Indoor smoke concentration detection method and system

Abstract

The embodiment of the invention provides an indoor smoke concentration detection method and system, and relates to the technical field of smoke concentration detection, and the method comprises the steps: obtaining an electrical characteristic signal on a smoke detector power supply loop; according to the electrical characteristic signal, the airflow state of the surrounding environment of the smoke detector is identified, and the airflow state comprises an airflow interference state, a standing observation state and a monitoring state; according to the airflow state, the working mode of the smoke detector is adjusted, the working mode of the smoke detector comprises automatic reference correction and smoke signal monitoring, and when the airflow state is an interference state or a monitoring state, the working mode of the smoke detector is adjusted to be smoke signal monitoring; and when the airflow state is a standing observation state, starting a waiting timer for timing, acquiring high-frequency sampling data of the smoke detector after timing of the waiting timer is finished, and adjusting the working mode of the smoke detector to be automatic reference correction according to the high-frequency sampling data. The accuracy and reliability of smoke detection can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of smoke concentration detection, and in particular to a method and system for detecting indoor smoke concentration. Background Art

[0002] Existing smoke detection methods face numerous challenges in practical application, particularly in environments with complex and variable airflow around the detector. Changes in the operating state of environmental control systems (such as air conditioning systems), such as variable airflow, can significantly affect the diffusion and concentration of smoke particles near the detector. This airflow disturbance can prevent actual smoke from effectively entering the detector's sensor cavity or dilute it, leading to delayed or missed alarms. Summary of the Invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a method and system for detecting indoor smoke concentration, aiming to improve the accuracy and reliability of smoke detection.

[0004] In a first aspect, an embodiment of the present application provides a method for detecting indoor smoke concentration, comprising: Obtaining electrical characteristic signals on the smoke detector power supply circuit; Identifying, based on the electrical characteristic signal, an airflow state in an environment surrounding the smoke detector, wherein the airflow state includes an airflow interference state, a static observation state, and a monitoring state; According to the airflow state, the working mode of the smoke detector is adjusted, and the working mode of the smoke detector includes automatic baseline calibration and monitoring of smoke signals, wherein, When the airflow state is an interference state or a monitoring state, adjusting the working mode of the smoke detector to monitor smoke signals; When the airflow state is a static observation state, a waiting timer is started, and after the waiting timer ends, high-frequency sampling data of the smoke detector is obtained, and the working mode of the smoke detector is adjusted to automatic baseline calibration according to the high-frequency sampling data of the smoke detector.

[0005] According to some embodiments of the present application, the steps of obtaining high-frequency sampling data of a smoke detector and adjusting the operating mode of the smoke detector to automatic baseline calibration according to the high-frequency sampling data of the smoke detector include: Obtaining high-frequency sampling data of the smoke detector, Acquiring micro-fluctuation data based on the high-frequency sampling data; Determining, based on the microscopic fluctuation data, that there is no weak airflow disturbance around the smoke detector; When there is no weak airflow disturbance around the smoke detector, the working mode of the smoke detector is adjusted to automatic baseline calibration.

[0006] According to some embodiments of the present application, the step of determining, based on the microscopic fluctuation data, that there is no weak airflow disturbance around the smoke detector includes: Performing time-frequency analysis on the micro-fluctuation data to obtain energy distribution of the micro-fluctuation data at different frequencies; identifying, based on the energy distribution, a specific frequency range associated with the movement of air particles under the influence of the airflow; Calculating an energy value within the specific frequency range based on the energy distribution and the specific frequency range; When the energy value within the specific frequency range is less than a preset energy threshold, it is determined that there is no weak airflow disturbance around the smoke detector.

[0007] According to some embodiments of the present application, the step of identifying a specific frequency range associated with the movement of air particles under the action of airflow includes: Analyzing the time series of energy distribution of the microscopic fluctuation data at different frequencies; identifying, based on the time series, dynamic characteristics of different airflow patterns presented by the energy distribution over the time series; Based on the dynamic characteristics, a specific frequency range associated with the movement of air particles in the current airflow pattern is determined.

