Optical attachment, system and method for training flame detector

Abstract

An optical attachment for training a flame detector is disclosed. The optical accessory includes a body defining a first opening and a second opening, the first opening and the second opening being positioned at opposite ends of the body. Further, a plurality of reflective plates are positioned within the body and movably coupled to the body, each reflective plate configured to move relative to the body from a first orientation to a second orientation. When each reflective plate is positioned in the first orientation, the plurality of reflective plates are configured to receive infrared waves from the first opening of the body and reflect the infrared waves toward the second opening of the body. And when each reflective plate is positioned in the second orientation, the plurality of reflective plates are configured to allow infrared waves to travel along a linear path from the first opening to the second opening of the body.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure relate generally to flame detectors, and more particularly, to apparatuses, systems, and methods for training a flame detector. BACKGROUND

[0002] In the industrial field, the need for advanced safety measures for fires has led to the development of various flame detection systems. Flame detection systems detect and alert the presence of a fire or flammable gas in an industry, thereby mitigating potential hazards and ensuring the safety of personnel and assets. In industrial applications, known flames can sometimes be present in the field of view of the flame detection system. Infrared energy emitted by these known flames is sometimes reflected from shiny objects within the field of view, which can result in undesirable false alarms.

[0003] The present inventors have identified a number of areas for improvement in the prior art and methods, which are the subject of the embodiments described herein. Through the efforts, wisdom, and innovation, many of these deficiencies, challenges, and problems have been addressed by developing the solutions included in the embodiments of the present disclosure, some examples of which are described in detail herein. SUMMARY

[0004] The following presents a simplified summary in order to provide a basic understanding of some aspects of the present disclosure. This summary is not an extensive overview, and is neither intended to identify key or critical elements nor to delineate the scope of such elements. Its purpose is to present some concepts of the described features in a simplified form as a prelude to the more detailed description that is presented later.

[0005] In example embodiments, an optical accessory for training a flame detector is disclosed. The optical accessory includes a body defining a first opening and a second opening positioned at opposite ends of the body. Further, the optical accessory includes a plurality of reflective plates positioned within the body and movably coupled to the body, each reflective plate configured to move from a first orientation to a second orientation relative to the body. When each reflective plate is positioned in the first orientation, the plurality of reflective plates are configured to receive an infrared wave from the first opening of the body and reflect the infrared wave toward the second opening of the body. When each reflective plate is positioned in the second orientation, the plurality of reflective plates are configured to allow an infrared wave to travel along a linear path from the first opening to the second opening of the body.

[0006] In some embodiments, the body of the optical accessory has a conical shape, a cylindrical shape, or a frustoconical shape.

[0007] In some embodiments, the optical accessory further includes at least one switch. The at least one switch is configured to switch the plurality of reflective plates between the first orientation and the second orientation. In some embodiments, the at least one switch corresponds to at least one of a mechanical switch or an electrical switch.

[0008] In another example embodiment, a system for training a flame detector is disclosed. The system includes an optical accessory mounted to the flame detector. The optical accessory includes a body defining a first opening and a second opening positioned at opposite ends of the body. Further, the optical accessory includes a plurality of reflective plates positioned within the body and movably coupled to the body, each reflective plate configured to move from a first orientation to a second orientation relative to the body. When each reflective plate is positioned in the first orientation, the plurality of reflective plates is configured to receive an infrared wave from the first opening of the body and reflect the infrared wave toward the second opening of the body and toward the flame detector. When each reflective plate is positioned in the second orientation, the plurality of reflective plates is configured to allow an infrared wave to travel along a linear path from the first opening to the second opening of the body and to the flame detector. Further, the system includes at least one processor communicatively coupled to the flame detector. The at least one processor is configured to train the flame detector using (i) a first data set indicative of the infrared wave received by the flame detector after reflection from the plurality of reflective plates and (ii) a second data set indicative of the infrared wave received by the flame detector after travel along the linear path.

[0009] In some embodiments, the at least one processor is configured to train the flame detector using a machine learning (ML) model having one or more parameters based at least on the first data set and the second data set.

[0010] In some embodiments, the one or more parameters include at least one of: an amplitude, a ratio, a power spectral density, a ratio of the power spectral density, a rise time, a fall time, a ratio of the rise time to the fall time, a growth pattern / quenching pattern, a peak, a valley, a moving average, a symmetry, a lack of symmetry around a center of distribution of the infrared wave, a heavy or light tail relative to a normal distribution of the infrared wave.

[0011] In some embodiments, the at least one processor is further configured to determine a presence or an absence of an unfriendly flame within a field of view of the flame detector.

