Country | Link |
---|---|
GB (1) | GB2530300B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
NO20180513A1 (en) * | 2018-04-16 | 2019-10-17 | Cflow Fish Handling As | C-fish – fish welfare control |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01195364A (en) * | 1988-01-29 | 1989-08-07 | Hitachi Ltd | Monitor device for ecology of fishes |
DE3826263A1 (en) * | 1988-08-02 | 1990-02-08 | Siemens Ag | Arrangement for the measurement of the concentrations of components in a gas mixture, using non-selective gas sensors |
JPH03177742A (en) * | 1989-12-05 | 1991-08-01 | Fujitsu Ltd | Automatic control mechanism for air conditioner |
EP0632268A1 (en) * | 1993-07-01 | 1995-01-04 | Johnson Service Company | Apparatus and method for determining the indoor air quality within an enclosed space |
EP0733880A1 (en) * | 1995-03-22 | 1996-09-25 | Advanced Optical Controls, Inc. | Sensor module |
US20030118230A1 (en) * | 2001-12-22 | 2003-06-26 | Haoshi Song | Coiled tubing inspection system using image pattern recognition |
US20080035324A1 (en) * | 2006-05-19 | 2008-02-14 | Reinhart Ciglenec | Integrated measurement based on an optical pattern-recognition |
-
2014
- 2014-09-18 GB GB1416511.2A patent/GB2530300B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01195364A (en) * | 1988-01-29 | 1989-08-07 | Hitachi Ltd | Monitor device for ecology of fishes |
DE3826263A1 (en) * | 1988-08-02 | 1990-02-08 | Siemens Ag | Arrangement for the measurement of the concentrations of components in a gas mixture, using non-selective gas sensors |
JPH03177742A (en) * | 1989-12-05 | 1991-08-01 | Fujitsu Ltd | Automatic control mechanism for air conditioner |
EP0632268A1 (en) * | 1993-07-01 | 1995-01-04 | Johnson Service Company | Apparatus and method for determining the indoor air quality within an enclosed space |
EP0733880A1 (en) * | 1995-03-22 | 1996-09-25 | Advanced Optical Controls, Inc. | Sensor module |
US20030118230A1 (en) * | 2001-12-22 | 2003-06-26 | Haoshi Song | Coiled tubing inspection system using image pattern recognition |
US20080035324A1 (en) * | 2006-05-19 | 2008-02-14 | Reinhart Ciglenec | Integrated measurement based on an optical pattern-recognition |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
NO20180513A1 (en) * | 2018-04-16 | 2019-10-17 | Cflow Fish Handling As | C-fish – fish welfare control |
WO2019203661A1 (en) * | 2018-04-16 | 2019-10-24 | Cflow Fish Handling As | C-fish – fish welfare control |
NO345829B1 (en) * | 2018-04-16 | 2021-08-30 | Cflow Fish Handling As | C-fish – fish welfare control |
Also Published As
Publication number | Publication date |
---|---|
GB201416511D0 (en) | 2014-11-05 |
GB2530300B (en) | 2021-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101858845B1 (en) | Fishing gear integration management system | |
CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
JP2007187575A (en) | Device and method of monitoring water quality | |
KR20160116715A (en) | Ocean monitoring system based on augmented reality, server and method thereof | |
JP2019209271A (en) | Water quality determination device and water quality determination method in waste water treatment facility | |
CN110929591A (en) | Transformer substation monitoring method and device, computer equipment and storage medium | |
CN106442908A (en) | Water quality abnormity detection and grading alarm method based on red zebra fish stress behaviors | |
CN113075065A (en) | Deep sea pipeline crack propagation monitoring and reliability evaluation system based on image recognition | |
CN113662530A (en) | Pig physiological growth state monitoring and early warning method | |
CN112643719A (en) | Tunnel security detection method and system based on inspection robot | |
GB2530300A (en) | Monitoring an environmental condition | |
US7822273B1 (en) | Method and apparatus for automatic corrosion detection via video capture | |
Kimura et al. | Early detection system of harmful algal bloom using drones and water sample image recognition | |
CN116990381A (en) | Scraper machine fault determination method and device and scraper machine fault determination system | |
CN117108458A (en) | Marine wind power partition corrosion safety assessment method, system, equipment and storage medium | |
CN111191499A (en) | Fall detection method and device based on minimum center line | |
JP2005150840A (en) | Water quality monitoring system and fish image recognition method used for same | |
KR20140108747A (en) | Environmental disturbance monitoring system of real-time information through monitoring of animal behavior and surrounding environment, and environmental disturbance analysis method | |
CN102620048B (en) | Image monitoring method for monitoring safety of valves in industrial boiler field | |
CN110781860B (en) | Intelligent oil spill monitoring alarm system and method for offshore oil platform | |
JP4273988B2 (en) | Water quality abnormality determination system, method thereof, image monitoring apparatus, program thereof and storage medium thereof | |
Hake et al. | Damage detection for port infrastructure by means of machine-learning-algorithms | |
US10732318B2 (en) | Biosensor device, system and method for monitoring a deep-water sea-floor | |
Bajaj et al. | Sea debris: A review of marine litter detection techniques | |
CN115236196A (en) | Pressure container monitoring system and method |