[0008] According to some embodiments of the present application, an airflow source device is further included; and the step of identifying the airflow state of the environment surrounding the smoke detector based on the electrical characteristic signal includes: Obtaining energy distribution of the electrical characteristic signal at different frequencies and changes in the time dimension; Determining, based on the energy distribution of the electrical characteristic signal at different frequencies and its change in the time dimension, that the electrical characteristic signal is an electrical fingerprint associated with the operating mode of the airflow source device, wherein the electrical fingerprint includes an electrical fingerprint corresponding to a variable frequency, low power consumption, or intermittent operating mode; determining an operating state of the airflow source device according to the electrical fingerprint; The airflow state of the surrounding environment of the smoke detector is identified according to the operating state of the airflow source device.

[0009] According to some embodiments of the present application, the step of determining, based on the energy distribution of the electrical characteristic signal at different frequencies and the change in the time dimension, that the electrical characteristic signal is an electrical fingerprint related to the operating mode of the airflow source device includes: extracting frequencies or harmonic frequencies associated with mechanical vibrations of the airflow source device from the energy distribution; Extracting an electrical response related to a start-up or stop process of the airflow source device from the change in the time dimension; Extracting frequencies or pulses related to non-airflow source equipment or environmental electromagnetic interference from the energy distribution and the changes in the time dimension; Comparing the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with the non-airflow source device or environmental electromagnetic interference to obtain a first difference result; The electrical feature is determined to be an electrical fingerprint associated with an operating mode of the airflow source device according to the first difference result.

[0010] According to some embodiments of the present application, the step of comparing the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with the non-airflow source device or environmental electromagnetic interference to obtain a first difference result includes: Performing time series analysis on the frequencies associated with the mechanical vibration of the airflow source device, the electrical responses associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequencies or pulses associated with non-airflow source devices or environmental electromagnetic interference; Extracting dynamic features of the intensity and duration in a time dimension based on the results of the time series analysis, wherein the dynamic features include a change trend, a fluctuation characteristic, and a persistence pattern; The dynamic feature is compared with a preset dynamic feature threshold for distinguishing an airflow source device from a preset non-airflow source interference to obtain a first difference result.

[0011] According to some embodiments of the present application, the step of extracting the dynamic features of the intensity and duration in the time dimension based on the results of the time series analysis, wherein the dynamic features include change trends, fluctuation characteristics, and persistence patterns, comprises: Extracting a change trend by calculating a moving average based on the results of the time series analysis; Extracting fluctuation characteristics by calculating standard deviation or variance based on the results of the time series analysis; The persistent pattern is extracted based on the results of the time series analysis by using an autocorrelation function or duration statistics.

[0012] According to some embodiments of the present application, after the airflow state is an interference state or a monitoring state and the working mode of the smoke detector is adjusted to monitor smoke signals, the method further includes: Obtaining the current reading and rate of change of the smoke detector; An alarm is triggered when the current reading exceeds a first preset threshold and the rate of change exceeds a second preset threshold.

[0013] In a second aspect, an embodiment of the present application provides an indoor smoke concentration detection system, the system comprising: An electrical characteristic signal acquisition module is used to acquire electrical characteristic signals on a power supply circuit of a smoke detector; an airflow state recognition module, configured to recognize the airflow state of the surrounding environment of the smoke detector based on the electrical characteristic signal, wherein the airflow state includes an airflow interference state, a static observation state, and a monitoring state; A smoke signal monitoring module is used to monitor smoke signals and provide current readings and change rates of smoke signals; The automatic baseline correction control module is used to start a waiting timer when the airflow state is a static observation state, and after the waiting timer ends, obtain the high-frequency sampling data of the smoke detector, and adjust the working mode of the smoke detector to automatic baseline correction according to the high-frequency sampling data.

