Multi-probe flame detection device, method and system

Abstract

The invention relates to the field of optical fiber sensing, in particular to a multi-probe flame detection device, method and system. The method comprises the steps that a plurality of optical fiber probes are configured, and the emitting directions corresponding to the probes are different, so that optical signals of boiler flames are collected from different angles and positions, the flame range detected by a flame sensor is enlarged, more details and characteristics of the flames can be captured, and the flame detection accuracy is improved. Comprise the shape of the flame, brightness distribution and possible abnormal points. And an optical fiber processing unit in the flame detection module further performs wavelength coding on the collected flame light, so that the composition and the state of the flame can be analyzed more accurately. Therefore, compared with a traditional single-point or limited-angle flame detection mode, the flame detection comprehensiveness can be remarkably improved, the flame range detected by the flame sensor is enlarged, and a more reliable guarantee is provided for safe operation of the boiler.

Description

Technical Field

[0001] The present application relates to the field of optical fiber sensing, and in particular to a multi-probe flame detection device, method and system. Background Art

[0002] In the current industrial production and operation of various thermal power plants, ensuring operational safety is always the top priority. To this end, real-time monitoring of combustion conditions has become an indispensable part, and among them, accurately determining the existence of flames is particularly important. Flame detection technology, as the core link in this monitoring process, plays a vital role. At present, the technology generally extends a flame sensor equipped with a fiber optic probe into the boiler so that the fiber optic probe can capture the specific wavelength of light released by the flame, and then accurately judge the real-time status of the flame.

[0003] However, in actual applications, due to certain changes in boiler load, the position of the flame often moves or expands based on the change in boiler load, which makes the detection area of ​​the flame sensor relatively limited, making it difficult to fully cover and accurately capture all the dynamics of the flame. Summary of the invention

[0004] In order to increase the flame range detected by the flame sensor, the present application provides a multi-probe flame detection device, method and system.

[0005] In a first aspect, the present application provides a multi-probe flame detection device, which adopts the following technical solution: A multi-probe flame detection device comprises a flame detection module, a control module and a plurality of optical fiber probes; The control module is electrically connected to the flame detection module and is used to control the flame detection module to detect the boiler flame; The flame detection module includes an optical fiber processing unit, and a plurality of optical fiber probes are connected to the flame detection module, each optical fiber probe has a different corresponding emission direction, and the optical fiber probe is used to collect the flame light of the boiler flame into the optical fiber, and the optical fiber processing unit performs wavelength encoding according to the collected flame light.

[0006] By adopting the above technical solution, by configuring multiple fiber optic probes, and each probe has a different corresponding emission direction, it is possible to collect the optical signal of the boiler flame from different angles and positions, increase the flame range detected by the flame sensor, and capture more details and characteristics of the flame, including the shape of the flame, brightness distribution, and possible abnormal points (such as local flameout or flame instability areas). The fiber optic processing unit in the flame detection module further encodes the wavelength of these collected flame lights, which helps to more accurately analyze the composition and state of the flame. Therefore, compared with the traditional single-point or limited-angle flame detection method, the device can significantly improve the comprehensiveness of flame detection, increase the flame range detected by the flame sensor, and provide more reliable protection for the safe operation of the boiler.

[0007] In a possible implementation, the control module is used to control the flame detection module to detect the boiler flame using various optical fiber probes.

[0008] By adopting the above technical solution, the flame detection module is controlled by the control module to use multiple fiber optic probes for flame detection, which can significantly improve the reliability and redundancy of flame detection. Since each fiber optic probe collects flame information from different angles and positions, even if a probe fails to work properly due to failure or contamination, other probes can still continue to provide valid flame data. This multi-probe design provides multiple safeguards for flame detection and reduces the risk of false alarms or missed alarms due to single point failures. Therefore, this solution has higher reliability in ensuring the safe operation of the boiler.

[0009] In a possible implementation, a gating module is installed between the flame detection module and the plurality of optical fiber probes, and the gating module is used to control the conduction of the optical fiber probes.

[0010] By adopting the above technical solution, the gating module can selectively conduct the optical fiber probe as needed. At a certain moment, only a specific probe is performing flame detection work, avoiding the waste of resources caused by all probes working at the same time. Especially when the boiler flame state is relatively stable, only some probes can be used for monitoring, thereby saving energy and reducing the system burden. At the same time, the gating module can also dynamically adjust the number and position of probes involved in the detection according to the specific needs of flame detection, ensuring that it can quickly respond and capture key information of the flame when needed, thereby improving detection efficiency.