[0012] In some embodiments, the body of the optical accessory has a tubular shape. The tubular shape is a conical shape, a cylindrical shape, or a frustoconical shape.

[0013] In yet another example implementation, a method for training a flame detector is disclosed. The method includes aiming the flame detector at a field of view having one or more friendly flames. Further, the method includes mounting an optical accessory onto the flame detector, wherein the flame detector includes a plurality of reflective panels each configured to move from a first orientation to a second orientation. Further, the method includes aiming the optical accessory at one of the one or more friendly flames. When each reflective panel is positioned in the first orientation, the plurality of reflective panels are configured to receive an infrared wave from the one of the one or more friendly flames and reflect the infrared wave toward the flame detector. When each reflective panel is positioned in the second orientation, the plurality of reflective panels are configured to allow an infrared wave from the one of the one or more friendly flames to travel to a flame detector along a linear path. The method then includes training, via at least one processor communicatively coupled to the flame detector, the flame detector using (i) a first data set indicative of the infrared wave received by the flame detector after reflection from the plurality of reflective panels and (ii) a second data set indicative of the infrared wave received by the flame detector after traveling along the linear path.

[0014] The above summary of the invention is provided for the purpose of summarizing some example implementations only and is provided in order to provide a basic understanding of aspects of the invention. Thus, it will be appreciated that the above described implementations are merely examples and are not intended to limit the scope of the invention in any way. It is recognized that numerous potential embodiments exist, some of which will be further described below, which are within the scope of the invention. BRIEF DESCRIPTION OF DRAWINGS

[0015] Thus, having generally described certain example implementations of the disclosure, reference will now be made to the following drawings, which are not necessarily drawn to scale, and wherein:

[0016] Figure 1 a block diagram illustrating a system for training a flame detector according to example implementations of the disclosure is illustrated;

[0017] Figure 2 a schematic perspective view of an optical accessory for training a flame detector according to example implementations of the disclosure is illustrated;

[0018] Figure 3A a flow diagram illustrating a method of a training mode of an optical accessory according to example implementations of the disclosure is illustrated;

[0019] Figure 3B a flow diagram illustrating a method of a monitoring mode of a system according to example implementations of the disclosure is illustrated; and

[0020] Figure 4 A flowchart showing a method for training a flame detector according to example embodiments of the present disclosure is illustrated. DETAILED DESCRIPTION

[0021] Some embodiments will now be described below with reference to the attached drawings, which are meant to be exemplary and not limiting. Indeed, various embodiments can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. These provide one or more specific embodiments of implementations, as defined in the written description.

[0022] The components illustrated in the figures represent components that can or can not be present in various embodiments of the application described herein, such that embodiments can include fewer or more components than those shown in the figures, without departing from the scope of the application. Some components can be omitted from one or more of the figures, or otherwise shown in dashed lines to illustrate that the components are optional in some embodiments.

[0023] As used herein, the term “includes” means includes but not limited to, and is to be interpreted in the same manner as “comprising” in the context of patent terminology. The use of broader terms such as “includes,” “comprises,” and “has” should be understood as providing support for narrower terms such as “consisting of,” “consisting essentially of,” and “consisting.”

[0024] The phrases “in various embodiments,” “in one embodiment,” “according to an embodiment,” “in some embodiments,” and the like generally mean that the particular feature, structure, or characteristic following the phrase can be included in at least one embodiment of the present disclosure, and can be included in more than one embodiment of the present disclosure (importantly, such phrases do not necessarily refer to the same embodiments).

[0025] The words “example” or “exemplary” are used herein to mean “serving as an example, instance, or illustration.” Any implementation described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other implementations.

[0026] If this specification states a component, feature, structure, or characteristic “may,” “could,” “should,” “would,” “can,” “likely,” “typically,” “optionally,” “for example,” “usually,” or “possibly” (or other similar language) be included or have a particular quality, that particular component, feature, structure, or characteristic need not be included or have the particular quality. Such components, features, structures, or characteristics can be optional in some embodiments, or it can be excluded.

[0027] The present disclosure provides various embodiments of optical accessories, systems, and methods for training a flame detector. Embodiments can include an optical accessory that mounts onto a flame detector. Embodiments can include a body that defines a first opening and a second opening positioned at opposite ends of the body. Embodiments can include a plurality of reflective plates positioned within the body and movably coupled to the body, each reflective plate configured to move from a first orientation to a second orientation relative to the body. In various embodiments, when each reflective plate is positioned in the first orientation, the plurality of reflective plates can be configured to receive an infrared wave from the first opening of the body and reflect the infrared wave toward the second opening of the body. In various embodiments, when each reflective plate is positioned in the second orientation, the plurality of reflective plates can be configured to allow the infrared wave to travel along a linear path from the first opening to the second opening of the body. Embodiments can include at least one processor communicatively coupled to the flame detector. Embodiments can be configured to train the flame detector using a first data set indicative of infrared waves received by the flame detector after reflection from the plurality of reflective plates and a second data set indicative of infrared waves received by the flame detector after travel along the linear path.

