Household gas stove intelligent safety management system based on Internet of Things and artificial intelligence

Through the intelligent safety management system of gas stoves based on the Internet of Things and artificial intelligence, the problem of insufficient safety management before and after the gas stove is ignited, and the full-stage safety assessment and flame abnormality detection are achieved, reducing the risk of accidents and improving the risk of accidents. Safety of gas stove.

CN119026922AActive Publication Date: 2024-11-26GUANGDONG SHUNDE GEE WEEDON ELECTRIC CO LTD

Patent Information

Application Number
CN202411505485.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-28
Publication Date
2024-11-26
Estimated Expiration
2044-10-28

AI Technical Summary

Technical Problem

The existing intelligent safety management technology of gas stove cannot ensure the safety of the gas stove before and after the gas stove is ignited, and cannot detect flame abnormalities and residual flames in real time, resulting in potential safety hazards.

Method used

Adopt the intelligent safety management system of household gas stoves based on the Internet of Things and artificial intelligence, including the ignition safety assessment module, the flame state analysis module and the flame residue identification module. The burner image is obtained through the photography device, and the ignition environment safety, real-time flame state and After the flame is turned off, the gas control knob will be automatically controlled and the alarm will be emitted.

Benefits of technology

The safety of the gas stove is ensured in the entire stage, and by detecting the flame status and residual flame in real time, identifying potential problems, reducing the risk of accidents caused by flame abnormalities, and improving the safety and comprehensive management of the gas stove during use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026922A_ABST
    Figure CN119026922A_ABST
Patent Text Reader

Abstract

The invention discloses a household gas stove intelligent safety management system based on the Internet of Things and artificial intelligence, and belongs to the technical field of safety management.The safety of an ignition environment is evaluated through an ignition safety evaluation module, and then the safety of a gas stove in the combustion stage is evaluated through a flame state analysis module according to the flame state; and finally, the safety of the flameout stage is ensured by detecting the residual flame through the flame residual identification module after flameout, and the safety of the gas stove in use is ensured in the whole stage.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of safety management, and in particular to an intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence. Background Art

[0002] Nowadays, gas stoves have become an indispensable kitchen appliance in people's daily lives. Gas stoves have brought great convenience to people's lives, but the use of gas stoves has certain risks. Improper use or problems with the gas stove itself can easily cause personal danger to users.

[0003] Therefore, intelligent safety management technology for gas stoves is indispensable. The invention patent with application number CN202310078423.4 discloses a safe gas stove control system, which detects whether there are pots on the gas stove after the fire is ignited through the anti-air burning module, and sends the detection signal to the controller. If there are pots, the gas stove is safely managed by sending an air intake control signal to the electronic valve control module and an oxygen distribution control signal to the fan speed regulation module; and the invention patent with application number 201910148981.7 discloses a gas stove safety control method, which collects images of the surrounding area of ​​the gas stove once every first preset time interval after the gas stove is turned on. If there is no face image in the images collected within the first preset time threshold, it is determined to turn off the gas stove for safety management. In the above-mentioned prior art, safety management is only performed when the gas stove is ignited and starts working, but safety management cannot be performed before ignition and after flameout, and the safety of the gas stove cannot be guaranteed in all stages. Therefore, the present invention provides an intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence. Summary of the invention