[0011] In a possible implementation, the control module collects boiler load, determines the optical fiber probe to be connected according to the boiler load, and controls the selection module to turn on the optical fiber probe to be connected, so as to control the optical fiber probe to be connected to detect the boiler flame.

[0012] By adopting the above technical solution, the boiler load data is collected in real time through the control module, and the optical fiber probe to be connected is intelligently selected according to the load conditions, realizing the intelligent and adaptive flame detection. This design can ensure that the flame detection is always carried out according to the actual operating status of the current boiler, thereby improving the pertinence and accuracy of the detection. As the boiler load changes, the characteristics of the flame, such as position, shape and intensity, will also change accordingly, and this solution can automatically adjust the detection strategy to ensure that the most critical and accurate flame information is always captured. This not only helps to promptly discover and deal with potential combustion problems, but also optimizes the combustion process and improves the operating efficiency and safety of the boiler.

[0013] In a second aspect, the present application provides a multi-probe flame detection method, which adopts the following technical solution: A multi-probe flame detection method, the method is applied to a multi-probe flame detection system, the multi-probe flame detection system comprises an electronic device and the multi-probe flame detection device according to any one of claims 1 to 4 above, the method is performed by the electronic device, and comprises: receiving a boiler load of a boiler to be inspected; Determining the flame position of the boiler to be detected based on the boiler load; Determine the optical fiber probe corresponding to the flame position; Based on the optical fiber probe, a detection instruction is generated, and the detection instruction is sent to the control module; Receiving the wavelength code sent by the control module; Based on the wavelength code, the flame state of the boiler to be inspected is determined.

[0014] By adopting the above technical solution, by receiving the boiler load data, the flame position can be intelligently determined based on the actual operating status and load conditions of the boiler. This precise flame position positioning ensures that flame detection can be carried out on the most critical combustion area inside the boiler, increasing the effectiveness of the flame range detected by the flame sensor. At the same time, the automated process in the solution - from determining the flame position to selecting the corresponding fiber optic probe, to generating detection instructions and sending them to the control module, and finally receiving the wavelength code and determining the flame state - greatly reduces human intervention and realizes the automation of flame detection, which not only improves detection efficiency, but also reduces the risk of errors caused by human factors.

[0015] In a possible implementation, determining the flame position of the boiler to be detected based on the boiler load includes: Obtaining the fuel type corresponding to the boiler to be detected; The boiler load and the fuel type are input into the deep learning network model, and the output flame position is obtained to obtain the flame position of the boiler to be detected.

[0016] By adopting the above technical solution, the two key factors of boiler load and fuel type are comprehensively considered and provided as input information to the deep learning network model. With its powerful data processing and pattern recognition capabilities, the deep learning model is able to mine the complex nonlinear relationship between boiler load and flame position, as well as the impact of different fuel types on flame position. Therefore, compared with traditional rule-based or experience-based methods, it can more accurately predict the flame position of the boiler to be detected. This increase in accuracy helps the flame detection system to locate the flame more accurately, thereby improving the effectiveness and safety of flame monitoring.

[0017] In a possible implementation, the boiler load and the fuel type are input into a deep learning network model, and an output flame position is obtained, including: Inputting the boiler load into a convolutional neural network model to obtain the flame center position of the boiler to be detected; Inputting the flame center position and the fuel type into a recurrent neural network model to obtain the flame length; The flame position of the boiler to be inspected is determined based on the flame center position and the flame length.

[0018] By adopting the above technical solution, the accuracy and detail capture capabilities of flame position prediction are improved by using CNN and RNN models in stages. With its powerful feature extraction capabilities, the CNN model can effectively extract key features related to the center position of the flame from the boiler load data, thereby accurately predicting the center position of the flame. The RNN model is good at processing sequence data and can further predict the length of the flame, that is, the extension range of the flame inside the boiler, based on the center position of the flame and the fuel type information. This staged and step-by-step prediction method enables the entire system to capture the shape and position information of the flame in more detail, thereby improving the accuracy and reliability of flame position prediction.

