Intelligent monitoring method and system for electrodeless ultraviolet device

Through intelligent monitoring methods and systems, the current transformer and UV photosensitive sensor can be used to judge the current and light intensity status of the infinite ultraviolet lamp in real time, solving the problem of inaccurate detection of the infinite ultraviolet lamp in time, and achieving higher fault detection accuracy and timely, protects lamp components.

CN118940081APending Publication Date: 2024-11-12SKYRAY OPTOELECTRONICS (SHANGHAI) CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410852233.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Existing pole-less ultraviolet lamps cannot be detected in time when they fail, resulting in damage to the components.

Method used

Using intelligent monitoring methods and systems, the current data of the impellerless ultraviolet lamp is collected through current transformers, pre-processed and labeled, constructed data sets, used deep learning models for diagnosis, and combined with UV photosensitive sensors to monitor the light intensity value to judge the lamp in real time Controls the working status and generates alarm information.

Benefits of technology

It realizes timely detection and accurate diagnosis of faultless ultraviolet lamps, improves the accuracy and timeliness of fault monitoring, and protects components from damage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940081A_ABST
    Figure CN118940081A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent monitoring method and system for an electrodeless ultraviolet lamp, and belongs to the technical field of ultraviolet, and the method comprises the steps: respectively collecting the current data of two paths of anode high-voltage cables of the electrodeless ultraviolet lamp in a normal working state and a fault working state through a current transformer; preprocessing the current data to obtain sample data; label making is carried out on the sample data, and a data set is constructed; training and testing a pre-built network by using the data set to obtain a diagnosis model; collecting real-time current data on two paths of anode high-voltage cables in the target electrodeless ultraviolet lamp; preprocessing the real-time current data; and inputting the preprocessed real-time current data into the diagnosis model to obtain a diagnosis result representing whether the target electrodeless ultraviolet lamp has a fault or not. According to the technical scheme of the invention, the method is higher in accuracy, and is more timely in fault monitoring, so that components can be better protected from being damaged.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electrodeless ultraviolet technology, and in particular to an intelligent monitoring method and system for an electrodeless ultraviolet lamp. Background Art

[0002] Since its inception, the infinite ultraviolet technology has gone through decades of development. It has achieved great development in many fields such as lighting, UV curing, UV sterilization, etc. It is now widely used in many industrial fields, such as optical fiber and cable, surface coating curing, adhesive curing, etc.

[0003] The basic principle of electrodeless ultraviolet technology is to use microwaves to ionize the inert gas in the lamp tube, so that the inert gas forms a plasma state and then heats the lamp tube. When the temperature of the lamp tube rises, the mercury in the lamp tube can evaporate and gasify. Under the action of the microwave electric field, the mercury vapor will collide with the plasma inert gas, so that the electrons in the outer layer of the inert gas nucleus will undergo energy level transitions, and when the transitioned electrons fall back, they will emit photons, some of which are ultraviolet light. Compared with traditional ultraviolet lamp tubes, this method eliminates the electrodes, making the luminous efficiency higher, the lamp tube life longer, the output more stable, and the startup speed is much higher than that of traditional electrode lamp tubes.

[0004] For cost and power considerations, existing electrodeless ultraviolet lamps generally use magnetrons as microwave sources. Microwaves are a type of high-frequency electromagnetic wave. The frequency of general industrial electrodeless ultraviolet lamps is basically around 2.45G. Due to the high frequency and power, the microwaves emitted by the microwave source cannot be transmitted through ordinary wires, and are not suitable for transmission using coaxial cables due to structural and application limitations.

[0005] At present, electrodeless UV lamps usually choose to use waveguides to guide microwaves into the resonant cavity and excite the load (i.e., the lamp tube). Due to the propagation characteristics of microwaves, microwaves also need to be confined to the waveguide and resonant cavity and shielded. If the shielding is not done well, such as there is an assembly gap or the shielding material is poor, it will cause local discharge and sparking in the lamp box. Even if the microwave shielding is well done, if the load cannot effectively absorb the microwaves, it will also cause local discharge and sparking, or it will cause the microwaves to be reflected back to the magnetron and received by the magnetron antenna, which will cause the magnetron antenna cover to explode or the magnetron to be damaged, making the magnetron life far shorter than the normal service life.