[0004] In order to solve the technical problems existing in the prior art, the present invention provides a household gas stove intelligent safety management system based on the Internet of Things and artificial intelligence, comprising: The ignition safety assessment module is used to analyze whether the kitchen environment where the gas stove is located is a safe ignition environment before the user ignites it. If so, it sends safe ignition information to the user's mobile terminal; if not, it sends unsafe ignition information to the user's mobile terminal; A photographing device, used to obtain a burner image; the burner image includes a burner combustion state image and a burner flameout state image; The photographic device acquires the burner combustion state image in real time after ignition and transmits it to the flame state analysis module through the network, and acquires the burner flameout state image after the gas stove is turned off and transmits it to the flame residue recognition module through the network; The flame state analysis module is used to analyze whether the flame of the gas stove is abnormal through the burner combustion state image after the user receives the safe ignition information and ignites the gas stove. If there is an abnormality, a flameout signal is sent to the control module; the control module is used to automatically control the gas control knob to return to the flameout position after receiving the flameout signal; A flame residue recognition module is used to identify whether there is flame residue through the burner flameout state image, and if so, to sound an alarm and send the alarm information to the user's mobile terminal; The flame state analysis module comprises: The knob position acquisition module is used to obtain the real-time rotation position of the gas control knob; Normal state prediction module, used to predict the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob; A flame recognition module, used to recognize the flame in the burner combustion state image and extract the flame image; A real-time state analysis module, used for analyzing the real-time flame state of the flame image; The abnormality judgment module is used to compare the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal. If it is abnormal, a flameout signal is sent to the control module.

[0005] Furthermore, the normal state prediction module predicts the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob, specifically through a pre-trained deep learning model, and uses the real-time rotation position of the gas control knob as the input of the deep learning model, and outputs the predicted height and predicted combustion range area of ​​the predicted normal flame.

[0006] Furthermore, the flame recognition module recognizes the flame in the burner combustion state image, specifically: Converting the burner combustion state image into a grayscale image, and smoothing the grayscale image using a Gaussian filter; Convert the grayscale image into a binary image using a threshold segmentation method; The flame outline is identified using edge detection algorithms; A flame image is extracted according to the flame outline.

[0007] Furthermore, if the flame recognition module recognizes that there is no flame in the burner combustion state image and the real-time rotation position of the gas control knob is not at the flameout position, the flame state analysis module sends a flameout signal to the control module.

[0008] Furthermore, the real-time state analysis module analyzes the real-time flame state of the flame image, specifically extracting the real-time flame height and the real-time combustion range area from the flame image.

[0009] Furthermore, the abnormality judgment module compares the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal, specifically: If the absolute value of the real-time flame height minus the corresponding predicted height is greater than the preset first threshold, and / or the absolute value of the real-time combustion range area minus the corresponding predicted combustion range area is greater than the preset second threshold, it is judged that the real-time flame state is abnormal and a flameout signal is sent to the control module.

[0010] Furthermore, the flame residue recognition module recognizes whether there is flame residue after the gas stove is turned off. Specifically, the photography module continues to obtain the burner off state image after the gas control knob returns to the off position and a first preset time has passed, and then the flame recognition module recognizes whether there is flame in the burner off state image. If so, it is determined that there is flame residue.

[0011] Furthermore, the ignition safety assessment module includes: A kitchen ventilation identification module is used to identify whether the kitchen is in a ventilation state; A gas leak identification module is used to identify whether the gas stove is in a leaking state; The first judgment module is used to judge whether the kitchen environment is in a safe ignition environment according to the recognition results of the kitchen ventilation recognition module and the gas leakage recognition module.

[0012] Furthermore, the kitchen ventilation identification module includes: The first monitoring module is used to obtain kitchen environment images in real time; A door and window recognition module, used to recognize doors and windows in the kitchen environment image; A door and window state judgment module is used to judge whether the doors and windows in the kitchen environment image are in an open state, and if so, judge that the kitchen is in a ventilated state; if not, judge that the kitchen is not in a ventilated state; The gas leakage identification module is specifically a gas sensor, which is used to monitor the gas concentration. If the gas concentration is greater than a preset threshold, it is determined that the gas stove is in a leakage state.

