Apparatus for detecting oil fumes and method therefor

Abstract

Proposed is an apparatus for detecting oil fumes in the air. The apparatus may comprise: a fine dust sensor configured to sense fine dust; a gas sensor configured to sense gases; and a processor configured to acquire oil fume information by using time-series sensor data or non-time-series sensor data acquired from the fine dust sensor and the gas sensor.

Description

Device for detecting oil vapor and method for the same

[0001] The present invention relates to an apparatus and a method for detecting oil vapor, and more specifically, to an apparatus and a method for sensing the concentration or presence of oil vapor based on at least two types of sensor data detectable in air.

[0002] Oil fumes are one of the most common pollutants that can occur in homes and cooking facilities among cooking fumes. Their size falls into the categories of ultrafine dust (2.5 µm or less) or fine dust (10 µm or less), and their harmful effects on the human body are mitigated through ventilation or the operation of air purifiers. The timing for filter replacement can be determined by judging lifespan based on the user's personal experience, or by methods such as generating an alarm by measuring the air quality at the exhaust outlet if a sensor for specific hazardous substances is present. However, judging lifespan based on experience cannot reflect the variability of filter lifespan due to the user's environment and behavior. Furthermore, in the case of filters specialized for household oil fumes, the absence of relevant sensors makes it difficult to generate replacement alarms based on sensor measurements.

[0003] The present invention proposes a sensor capable of detecting oil vapor, a device including a sensor, or a system including the same.

[0004] In order to solve the problems of determining the replacement time of filters for existing air purifiers or sensing oil vapor in the air, the present invention proposes a sensor capable of detecting oil vapor, a device including such a sensor, or a system including such a sensor.

[0005] More specifically, the present invention proposes a sensor, a device including such a sensor, or a system including such a sensor, capable of designing and training an artificial intelligence model for oil vapor sensing to sense oil vapor in the air and, based thereon, providing user notifications or filter lifespan information.

[0006] The problems to be solved by the present invention are not limited to the problems to be solved above, and other problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below.

[0007] According to one embodiment of the present invention, a device for detecting oil fume in the air is proposed, and the device may include a fine dust sensor configured to sense fine dust; a gas sensor configured to sense gas; and a processor configured to acquire oil fume information using time-series sensor data or non-time-series sensor data acquired from the fine dust sensor and the gas sensor.

[0008] Additionally or alternatively, the above vapor information may include the presence or absence of vapor or the vapor concentration.

[0009] Additionally or alternatively, the processor may be configured to use a learning-evaluation model to obtain vapor information from the time-series sensor data or the non-time-series sensor data.

[0010] Additionally or alternatively, the processor may be configured to update the time-series sensor data or the non-time-series sensor data and to update the learning-evaluation model using the updated sensor data.

[0011] Additionally or alternatively, the processor may be configured to output a signal for device operation control according to the vapor information.

[0012] Additionally or alternatively, the processor may be configured to output a visual or auditory notification through a human-machine interface according to the vapor information.

[0013] Additionally or alternatively, the processor may be configured to output the vapor information through a human-machine interface or transmit the vapor information to a server or service app.

[0014] Additionally or alternatively, the processor may be configured to transmit the time-series sensor data or the non-time-series sensor data as the vapor information satisfies preset conditions.

[0015] Additionally or alternatively, the processor may be configured to generate life information of the vapor filter using the vapor information.

[0016] Additionally or alternatively, the processor may be configured to output the lifespan information of the generated vapor filter through a human-machine interface or to transmit the lifespan information of the generated vapor filter to a server or service app.

[0017] According to another embodiment of the present invention, a method for detecting oil vapor in air may include the step of acquiring time-series or non-time-series fine dust sensor data—the time-series or non-time-series sensor data including fine dust sensor data and gas sensor data—; and the step of acquiring oil vapor information using the time-series or non-time-series sensor data.

[0018] Additionally, according to another embodiment of the present invention, a computer-readable medium is proposed that stores code configured to execute the method for detecting oil vapor described above by a computer or processor.

[0019] The above-mentioned problem-solving methods are merely some of the embodiments of the present invention, and various embodiments reflecting the technical features of the present invention can be derived and understood by those skilled in the art based on the detailed description of the present invention to be described below.

[0020] The present invention has the following technical effects.

[0021] According to the present invention, information on oil vapor in the air, that is, the detection of the presence or absence of oil vapor or the measurement of oil vapor concentration, can be obtained.

[0022] According to the present invention, information on oil vapor in the air can be accurately measured or estimated.

[0023] In addition, according to the present invention, a vapor sensing model can be updated using measured or estimated vapor information in the air.