[0006] At present, there are mainly the following ideas to solve the above problems: 1. Add an isolator or circulator. A circulator is a device that allows forward microwaves to pass through with very little attenuation, that is, it allows microwaves from the magnetron to the resonant cavity to pass through, while greatly suppressing reverse microwaves, that is, microwaves from the resonant cavity to the magnetron cannot pass through the circulator. The disadvantage is that it increases mechanical complexity, and the excess microwaves need to be discharged or absorbed, and it also cannot protect other components inside the resonant cavity or lamp housing.

[0007] 2. Strengthen shielding. The approach is to choose better waveguide structure and shielding materials, but this still cannot avoid the occurrence of sparks caused by the load's inability to absorb microwaves.

[0008] 3. Use microwave detection. One of the disadvantages of microwave detection is that it is difficult to set the sensitivity standard of microwave probes. Another disadvantage is that there is not enough space inside the resonant cavity to install microwave probes, so microwave probes are often installed outside the light box. In addition, since the light box as a whole is often shielded, it is difficult for the microwave probe located outside the light box to detect microwave changes inside it. At the same time, the installation position of the microwave probe has a lot to do with its sensitivity. Therefore, the use of microwave probes to detect whether the load fully absorbs microwaves cannot effectively guarantee accuracy.

[0009] 4. Use light intensity detection. The electrodeless UV lamp is the largest load of microwaves. If the lamp cannot absorb microwaves and convert them into light energy output, the microwaves will be reflected back to the magnetron and damage it. For example, if the lamp leaks or the mercury fails to vaporize in time, the lamp cannot be lit, resulting in microwave reflection. Therefore, by detecting the state of the lamp (bright or dark) through the photosensitive element, it can be indirectly known whether the microwave is absorbed. However, the limitation of this method is that the working state of the lamp cannot be discovered in time, because it takes a process for the lamp to light up, usually between several seconds and even more than ten seconds, and the photosensitive device also needs a certain amount of time to detect feedback. During this period of time, ignition may have occurred or the magnetron may have been damaged. Therefore, the light intensity detection method has a large delay, and feedback can usually only be given after the fault has occurred and the equipment has suffered losses. Summary of the invention

[0010] In view of the problem in the prior art that failure of an electrodeless ultraviolet lamp cannot be detected in time, which leads to component damage, the purpose of the present invention is to provide an intelligent monitoring method and system for an electrodeless ultraviolet lamp, so as to at least partially solve the above problem.

[0011] To achieve the above object, the technical solution of the present invention is: In a first aspect, the present invention provides an intelligent monitoring method for an electrodeless ultraviolet lamp, the method comprising ignition monitoring, the ignition monitoring comprising the following steps: The current data on the two anode high-voltage cables of the electrodeless ultraviolet lamp under normal working state and fault working state are collected through current transformers; Preprocessing the current data to obtain sample data; Labeling the sample data and constructing a data set; Using the data set to train and test the pre-built network to obtain a diagnostic model; Collect real-time current data on the two anode high-voltage cables in the target electrodeless UV lamp; Preprocessing the real-time current data; The pre-processed real-time current data is input into the diagnostic model to obtain a diagnostic result indicating whether the target electrodeless ultraviolet lamp has a fault.

[0012] In a preferred embodiment, the step of preprocessing the current data to obtain sample data includes: Sliding sampling is performed on the current data through a sliding window to obtain a plurality of current signal segments; The points in the current signal segment where the current amplitude is lower than the current threshold are reset to zero, thereby obtaining sample data containing only the ignition feature.

[0013] In a preferred embodiment, the window size of the sliding window is 5s and the sliding step size is 1s.

[0014] In a preferred embodiment, the current threshold is 13A.

[0015] In a preferred embodiment, the method further comprises light intensity monitoring, and the light intensity monitoring comprises the following steps: The real-time light intensity value of the lamp tube in the target electrodeless ultraviolet lamp is collected through the UV photosensitive sensor; Determine whether the real-time light intensity value exceeds the preset light intensity threshold, if yes, proceed to the next step, otherwise determine it as a faulty working state; According to the identity information of the target electrodeless ultraviolet lamp, the initial value of the light intensity of the lamp tube is obtained; It is determined whether the ratio of the real-time light intensity value to the initial light intensity value exceeds a preset ratio. If yes, it is determined that the target electrodeless ultraviolet lamp is in a normal working state; otherwise, it is determined to be in a faulty working state.