[0019] In a possible implementation, determining the optical fiber probe corresponding to the flame position includes: Obtain the detection range corresponding to each optical fiber probe; Based on the flame position of the boiler to be detected and the detection range corresponding to each optical fiber probe, at least one target optical fiber probe is selected from multiple optical fiber probes, and the detection range corresponding to the target optical fiber probe can cover the flame position; Based on the target optical fiber probe, the optical fiber probe corresponding to the flame position is determined.

[0020] By adopting the above technical solution, by accurately matching the flame position with the detection range of the fiber optic probe, the fiber optic probe that can most accurately capture flame information can be selected as the target fiber optic probe. This targeted selection ensures that flame detection can be concentrated in the area where the flame actually exists, avoiding interference from irrelevant areas, thereby improving the accuracy of flame detection. In addition, since the target fiber optic probe can directly cover the flame position, it can more accurately reflect the shape, intensity and dynamic changes of the flame, providing reliable data support for subsequent flame state analysis and fault warning.

[0021] In a third aspect, the present application provides a multi-probe flame detection system, the system comprising: The multi-probe flame detection device according to any one of claims 1 to 4; Electronic equipment.

[0022] In a fourth aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the multi-probe flame detection method described in the second aspect above.

[0023] In a fifth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the multi-probe flame detection method described in the second aspect.

[0024] In summary, this application includes the following beneficial technical effects: By configuring multiple fiber optic probes, and each probe has a different corresponding emission direction, it is possible to collect the optical signal of the boiler flame from different angles and positions, increasing the flame range detected by the flame sensor, and being able to capture more details and characteristics of the flame, including the shape of the flame, brightness distribution, and possible abnormal points (such as local flameout or flame instability areas). The fiber optic processing unit in the flame detection module further encodes the wavelength of the collected flame light, which helps to more accurately analyze the composition and state of the flame. Therefore, compared with traditional single-point or limited-angle flame detection methods, this device can significantly improve the comprehensiveness of flame detection, increase the flame range detected by the flame sensor, and provide more reliable protection for the safe operation of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1is a schematic diagram of a multi-probe flame detection device provided in an embodiment of the present application; Figure 2 is a schematic diagram of another multi-probe flame detection device provided in an embodiment of the present application; Figure 3 It is a schematic flow chart of a multi-probe flame detection method provided in an embodiment of the present application; Figure 4 It is a structural schematic diagram of a multi-probe flame detection system provided in an embodiment of the present application; Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: 10, multi-probe flame detection device; 101, flame detection module; 102, control module; 103, optical fiber probe; 1011, optical fiber processing unit; 104, gating module. DETAILED DESCRIPTION

[0026] The following is combined with Figure 1-5 This application is described in further detail.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In order to facilitate understanding of the technical solution proposed in this application, several elements introduced in the description of this application are first introduced here. It should be understood that the following introduction is only for the convenience of understanding these elements, so as to understand the content of the embodiments of this application, and does not necessarily cover all possible situations.

[0029] The flame detector is an important part of the boiler furnace safety monitoring system. It is mainly used to monitor and judge the presence or absence of flame in the furnace to ensure the safe and stable operation of the boiler. When the fuel burns, the flame will produce ultraviolet light, visible light and infrared light of a certain intensity. The flame detector receives these light signals through the optical fiber sensor element and transmits them to the detector for processing. The optical sensor and photosensitive element inside the detector will analyze and judge the received light signals to determine whether the flame exists.

[0030] The flame detector mainly includes a control module, an optical fiber component and a signal processing module. The control optical component includes a fiber optic probe and a fiber optic protection tube. Generally, a flame sensor equipped with a fiber optic probe is inserted into the boiler so that the fiber optic probe can capture the specific wavelength light released by the flame, and then accurately judge the real-time status of the flame.

[0031] However, in actual applications, due to certain changes in boiler load, the position of the flame often moves or expands based on the change in boiler load, which makes the detection area of ​​the flame sensor relatively limited, making it difficult to fully cover and accurately capture all the dynamics of the flame.