[0028] Figure 1 A block diagram of a system 100 for training a flame detector 102 according to example embodiments of the present disclosure is illustrated. The system 100 can include an optical accessory 104. Further, the flame detector 102 can include at least one processor 106, a memory 108, an infrared (IR) signal processing unit 110, and a machine learning (ML) model 112.

[0029] In some embodiments, the optical accessory 104 mounts onto the flame detector 102. In some embodiments, the optical accessory 104 is positioned proximate to, but spaced apart from, the flame detector 102. In some embodiments, the optical accessory 104 is positioned proximate to the flame detector 102 such that the optical accessory 104 is in contact with the flame detector. The optical accessory 104 can include a body 202 Figure 2 that defines a first opening 204 Figure 2 and a second opening 206 Figure 2 . In some embodiments, the body 202 of the optical accessory 104 can include a tubular shape. Further, the tubular shape can correspond to a conical shape, a cylindrical shape, or a truncated cone shape. The first opening 204 and the second opening 206 can be positioned at opposite ends of the body 202. Further, the optical accessory 104 can include a plurality of reflective plates 208 Figure 2 . The plurality of reflective plates 208 can be positioned within the body 202 and movably coupled to the body. Each reflective plate from the plurality of reflective plates 208 can be configured to move from a first orientation to a second orientation relative to the body 202, as illustrated in FIG. 1. In various embodiments, when each reflective plate is positioned in the first orientation, the plurality of reflective plates 208 can be configured to receive an infrared wave from the first opening 204 of the body 202 and reflect the infrared wave toward the second opening 206 of the body 202. In various embodiments, when each reflective plate is positioned in the second orientation, the plurality of reflective plates 208 can be configured to allow the infrared wave to travel along a linear path from the first opening 204 to the second opening 206 of the body 202.Figure 2 The first orientation 214 depicted in the top image Figure 2 Move to, as Figure 2 The second orientation 216 depicted in the bottom image Figure 2 Each of the multiple reflectors 208 may include a reflective material such as silver, aluminum, stainless steel, etc.

[0030] In some implementations, when each reflector is positioned in a first orientation, the plurality of reflectors 208 may be configured to receive infrared (IR) waves 226 from the first opening 204 of the body 202. Figure 2 Then, a plurality of reflectors 208 can be configured to reflect IR waves 226 toward the second opening 206 of the body 202 and toward the flame detector 102. For example, IR waves 226 can enter the first opening 204 and reflect toward the first reflector 210. Figure 2 ) moves forward, and then from the first reflector 210 toward the second reflector 212 ( Figure 2 The reflection occurs, and subsequently, the reflection occurs from the second reflector 212 toward the second opening 206 of the body 202, as shown below. Figure 2 The top image depicts this. In one example, the IR wave 226 reflected toward the second opening 206 corresponds to the reflected IR wave 226.

[0031] In some implementations, when each reflector is positioned in a second orientation 216, the plurality of reflectors 208 can be configured to allow the IR wave 226 to travel along a linear path from the first opening 204 of the body 202 to the second opening 206 and to the flame detector 102, such as Figure 2 The bottom image depicts this. In one example, the IR wave 226 traveling along a linear path can correspond to the direct IR wave 226.

[0032] In some embodiments, the optical accessory 104 may also include at least one switch (not shown). The at least one switch may be configured to switch the plurality of reflectors 208 between a first orientation 214 and a second orientation 216. In one example, the at least one switch may correspond to at least one of a mechanical switch or an electrical switch. A mechanical switch may include physical mechanisms, such as levers, buttons, or dials, for manually adjusting the plurality of reflectors 208. An electrical switch may be operated by electronic control signals to remotely or automatically adjust the plurality of reflectors 208.