[0024] In addition, according to the present invention, devices for ventilation or air purification can be controlled using measured or estimated air vapor information.

[0025] The effects according to the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the following detailed description of the invention.

[0026] The accompanying drawings, which are included as part of the detailed description to aid in understanding the present invention, provide embodiments of the present invention and explain the technical concept of the present invention together with the detailed description.

[0027] Figure 1 illustrates a typical indoor ventilation system.

[0028] Figure 2 shows the change over time of heterogeneous sensing data according to the present invention.

[0029] FIG. 3 illustrates the structure of a learning and evaluation model for vapor sensing according to the present invention.

[0030] FIGS. 4 to 9 illustrate operation scenarios of a sensor, device, or system, etc., for vapor sensing according to the present invention.

[0031] FIG. 10 illustrates a block diagram of a sensing device for oil vapor sensing according to the present invention.

[0032]

[0033] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols will be assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. Furthermore, in describing embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0034] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0035] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0036] A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0037] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0038]

[0039] Figure 1 illustrates a typical indoor ventilation system.

[0040] An indoor ventilation system utilizing sensing data, such as fine dust, is a smart system that monitors indoor air quality in real time and automatically controls ventilation units (fans) as needed to purify the air or exchange indoor and outdoor air. Such a system can be used in various environments, including homes, offices, and public spaces.

[0041] The Wallpad (Main Controller) is a central control device installed within a residential space that controls the ventilation system based on sensor data and user input. Through the Wallpad's user interface (UI), users can check indoor air quality information or adjust ventilation settings. Additionally, the Wallpad connects with user devices (e.g., smartphones) to enable remote control and monitoring.

[0042] The user terminal (or the application installed on it) can communicate with the wall pad to remotely control the system or check its status. The user terminal can deliver the indoor air quality status to the user in real time through a notification function. For example, if indoor fine dust levels exceed the standard limit, the app can send a notification to the user, recommend ventilation, or initiate automatic action.

[0043] The ventilation controller can be configured to control the ventilation unit (fan) by connecting directly to the wall pad or communicating wirelessly. The ventilation controller can control the fan's speed, direction, operating time, etc., based on sensor data and commands from the wall pad.

[0044] The sensor is configured to measure fine dust (PM2.5, PM10), carbon dioxide (CO2), volatile organic compounds (VOCs), temperature, and humidity. Data measured by the sensor is transmitted to a wall panel and reflected in real-time monitoring and ventilation control. Sensors are installed both indoors and outdoors, allowing them to measure the condition of the outside air as well.

[0045] The ventilation unit (fan) is responsible for the exchange of indoor and outdoor air or indoor air circulation. The ventilation unit can automatically adjust the fan's operating status (ON / OFF) and speed based on sensor data and user settings. The ventilation unit includes a high-performance filter to purify outside air before introducing it into the room or to expel contaminated indoor air.

[0046] The indoor ventilation system enables automated air quality management. When indoor air quality deteriorates, the system operates automatically to maintain a comfortable environment without user intervention.

[0047] Furthermore, indoor ventilation systems can optimize energy efficiency by reducing energy consumption through minimizing fan operation when ventilation is not necessary. The system allows for the setting of ventilation schedules by time of day, which can also enhance energy efficiency.

[0048] In addition, the indoor ventilation system can implement a strategy to improve indoor air quality solely through indoor air circulation when the outside air is contaminated.

[0049] Meanwhile, as another variation of the indoor ventilation system, there is a structure in which the user terminal is directly connected to the ventilation controller or sensor. That is, a wall pad is not used, and the user terminal receives sensor data from the sensor and can control the ventilation controller if necessary.

[0050]

[0051] Figure 2 shows the change over time of heterogeneous sensing data according to the present invention.

[0052] Particulate matter sensors (PM sensors) measure the amount of particles in the atmosphere using principles such as beta ray or light scattering methods. Among gas sensors, tVOC sensors that react to tVOCs (Total Volatile Organic Compounds) include semiconductor, electrochemical, catalytic combustion, and infrared absorption scattering types. Light scattering PM sensors and semiconductor tVOC sensors are mainly applied in household air purifiers. Depending on the type, tVOC sensors may exhibit different reactivity to target gases, and multi-gas sensors arranged in parallel to detect multiple types of gases in a single sensor are also widely used.

[0053] Oil vapor is mainly composed of particles of 10 μm or less and simultaneously exhibits the characteristics of volatile organic compounds, so signals can be obtained from tVOC sensors as well as PM sensors. As shown in Fig. 2, PM sensing data and tVOC sensing data can vary over time, and this information is used to sense oil vapor in the indoor environment.