[0014] According to the technical solution of the embodiment of the present application, at least the following beneficial effects are achieved: obtaining an electrical characteristic signal on the power supply circuit of the smoke detector; identifying the airflow state of the environment surrounding the smoke detector based on the electrical characteristic signal, wherein the airflow state includes an airflow interference state, a static observation state, and a monitoring state; adjusting the working mode of the smoke detector based on the airflow state, wherein the working mode of the smoke detector includes automatic baseline calibration and monitoring of smoke signals, wherein when the airflow state is an interference state or a monitoring state, the working mode of the smoke detector is adjusted to monitoring of smoke signals; when the airflow state is a static observation state, a waiting timer is started, and after the waiting timer expires, high-frequency sampling data of the smoke detector is obtained, and the working mode of the smoke detector is adjusted to automatic baseline calibration based on the high-frequency sampling data of the smoke detector. The embodiment of the present application can improve the accuracy and reliability of smoke detection.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0017] Figure 1 A flow chart of a method for detecting indoor smoke concentration provided by one embodiment of the present application; Figure 2 A schematic diagram of a flow chart for adjusting the working mode of a smoke detector to automatic baseline calibration according to an embodiment of the present application; Figure 3 A schematic diagram of a process for determining that there is no weak airflow disturbance around a smoke detector according to an embodiment of the present application; Figure 4 A schematic diagram of a process for triggering a fire source alarm according to an embodiment of the present application; Figure 5 A schematic diagram of a subsequent process for identifying a difference signal of an airflow state in an environment surrounding a smoke detector according to an embodiment of the present application; Figure 6 A schematic diagram of a process for determining an electrical characteristic as an electrical fingerprint associated with an operating mode of an airflow source device according to an embodiment of the present application; Figure 7 A schematic diagram of a process for obtaining a first difference result provided in one embodiment of the present application; Figure 8 A schematic diagram of a process for extracting dynamic features provided in one embodiment of the present application; Figure 9 A schematic diagram of a subsequent flow chart for adjusting the working mode of a smoke detector to monitor a smoke signal according to an embodiment of the present application; Figure 10 A schematic diagram of an indoor smoke concentration detection system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical methods and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. It should be noted that the term "multiple" (or multiple items) used in the description of the embodiments of this application means more than two. "greater than," "less than," and "exceed" are to be understood as excluding the number indicated, while "above," "below," and "within" are to be understood as inclusive. The use of terms such as "first" and "second" is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the situation where A exists alone, A and B exist at the same time, or B exists alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can mean: a exists alone, b exists alone, c exists alone, a and b exist at the same time, a and c exist at the same time, b and c exist at the same time, or a, b and c exist at the same time, wherein a, b, c can be single or multiple.

[0019] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0020] Based on the above situation, the present application proposes a method and system for detecting indoor smoke concentration, aiming to improve the accuracy and reliability of smoke detection.

[0021] The indoor smoke concentration detection method provided in the embodiments of the present application can be applied to a terminal or a server, or can be software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet computer, laptop computer, desktop computer, etc.; the server can be configured as an independent physical server, or as a server cluster or distributed system consisting of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms; the software can be an application that implements the indoor smoke concentration detection method, etc., but is not limited to the above forms. Embodiments of the present application can be used in a wide variety of general-purpose or specialized computer system environments or configurations. For example, personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above, and the like. The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communications network. In distributed computing environments, program modules may be located in local and remote computer storage media, including storage devices. It should be noted that in various embodiments of the present invention, when data related to the characteristics of an object (e.g., a user) is processed based on its attribute information or attribute information sets, permission or consent from the corresponding object will be obtained. Furthermore, the collection, use, and processing of this data will comply with relevant laws and standards. In addition, when the embodiment of the present invention needs to obtain the attribute information of an object, it will obtain the separate permission or separate consent of the corresponding object through a pop-up window or jump to a confirmation page. After clearly obtaining the separate permission or separate consent of the corresponding object, it will obtain the relevant data of the object necessary to enable the normal operation of the embodiment of the present invention.

[0022] See also Figure 1 , Figure 1 A flow chart of a method for detecting indoor smoke concentration provided by an embodiment of the present application is provided. The method for detecting indoor smoke concentration provided by an embodiment of the present application includes but is not limited to steps S110 to S150, and each step is introduced in sequence below. Step S110: obtaining an electrical characteristic signal on a power supply circuit of the smoke detector; Step S120: Identify the airflow state of the smoke detector's surrounding environment based on the electrical characteristic signal, where the airflow state includes an airflow interference state, a static observation state, and a monitoring state. Step S130: adjusting the working mode of the smoke detector according to the airflow state, the working mode of the smoke detector including automatic baseline calibration and monitoring of smoke signals; Step S140: When the airflow state is an interference state or a monitoring state, adjusting the working mode of the smoke detector to monitor the smoke signal; Step S150: When the airflow state is a static observation state, start a waiting timer, and after the waiting timer ends, obtain high-frequency sampling data of the smoke detector, and adjust the working mode of the smoke detector to automatic baseline calibration according to the high-frequency sampling data.