[0033] In some embodiments, the system 100 can include a flame detector 102. The flame detector 102 can include a plurality of IR sensors 114. The plurality of IR sensors 114 can include a first IR sensor, a second IR sensor, and up to an “N” number of IR sensors. Each IR sensor of the plurality of IR sensors 114 can be configured to detect IR waves 226 from a monitored zone (not shown), including reflected IR waves 226 and direct IR waves 226. The monitored zone can correspond to a zone in which a hazardous flame can be present, and in which the presence is desired to be detected. Further, the IR signal processing unit 110 can be configured to process the received IR waves 226. The IR signal processing unit 110 can receive and interpret the infrared waves detected by the plurality of IR sensors 114. Upon receiving the IR waves 226, the IR signal processing unit 110 can convert the IR waves 226 into electrical signals. The electrical signals can be further analyzed and processed to extract meaningful information from the IR waves 226. In some embodiments, the IR signal processing unit 110 can filter out noise, enhance signal clarity from the IR waves 226, while converting the IR waves 226 into electrical signals. Additionally, the IR signal processing unit 110 can incorporate digital signal processing (DSP) to optimize performance and accuracy, thereby ensuring reliable operation in the processing of the IR waves 226, as well as precise detection and control capabilities. Accordingly, the IR signal processing unit 110 can provide processed IR waves 226 from the monitored zone. It will be apparent to those skilled in the art that the flame detector 102 can measure thermal radiation or infrared (IR) emissions from infrared waves within a field of view (FOV) of the flame detector 102.

[0034] In some embodiments, the at least one processor 106 can be communicatively coupled to the flame detector 102. The at least one processor 106 can be configured to receive the output 118 of the IR signal processing unit 110 to determine whether the IR waves 226 correspond to a flame. Meanwhile, the at least one processor 106 can be configured to train the flame detector 102 using the training dataset 116. The training dataset 116 can include a first dataset and a second dataset. The first dataset can indicate the IR waves 226 received by the flame detector 102 after reflection from the plurality of reflective plates 208, i.e., the reflected IR waves 226. The second dataset can indicate the IR waves 226 received by the flame detector 102 after traveling along the linear path, i.e., the direct IR waves 226.

[0035] In some implementations, at least one processor 106 may be configured to train the flame detector 102 using an ML model 112. The ML model 112 may include one or more parameters based at least on a first dataset and a second dataset. Furthermore, the one or more parameters may include at least one of the following: amplitude, ratio, power spectral density, ratio of the power spectral density, rise time, fall time, ratio of the rise time to the fall time, growth pattern / quenching pattern, peak, trough, moving average, symmetry, lack of symmetry around the distribution center of the infrared wave, heavy tail or light tail relative to the normal distribution of the infrared wave. The ML model 112 may classify the training dataset based on one or more parameters of the ML model and a threshold of the ML model. The threshold of the ML model may determine a decision boundary for classifying the first and second datasets from the flame detector, thereby ensuring that IR waves 226 that meet or exceed the threshold are classified as having or not having an unfriendly flame. The at least one processor 106 may then be configured to determine whether an unfriendly flame exists or does not exist within the FOV of the flame detector 102. At least one processor 106 can determine the presence or absence of a flame detector 102 based at least on training the flame detector 102 using an ML model 112.

[0036] In some embodiments, at least one processor 106 may include suitable logic components, circuitry, and / or interfaces operable to execute one or more instructions stored in memory 108 to perform predetermined operations. In one embodiment, at least one processor 106 may be configured to decode and execute any instructions received from one or more other electronic devices or servers. At least one processor 106 may be configured to execute one or more computer-readable program instructions, such as program instructions for performing any functions described herein. Furthermore, at least one processor 106 may be implemented using one or more processor technologies known in the art. Examples of at least one processor 106 include, but are not limited to, one or more general-purpose processors (e.g., or Advanced Micro (AMD) microprocessors) and / or one or more dedicated processors (e.g., digital signal processors or System-on-a-Chip (SOC) Field Programmable Gate Array (FPGA) processor.

[0037] In some embodiments, the memory 108 can be configured to store a set of instructions and data for execution by the one or more processors 106. In one example, the memory 108 can correspond to a non-volatile memory 108. Further, the memory 108 can include one or more instructions that are executable by the at least one processor 106 to perform a particular operation. The memory 108 can be configured to include instructions for training the flame detector 102 using a first data set indicative of infrared waves received by the flame detector 102 after reflection from a plurality of reflective panels 208 and a second data set indicative of infrared waves received by the flame detector 102 after traveling along a linear path. The memory 108 can be configured to include instructions for training the flame detector 102 using the ML model 112 having one or more parameters based at least on the first data set and the second data set. Further, the memory 108 can be configured to include instructions for determining a presence or an absence of an unfriendly flame within a FOV of the flame detector 102. It will be apparent to those of ordinary skill in the art that the one or more instructions stored in the memory 108 enable the hardware of the flame detector 102 to perform a predetermined operation. Some known implementations of the memory 108 include, but are not limited to, a fixed (hard) drive, magnetic tape, a floppy disk, an optical disk, a compact disk read-only memory (CD-ROM), and a magneto-optical disk, a semiconductor memory such as ROM, random access memory (RAM), programmable read-only memory (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), a flash memory, a magnetic or optical card, or other type of media / machine-readable medium suitable for storing electronic instructions.