[0013] Furthermore, the determination of whether the kitchen environment is in a safe ignition environment is specifically as follows: If the kitchen is in a ventilated state and the gas stove is not in a leaking state, the kitchen environment is judged to be in a safe ignition environment; If the kitchen is not in a ventilated state, and / or the gas stove is in a leaking state, it is determined that the kitchen environment is not in a safe ignition environment.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention first evaluates the safety of the ignition environment, then evaluates the safety of the gas stove combustion stage according to the flame state, and finally detects the residual flame after the flame is turned off to ensure the safety of the flameout stage, thereby ensuring the safety of the gas stove in all stages. By detecting whether the kitchen doors and windows are open, it can be judged whether the kitchen is in a ventilated state, and whether there is a gas leak, and then whether the kitchen is in a safe ignition environment, further improving the safety of gas stove use; By judging whether the real-time height and real-time combustion range of the real-time flame match the predicted height and combustion range of the flame corresponding to the current rotation position of the gas control knob, and then judging whether the real-time flame state is abnormal, it is possible to quickly identify changes in flame shape caused by gas flow control failure or gas leakage, which helps to discover potential problems in a timely manner, reduce the risk of accidents caused by abnormal flames, and improve the safety of gas stoves during use; By detecting whether there is any residual flame after the flame is turned off, potential problems such as failure of the flameout protection device, loose closure of the gas valve, or leakage of the internal gas pipeline or connectors can be discovered in a timely manner, which further improves the safety of the gas stove operation and the comprehensiveness of the gas stove safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 It is a structural block diagram of an intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence of the present invention; Figure 2 It is a structural block diagram of a flame state analysis module of a household gas stove intelligent safety management system based on the Internet of Things and artificial intelligence of the present invention; Figure 3 It is a structural block diagram of an ignition safety assessment module of an intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence of the present invention; Figure 4The present invention is a structural block diagram of a kitchen ventilation identification module of a household gas stove intelligent safety management system based on the Internet of Things and artificial intelligence. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0020] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0021] Embodiment 1 See also Figure 1 As shown, the present invention provides an intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence, comprising: An ignition safety assessment module, a photographic device, a flame state analysis module, a control module and a flame residue identification module, as well as a central processing unit that is in communication with the above modules and devices.

[0022] The ignition safety assessment module is used to analyze whether the kitchen environment where the gas stove is located is in a safe ignition environment before the user ignites the gas stove. If so, safe ignition information is sent to the user's mobile terminal. If not, unsafe ignition information is sent to the user's mobile terminal.

[0023] A photographing device, used to obtain a burner image; the burner image includes a burner combustion state image and a burner flameout state image; The photographic device acquires the combustion state image of the burner in real time after ignition and transmits it to the flame state analysis module through the network, and acquires the flameout state image of the flameout burner after the gas stove is turned off and transmits it to the flame residue recognition module through the network; The flame state analysis module is used to analyze whether the flame of the gas stove is abnormal through the burner combustion state image after the user receives the safe ignition information and ignites the gas stove. If there is an abnormality, a flameout signal is sent to the control module; the control module automatically controls the gas control knob to return to the flameout position after receiving the flameout signal; The flame residue recognition module is used to identify whether there is flame residue through the burner flameout state image, and if so, to sound an alarm and send the alarm information to the user's mobile terminal.

[0024] See also Figure 2 As shown, the flame state analysis module specifically includes a photography module, a knob position acquisition module, a normal state prediction module, a flame recognition module, a real-time state analysis module and an abnormality judgment module.

[0025] The burner image is an image that has been preprocessed.

[0026] The burner is an important part of the gas stove, and air intake, gas mixing and combustion are all completed through this component.

[0027] The knob position acquisition module is used to acquire the real-time rotation position of the gas control knob.

[0028] The gas control knob is used to adjust the gas flow rate, thereby controlling the size of the flame. Usually each burner has an independent control knob to facilitate adjusting the firepower of each burner separately.

[0029] The normal state prediction module is used to predict the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob.

[0030] The flame recognition module is used to recognize the flame in the burner combustion state image and extract the flame image.

[0031] The real-time state analysis module is used to analyze the real-time flame state of the flame image.

[0032] The abnormality judgment module is used to compare the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal. If it is abnormal, it sends a flameout signal to the control module.

[0033] The normal state prediction module predicts the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob, specifically through a pre-trained deep learning model, inputs the real-time rotation position of the gas control knob, and outputs the predicted height and predicted combustion range area of ​​the predicted normal flame.