[0032] In view of this, the embodiment of the present application provides a multi-probe flame detection device 10, which collects the optical signal of the boiler flame from different angles and positions by configuring multiple optical fiber probes, and each probe has a different corresponding emission direction, thereby increasing the flame range detected by the flame sensor, and being able to capture more details and characteristics of the flame, including the shape of the flame, brightness distribution, and possible abnormal points (such as local flameout or flame instability areas). The optical fiber processing unit in the flame detection module further encodes the wavelength of the collected flame light, which helps to more accurately analyze the composition and state of the flame. Therefore, compared with the traditional single-point or limited-angle flame detection method, the device can significantly improve the comprehensiveness of flame detection, increase the flame range detected by the flame sensor, and provide more reliable protection for the safe operation of the boiler.

[0033] See also Figure 1 , the first embodiment of the present application provides a multi-probe flame detection device 10, including: a flame detection module 101, a control module 102 and a plurality of optical fiber probes 103; Specifically, the control module 102 is electrically connected to the flame detection module 101, and is used to control the flame detection module 101 to detect the boiler flame. The control module 102 can control the operation of the entire flame detection device, including starting the flame detection module 101, receiving and processing data from the flame detection module 101, and judging the flame state (such as whether there is a flame, flame intensity, etc.) according to preset logical rules. Furthermore, the control module 102 can also interact with the user interface (such as a display screen, buttons, etc.) so that the user can monitor the flame state and adjust the detection parameters.

[0034] The flame detection module 101 includes an optical fiber processing unit 1011, and a plurality of optical fiber probes 103 are connected to the flame detection module 101. The optical fiber probes 103 are used to collect the flame light of the boiler flame into the optical fiber. The optical fiber processing unit 1011 performs wavelength encoding according to the collected flame light, that is, the flame detection module 101 is responsible for receiving the flame light signal from the optical fiber probe 103, and the optical fiber processing unit 1011 performs wavelength encoding on the collected flame light for subsequent analysis and identification of the flame state. Among them, the optical fiber processing unit 1011 includes components such as a photodiode, an optical amplifier, an optical filter, and a spectrometer.

[0035] The optical fiber probe 103 is responsible for collecting the flame light of the boiler flame into the optical fiber so as to transmit it to the flame detection module 101 for processing. Since each optical fiber probe 103 has a different corresponding emission direction, they can cover different areas of the boiler flame, thereby providing more comprehensive flame detection information. Among them, high-purity silica or germanium-doped silica is usually used for manufacturing.

[0036] Further, the control module 102 can be used to control the flame detection module 101 to detect the boiler flame using each fiber optic probe 103. Specifically, the control module 102 can select one or more fiber optic probes 103 from the multiple fiber optic probes 103 as the detection fiber optic probe 103, and detect the signal according to the detection fiber optic probe 103, so that the flame detection module 101 selects the detection fiber optic probe 103 to detect the boiler flame according to the detection signal.

[0037] See also Figure 2, a gating module 104 is installed between the flame detection module 101 and the multiple optical fiber probes 103, and the main function of the gating module 104 is to control the conduction of the optical fiber probes 103. Specifically, the gating module 104 can switch between the multiple optical fiber probes 103, and selectively conduct one or several optical fiber probes 103, so as to transmit the optical signal of the flame to the flame detection module 101 for processing. This switching function enables the multi-probe flame detection device 10 to flexibly monitor different areas of the boiler flame, thereby improving the accuracy and reliability of flame detection. Specifically, the control module 102 sends a detection signal to the flame detection module 101, and the flame detection module 101 sends a control instruction to the gating module 104 based on the detection signal. The gating module 104 receives the control instruction from the control module 102, and according to the received control instruction, the gating module 104 will select the detection optical fiber probe 103 from the multiple optical fiber probes 103 for conduction. The selected detection optical fiber probe 103 will transmit the optical signal of the flame to the flame detection module 101. In this process, the gating module 104 acts as a bridge, ensuring that the optical signal can be smoothly transmitted from one component to another. After the signal transmission is completed, the gating module 104 can send a feedback signal to the control module 102 to inform it that the specified operation has been completed. The control module 102 can adjust the subsequent detection instructions or perform other operations based on this feedback signal.