[0038] The system 100 can also include an output 118. The output 118 can be coupled to the at least one processor 106. The output 118 can generate information regarding whether the IR waves 226 correspond to a presence or an absence of an unfriendly flame based on the output of the IR signal processing unit 110 and the at least one processor 106. The output 118 can generate information regarding a presence or an absence of an unfriendly flame as a flame or no flame, respectively. In one example, the output 118 can generate a presence of an unfriendly flame when the IR signal processing unit 110 determines that the received IR waves 226 correspond to a flame and the at least one processor 106 determines that the received IR waves correspond to direct IR waves 226. In another example, the output 118 can generate an absence of an unfriendly flame when the IR signal processing unit 110 determines that the IR waves 226 correspond to a flame and the at least one processor 106 determines that the IR waves 226 correspond to reflected IR waves 226.

[0039] In one example embodiment, the output 118 can correspond to a digital output to generate information in a discrete digital format. The digital output can generate a discrete signal, such as a high state or a low state, indicating binary information, such as the presence or absence of an unfriendly flame. The digital output can be based on the system 100 triggering an alarm (digital high) or confirming safety (digital low) to ensure accurate and effective response to fire risks in industrial or commercial environments. In another example embodiment, the output 118 can correspond to an analog output to provide a continuous representation of temperature to enable real-time monitoring and analysis. The analog output can provide a continuous voltage or current signal proportional to the intensity of the detected IR waves 226, indicating the presence or absence of an unfriendly flame based on direct or reflected IR waves 226.

[0040] In various examples, the system 100 can be installed near a monitored area. In some embodiments, the monitored area can be an area that is prone to fire, such as an industrial oil site. It will be apparent to those skilled in the art that a prone-to-fire area is an area in which a fire is most likely to occur or has a higher tendency to occur. In various examples, a prone-to-fire area is an area in which a fire is expected to be present during normal operation. For example, a fire can be projected from a flare stack during normal operation of the flare stack.

[0041] It will be apparent to those skilled in the art that the processing steps can be performed by the at least one processor 106 of the system 100 using the IR signal processing unit 110 and the machine learning model, without departing from the scope of the present disclosure.

[0042] It is apparent that the above-mentioned components of the system 100 are provided for illustrative purposes only. In another embodiment, the system 100 can include other components, such as a controller unit, a microprocessor unit (MPU), a microcontroller unit (MCU), and the like, without departing from the scope of the present disclosure.

[0043] Figure 2 A schematic perspective view of the optical accessory 104 for training the flame detector 102 is illustrated in accordance with an example embodiment of the present disclosure. The description of the optical accessory 104 is provided in conjunction with the description of the flame detector 102. Figure 1 The description of the optical accessory 104 is provided in conjunction with the description of the flame detector 102. Figure 2 The description of the optical accessory 104 is provided in conjunction with the description of the flame detector 102.

[0044] As Figure 1As described herein, the optical accessory 104 can be mounted to the flame detector 102. The optical accessory 104 can be positioned proximate to, but spaced apart from, the flame detector 102. The optical accessory 104 can be positioned proximate to the flame detector 102 such that the optical accessory 104 is in contact with the flame detector. The optical accessory 104 can include a body 202 that defines a first opening 204 and a second opening 206. In some embodiments, the body 202 of the optical accessory 104 can include a tubular shape. Further, the tubular shape can correspond to a conical shape, a cylindrical shape, or a truncated cone shape. The first opening 204 and the second opening 206 can be positioned at opposite ends of the body 202.

[0045] In some embodiments, the optical accessory 104 can include a plurality of reflective plates 208. Further, the plurality of reflective plates can include a first reflective plate 210 and a second reflective plate 212. The first reflective plate 210 and the second reflective plate 212 can be positioned within the body 202 and can be movably coupled to the body. In some embodiments, the first reflective plate 210 and the second reflective plate 212 can be fabricated in one or more shapes that can include at least one of a parabolic reflector, an elliptical reflector, a planar reflector, a corner cube reflector, or a Fresnel reflector. In some embodiments, the first reflective plate 210 and the second reflective plate 212 can be arranged in parallel such that the received IR waves can be appropriately reflected and / or transmitted between the first reflective plate 210 and the second reflective plate 212, as depicted in the top image of FIG. 2. Figure 2

[0046] In some embodiments, the first reflective plate 210 and the second reflective plate 212 can be configured to move from a first orientation 214 to a second orientation 216 relative to the body 202. In some embodiments, when the first reflective plate 210 and the second reflective plate 212 are positioned in the first orientation 214, as depicted in the top image of FIG. 2, the plurality of reflective plates can be configured to receive IR waves 226 from the first opening 204 of the body 202. Herein, the IR waves 226 can be received from the first friendly flame 218 of the zone 220. Then, the plurality of reflective plates can be configured to reflect the IR waves 226 toward the second opening 206 of the body 202 and toward the flame detector 102. Figure 2