[0034] Normally, the closer the real-time rotation position of the gas control knob is to the flameout position, the smaller the gas flow rate, the smaller the flame height, and the smaller the combustion range area. The farther the real-time rotation position is from the flameout position, the greater the gas flow rate, the higher the flame height, and the larger the combustion range area.

[0035] The deep learning model is trained using different rotation positions of the gas control knob and corresponding normal flame images as training sets, and the corresponding normal flame images contain corresponding flame height features and combustion range features.

[0036] The deep learning model may optionally use convolutional neural networks (CNNs), which are particularly good at processing image data, can extract features from images and predict flame states; convolutional neural networks can automatically learn spatial hierarchical structures and are very suitable for processing visual data, such as the shape, color and size of flames. The deep learning model may also optionally use generative adversarial networks (GANs), which can be used to generate possible images of flames at specific knob positions to improve the accuracy of visual prediction results. Generative adversarial networks can generate realistic flame images, which is very intuitive for understanding and verifying prediction results.

[0037] The flame recognition module recognizes the flame in the burner combustion state image, specifically: Converting the burner combustion state image into a grayscale image to reduce computational complexity, and smoothing the grayscale image using a Gaussian filter to remove noise; Convert the grayscale image into a binary image using a threshold segmentation method; The flame outline is identified using edge detection algorithms; A flame image is extracted according to the flame outline.

[0038] If the flame recognition module recognizes that there is no flame in the burner combustion state image and the real-time rotation position of the gas control knob is no longer at the flameout position, the flame state analysis module sends a flameout signal to the control module.

[0039] In some embodiments, the process of identifying the flame outline using an edge detection algorithm further includes applying morphological operations such as opening and closing operations to fill holes and remove small noise points, so as to further optimize the identification of the flame outline.

[0040] The edge detection algorithm may be any of the following: Sobel operator, Sobel operator is a first-order derivative operator based on image gradient, used to detect edges in the horizontal and vertical directions. It convolves the image through two 3x3 matrices (one to detect vertical edges and the other to detect horizontal edges), thereby calculating the gradient strength and direction of each pixel. The area with high gradient strength represents the edge. The Sobel operator has a good suppression effect on noise and can provide edge direction information; Canny edge detection uses a Gaussian filter to smooth the image and reduce the impact of noise. It applies a differential operator to calculate the gradient amplitude and direction of the image, processes the gradient amplitude according to the gradient direction, retains the pixels with the local maximum value as edge pixels, and suppresses the pixels with non-maximum values. This ensures that the edge is a single pixel wide, while removing false edge responses caused by noise, and finally performs dual threshold detection and edge connection. Canny edge detection accurately locates edges and has a low false detection rate. Through dual threshold detection and edge connection, isolated weak edge responses can be reduced.

[0041] The real-time state analysis module analyzes the real-time flame state of the flame image, specifically extracting the real-time flame height and the real-time combustion range area from the flame image, specifically including: Extracting the flame contour in the flame image using an edge detection algorithm and determining the flame boundary using contour analysis; Apply morphological operations such as opening and closing to fill holes and remove small particles; Identify connected areas of flame; Determine the highest pixel and the lowest pixel of the flame outline, and the real-time flame height is the actual distance represented by the vertical distance between the highest pixel and the lowest pixel; Calculate the number of pixels in the flame connected area and multiply it by the actual area represented by each pixel to obtain the real-time combustion range area.

[0042] The abnormality judgment module compares the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal, specifically: If the absolute value of the real-time flame height minus the corresponding predicted height is greater than the preset first threshold, and / or the absolute value of the real-time combustion range area minus the corresponding predicted combustion range area is greater than the preset second threshold, it is judged that the real-time flame state is abnormal and a flameout signal is sent to the control module.

[0043] If the actual flame power of the gas stove deviates greatly from the normal flame power corresponding to the real-time rotation position of the gas control knob, this may mean that the gas flow control has failed or there is a leak, which will bring a series of safety hazards. Therefore, a flameout signal is sent to the control module to achieve safe management of the gas stove.