[0038] Furthermore, the change of boiler load will affect the shape of boiler flame. When boiler load increases, the primary and secondary air volume increases and the wind speed increases, the rigidity of coal powder jet ejected by burner is strong, the flame deviates from the geometric center line of combustion less, and the flame shape is more compact. On the contrary, when boiler load decreases, due to the decrease of primary and secondary air volume and wind speed, the rigidity of jet is weakened, the flame deviates from the geometric center line of combustion more, and the flame shape becomes more dispersed. Therefore, the optical fiber probe 103 for detecting boiler flame can be determined according to boiler load. Specifically, the control module 102 collects boiler load of boiler through sensor. After collecting boiler load data, the control module 102 can analyze these data by built-in algorithm to understand the flame position of boiler; or, the control module 102 sends the collected boiler load to the electronic device and receives the flame position sent by the electronic device. Based on the analysis result of boiler load, the control module 102 determines which optical fiber probes 103 are most suitable for current flame detection according to the layout of optical fiber probes 103 and the structure of boiler to obtain the optical fiber probes 103 to be connected. After determining the optical fiber probe 103 to be connected, the control module 102 sends a detection signal to the flame detection module 101, and the flame detection module 101 sends a control instruction to the gating module 104 based on the detection signal. After receiving the control instruction, the gating module 104 will turn on the optical fiber probe 103 to be connected according to the instruction. When the optical fiber probe 103 to be connected is turned on, the optical fiber probe 103 to be connected will start to collect the optical signals of the boiler flame and transmit these signals to the flame detection module 101. The flame detection module 101 will process and analyze these signals to determine the state of the flame.

[0039] See also Figure 3 The second embodiment of the present application provides a multi-probe flame detection method, which is applied to a multi-probe flame detection system. The multi-probe flame detection system includes an electronic device and the multi-probe flame detection device of the above embodiment. The method is executed by the electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited to the embodiment of the present application. The method includes: Step S301: receiving the boiler load of the boiler to be detected.

[0040] The unit of boiler load can be kcal / hour or watt. The control module collects the boiler load of the boiler through the sensor. After the control module collects the boiler load, the control module sends the boiler load to the electronic device, and the electronic device receives the boiler load of the boiler to be detected.

[0041] Step S302: Determine the flame position of the boiler to be inspected based on the boiler load.

[0042] After receiving the boiler load data, the flame position can be predicted using the existing flame position prediction model. Specifically, the boiler load of the boiler to be detected is input into the trained flame position prediction model, and the flame position of the boiler to be detected output by the flame position prediction model is obtained to obtain the flame position of the boiler to be detected. The flame position prediction model is trained with a large number of boiler load samples and flame position samples.

[0043] Step S303: determine the optical fiber probe corresponding to the flame position.

[0044] Each optical fiber probe corresponds to a detection range and a number, and the number and detection range corresponding to each optical fiber probe are recorded in the optical fiber database.

[0045] After the flame position of the boiler to be detected is obtained, based on the detection range corresponding to each optical fiber probe, it is determined whether there is an optical fiber probe that can fully detect the flame position from the detection ranges corresponding to the multiple optical fiber probes. If there is an optical fiber probe that can fully detect the flame position, the optical fiber probe that can fully detect the flame position is determined as the optical fiber probe corresponding to the flame position; if there is no optical fiber probe that can fully detect the flame position, at least two optical fiber probes that can cover all flame positions are determined based on the detection ranges corresponding to the multiple optical fiber probes, and the at least two optical fiber probes are used as the optical fiber probes corresponding to the flame position.

[0046] Step S304: Generate a detection instruction based on the optical fiber probe, and send the detection instruction to the control module.

[0047] The detection instruction includes the serial number of the optical fiber probe corresponding to the flame position.

[0048] After obtaining the optical fiber probe corresponding to the flame position, a corresponding detection instruction is generated based on the determined optical fiber probe, and then the instruction is sent to the control module, which is responsible for executing the specific detection operation.

[0049] Step S305: receiving the wavelength code sent by the control module.

[0050] The control module activates the corresponding optical fiber probe according to the received detection instruction and collects the optical signal of the flame. These optical signals are transmitted to the flame detection module through the optical fiber. After being processed by the optical fiber processing unit, the wavelength code is generated. The electronic device receives the wavelength code sent by the control module. Among them, the wavelength code can reflect the specific spectral characteristics of the flame light and can be used to judge the state of the flame.

[0051] Step S306: Determine the flame state of the boiler to be detected based on the wavelength coding.

[0052] The optical fiber database may also include multiple wavelength codes and flame states corresponding to each wavelength code, wherein the flame states include normal combustion, unstable flame, flame extinction, and the like.