[0016] In a preferred embodiment, when the target electrodeless ultraviolet lamp is determined to be in a faulty working state, the method further comprises the following steps: Generate first alarm information according to the identity information of the target electrodeless ultraviolet lamp and the type of fault, and send it to the first user; and / or, A second alarm message is generated according to the identity information of the target electrodeless ultraviolet lamp, the type of fault and historical data, and is sent to a second user.

[0017] In a second aspect, the present invention also provides an intelligent monitoring system for an electrodeless ultraviolet lamp, comprising: Current transformer, used to collect real-time current data on two anode high-voltage cables in the target electrodeless ultraviolet lamp; UV photosensor, used to collect the real-time light intensity value of the lamp tube in the target electrodeless ultraviolet lamp; and a host computer, which is communicatively connected with the current transformer and the UV photosensor, and is used to determine whether the target electrodeless ultraviolet lamp fails according to the real-time current data and the real-time light intensity value.

[0018] In a preferred embodiment, the host computer is connected to the current transformer and the UV light sensor via Ethernet, I / O, RS485 or DEVICENET protocol communication.

[0019] In a third aspect, the present invention further provides an electronic device, characterized in that it includes a memory storing executable program code and a processor coupled to the memory; wherein the processor calls the executable program code stored in the memory to execute the method as described above.

[0020] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, characterized in that: the computer program executes the method described above when executed by a processor.

[0021] By adopting the above technical scheme, the beneficial effect of the present invention is that in the technical scheme of the present invention, by collecting and identifying the anode current of the electrodeless ultraviolet lamp, it can be determined whether the electrodeless ultraviolet lamp has a spark phenomenon. In addition, by analyzing the density of the spark phenomenon, it can be determined whether the electrodeless ultraviolet lamp has a fault. Compared with traditional technology, the technical scheme of the present invention has higher accuracy and more timely monitoring of faults, thereby better protecting components from damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The figure is a flow chart of the intelligent monitoring method for the electrodeless ultraviolet lamp in the first embodiment of the present invention.

[0023] Figure 2 It is a flow chart of the intelligent monitoring method for electrodeless ultraviolet lamp in the second embodiment of the present invention.

[0024] Figure 3 It is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0025] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0026] Embodiment 1 like Figure 1 As shown, an embodiment of the present invention provides an intelligent monitoring method for an electrodeless ultraviolet lamp, the method includes monitoring for ignition phenomenon, and the steps of ignition monitoring specifically include: Step S1. Using current transformers, current data on two anode high-voltage cables of the electrodeless ultraviolet lamp are collected under normal working conditions and fault working conditions.

[0027] There are many factors that lead to sparking, including sparking of magnetron, sparking of insulation short circuit of high-voltage cable, and sparking of discharge of waveguide or other parts. These conditions that lead to sparking are collectively referred to as faulty working conditions of electrodeless ultraviolet lamp.

[0028] Through the observation of the sparking phenomenon, it is found that when the sparking phenomenon occurs, the anode current of the electrodeless ultraviolet lamp will rise instantly. This instantaneous mutation lasts only a few milliseconds, and the current value will suddenly increase to more than ten times (for example, 18 times) the normal current value, up to 13 amperes. Therefore, this embodiment uses the instantaneous and large-scale mutation of the anode current as the basis for identifying the occurrence of the sparking phenomenon.

[0029] Therefore, this embodiment collects current data of the two anode high-voltage cables of the electrodeless ultraviolet lamp under different specific factors, and the data collection interval is 1ms. At the same time, the cable data of the two anode high-voltage cables of the intact electrodeless ultraviolet lamp is also collected, and the data sampling interval is also 1ms.

[0030] Step S2: Preprocess the current data to obtain sample data.

[0031] In this embodiment, the steps of preprocessing the current data and obtaining sample data include: Step S21: Sliding sampling is performed on the current data through a sliding window to obtain a plurality of current signal segments.

[0032] It is understandable that the current data collected in step S1 is usually a long current waveform, which is not suitable for direct use as input, and usually requires a suitable length segment to be cut out. Considering that the occurrence of the ignition phenomenon under the fault state has a certain correlation in timing, such as multiple consecutive ignitions in a short period of time, in order not to miss such ignition phenomena that can characterize the fault and are interrelated, this embodiment performs sliding sampling of the current data in a sliding window manner, and specifically configures the window size of the sliding window to be 5s and the sliding step length to be 1s.