[0054] PM sensors measure not only oil vapor but also other fine dust or water vapor particles, and tVOC sensors also react to various organic compounds other than oil vapor, so the accuracy of oil vapor measurement cannot be guaranteed based solely on the measurement values ​​of individual sensors.

[0055] In addition, in addition to PM sensors and tVOC sensors, IAQ (Internal Air Quality) sensors, toluene sensors, H2 sensors, NH3 sensors, H2S sensors, CO2 sensors, NOx sensors, temperature and humidity sensors, etc., may be used as sensors for sensing oil vapor.

[0056] In addition, measuring the presence or concentration of vapor based solely on the numerical value of sensor data is only possible through rule-based judgments based on whether the numerical value of sensor data exceeds (or is below) a threshold, so the reliability of vapor measurement is inevitably low.

[0057] The present invention aims to provide a vapor sensing algorithm that senses the occurrence and extent of vapor generation through an algorithm utilizing artificial intelligence based on two types of sensor data. Below, as a representative example, a vapor sensing algorithm that senses the occurrence and extent of vapor generation through an algorithm utilizing artificial intelligence based on simultaneously measured PM sensor data and tVOC gas sensor data is described.

[0058]

[0059] FIG. 3 illustrates the structure of a learning and evaluation model for vapor sensing according to the present invention.

[0060] Sensing data obtained by utilizing the vapor sensing algorithm according to the present invention can be used to enhance the learning sensor data set, and improved vapor sensing is possible by updating the device with an improved model derived therefrom.

[0061] In actual usage environments, the amount of oil vapor or its hourly change obtained through an oil vapor sensing model can be immediately notified to the user, or the accumulated amount can be notified at regular intervals. Based on the stored cumulative history and total accumulated amount, it can also provide analysis results of the user's lifestyle patterns or generate and notify filter lifespan information.

[0062] Hereinafter, a learning and evaluation model for vapor sensing according to the present invention (hereinafter referred to as the “vapor sensing model”) will be described.

[0063] Referring to FIG. 3, in sequence, the vapor sensing model designs and trains the vapor sensing model, and uses it to measure air to obtain vapor information such as the presence or concentration of vapor, or performs evaluations such as generating user notifications or obtaining filter life information based on the obtained vapor information.

[0064] In the following description, the vapor sensing model is described as performing the procedure illustrated in FIG. 3, but in cases where it is implemented as a device configuration such as a sensor or a sensing device, the sensor or the sensing device or its processor may be configured to perform the procedure below. Additionally, the vapor sensing model may be executed or operated on, for example, a cloud server rather than on a sensor or a sensing device.

[0065] The vapor sensing model can acquire learning sensor data (S310). For example, the learning sensor data may include fine dust (PM) sensing data acquired through a PM sensor and tVOC sensing data acquired through a tVOC sensor.

[0066] The vapor sensing model can construct or enhance a time-series data set over time using sensor data for training (S320).

[0067] A time-series data set can be constructed using learning sensor data, that is, at least some of the sensing data acquired through each sensor.

[0068] Furthermore, it may be difficult to construct a sufficient amount of training sensor data using sensor data acquired in limited environments. Accordingly, to ensure the robustness of the vapor sensing model, the acquired sensor data can be augmented. Data augmentation techniques that can be utilized include amplitude scaling, time scaling, noise addition, warping, cropping, and shifting. Additionally, generative AI-based methods such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) can be used as data augmentation techniques.

[0069] Subsequently, the vapor sensing model can preprocess or embedding the time-series dataset of the sensor data.

[0070] In data preprocessing, PM sensor data can be converted to an appropriate signal range through amplitude scaling or amplitude shifting. Additionally, in the case of tVOC sensor data, the signal range of the raw data is converted through amplitude adjustment or normalization, and the scaling factor can be a preset constant or a maximum value or average value over a specific interval.

[0071] Embedding transformation is a process of extracting new features from the relationships between existing features or changing them into key features. In the embedding transformation process, features such as ratios between specific features, the n-th derivative (differentiation) of individual features, and Fourier transform segments can be used. Additionally, during the embedding transformation process, features that are effectively reduced or transformed through dimensionality reduction methods such as PCA (Principal Component Analysis), UMAP (Uniform Manifold Approximation and Projection), and VAE can be defined and used as input layers.

[0072] The vapor sensing model can be designed or acquired using data obtained through S310 to S330, and trained.

[0073] A training model for training a vapor sensing model can be selected by considering environmental conditions, including the problem definition, characteristics of the dataset, the form, structure, and performance of the final output, and the model size. Among supervised learning models, non-time series models, time series models, or hybrid non-time series and time series models may be used, and unsupervised learning or self-supervised learning models may also be utilized.