[0047] ​​The reflected IR waves 226 from the plurality of friendly flames can be used to train the flame detector 102. For example, the flame detector 102 can be trained with a plurality of friendly flames by individually sequentially training the flame detector 102 with each friendly flame. For example, the plurality of reflective panels can be configured to receive reflected IR waves 226 from the second friendly flame 222, and subsequently configured to receive IR waves 226 from the third friendly flame 224 of the zone 220. Accordingly, a first data set can be generated that indicates the IR waves 226, i.e., the reflected IR waves 226, received by the flame detector 102 from the first friendly flame 218, the second friendly flame 222, and the third friendly flame 224 of the zone 220 after reflection from the plurality of reflective panels. As will become apparent in view of the present disclosure, the reflected IR waves 226 can mimic or resemble IR waves from a friendly or known flame that are subsequently reflected from shiny or reflective materials within the zone 220, which can undesirably result in false alarms.

[0048] In some embodiments, when the first reflective panel 210 and the second reflective panel 212 are positioned in the second orientation 216, the plurality of reflective panels can be configured to allow IR waves 226 to travel along a linear path from the first opening 204 to the second opening 206 of the main body 202 and to the flame detector 102. Herein, the IR waves 226 can be received from the first friendly flame 218 of the zone 220. The direct IR waves 226 from the plurality of friendly flames can be used to train the flame detector 102. For example, the flame detector 102 can be trained with a plurality of friendly flames by individually sequentially training the flame detector 102 with each friendly flame. For example, the system 100 can be configured such that the flame detector 102 receives direct IR waves 226 from the second friendly flame 222, and subsequently configured such that the flame detector 102 receives direct IR waves 226 from the third friendly flame 224 of the zone 220. Accordingly, a second data set can be generated that indicates the IR waves 226, i.e., the direct IR waves 226, received by the flame detector 102 from the first friendly flame 218, the second friendly flame 222, and the third friendly flame 224 of the zone 220 after traveling along the linear path. As will become apparent in view of the present disclosure, the direct IR waves 226 can mimic or resemble IR waves emitted from an undesirable or unfriendly flame in the zone 220.

[0049] In some embodiments, the at least one processor 106 can be configured to train the flame detector 102 using the training data set 116. The training data set 116 can include a first data set of reflected IR waves 226 from the first friendly flame 218, the second friendly flame 222, and the third friendly flame 224 of the zone 220, and a second data set of direct IR waves 226 from the first friendly flame 218, the second friendly flame 222, and the third friendly flame 224 of the zone 220. In some embodiments, the at least one processor 106 can be configured to train the flame detector 102 using the ML model 112. The ML model 112 can include one or more parameters based at least on the first data set and the second data set. The at least one processor 106 can then be configured to determine a presence or an absence of an unfriendly flame in the zone 220 within the FOV of the flame detector 102.

[0050] Figure 3A A flowchart illustrating a method 300 showing a training mode of the optical accessory 104 according to example embodiments of the present disclosure is illustrated. Figure 3B A flowchart illustrating a method 316 showing a monitoring mode of the system 100 according to example embodiments of the present disclosure is illustrated. The method 316 is described in conjunction with Figures 1-2 The method 316 is described. Figures 3A-3B The method 316 is described.

[0051] Referring to Figure 3A , the training mode of the flame detector 102 can include configuring the flame detector 102 to learn and adjust sensitivity thresholds and response parameters based on controlled exposure to one or more friendly flames using the optical accessory 104. At operation 302, the flame detector 102 can be installed and enter a training mode. At operation 304, the optical accessory 104 can be installed onto or near the flame detector 102 and facing the first friendly flame 218. At operation 306, the optical accessory 104 can be positioned in a first position such that the flame detector 102 receives the reflected IR waves 226. The at least one processor 106 can be commanded to collect a first data set. The reflected IR waves 226 can be received by the flame detector 102 from the first friendly flame 218.

[0052] At operation 308, the optical attachment 104 can be positioned in a second position such that the flame detector 102 receives direct IR waves 226. The at least one processor 106 can be commanded to collect a second data set. The direct IR waves 226 can be received from the first friendly flame 218. At operation 310, the optical attachment 104 can be pointed at a second friendly flame 222. At operation 312, operations 302-310 can be repeated for the second friendly flame 222. In some embodiments, operations 302-310 can be repeated for the third friendly flame 224 and other one or more friendly flames. At operation 314, the flame detector 102 can be trained with the first data set and the second data set, and the ML model 112 can be stored in the memory 108 of the flame detector 102. The ML model 112 can be stored in the memory 108 to determine the presence or absence of an unfriendly flame within the FOV of the flame detector 102.