[0023] It should be noted that the electrical characteristic signal is an electrical parameter in the smoke detector's power supply circuit that reflects changes in the operation of surrounding electrical equipment or environmental electromagnetic activity. It can be collected using devices such as current sensors, voltage sensors, or spectrum analyzers. The airflow state refers to the specific conditions of air flow around the smoke detector, including the airflow interference state, the static observation state, and the monitoring state. These conditions can be identified based on the electrical characteristic signal. The airflow interference state occurs when airflow fluctuations around the smoke detector are caused by the operation of external equipment. The static observation state indicates that the airflow around the smoke detector is relatively stable or free of significant airflow disturbances. The monitoring state occurs when the airflow source equipment around the smoke detector is operating, but the airflow intensity or pattern is insufficient to cause significant interference. This state ensures that the smoke detector continues to perform its smoke detection function. The wait timer is a timing mechanism used to delay operation under specific conditions. This is primarily to ensure that the ambient airflow has sufficient time to fully stabilize during the static observation state. High-frequency sampling data is signal data collected by the smoke detector at a high frequency over a short period of time. It is primarily used to capture subtle environmental fluctuations and provide a reliable basis for automatic baseline calibration.

[0024] In one embodiment, analog signals collected by integrating a Hall-effect current sensor or a high-precision voltage sensor into the smoke detector's power line are converted into digital signals and transmitted to an embedded microcontroller, such as an ARM Cortex-M series processor. A software module running within the microcontroller performs real-time analysis of these digitized electrical signature signals. The software module can perform a fast Fourier transform (FFT) to obtain the signal's frequency distribution and compare it against a pre-set electrical fingerprint library. This fingerprint library contains typical electrical signatures corresponding to airflow sources such as air conditioning systems and exhaust fans operating in different modes (e.g., variable frequency, low power, and intermittent operation). Using a support vector machine (SVM) or neural network, the system can determine whether the current airflow state is an airflow disturbance, static observation, or monitoring state. Based on the identified airflow state, the microcontroller adjusts the smoke detector's operating mode by controlling the operating parameters of the detector's internal photoelectric sensing unit and signal processing unit. When an airflow disturbance or monitoring state is identified, the microcontroller instructs the smoke detector to remain in the smoke signal monitoring mode. In this mode, the smoke detector continuously monitors smoke concentration at a normal sampling rate and transmits the data to the alarm processing unit. When the device identifies the stationary observation state, the microcontroller starts a software timer, set to, for example, 5 minutes. After the timer expires, the microcontroller instructs the photoelectric sensor unit to collect high-frequency data from the smoke detector at a higher frequency (e.g., 1000 times per second). This high-frequency data is then fed into a micro-fluctuation analysis module, which analyzes minute fluctuations in the data to confirm that the environment is truly free of even the slightest airflow disturbance. Once confirmed, the microcontroller triggers an automatic baseline correction procedure, at which point the detector records the current ambient signal as the new clean air baseline.

[0025] Notably, by acquiring the electrical signature signal from the smoke detector's power supply circuit and identifying the surrounding airflow state, the present embodiment of the system is able to distinguish between airflow disturbance, static observation, and monitoring conditions. When airflow is disturbed or continuous monitoring is required, the smoke detector focuses on monitoring the smoke signal, preventing airflow fluctuations from interfering with smoke signal determination. When the airflow is in the static observation state, a wait timer and high-frequency sampling data analysis ensure that automatic baseline calibration is performed only when the environment is truly stable and free of minor airflow disturbances. This effectively prevents environments containing low smoke concentrations from being mistakenly set as clean air reference points, improving smoke detection accuracy and enhancing the system's operational reliability in complex indoor environments.

[0026] See also Figure 2 , Figure 2A flowchart of adjusting the working mode of a smoke detector to automatic baseline correction is provided for an embodiment of the present application; regarding the above-mentioned step S150 of obtaining high-frequency sampling data of the smoke detector, adjusting the working mode of the smoke detector to automatic baseline correction according to the high-frequency sampling data, including but not limited to steps S210 to S240, each step is introduced in turn below. Step S210: obtaining high-frequency sampling data of the smoke detector; Step S220: Acquire microscopic fluctuation data based on the high-frequency sampling data; Step S230: Determine based on the microscopic fluctuation data that there is no weak airflow disturbance around the smoke detector; Step S240: When there is no slight airflow disturbance around the smoke detector, adjust the working mode of the smoke detector to automatic baseline calibration.