[0033] Step S22: Zeroing is performed on the points in the current signal segment where the current amplitude is lower than the current threshold, thereby obtaining sample data containing only ignition features.

[0034] It is understandable that the focus of the embodiments of the present invention is on the spark phenomenon, which is characterized by instantaneous large current. Therefore, in order to reduce the complexity of data processing, this embodiment returns all points in the current signal segment where the current amplitude is lower than the current threshold to zero, thereby obtaining sample data containing only spark characteristics.

[0035] The current threshold in this embodiment is set to 13 A, and of course it can be other values ​​in other embodiments. Alternatively, the current average value can be calculated for the collected current data, and a certain multiple of the current average value can be used as the current threshold.

[0036] Step S3: Label the sample data and construct a dataset.

[0037] After processing in step S2, the length of the sample data is 5s, and there are only discrete points (or no discrete points) in it. Labels can be manually made according to the number of discrete points. For example, if the number of discrete points is greater than or equal to the preset number, a fault label is added, and if the number is less than the preset number, a normal label is added.

[0038] By analyzing the sample data under normal working conditions, it can be found that even if the electrodeless UV lamp is intact, it will also spark, but the frequency of this spark is low (no more than 3 times within 8 hours), and it does not show continuity and periodicity. Therefore, if a single spark occurs in the sample data, it is not considered a fault. The possible reason for this is the current fluctuation caused by interference.

[0039] In this embodiment, the occurrence of ignition phenomena three or more times within 5s (i.e., the length of the sample data) is specifically defined as a fault. In addition, since each time the ignition phenomenon occurs, the instantaneous large current will last for several milliseconds, and the collection interval of the current data in step S1 is 1ms, in the sample data, a single ignition phenomenon will correspond to a discrete point group (which contains several adjacent discrete points). Therefore, when three or more discrete point groups appear in the sample data, a fault label is added to it. In addition, when the ignition phenomenon occurs continuously, multiple discrete point groups will be concentrated together, and this sample data will also be added with a fault label.

[0040] It is understandable that even if the electrodeless ultraviolet lamp is working in a faulty state, it does not mean that a predetermined number of discrete point groups (i.e., sparking phenomena) exist or reach in each sample data. The reason is that in the faulty working state, the occurrence of sparking phenomena is not dense and continuous. Therefore, manual identification and labeling of each sample data is required.

[0041] After labeling the sample data, a data set is formed and divided into a training set and a test set in a ratio of 7:1. The ratio of fault labels to normal labels in the training set and the test set is also consistent.

[0042] Step S4: Use the data set to train and test the pre-built network to obtain a diagnostic model.

[0043] In this embodiment, the network samples a transformer model with good classification effect for one-dimensional data, and uses a deep learning framework (such as PyTorch or TensorFlow) to perform model training. Of course, in other preferred embodiments, other algorithms or networks can also be used.

[0044] Step S5: collecting real-time current data on two anode high-voltage cables in the target electrodeless ultraviolet lamp.

[0045] Step S6: pre-process the collected real-time current data.

[0046] Step S7: Input the preprocessed real-time current data into the diagnostic model to obtain a diagnostic result indicating whether the target electrodeless ultraviolet lamp is faulty.

[0047] In the actual monitoring process, after collecting (1ms collection interval) the real-time current data on the two anode high-voltage cables in the target electrodeless ultraviolet lamp, the collected real-time current data is preprocessed according to the same preprocessing process as step S2, thereby obtaining a current signal segment with a length of 5s. After inputting it into the diagnostic model, a diagnostic result indicating whether the target electrodeless ultraviolet lamp is faulty can be obtained.

[0048] It can be understood that during actual monitoring, 5 seconds are moved forward from the current moment to obtain a current signal segment with a length of 5 seconds, and the points where the current amplitude is lower than the current threshold are reset to zero and then input into the diagnostic model. In this way, a response can be made as soon as a fault is detected.

[0049] Generally, when the target electrodeless ultraviolet lamp is determined to be in a faulty working state in step S7, the method disclosed in the embodiment of the present invention further includes the following steps: Step S8. Generate a first alarm message according to the identity information of the target electrodeless ultraviolet lamp and the type of fault, and send it to the first user; and / or, Step S9. Generate second alarm information according to the identity information of the target electrodeless ultraviolet lamp, the type of fault and historical data, and send it to the second user.