[0074] Representative models that use non-time-series sensing data at individual time points as features include deep neural network (DNN) models such as multi-layer perceptrons (MLPs), random forests, and support vector machines (SVMs).

[0075] When utilizing time-series characteristics within a dataset, the trends of change in each sensing data over time are grouped into input data or embeddings to train a time-series model (e.g., RNN, LSTM, time-series transformer, etc.). Unlike non-time-series models that use data from a single point in time, training proceeds sequentially according to the flow of time, or input data can be reconstructed to include temporal information for use in training. Typically, training can be performed using models such as CNN (convolutional neural network) or LSTM (long-short term memory).

[0076] In the case of a binary classification problem that determines only the presence or absence of vapor, the dimension of the final output vector is 2, and in the case of multi-class classification, the dimension is adjusted according to the number of classifications.

[0077] In the case of regression models such as oil vapor concentration prediction, the model can be configured to derive continuous output values ​​by excluding the final Softmax layer.

[0078] Clustering is a representative example of unsupervised or self-supervised learning. When label information is absent or provided only in limited quantities, a model can be trained to independently understand the internal characteristics of the data and perform tasks such as classification.

[0079] Through the training of various models, model-specific parameters can be determined and used for evaluation.

[0080] To explain the evaluation, once the design or training of the vapor sensing model is completed, the vapor sensing model can perform an evaluation, that is, an evaluation task to acquire vapor information such as the presence or concentration of vapor in the air.

[0081] The vapor sensing model can acquire sensor data from the sensors (S350).

[0082] The vapor sensing model can obtain vapor information, such as the presence or absence of vapor in the air or the concentration of vapor, using a vapor sensing model learned based on the acquired sensor data (S360).

[0083] After that, the vapor sensing model can generate user notifications or filter life information based on the vapor information (S370).

[0084] User notifications may include alerts that airborne oil vapor has been detected or alerts regarding the concentration of airborne oil vapor. Filter life information can be generated using oil vapor concentration over time and ventilation fan data (rotation speed, air permeability based on rotation, etc.). If a ventilation unit (e.g., an air purifier) ​​is equipped with an oil vapor-specific filter, the acquired oil vapor-based filter life information has the advantage of notifying the user of a more accurate filter replacement time.

[0085] Additionally, the vapor sensing model can update the dataset (S380) or perform a model update (S390) by training the model using the updated dataset. Through this, the accuracy or reliability of obtaining information on vapor in the air, including information on the presence or absence of vapor or vapor concentration, can be improved.

[0086]

[0087] FIGS. 4 to 9 illustrate operation scenarios of a sensor, device, or system, etc., for vapor sensing according to the present invention.

[0088] FIG. 4 illustrates a system for oil vapor sensing according to the present invention. FIG. 4 illustrates a first scenario of on-device standalone operation in which the oil vapor detection device (10) directly performs the operation or procedure of FIG. 3 described above.

[0089] The vapor detection device (10) may be configured to design, create, or learn a vapor sensing model (i.e., a learning-evaluation model for vapor sensing) as described with reference to FIG. 3, and to obtain vapor information by processing sensor data obtained through the vapor sensing model.

[0090] The vapor detection device (10) can store sensor data and record it in a time series. Time-series sensor data can be used to obtain vapor information. In addition, non-time-series sensor data can be used to obtain vapor information.

[0091] The vapor detection device (10) may be composed of a single sensor module or a sensor station including multiple sensors.

[0092] Additionally, the vapor detection device (10) can be configured to update the vapor sensing model using the acquired sensor data.

[0093] Additionally, the vapor detection device (10) may be configured to transmit device operation control to a home appliance (20) including a ventilation unit. Whether to transmit the device operation control or to include information may be determined based on acquired vapor information.

[0094] For example, the device drive control may be configured to be transmitted to the home appliance (20) when vapor information exceeding a certain range difference from the vapor information that formed the basis of the previous device drive control is obtained. Alternatively, the device drive control may be configured to be transmitted periodically to the home appliance (20) regardless of the content of the vapor information.

[0095] For example, the device drive control may include information regarding the degree of need for ventilation or purification, such as a first level of ventilation or air purification need, a second level of ventilation or air purification need, etc. For example, the device drive control may include oil vapor information. The oil vapor information may include information on whether oil vapor is present in the air or the concentration of oil vapor. When oil vapor information is included in the device drive control, the home appliance (20) may directly control the device drive according to the oil vapor information.