[0027] It should be noted that high-frequency sampling data refers to signal data with high time resolution that is continuously collected by the smoke detector in a short period of time; micro-fluctuation data refers to quantitative information obtained after specific processing of the high-frequency sampling data, which can reflect the movement of air particles around the smoke detector or subtle disturbances in the environment. It can be extracted by filtering, differencing, Fourier transform or wavelet analysis of the high-frequency sampling data to remove noise and highlight weak fluctuation components. The purpose is to more clearly characterize subtle changes in the environment around the smoke detector, especially the characteristics related to airflow disturbances, so as to extract useful airflow disturbance information from the original data.

[0028] In one embodiment, when a smoke detector is in a static observation state and a waiting timer expires, the photoelectric sensor within the smoke detector continuously samples ambient light scattering signals at a frequency of, for example, 1000 times per second, thereby acquiring high-frequency sampling data. This raw high-frequency sampling data is then fed into a digital signal processor. The processor pre-processes this data by applying a bandpass filter to remove DC offset and high-frequency noise, retaining only signal components in the 0.1 Hz to 10 Hz range, which are typically associated with the subtle movement of airborne particles. The processor then calculates the root mean square (RMS) value of the filtered signal within a specific time window (e.g., every 1 second) and uses this RMS value as micro-fluctuation data. The system then compares this calculated micro-fluctuation data with a preset energy threshold. For example, if the RMS value is less than 0.05 volts, it is determined that there are no minor airflow disturbances around the smoke detector. Once the environment is stable and there are no minor airflow disturbances, the system sends a command to the smoke detector's core control unit, instructing it to enter automatic baseline calibration mode, thereby precisely adjusting the smoke detector's reference point.

[0029] See also Figure 3 , Figure 3 A schematic diagram of a process for determining the absence of minor airflow disturbances around a smoke detector according to one embodiment of the present application is provided. Regarding step S230, determining the absence of minor airflow disturbances around the smoke detector based on microscopic fluctuation data, including but not limited to steps S310 to S340, each of which is described below. Step S310: Perform time-frequency analysis on the micro-fluctuation data to obtain the energy distribution of the micro-fluctuation data at different frequencies; Step S320: Identify a specific frequency range related to the movement of air particles under the action of airflow based on the energy distribution; Step S330: Calculate the energy value within the specific frequency range according to the energy distribution and the specific frequency range; Step S340: When the energy value within the specific frequency range is less than the preset energy threshold, it is determined that there is no weak airflow disturbance around the smoke detector.

[0030] It should be noted that time-frequency analysis is a technique that converts signals from the time or frequency domain to the time-frequency domain in order to simultaneously observe how the frequency components of the signal change over time. Energy distribution is the energy intensity or power spectral density of the signal at different frequency points or frequency intervals after time-frequency analysis. Identifying specific frequency ranges associated with the movement of air particles under the action of airflow refers to screening out the frequency intervals corresponding to the vibrations or disturbances caused by air particles driven by airflow from the energy distribution of microscopic fluctuation data. This can be achieved by matching a pre-established airflow characteristic frequency model, automatically identifying historical data through machine learning algorithms, or analyzing characteristics such as the peak value, bandwidth, and duration of the energy distribution. The preset energy threshold is a predetermined critical value used to determine whether the energy value within a specific frequency range is small enough to determine the absence of weak airflow disturbances.

[0031] In one embodiment, when determining whether there is weak airflow disturbance around a smoke detector, the system acquires high-frequency sampled data from the smoke detector and extracts microscopic fluctuation data from it. Using a short-time Fourier transform (SFT) method, the continuous microscopic fluctuation data stream is segmented into a series of overlapping short time frames. A Hanning window function is applied to each time frame to reduce spectral leakage. A fast Fourier transform (FFT) is then performed to obtain the power spectral density (i.e., energy distribution) at different frequencies for each time frame. The frame length is set to 256 sampling points, the overlap ratio is 50%, and the number of FFT points is 512. Based on the obtained energy distribution, the specific frequency range associated with the movement of air particles under the influence of airflow is identified. Through extensive experimental data and theoretical analysis, it can be determined that the energy of air particle movement caused by weak indoor airflow (such as air conditioning and air disturbance caused by human movement) is primarily concentrated in the frequency range of 5Hz to 50Hz. The power spectral density within the 5Hz to 50Hz frequency range can be integrated to obtain the total energy value within this frequency range. The calculated energy value within the specific frequency range is then compared with a preset energy threshold. By taking multiple measurements in a clean environment without airflow disturbances and performing statistical analysis, an empirical energy threshold, such as -60dB (or a corresponding linear value), can be determined. When the calculated energy value in the 5Hz to 50Hz frequency range is less than this -60dB threshold, the system can determine that there is no weak airflow disturbance around the smoke detector. When the energy value is greater than or equal to this threshold, it is considered that weak airflow disturbance is present.