[0053] The embodiment of the present application provides a multi-probe flame detection method, which can intelligently determine the position of the flame based on the actual operating status and load conditions of the boiler by receiving boiler load data. This precise flame position positioning ensures that flame detection can be performed on the most critical combustion area inside the boiler, increasing the effectiveness of the flame range detected by the flame sensor. At the same time, the automated process in the solution - from determining the flame position to selecting the corresponding fiber optic probe, to generating detection instructions and sending them to the control module, and finally receiving the wavelength code and determining the flame state - greatly reduces the intervention of human operation and realizes the automation of flame detection, which not only improves the detection efficiency, but also reduces the risk of errors caused by human factors.

[0054] After receiving the wavelength code sent by the control module, the received wavelength code is compared with a preset flame state database, and the flame state is determined according to the characteristics of the wavelength code.

[0055] A possible implementation of the embodiment of the present application is that in the above step S302, the flame position of the boiler to be detected is determined based on the boiler load, including: Get the fuel type corresponding to the boiler to be tested; The boiler load and fuel type are input into the deep learning network model, and the output flame position is obtained to obtain the flame position of the boiler to be tested.

[0056] The optical fiber database may also include flame positions of different fuel types and different loads. The flame position may include flame center position, flame shape and flame length.

[0057] Specifically, the fuel type corresponding to each boiler may be different, and the flame shape or flame length generated by different fuel types may also be different. Therefore, the fuel type of the boiler to be detected can be obtained, and the fuel type and boiler load of the boiler to be detected can be input into the trained deep learning network model, and the flame position of the boiler to be detected output by the deep learning network model can be obtained to obtain the flame position of the boiler to be detected. Among them, the deep learning network model is trained with a large number of fuel type samples, boiler load samples and flame position samples.

[0058] A possible implementation of the embodiment of the present application, in the above embodiment, inputs the boiler load and the fuel type into the deep learning network model, and obtains the output flame position, including: The boiler load is input into the convolutional neural network model to obtain the flame center position of the boiler to be tested; The flame center position and fuel type are input into the recurrent neural network model to obtain the flame length; The flame position of the boiler to be inspected is determined based on the flame center position and the flame length.

[0059] Specifically, during the operation of the boiler, the boiler load data and the fuel type are obtained. After the boiler load and the fuel type are obtained, the real-time boiler load data is input into the trained CNN model to obtain the predicted flame center position. The CNN model is trained using the collected boiler load data and the corresponding flame center position as training data to obtain a trained CNN model.

[0060] Furthermore, the predicted flame center position and fuel type are input into the trained RNN model to obtain the predicted flame length. The flame center position and fuel type predicted by the trained CNN model are used as the input of the RNN model, and the RNN model is trained to obtain the trained RNN model.

[0061] Combining the predicted flame center position and flame length, the specific position of the flame in the boiler can be determined. Specifically, the horizontal and vertical positions of the flame center and a length value (indicating the extension range of the flame) can be represented by two-dimensional coordinates to obtain the flame position of the boiler to be tested.

[0062] In a possible implementation of the embodiment of the present application, in the above step S303, determining the optical fiber probe corresponding to the flame position includes: Obtain the detection range corresponding to each optical fiber probe; Based on the flame position of the boiler to be detected and the detection range corresponding to each optical fiber probe, at least one target optical fiber probe is selected from multiple optical fiber probes, and the detection range corresponding to the target optical fiber probe can cover the flame position; Based on the target fiber optic probe, determine the fiber optic probe corresponding to the flame position.

[0063] Specifically, the predicted flame position is compared with the detection range of each fiber optic probe. If the flame position (or a part of the flame) is within the detection range of a fiber optic probe, then this fiber optic probe is considered as a candidate target fiber optic probe. From all candidate fiber optic probes, at least one fiber optic probe that can cover the flame position is selected as the target fiber optic probe.

[0064] If the flame position is large or irregular in shape, multiple fiber optic probes may be needed to cover it together. In this case, all fiber optic probes that can cover the flame position are screened out as target fiber optic probes. If multiple target fiber optic probes are screened out, at least two target fiber optic probes that can cover the flame position are used as target fiber optic probe groups. After obtaining multiple groups of target fiber optic probe groups, a group of target fiber optic probe groups is randomly selected as the fiber optic probe corresponding to the flame position.