[0053] Reference is made to Figure 3B The monitoring mode of the flame detector 102 can activate an operational state of the flame detector 102. In the operational state, the flame detector 102 can continuously scan the environment to determine the presence or absence of an unfriendly flame based on the training in the training mode.

[0054] At operation 318, the optical attachment 104 can be removed and the flame detector 102 can be put into the monitoring mode. At operation 320, the flame detector 102 can continuously process data of the plurality of IR sensors. The data can correspond to the first data set and the second data set indicative of the received IR waves 226 from the monitored zone. At operation 322, the data can be processed by the IR signal processing unit 110 and the at least one processor 106 to detect a flame. Concurrently with operation 322, at operation 324, the data can be fed to the ML model 112 which classifies the data based on one or more parameters of the ML model 112 and a threshold value of the ML model 112. The classification of the data can facilitate determining the presence or absence of an unfriendly flame based on the learning of the training data sets 116 in the training mode.

[0055] At operation 326, the at least one processor 106 can provide an output of the IR signal processing unit 110 as a flame based on the processed data. At operation 328, the output of the ML model 112 can be provided as the direct IR waves 226 or the reflected IR waves 226 when the reflected infrared waves are obtained to provide the output 118 as the absence of an unfriendly flame.

[0056] Figure 4 A flowchart illustrating a method 400 of a system for training a flame detector 102 according to an example embodiment of the present disclosure is exemplified. The method 400 is described in conjunction with Figures 1-3B Reference is made to Figure 4 which is described.

[0057] At operation 402, the flame detector 102 can be aimed at a FOV having one or more friendly flames. For example, the flame detector 102 is aimed at a FOV having the first friendly flame 218. At operation 404, the optical accessory 104 can be mounted onto the flame detector 102, where the flame detector 102 includes a plurality of reflective plates 208 that are each configured to move from a first orientation to a second orientation, and vice versa. In some embodiments, the optical accessory 104 can have a body 202 that has a tubular shape that narrows the area of the field of view sensed by the flame detector 102. The tubular shape can correspond to a conical shape, a cylindrical shape, or a truncated cone shape. In some embodiments, the optical accessory 104 can also include at least one switch. The at least one switch can be configured to switch the plurality of reflective plates 208 between the first orientation and the second orientation. Further, the at least one switch can correspond to at least one of a mechanical switch or an electrical switch. For example, the optical accessory 104 is mounted onto the flame detector 102 that is aimed at a FOV having the first friendly flame 218.

[0058] At operation 406, the optical accessory 104 can be aimed at one of the one or more friendly flames. In some embodiments, when each reflective plate is positioned in the first orientation, the plurality of reflective plates 208 can be configured to receive an infrared wave from one of the one or more friendly flames and reflect the infrared wave toward the flame detector 102. In some embodiments, when each reflective plate is positioned in the second orientation, the plurality of reflective plates 208 can be configured to allow an infrared wave from one of the one or more friendly flames to travel along a linear path to the flame detector 102. For example, the optical accessory 104 is aimed at a FOV having the first friendly flame 218

[0059] At operation 408, the at least one processor 106 communicatively coupled to the flame detector 102 can be configured to train the flame detector 102 using the first data set indicative of the infrared waves received by the flame detector 102 after reflection from the plurality of reflective plates 208 and the second data set indicative of the infrared waves received by the flame detector 102 after traveling along the linear path. In some embodiments, training the flame detector 102 via the at least one processor 106 communicatively coupled to the flame detector 102 can include using the ML model 112 having one or more parameters based at least on the first data set and the second data set. The one or more parameters can include at least one of: an amplitude, a ratio, a power spectral density, a ratio of power spectral densities, a rise time, a fall time, a ratio of rise time to fall time, a growth pattern / quenching pattern, a peak, a valley, a moving average, a symmetry, a lack of symmetry about a center of distribution of the infrared waves, a heavy or light tail relative to a normal distribution of the infrared waves. For example, the at least one processor 106 trains the flame detector 102 using the ML model 112, the generated first data set indicative of the IR waves 226 received by the flame detector 102 from the first friendly flame 218 after reflection from the plurality of reflective plates 208, and the generated second data set indicative of the IR waves 226 received by the flame detector 102 from the first friendly flame 218 after traveling along the linear path.