[0032] See also Figure 4 , Figure 4 A flowchart of triggering a fire alarm according to an embodiment of the present application is provided. Regarding the aforementioned step S320 of identifying a specific frequency range associated with the movement of air particles under the action of airflow, including but not limited to steps S410 to S430, each step is described in turn below. Step S410: Analyze the time series of energy distribution of micro-fluctuation data at different frequencies; Step S420: identifying dynamic characteristics of different airflow patterns presented by energy distribution in the time series according to the time series; Step S430: Determine a specific frequency range related to the movement of air particles in the current airflow pattern based on the dynamic characteristics.

[0033] It should be noted that analyzing the time series of energy distribution of micro-fluctuation data at different frequencies refers to analyzing the records of changes in the energy intensity of micro-fluctuation data at different frequencies over time. The energy spectrum of micro-fluctuation data at various frequencies can be obtained at different time points by continuously performing time-frequency analysis methods such as short-time Fourier transform or wavelet transform, and these energy spectra are arranged in chronological order. The dynamic characteristics of identifying different airflow patterns presented by energy distribution in time series are regular or irregular change patterns of energy distribution in time series that can distinguish different airflow states. They can be drift of energy peak frequency, periodic increase or decrease of energy in specific frequency bands, diffusion or contraction of energy on the frequency axis, and the speed and duration of these changes. They can be extracted by calculating the statistics of energy distribution time series, trend analysis, periodic analysis or pattern recognition algorithms.

[0034] In one embodiment, a wavelet transform is performed on the microscopic fluctuation data for the last five seconds every second to generate a series of energy coefficients at different frequency scales. The changes in these coefficients over time are recorded to form a time-frequency energy matrix. Each column of this matrix represents the frequency energy distribution at a point in time, and each row represents the change in energy at a specific frequency over time. Principal component analysis or independent component analysis is performed on specific frequency bands (e.g., 0.1Hz-10Hz) within the time-frequency energy matrix to extract the primary dynamic components that characterize the airflow pattern. Rapid and large fluctuations in low-frequency energy (0.1Hz-1Hz) within a short period of time may indicate turbulent airflow; periodic increases and decreases in high-frequency energy (5Hz-10Hz) may indicate regular pulsed airflow. Finally, based on the identified dynamic features, the specific frequency range associated with the movement of air particles in the current airflow pattern is determined. A mapping table is pre-established between airflow patterns and frequency ranges. When the "turbulent" dynamic feature is identified, the system can search the mapping table and determine a wider frequency range, for example, 0.05Hz to 20Hz, as the specific frequency range associated with the movement of air particles in the current airflow pattern. When the "stable laminar flow" dynamic feature is identified, a narrow low-frequency range, such as 0.01Hz to 0.5Hz, can be determined. This dynamic adjustment of the frequency range ensures that the frequency components that truly reflect particle motion can be accurately focused in different airflow environments, thereby improving the accuracy of judgment.

[0035] See also Figure 5 , Figure 5A schematic diagram of a subsequent process for identifying the airflow state of the smoke detector's surrounding environment based on the difference signal provided in one embodiment of the present application. Regarding step S120 , identifying the airflow state of the smoke detector's surrounding environment based on the electrical characteristic signal, including but not limited to steps S510 through S540 , each of which is described below. Step S510: Obtain the energy distribution of the electrical characteristic signal at different frequencies and its change in the time dimension; Step S520: Determine, based on the energy distribution of the electrical characteristic signal at different frequencies and its change in the time dimension, that the electrical characteristic signal is an electrical fingerprint associated with the operating mode of the airflow source device, wherein the electrical fingerprint includes an electrical fingerprint corresponding to a variable frequency, low power consumption, or intermittent operating mode; Step S530: determining the operating status of the airflow source device according to the electrical fingerprint; Step S540: Identify the airflow state of the environment surrounding the smoke detector according to the operating state of the airflow source device.