[0065] See also Figure 4 The third embodiment of the present application provides a multi-probe flame detection system 4, which includes: As described above, the multi-detector flame detection device 10 and the electronic device 40 of the first embodiment.

[0066] In a possible implementation of the embodiment of the present application, the electronic device 40 includes: at least one processor 401; Memory 403; At least one application, wherein the at least one application is stored in the memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the multi-detector flame detection method of the second embodiment.

[0067] See also Figure 5 , Figure 5 The electronic device 40 shown includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the electronic device 40 may also include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the electronic device 40 does not constitute a limitation on the embodiments of the present application.

[0068] Processor 401 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0069] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0070] The memory 403 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0071] The memory 403 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 401. The processor 401 is used to execute the application code stored in the memory 403 to implement the contents shown in the above method embodiment.

[0072] The electronic devices include but are not limited to: mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0073] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0074] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0075] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A multi-probe flame detection device, characterized in that: include: Flame detection module, control module and multiple fiber optic probes; The control module is electrically connected to the flame detection module and is used to control the flame detection module to detect the boiler flame; The flame detection module includes an optical fiber processing unit, and a plurality of optical fiber probes are connected to the flame detection module, each optical fiber probe has a different corresponding emission direction, and the optical fiber probe is used to collect the flame light of the boiler flame into the optical fiber, and the optical fiber processing unit performs wavelength encoding according to the collected flame light.

2. The multi-probe flame detection device according to claim 1, characterized in that: The control module is used to control the flame detection module to detect the boiler flame using various optical fiber probes.

3. The multi-probe flame detection device according to claim 1 or 2, characterized in that: A gating module is installed between the flame detection module and the plurality of optical fiber probes, and the gating module is used to control the conduction of the optical fiber probes.

4. The multi-probe flame detection device according to claim 3, characterized in that: The control module collects boiler load, determines the optical fiber probe to be connected according to the boiler load, and controls the gating module to turn on the optical fiber probe to be connected, so as to control the optical fiber probe to be connected to detect the boiler flame.

5. A multi-probe flame detection method, characterized in that: The method is applied to a multi-probe flame detection system, the multi-probe flame detection system comprises an electronic device and a multi-probe flame detection device according to any one of claims 1 to 4, the method is performed by the electronic device, and the method comprises: receiving a boiler load of a boiler to be inspected; Determining the flame position of the boiler to be detected based on the boiler load; Determine the optical fiber probe corresponding to the flame position; Based on the optical fiber probe, a detection instruction is generated, and the detection instruction is sent to the control module; Receiving the wavelength code sent by the control module; Based on the wavelength code, the flame state of the boiler to be inspected is determined.

6. The multi-probe flame detection method according to claim 5, characterized in that: The step of determining the flame position of the boiler to be detected based on the boiler load includes: Obtaining the fuel type corresponding to the boiler to be detected; The boiler load and the fuel type are input into the deep learning network model, and the output flame position is obtained to obtain the flame position of the boiler to be detected.

7. The multi-probe flame detection method according to claim 6, characterized in that: The step of inputting the boiler load and the fuel type into a deep learning network model and obtaining an output flame position includes: Inputting the boiler load into a convolutional neural network model to obtain the flame center position of the boiler to be detected; Inputting the flame center position and the fuel type into a recurrent neural network model to obtain the flame length; The flame position of the boiler to be inspected is determined based on the flame center position and the flame length.

8. The multi-probe flame detection method according to claim 6 or 7, characterized in that: The optical fiber probe for determining the flame position corresponding to the flame position includes: Obtain the detection range corresponding to each optical fiber probe; Based on the flame position of the boiler to be detected and the detection range corresponding to each optical fiber probe, at least one target optical fiber probe is selected from multiple optical fiber probes, and the detection range corresponding to the target optical fiber probe can cover the flame position; Based on the target optical fiber probe, the optical fiber probe corresponding to the flame position is determined.

9. A multi-probe flame detection system, characterized in that: The system comprises: The multi-probe flame detection device according to any one of claims 1 to 4; Electronic equipment.

10. The multi-detector flame detection system according to claim 9, characterized in that: The electronic device comprises: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the multi-probe flame detection method according to any one of claims 5 to 8.

Images