[0044] The flame residue recognition module recognizes whether there is flame residue after the gas stove is turned off. Specifically, the photography module continues to obtain the burner off state image after the gas control knob returns to the off position and a first preset time has passed, and then the flame recognition module recognizes whether there is flame in the burner off state image. If so, it is determined that there is flame residue.

[0045] The flame recognition module recognizes whether there is a flame in the burner flameout state image, which is consistent with the principle of the steps when recognizing the flame in the burner combustion state image.

[0046] It is very dangerous if the flame continues to burn after the gas stove is turned off. This may indicate that there is a serious technical problem with the gas stove, such as a failure of the flameout protection device, a gas valve not closed tightly, or leakage in the internal gas pipeline or connector, which requires immediate attention and processing. Therefore, the present invention also identifies the residual flame after the flame is turned off, thereby improving the safety of the gas stove operation and the comprehensiveness of the gas stove safety management.

[0047] In some embodiments, see Figure 3 As shown, the ignition safety assessment module includes: a kitchen ventilation identification module, a gas leakage identification module and a first judgment module.

[0048] The kitchen ventilation identification module is used to identify whether the kitchen is in a ventilation state.

[0049] The gas leakage identification module is used to identify whether the gas stove is in a leakage state.

[0050] The first judgment module is used to judge whether the kitchen environment is in a safe ignition environment according to the recognition results of the kitchen ventilation recognition module and the gas leakage recognition module, specifically: If the kitchen is in a ventilated state and the gas stove is not in a leaking state, the kitchen environment is judged to be in a safe ignition environment; If the kitchen is not in a ventilated state, and / or the gas stove is in a leaking state, it is determined that the kitchen environment is not in a safe ignition environment.

[0051] In some embodiments, see Figure 4 As shown, the kitchen ventilation identification module includes: a first monitoring module, a door and window identification module and a door and window status judgment module.

[0052] The first monitoring module is used to obtain kitchen environment images in real time; The door and window recognition module is used to recognize doors and windows in the kitchen environment image; The door and window state judgment module is used to judge whether the doors and windows in the kitchen environment image are in an open state. If so, it is judged that the kitchen is in a ventilated state; if not, it is judged that the kitchen is not in a ventilated state.

[0053] The gas leakage identification module is specifically a gas sensor, which is installed above the gas stove or near the gas pipeline to monitor the gas concentration. If the concentration is greater than a preset threshold, it is determined that the gas stove is in a leakage state.

[0054] In some embodiments, the system further includes a pot recognition module for identifying whether there is a pot on the burning gas stove in the kitchen environment image. If there is no pot, a flameout signal is sent to the control module after a second preset time.

[0055] If the gas stove is lit but no pot is placed on it, the flame may spread to objects that should not be exposed to the fire source, causing a fire. By detecting whether there is a pot above the flame, the system's pot recognition module can prevent such accidents from happening, further improving the safety of gas stove use.

[0056] Embodiment 2 The present invention also provides a household gas stove intelligent safety management method based on the Internet of Things and artificial intelligence, comprising the following steps: S1. Before the user ignites the gas stove, analyze whether the kitchen environment where the gas stove is located is in a safe ignition environment. If so, send safe ignition information to the user's mobile terminal; if not, send unsafe ignition information to the user's mobile terminal; S2. After the user receives the safe ignition information and ignites the gas stove, it analyzes whether the flame of the gas stove is abnormal. If there is an abnormality, a flameout signal is sent to the control module; S3, the control module automatically controls the gas control knob to return to the flameout position after receiving the flameout signal; S4. After the gas stove is turned off, it is identified whether there is residual flame. If so, a sound alarm is issued and the alarm information is sent to the user's mobile terminal.