[0036] In one embodiment, a high-precision current sensor connected to the smoke detector's power supply circuit collects current signals in real time. The collected analog signal is converted to a digital signal via an analog-to-digital converter (ADC) and input into a digital signal processor (DSP). The DSP performs a fast Fourier transform (FFT) to calculate the signal's spectrum, thereby determining the energy distribution at different frequencies. The DSP also samples and stores the signal in the time domain to analyze its amplitude, frequency, or phase changes over time. A support vector machine (SVM) or convolutional neural network (CNN) model is constructed. This model learns from a large number of electrical signal samples (including their frequency spectra and time domain waveforms) from known airflow source devices (such as air conditioners and exhaust fans) operating in variable frequency, low-power, or intermittent modes to identify corresponding electrical fingerprints. When the real-time electrical signature signal processed by the DSP is input into the model, the model outputs a classification result, indicating whether the current signal matches a specific electrical fingerprint. If a harmonic peak at a specific frequency is detected and its frequency changes smoothly over time, it may be identified as the electrical fingerprint of variable frequency mode; if the overall signal energy level remains consistently below a certain threshold, it may be identified as the electrical fingerprint of low power mode; if the signal exhibits regular periodic on-off pulses, it may be identified as the electrical fingerprint of intermittent operation mode. If the model identifies an electrical fingerprint associated with variable frequency mode, the system can determine that the airflow source device is currently in variable frequency operation; if the electrical fingerprint of low power mode is identified, the device is determined to be in low power operation. These operating states can be stored in a status register. Finally, if the airflow source device (such as an air conditioner) is determined to be operating at high speed, it can be inferred that the environment surrounding the smoke detector is in an airflow interference state; if the airflow source device is in a stopped or standby state, it can be inferred that the environment is in a static observation state; if the airflow source device is in a low-speed or intermittent operation state, it can be inferred that the environment is in a monitoring state.

[0037] See also Figure 6 , Figure 6 A schematic diagram of a process for determining an electrical characteristic as an electrical fingerprint associated with the operating mode of an airflow source device, provided in accordance with one embodiment of the present application. Regarding step S520, determining the electrical characteristic signal as an electrical fingerprint associated with the operating mode of the airflow source device based on the energy distribution of the electrical characteristic signal at different frequencies and its changes in the time dimension, including but not limited to steps S610 to S650, each of which is described in sequence below. Step S610: extracting frequencies or harmonic frequencies related to mechanical vibrations of the airflow source device from the energy distribution; Step S620: extracting electrical responses related to the start or stop process of the airflow source device from the changes in the time dimension; Step S630: extracting frequencies or pulses related to non-airflow source equipment or environmental electromagnetic interference from the energy distribution and time dimension changes; Step S640: Compare the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the frequency or pulse intensity and duration associated with the non-airflow source device or environmental electromagnetic interference to obtain a first difference result; Step S650: Determine, based on the first difference result, that the electrical feature is an electrical fingerprint associated with the operating mode of the airflow source device.

[0038] In one embodiment, specific frequency components associated with the mechanical vibration of airflow source equipment (e.g., air conditioner fans) are identified and extracted from this energy distribution, such as a fundamental frequency of 50 Hz or 60 Hz and its harmonic frequencies (e.g., 100 Hz, 150 Hz, etc.). These frequencies typically manifest as sustained and stable energy peaks. By monitoring the instantaneous rate of change of current or voltage, electrical responses associated with the start-up or shutdown of the airflow source equipment can be extracted, such as a step-like increase in current during air conditioner startup or a rapid decrease in current during shutdown. These responses are typically transient, with specific rise or fall times. Furthermore, high-frequency noise (e.g., radio frequency interference) or short, high-amplitude pulses (e.g., arc discharges) are identified. These signals typically have a frequency range or duration that differs from the characteristics of the airflow source equipment. Next, the energy intensity and duration of frequencies associated with the mechanical vibration of the airflow source equipment are compared with the amplitude and duration of the electrical response associated with the start-up or shutdown of the airflow source equipment, and the intensity and duration of frequencies or pulses associated with non-airflow source equipment or environmental electromagnetic interference. This comparison can be performed based on pre-set rules or pattern matching algorithms. When the energy of a certain frequency is continuously stable and the intensity reaches a preset threshold, it tends to be judged as a feature of the airflow source device; when a short high-amplitude pulse appears, it tends to be judged as interference. Ultimately, based on the first difference result obtained from this multi-dimensional comparison, the system can determine whether the current electrical feature is related to the operating mode of the airflow source device, thereby generating an accurate electrical fingerprint. When the comparison result shows that the main feature is highly matched with the known fingerprint pattern of the airflow source device, and the interference feature is effectively excluded, it can be determined that the electrical feature is the electrical fingerprint of the airflow source device.