[0050] The first user refers to a staff member who is qualified to operate or manage the target electrodeless ultraviolet lamp, and specifically refers to the user-end device associated with it, such as a computer, mobile phone or tablet computer. The first alarm information contains the identity information of the target electrodeless ultraviolet lamp that has failed and the specific fault type (here it refers to the ignition fault). The identity information of the target electrodeless ultraviolet lamp is used to indicate the location and model of the electrodeless ultraviolet lamp, so as to facilitate the first user to quickly locate the fault point and carry the corresponding maintenance tools for troubleshooting.

[0051] The second user refers to the staff who are qualified to maintain and repair the target electrodeless ultraviolet lamp, including the supplier or manufacturer when necessary, and specifically refers to the user-end equipment associated with it, such as computers, mobile phones or tablets. In addition to the identity information of the target electrodeless ultraviolet lamp that has failed and the specific fault type (here refers to the ignition failure), the second alarm information also includes the corresponding historical data, so that the maintenance personnel can quickly determine the specific faulty components in the target electrodeless ultraviolet lamp based on their experience through this information.

[0052] Embodiment 2 On the basis of the first embodiment, the method provided in this embodiment also includes light intensity monitoring. The light intensity of the light emitted by the electrodeless ultraviolet lamp is also an important parameter data, which can also characterize the working state of the electrodeless ultraviolet lamp. In this embodiment, if Figure 2 As shown, light intensity monitoring includes the following steps: Step S11. Collect the real-time light intensity value of the lamp tube in the target electrodeless ultraviolet lamp through the UV photosensor.

[0053] Step S12: Determine whether the real-time light intensity value exceeds the preset light intensity threshold value, if yes, proceed to the next step, otherwise it is determined as a faulty working state.

[0054] The preset light intensity threshold in this step is usually set low. The main function of this step is to determine whether the lamp tube is successfully started. If it is successfully started, proceed to the next step. If it is not successfully started, it can be directly determined that the target electrodeless ultraviolet lamp is faulty.

[0055] Step S13: According to the identity information of the target electrodeless ultraviolet lamp, the initial value of the light intensity of the lamp tube is obtained.

[0056] Step S14: determine whether the ratio of the real-time light intensity value to the initial light intensity value exceeds a preset ratio. If yes, determine that the target electrodeless ultraviolet lamp is in a normal working state; otherwise, determine that it is in a faulty working state.

[0057] It is understandable that for different models of electrodeless ultraviolet lamps, the lamp tubes used and the input microwave frequency meter powers are different, which makes the initial light intensity values ​​of the lamp tubes in good condition also different. Therefore, it is necessary to obtain the initial light intensity value of the lamp tube from the database based on the identity information of the target electrodeless ultraviolet lamp.

[0058] It is also understandable that the electrodeless ultraviolet lamp is a consumable part, and its light intensity will decay over time. When it decays to a certain extent, its absorption rate for microwaves will be difficult to meet the requirements, thus causing microwave reflection. Therefore, this embodiment determines the working status of the target electrodeless ultraviolet lamp by judging whether the ratio of the real-time light intensity value to the initial light intensity value exceeds a preset ratio (for example, 30%), so as to take precautionary measures to prevent equipment damage caused by continued use of the lamp tube.

[0059] Embodiment 3 The present invention also provides an intelligent monitoring system for an electrodeless ultraviolet lamp, comprising a current transformer, a UV photosensor and a host computer, wherein the host computer is connected to the current transformer and the UV photosensor via Ethernet, I / 0, RS485 or DEVICENET protocol communication.

[0060] Among them, the current transformer is used to collect real-time current data on the two anode high-voltage cables in the target electrodeless ultraviolet lamp; the UV photosensitive sensor is used to collect the real-time light intensity value of the lamp tube in the target electrodeless ultraviolet lamp; the host computer is used to determine whether the target electrodeless ultraviolet lamp is faulty based on the real-time current data and the real-time light intensity value.

[0061] Specifically, the host computer determines whether the target electrodeless ultraviolet lamp fails by executing the methods disclosed in the first and second embodiments.

[0062] Embodiment 4 An electronic device, such as Figure 3As shown, it includes a memory storing executable program code and a processor coupled to the memory; wherein the processor calls the executable program code stored in the memory to execute the method steps disclosed in the above embodiment.