[0096] Additionally, the home network may include a server (30). The server (30) may include a service app for indoor air management. Furthermore, the server (30) may not be a physical configuration. That is, the server (30) may include a remote server connected to the home network.

[0097] There are no restrictions on the managing entity of the server (30), and it may not be managed by the user of the vapor detection device (10).

[0098] The vapor detection device (10) may be configured to transmit acquired vapor information to a server (30). The transmission of vapor information may be performed only when a preset condition is satisfied, or it may be performed periodically. The server (30) may store the vapor information and record it in a time-series manner.

[0099] The server (30) may be configured to transmit device operation control to the home appliance (20) based on the received vapor information. The transmission of the device operation control or the inclusion of information may be determined based on the acquired vapor information. For example, the device operation control may include information regarding the degree of need for ventilation or purification, such as a first level of need for ventilation or air purification, a second level of need for ventilation or air purification, etc. For example, the device operation control may include vapor information. The vapor information may include information on the presence of vapor in the air or vapor concentration. When vapor information is included in the device operation control, the home appliance (20) may directly control the device operation according to the vapor information.

[0100] The home appliance (20) may be configured to control a motor or a fan according to device drive control received from a vapor detection device (10) or a server (30). The home appliance (20) includes a device configured to discharge indoor air to the outside or filter air, such as a ventilation fan, an air purifier, an air conditioner, or a heat exchanger, and the type thereof is not limited.

[0101] The vapor detection device (10) can store vapor information and record it in a time series. The vapor detection device (10) can be configured to predict the remaining lifespan of a filter (e.g., a vapor-specialized filter) using the time-series vapor information. In predicting the remaining lifespan of the filter, information regarding the fan speed of the home appliance (20) or fan speed information over time, the amount of air passing through the filter or the amount of air passing through the filter over time, the time or amount of air passing through the filter (or amount of vapor passing through), etc., may be used.

[0102] Alternatively, the server (30) may store vapor information and record it in a time series. The server (30) may be configured to predict the remaining lifespan of a filter (e.g., a vapor-specialized filter) using the time-series vapor information. In predicting the remaining lifespan of the filter, information regarding the fan speed of the home appliance (20) or fan speed information over time, the amount of air passing through the filter or the amount of air passing through the filter over time, the time or amount of air passing through the filter (or amount of vapor passing through), etc., may be used.

[0103] Predicting the total lifespan of a filter can be as follows.

[0104] 1. Estimate the filter life by comparing the total filter vapor capacity defined in advance with the cumulative value of vapor generated during actual use.

[0105] 2. Estimate the filter life by comparing the total available filter vapor time defined in advance with the cumulative value of the number or time of vapor generation events.

[0106] At this time, filter specifications such as total vapor capacity or total available time can be defined by considering vapor removal efficiency, vapor capture capacity, pressure loss, etc.

[0107] Meanwhile, in the system illustrated in FIG. 4, the vapor detection device (10) acquires vapor information but may not transmit device operation control to the home appliance (20). Additionally, the vapor detection device (10) may transmit vapor information to the server (30). That is, the vapor detection device (10) may only perform the role of sensing or monitoring vapor present in the indoor air.

[0108]

[0109] FIG. 5 illustrates a system for vapor sensing according to the present invention. FIG. 5 illustrates a first scenario of on-device-server collaboration operation in which a vapor detection device (10) and a server (30) perform the operation or procedure of FIG. 3 described above together.

[0110] Fig. 5 illustrates a scenario in which the vapor detection device (10) designs or creates a vapor sensing model, and updates to the vapor sensing model are performed by a server (30). Additionally, the vapor detection device (10) is configured to transmit vapor information or sensor data to the server (30), and the sensor data can be used to update the vapor sensing model.

[0111] The server (30) may include a service app for indoor air management. Additionally, the server (30) may not be a physical configuration. That is, the server (30) may include a remote server connected to a home network.

[0112] The server (30) may be configured to generate update information for updating a vapor sensing model based on vapor information or sensor data (i.e., the “dataset”) of FIG. 3 received from the vapor detection device (10).

[0113] When sensor data is received from the vapor detection device (10), the server (30) may be configured to obtain vapor information using the received sensor data.

[0114] The server (30) can store sensor data received from the vapor detection device (10) and can record it in a time series. Time-series sensor data can be used to obtain vapor information. In addition, non-time-series sensor data can be used to obtain vapor information.

[0115] Here, the update information may include information that enables obtaining an updated vapor sensing model based on a vapor sensing model previously stored in the vapor detection device (10). Accordingly, the vapor detection device (10) may be configured to update the vapor sensing model using the received update information.