[0060] In some embodiments, the method can further include determining a presence or an absence of an unfriendly flame within a field of view of the flame detector 102. For example, the at least one processor 106 determines, based on the training using the first friendly flame 218, an absence of an unfriendly flame in the oil refinery. As will be appreciated in light of the present disclosure, one or more parameters from the first data set can be similar or identical to one or more parameters from a reflection of a known or friendly flame, which can be indicative of the infrared waves received by the flame detector 102 after reflection from the plurality of reflective plates (i.e., reflected IR waves 226). Thus, when the system 100 is in a monitoring mode, the at least one processor 106 can determine an absence of an unfriendly flame based on a similarity of the parameters of the received IR waves compared to the parameters of the first data set. Similarly, one or more parameters from the second data set can be similar or identical to one or more parameters from an unfriendly flame, which can be indicative of the infrared waves received by the flame detector 102 after traveling along the linear path (i.e., direct IR waves 226). Thus, when the system 100 is in a monitoring mode, the at least one processor 106 can determine a presence of an unfriendly flame based on a similarity of the parameters of the received IR waves compared to the parameters of the second data set.

[0061] Many modifications and other embodiments of the present application set forth herein will come to mind to one skilled in the art to which the present application pertains having the benefit of the teachings presented in the foregoing description and the associated drawings. Therefore, it is to be understood that the present application is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, although the foregoing description and the associated drawings set forth example embodiments in the context of certain example combinations of elements and / or functions, one of ordinary skill in the art will appreciate that other combinations of elements and / or functions are also possible. In this regard, for example, the methods described herein can be carried out in a different order than as described, or using a different combination of elements and / or functions. With respect to the use of temporal terms, such as "before" and "after," the content of such terms is used as described herein and can be relative to a reference time. Further, although the terminology used herein is for the purpose of describing particular embodiments and is in no way limiting, it is to be understood that the use of singular or plural number terms can be changed as can be suitable.

Claims

1. An optical accessory for training a flame detector, the optical accessory comprising: A main body defining a first opening and a second opening, the first opening and the second opening being positioned at opposite ends of the main body; and A plurality of reflectors are positioned within the body and movably coupled to the body, each reflector being configured to move relative to the body from a first orientation to a second orientation. When each reflector is positioned with the first orientation, the plurality of reflectors are configured to receive infrared waves from the first opening of the body and reflect the infrared waves toward the second opening of the body. When each reflector is positioned in the second orientation, the plurality of reflectors are configured to allow infrared waves to travel along a linear path from the first opening to the second opening of the body.

2. The optical accessory according to claim 1, wherein the body of the optical accessory has a conical shape, a cylindrical shape, or a truncated cone shape.

3. The optical accessory of claim 1, further comprising at least one switch, wherein the at least one switch is configured to switch the plurality of reflectors between the first orientation and the second orientation.

4. The optical accessory according to claim 3, wherein the at least one switch corresponds to at least one of a mechanical switch or an electrical switch.

5. A system for training a flame detector, the system comprising: Optical accessories, which are mounted on the flame detector and include: A body defining a first opening and a second opening, the first opening and the second opening being positioned at opposite ends of the body; and A plurality of reflectors are positioned within the body and movably coupled to the body, each reflector being configured to move relative to the body from a first orientation to a second orientation. When each reflector is positioned in the first orientation, the plurality of reflectors are configured to receive infrared waves from the first opening of the body and reflect the infrared waves toward the second opening of the body and toward the flame detector. When each reflector is positioned in the second orientation, the plurality of reflectors are configured to allow infrared waves to travel along a linear path from the first opening of the body to the second opening and to the flame detector; and At least one processor, communicatively coupled to the flame detector, wherein the at least one processor is configured to train the flame detector using (i) a first dataset indicating the infrared waves received by the flame detector after reflection from the plurality of reflectors and (ii) a second dataset indicating the infrared waves received by the flame detector after traveling along the linear path.

6. The system of claim 5, wherein the at least one processor is configured to train the flame detector using a machine learning (ML) model having at least one or more parameters based on the first dataset and the second dataset.

7. The system of claim 6, wherein the one or more parameters include at least one of the following: amplitude, ratio, power spectral density, ratio of the power spectral density, rise time, fall time, ratio of the rise time to the fall time, growth mode / quenching mode, peak, valley, moving average, symmetry, lack of symmetry around the distribution center of the infrared wave, heavy tail or light tail relative to the normal distribution of the infrared wave.

8. The system of claim 5, wherein the at least one processor is further configured to determine whether an unfriendly flame exists or does not exist within the field of view of the flame detector.

9. The system of claim 5, wherein the body of the optical accessory has a tubular shape.

10. The system of claim 9, wherein the tubular shape is a conical shape, a cylindrical shape, or a truncated cone shape.

Images