[0057] Step S1 specifically includes the following steps: T1. Identify whether the kitchen is in a ventilated state and whether the gas stove is in a leaking state; T2, used to determine whether the kitchen environment is in a safe ignition environment according to the recognition results of the kitchen ventilation recognition module and the gas leakage recognition module, specifically: If the kitchen is in a ventilated state and the gas stove is not in a leaking state, the kitchen environment is judged to be in a safe ignition environment; If the kitchen is not in a ventilated state, and / or the gas stove is in a leaking state, it is determined that the kitchen environment is not in a safe ignition environment.

[0058] Step S2 specifically includes the following steps: R1, real-time acquisition of the burner combustion status image and the real-time rotation position of the gas control knob; R2, predicting the corresponding normal flame state according to the real-time rotation position of the gas control knob; R3. Identify the flame in the burner combustion state image and extract the flame image.

[0059] R4. Analyze the real-time flame status of the flame image.

[0060] R5. Compare the real-time flame state with the corresponding normal flame state to determine whether the real-time flame state is abnormal. If abnormal, send a flameout signal to the control module.

[0061] Step S4 specifically includes the following steps: U1. Obtain the burner flameout status image after the gas control knob returns to the flameout position and the first preset time has passed. U2. Identify whether there is flame in the burner flameout state image, and if so, determine whether there is flame residue.

[0062] Embodiment 3 The present invention also provides an electronic device, comprising: a processor, a sending device, an input device, an output device and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes a method as any one of the possible implementation methods described above.

[0063] Embodiment 4 The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0064] The beneficial effects of the present invention are: The present invention first evaluates the safety of the ignition environment, then evaluates the safety of the gas stove combustion stage according to the flame state, and finally detects the residual flame after the flame is turned off to ensure the safety of the flameout stage, thereby ensuring the safety of the gas stove in all stages. By detecting whether the kitchen doors and windows are open, it can be judged whether the kitchen is in a ventilated state, and whether there is a gas leak, and then whether the kitchen is in a safe ignition environment, further improving the safety of gas stove use; By judging whether the real-time height and real-time combustion range of the real-time flame match the predicted height and combustion range of the flame corresponding to the current rotation position of the gas control knob, and then judging whether the real-time flame state is abnormal, it is possible to quickly identify changes in flame shape caused by gas flow control failure or gas leakage, which helps to discover potential problems in a timely manner, reduce the risk of accidents caused by abnormal flames, and improve the safety of gas stoves during use; By detecting whether there is any residual flame after the flame is turned off, potential problems such as failure of the flameout protection device, loose closure of the gas valve, or leakage of the internal gas pipeline or connectors can be discovered in a timely manner, which further improves the safety of the gas stove operation and the comprehensiveness of the gas stove safety management.

[0065] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0066] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An intelligent safety management system for household gas stoves based on the Internet of Things and artificial intelligence, characterized in that: include: The ignition safety assessment module is used to analyze whether the kitchen environment where the gas stove is located is a safe ignition environment before the user ignites it. If so, it sends safe ignition information to the user's mobile terminal; if not, it sends unsafe ignition information to the user's mobile terminal; A photographing device, used to obtain a burner image; the burner image includes a burner combustion state image and a burner flameout state image; The photographic device acquires the burner combustion state image in real time after ignition and transmits it to the flame state analysis module through the network, and acquires the burner flameout state image after the gas stove is turned off and transmits it to the flame residue recognition module through the network; The flame state analysis module is used to analyze whether the flame of the gas stove is abnormal through the burner combustion state image after the user receives the safe ignition information and ignites the gas stove. If there is an abnormality, a flameout signal is sent to the control module; the control module is used to automatically control the gas control knob to return to the flameout position after receiving the flameout signal; A flame residue recognition module is used to identify whether there is flame residue through the burner flameout state image, and if so, to sound an alarm and send the alarm information to the user's mobile terminal; The flame state analysis module comprises: The knob position acquisition module is used to obtain the real-time rotation position of the gas control knob; Normal state prediction module, used to predict the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob; A flame recognition module, used to recognize the flame in the burner combustion state image and extract the flame image; A real-time state analysis module, used for analyzing the real-time flame state of the flame image; The abnormality judgment module is used to compare the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal. If it is abnormal, a flameout signal is sent to the control module.

2. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 1 is characterized in that: The normal state prediction module predicts the corresponding normal flame state through artificial intelligence according to the real-time rotation position of the gas control knob, specifically through a pre-trained deep learning model. The real-time rotation position of the gas control knob is used as the input of the deep learning model, and the predicted height and predicted combustion range area of ​​the predicted normal flame are output.

3. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 1 is characterized in that: The flame recognition module recognizes the flame in the burner combustion state image, specifically: Converting the burner combustion state image into a grayscale image, and smoothing the grayscale image using a Gaussian filter; Convert the grayscale image into a binary image using a threshold segmentation method; The flame outline is identified using edge detection algorithms; A flame image is extracted according to the flame outline.

4. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 1 is characterized in that: If the flame recognition module recognizes that there is no flame in the burner combustion state image and the real-time rotation position of the gas control knob is not at the flameout position, the flame state analysis module sends a flameout signal to the control module.

5. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 2 is characterized in that: The real-time state analysis module analyzes the real-time flame state of the flame image, specifically extracting the real-time flame height and the real-time combustion range area from the flame image.

6. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 5 is characterized in that: The abnormality judgment module compares the real-time flame state with the corresponding normal flame state to judge whether the real-time flame state is abnormal, specifically: If the absolute value of the real-time flame height minus the corresponding predicted height is greater than the preset first threshold, and / or the absolute value of the real-time combustion range area minus the corresponding predicted combustion range area is greater than the preset second threshold, it is judged that the real-time flame state is abnormal and a flameout signal is sent to the control module.

7. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 1 is characterized in that: The flame residue recognition module recognizes whether there is flame residue after the gas stove is turned off. Specifically, the photography module continues to obtain the burner off state image after the gas control knob returns to the off position and a first preset time has passed, and then the flame recognition module recognizes whether there is flame in the burner off state image. If so, it is determined that there is flame residue.

8. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 1 is characterized in that: The ignition safety assessment module comprises: A kitchen ventilation identification module is used to identify whether the kitchen is in a ventilation state; A gas leak identification module is used to identify whether the gas stove is in a leaking state; The first judgment module is used to judge whether the kitchen environment is in a safe ignition environment according to the recognition results of the kitchen ventilation recognition module and the gas leakage recognition module.

9. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 8 is characterized in that: The kitchen ventilation identification module comprises: The first monitoring module is used to obtain kitchen environment images in real time; A door and window recognition module, used to recognize doors and windows in the kitchen environment image; A door and window state judgment module is used to judge whether the doors and windows in the kitchen environment image are in an open state, and if so, judge that the kitchen is in a ventilated state; if not, judge that the kitchen is not in a ventilated state; The gas leakage identification module is specifically a gas sensor, which is used to monitor the gas concentration. If the gas concentration is greater than a preset threshold, it is determined that the gas stove is in a leakage state.

10. The household gas stove intelligent safety management system based on Internet of Things and artificial intelligence according to claim 8, characterized in that: The determination of whether the kitchen environment is in a safe ignition environment is specifically as follows: If the kitchen is in a ventilated state and the gas stove is not in a leaking state, the kitchen environment is judged to be in a safe ignition environment; If the kitchen is not in a ventilated state, and / or the gas stove is in a leaking state, it is determined that the kitchen environment is not in a safe ignition environment.

Citation Information

Patent Citations

  • Gas stove safety control method, device, equipment and storage medium

    CN110030588A

  • Safe gas stove control system

    CN116182205A

  • Boiler / drying oven hearth flameout automatic detection method and automatic protective system

    CN101509669A

  • Safety detecting system, method and device

    CN107940514A

  • Control method and control device for gas wall-hanging stove residual flame fault

    CN109341090A

Cited By

  • Plasma stove abnormity monitoring method, device, equipment and medium

    CN119885042A