[0116] Meanwhile, the server (30) may be configured to receive an initial vapor sensing model from the vapor detection device (10). Accordingly, the server (30) may store the same vapor sensing model as the vapor detection device (10), and accordingly, the server (30) may be configured to directly update the vapor sensing models using the update information.

[0117] Device drive control and other details not described with reference to FIG. 5 may be applied identically or similarly to the control and operation of the scenario described with reference to FIG. 4, and for the sake of simplicity of explanation, they are omitted from the description of FIG. 5.

[0118] Meanwhile, in the system illustrated in FIG. 5, the vapor detection device (10) may acquire vapor information and transmit it to the server (30), but may not transmit device operation control to the home appliance (20). Additionally, the server (30) may not transmit device operation control to the home appliance (20). That is, the vapor detection device (10) may only perform the role of sensing or monitoring vapor present in the indoor air.

[0119]

[0120] FIG. 6 illustrates a system for vapor sensing according to the present invention. FIG. 6 illustrates a first scenario of server operation in which the server (30) primarily performs the operation or procedure of FIG. 3 described above.

[0121] FIG. 6 illustrates a scenario in which, unlike FIG. 4 and FIG. 5, a vapor detection sensor (100) is included in the home network instead of a vapor sensing device.

[0122] In the scenario of FIG. 6, the vapor detection sensor (100) may be configured to acquire sensor data and transmit the acquired sensor data to a server (30). The vapor detection sensor (100) may include a fine dust sensor and a tVOC sensor. Accordingly, the sensor data may include fine dust sensor data and tVOC sensor data. That is, sensor data such as that in FIG. 2 may be acquired and transmitted.

[0123] Additionally, unlike FIGS. 4 and 5, the server (30) may be configured to directly design, create, or update a vapor sensing model. That is, the server (30) of FIG. 6 is configured to operate almost similarly to the vapor sensing device (10) of FIG. 4.

[0124] The advantage of the scenario of Fig. 6 is that a separate vapor sensing device is not required, and thus, vapor sensing and control of home appliances through it can be provided in a home network relatively simply and inexpensively. That is, since the server (30) is configured as a service app and the vapor sensing model is designed, created, or updated on a remote server, the data processing load or the required performance for it is not high at the local level. However, since the vapor detection sensor (100) needs to be continuously transmitted to the server (30), the quality of the network within the home network needs to be maintained in an excellent and uniform manner.

[0125] Device drive control and other details not described with reference to FIG. 6 may be applied identically or similarly to the control and operation of the scenario described with reference to FIG. 4, and for the sake of simplicity of explanation, they are omitted from the description of FIG. 6.

[0126]

[0127] FIG. 7 illustrates a system for vapor sensing according to the present invention. FIG. 7 illustrates a second scenario of on-device standalone operation in which the vapor detection device (10) directly performs the operation or procedure of FIG. 3 described above, but is embedded in a home appliance (20).

[0128] The vapor detection device (10) is embedded in the home appliance (20). Accordingly, the vapor detection device (10) operates almost similarly to the vapor detection device (10) of FIG. 4, and, although not shown, can be configured to perform device operation control of the home appliance (20) according to vapor information.

[0129] Additionally, the home network may include a server (30). The server (30) may include a service app for indoor air management. Furthermore, the server (30) may not be a physical configuration. That is, the server (30) may include a remote server connected to the home network.

[0130] The vapor detection device (10) or the home appliance (20) may be configured to transmit vapor information to a server (30). The server (30) may store the vapor information and record it in a time-series manner.

[0131] The server (30) can be configured to transmit device operation control to the home appliance (20) based on the received vapor information.

[0132] Device drive control and other details not described with reference to FIG. 7 may be applied identically or similarly to the control and operation of the scenario described with reference to FIG. 4, and for the sake of simplicity of explanation, they are omitted from the description of FIG. 7.

[0133]

[0134] FIG. 8 illustrates a system for vapor sensing according to the present invention. FIG. 8 illustrates a second scenario of on-device-server collaboration in which a vapor detection device (10) and a server (30), which are embedded in and implemented in a home appliance (20), perform the operation or procedure of FIG. 3 described above together.

[0135] The vapor detection device (10) is embedded in a home appliance (20). The vapor detection device (10) of FIG. 8 illustrates a scenario in which a vapor sensing model is designed or created, and the update of the vapor sensing model is performed by a server (30). Accordingly, the vapor detection device (10) can operate in a manner similar to the vapor detection device (10) of FIG. 5.

[0136] The server (30) may include a service app for indoor air management. Additionally, the server (30) may not be a physical configuration. That is, the server (30) may include a remote server connected to a home network.