[0063] Embodiment 5 A computer storage medium stores a computer program, and when the computer program is executed by a processor, the method steps disclosed in the above embodiment are executed.

[0064] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] It should be noted that, in the description of the present invention, the directions or positional relationships indicated by the terms "up", "down", "left", "right", "front", "back", etc. are descriptions of the structure of the present invention based on the accompanying drawings, and are only for the convenience of describing the present invention, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0068] The "first" and "second" in this technical solution are only used to distinguish the names of the same or similar structures, or corresponding structures with similar functions, and are not an arrangement of the importance of these structures, nor do they have a ranking, comparison of size, or other meanings.

[0069] In addition, unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be a connection between the two structures. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood based on the overall idea of ​​the present invention and the specific context of the present solution.

[0070] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, various changes, modifications, substitutions and variations of these embodiments are made without departing from the principles and spirit of the present invention, and still fall within the scope of protection of the present invention.

Claims

1. An intelligent monitoring method for an electrodeless ultraviolet lamp, characterized in that: The method includes ignition monitoring, which includes the following steps: The current data on the two anode high-voltage cables of the electrodeless ultraviolet lamp under normal working state and fault working state are collected through current transformers; Preprocessing the current data to obtain sample data; Labeling the sample data and constructing a data set; Using the data set to train and test the pre-built network to obtain a diagnostic model; Collect real-time current data on the two anode high-voltage cables in the target electrodeless UV lamp; Preprocessing the real-time current data; The pre-processed real-time current data is input into the diagnostic model to obtain a diagnostic result indicating whether the target electrodeless ultraviolet lamp has a fault.

2. The method according to claim 1, characterized in that: The step of preprocessing the current data to obtain sample data comprises: Sliding sampling is performed on the current data through a sliding window to obtain a plurality of current signal segments; Points in the current signal segment where the current amplitude is lower than the current threshold are reset to zero, thereby obtaining sample data containing only ignition features.

3. The method according to claim 2, characterized in that: The window size of the sliding window is 5s and the sliding step size is 1s.

4. The method according to claim 2, characterized in that: The current threshold is 13A.

5. The method according to claim 1, characterized in that: The method further includes light intensity monitoring, which includes the following steps: The real-time light intensity value of the lamp tube in the target electrodeless ultraviolet lamp is collected through the UV photosensitive sensor; Determine whether the real-time light intensity value exceeds the preset light intensity threshold, if yes, proceed to the next step, otherwise determine it as a faulty working state; According to the identity information of the target electrodeless ultraviolet lamp, the initial value of the light intensity of the lamp tube is obtained; It is determined whether the ratio of the real-time light intensity value to the initial light intensity value exceeds a preset ratio. If yes, it is determined that the target electrodeless ultraviolet lamp is in a normal working state; otherwise, it is determined to be in a faulty working state.

6. The method according to any one of claims 1 to 5, characterized in that: When the target electrodeless ultraviolet lamp is determined to be in a faulty working state, the method further comprises the following steps: Generate first alarm information according to the identity information of the target electrodeless ultraviolet lamp and the type of fault, and send it to the first user; and / or, A second alarm message is generated according to the identity information of the target electrodeless ultraviolet lamp, the type of fault and historical data, and is sent to a second user.

7. An intelligent monitoring system for an electrodeless ultraviolet lamp, characterized in that: include Current transformer, used to collect real-time current data on two anode high-voltage cables in the target electrodeless ultraviolet lamp; UV photosensor, used to collect the real-time light intensity value of the lamp in the target electrodeless ultraviolet lamp; and a host computer, which is communicatively connected with the current transformer and the UV photosensor, and is used to determine whether the target electrodeless ultraviolet lamp fails according to the real-time current data and the real-time light intensity value.

8. The system according to claim 7, characterized in that: The host computer is connected to the current transformer and the UV light sensor through Ethernet, I / 0, RS485 or DEVICENET protocol communication.

9. An electronic device, characterized in that: It comprises a memory storing executable program code and a processor coupled to the memory; wherein the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

Citation Information

Patent Citations

  • Power cable current detection alarm system

    CN114062762A

  • Partial discharge detection method based on UV radiation

    CN117907759A

  • UV lamp curing equipment based on light intensity detection

    CN218536046U