[0137] The server (30) may store the same vapor sensing model as the vapor detection device (10), and accordingly, the server (30) may be configured to directly update the vapor sensing model using the update information.

[0138] Device drive control and other details not described with reference to FIG. 8 may be applied identically or similarly to the control and operation of the scenario described with reference to FIG. 4 and FIG. 5, and for the sake of simplicity of explanation, they are omitted from the description of FIG. 8.

[0139]

[0140] FIG. 9 illustrates a system for vapor sensing according to the present invention. FIG. 9 illustrates a second scenario of server operation in which the server (30) primarily performs the operation or procedure of FIG. 3 described above.

[0141] A vapor detection sensor (100) is embedded in a home appliance (20). The vapor detection sensor (100) may be configured to acquire sensor data and transmit the acquired sensor data to a server (30). The vapor detection sensor (100) may include a fine dust sensor and a tVOC sensor. Accordingly, the sensor data may include fine dust sensor data and tVOC sensor data. That is, sensor data such as that shown in FIG. 2 may be acquired and transmitted.

[0142] Additionally, unlike FIGS. 4 and 5, the server (30) may be configured to directly design, create, or update a vapor sensing model. That is, the server (30) of FIG. 9 is configured to operate almost similarly to the vapor sensing device (10) of FIG. 4.

[0143] Device drive control and other details not described with reference to FIG. 9 may be applied identically or similarly to the control and operation of the scenario described with reference to FIG. 4 or FIG. 6, and for the sake of simplicity of explanation, they are omitted from the description of FIG. 9.

[0144]

[0145] FIG. 10 illustrates a block diagram of a sensing device for oil vapor sensing according to the present invention.

[0146] The sensing device (10) may include a sensor (100) and a processor (101).

[0147] The sensing device (10) is a device for detecting oil vapor in the air.

[0148] The sensor (100) is configured to acquire at least two types of sensor data and to acquire air characteristics in the air. Preferably, the sensor (100) may include a fine dust sensor configured to sense fine dust and a gas sensor configured to sense gas. The gas sensor may include a tVOC sensor.

[0149] The processor (101) may be configured to obtain vapor information using time-series sensor data or non-time-series sensor data obtained from the fine dust sensor and the gas sensor. Here, the vapor information may include the presence or absence of vapor or the vapor concentration.

[0150] The processor (101) may be configured to use a learning-evaluation model to obtain vapor information from the time-series sensor data or the non-time-series sensor data. Here, the learning-evaluation model is the model described with reference to FIG. 3 and corresponds to the “vapor sensing model.”

[0151] The processor (101) may be configured to update the time-series sensor data or the non-time-series sensor data and to update the learning-evaluation model using the updated sensor data.

[0152] Meanwhile, the update of the learning-evaluation model may be triggered by the server (30) illustrated in FIGS. 4 to 9, rather than by the sensing device (10). According to this embodiment, the processor (101) may be configured to receive information about the updated learning-evaluation model from the server (30) based on the time-series sensor data or the non-time-series sensor data. The information about the updated learning-evaluation model may include information that enables the acquisition of the updated learning-evaluation model based on a previously stored learning-evaluation model. Accordingly, the processor (101) may be configured to update the learning-evaluation model using the information about the updated learning-evaluation model.

[0153] The processor (101) may be configured to output a signal for controlling the operation of the device according to the acquired vapor information. The signal for controlling the operation of the device may include a control signal for driving or rotating the fan of the device, i.e., an air purifier or a ventilation unit. Accordingly, the air purifier or ventilation unit may drive the fan and filter out vapor by causing indoor air to pass through a filter, or remove or reduce vapor from the indoor air by discharging indoor air to the outside.

[0154] The processor (101) may be configured to output a visual or auditory notification through a human-machine interface according to the acquired vapor information. The human-machine interface (HMI) may output not only visual or auditory notifications, but also haptic notifications or various other notifications.

[0155] The processor (101) is configured to output the acquired vapor information through an audiovisual human-machine interface or to transmit the vapor information to a server or service app.

[0156] The processor (101) may be configured to output the acquired vapor information through a human-machine interface or to transmit the vapor information to a server (30) or a service app. Through this, the vapor information can be transmitted to a user or an administrator managing an indoor ventilation system including a sensor device (10).

[0157] The processor (101) may be configured to transmit the time-series sensor data or the non-time-series sensor data as the acquired vapor information satisfies a preset condition. The time-series or non-time-series sensor data may be transmitted to a server (30) or a service app.

[0158] Additionally, the processor (101) may be configured to generate lifespan information of the vapor filter using the acquired vapor information. The processor (101) may be configured to output the generated lifespan information of the vapor filter through a human-machine interface or to transmit the generated lifespan information of the vapor filter to a server (30) or a service app.

[0159] Additionally, the sensing device (10) may further include a human-machine interface (HMI) (102). The human-machine interface (HMI) (102) includes means for providing visual or auditory notifications to the user, and may include, for example, a display, a speaker (buzzer), or an LED light. Notifications that the HMI (102) can provide may include not only visual or auditory notifications but also haptic notifications such as vibration, and the present invention is not limited thereto.

[0160] For example, if it is determined that the vapor concentration exceeds a threshold, the processor (101) can control the provision of a visual notification, an auditory notification, or a haptic notification through the HMI (102).

[0161]

[0162] Even if not described with reference to FIG. 10, the sensing device (10) of the present invention may perform the operation according to the present invention as described above in FIG. 2 to FIG. 9.

[0163]

[0164] In addition, as another aspect of the present invention, the operation of the above-described proposal or invention may be provided as code that can be implemented, practiced, or executed by a "computer" (a comprehensive concept including a system on chip (SoC) or (micro)processor, etc.), or as a computer-readable storage medium or computer program product that stores or contains said code, and the scope of the present invention may be extended to said code or as a computer-readable storage medium or computer program product that stores or contains said code.

[0165]

[0166] The detailed description of the preferred embodiments of the present invention disclosed above is provided to enable those skilled in the art to implement and practice the present invention. Although the present invention has been described with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention as described in the following claims. Accordingly, the present invention is not intended to be limited to the embodiments shown herein, but to be given the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. As a device for detecting oil fume in the air, A fine dust sensor configured to sense fine dust; A gas sensor configured to sense gas; and A device comprising a processor configured to acquire vapor information using time-series sensor data or non-time-series sensor data acquired from the fine dust sensor and the gas sensor.

2. In paragraph 1, the device wherein the vapor information includes the presence or absence of vapor or the concentration of vapor.

3. A device according to claim 1, wherein the processor is configured to use a learning-evaluation model to obtain vapor information from the time-series sensor data or the non-time-series sensor data.

4. In paragraph 3, the processor is: A device configured to update the time-series sensor data or the non-time-series sensor data, and to update the learning-evaluation model using the updated sensor data.

5. In paragraph 1, the processor is: A device configured to output a signal for controlling the operation of a device according to the above vapor information.

6. In paragraph 1, the processor is: A device configured to output a visual or auditory notification via a human-machine interface according to the above vapor information.

7. In paragraph 1, the processor is: A device configured to output the above vapor information through a human-machine interface or to transmit the above vapor information to a server or service app.

8. In paragraph 1, the processor is: A device configured to transmit the time-series sensor data or the non-time-series sensor data as the above vapor information satisfies preset conditions.

9. In paragraph 1, the processor is: A device configured to generate life information of a vapor filter using the above vapor information.

10. In paragraph 9, the processor is: A device configured to output the lifespan information of the generated vapor filter through a human-machine interface or to transmit the lifespan information of the generated vapor filter to a server or service app.

11. A method for detecting oil vapor in air, A step of acquiring time-series or non-time-series fine dust sensor data - said time-series or non-time-series sensor data includes fine dust sensor data and gas sensor data -; and A method comprising the step of obtaining vapor information using the above-mentioned time-series or non-time-series sensor data.

12. In paragraph 11, the above vapor information includes the presence or absence of vapor or the concentration of vapor.

13. A method according to claim 11, comprising the step of using a learning-evaluation model to obtain vapor information from the time-series sensor data or the non-time-series sensor data.

14. In paragraph 13, the step of updating the time-series sensor data or the non-time-series sensor data; and A method comprising the step of updating the learning-evaluation model using the updated sensor data.

15. In Paragraph 11, A method comprising the step of outputting a signal for device operation control according to the above vapor information.

16. In Paragraph 11, A method comprising the step of outputting an audiovisual notification through an audiovisual human-machine interface according to the above vapor information.

17. A method according to claim 11, comprising the step of outputting the vapor information through an audiovisual human-machine interface or transmitting the vapor information to a server or service app.

18. A method according to claim 11, comprising the step of transmitting the time-series sensor data or the non-time-series sensor data as the vapor information satisfies a preset condition.

19. A method according to claim 11, comprising the step of generating life information of a vapor filter using the above vapor information.

20. A method according to claim 19, comprising the step of outputting the lifespan information of the generated vapor filter through an audiovisual human-machine interface or transmitting the lifespan information of the generated vapor filter to a server or service app.

21. A computer-readable medium storing code configured to execute a method according to any one of paragraphs 11 through 20 by a computer or processor.

Images