[0039] See also Figure 7 , Figure 7 A schematic diagram of a process for obtaining a first difference result is provided for one embodiment of the present application. Regarding step S640, the process of obtaining the first difference result by comparing the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with non-airflow source devices or environmental electromagnetic interference includes but is not limited to steps S710 to S730, each of which is described below in sequence. Step S710: Perform time series analysis on the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with non-airflow source devices or environmental electromagnetic interference; Step S720: Extract dynamic features of intensity and duration in the time dimension based on the time series analysis results. The dynamic features include change trends, fluctuation characteristics, and persistence patterns. Step S730: Obtain a first difference result based on the dynamic feature and a preset dynamic feature threshold for distinguishing between an airflow source device and a preset non-airflow source interference.

[0040] In one embodiment, it is necessary to identify an inverter air conditioner as an airflow source and distinguish it from the electromagnetic interference generated by a nearby intermittently operating induction cooker. First, a sensor acquires the electrical signature signal from the smoke detector's power supply circuit. The sensor then extracts specific frequencies associated with the inverter air conditioner's mechanical vibration (e.g., the fundamental frequency of the compressor or fan and its harmonics), electrical responses associated with the air conditioner's startup and shutdown processes (e.g., transient surges in startup current or voltage drops during shutdown), and frequencies or pulses associated with the induction cooker's operation (e.g., high-frequency switching noise). Time series analysis is then performed on the extracted intensity and duration data.

[0041] In one embodiment, for the changing trend, the slope of the sliding average can be calculated. If the slope is close to zero for a long time, it indicates that the trend is stable; if the slope is continuously positive or negative, it indicates that there is an upward or downward trend. For the fluctuation characteristics, the standard deviation or variance of the intensity within the sliding window can be calculated. A larger standard deviation indicates a severe fluctuation. The residence time distribution of the signal within a specific intensity or duration range is analyzed, or the autocorrelation function is calculated to identify periodicity. For example, the startup process of a variable frequency air conditioner may be manifested as the intensity rising rapidly from 0 to a stable value within 10 seconds, with small fluctuations; while the interference of an induction cooker may be manifested as a spike in intensity within 1 second, followed by a rapid decrease, with large fluctuations and short duration. Finally, the extracted dynamic features are compared with the preset dynamic feature threshold.

[0042] See also Figure 8 , Figure 8 A schematic diagram of a process for extracting dynamic features provided in one embodiment of the present application. Regarding step S720, which extracts dynamic features of intensity and duration in the time dimension, dynamic features include changing trends, fluctuation characteristics, and persistence patterns, including but not limited to steps S810 to S830. Each step is described below in turn. Step S810: extracting a change trend by calculating a moving average according to the result of the time series analysis; Step S820: extracting fluctuation characteristics by calculating standard deviation or variance based on the results of the time series analysis; Step S830: extracting a persistent pattern through an autocorrelation function or duration statistics according to the result of the time series analysis.

[0043] It should be noted that the standard deviation or variance is a statistic that measures the degree of dispersion of data points relative to their mean value. The standard deviation is the square root of the variance. Both reflect the fluctuation range of the data. It can be achieved by using the calculation formula of the sample standard deviation or the population standard deviation. Its purpose is to quantify the stability or instability of the signal; the autocorrelation function is a function that measures the degree of correlation between time series data and itself at different time lags. Duration statistics refers to counting and analyzing the length of time a signal remains in a specific state. It can be achieved by using methods such as the Pearson correlation coefficient, Granger causality test or histogram analysis. Its purpose is to reveal the periodicity, repeatability or instantaneous characteristics of the signal.

[0044] In one embodiment, to extract changing trends, a moving average is calculated over a 5-second sliding window. This means the average of the intensity or duration over the past 5 seconds is calculated every 1 second. This smooths out transient fluctuations and reveals the overall upward or downward trend of the signal. To extract fluctuation characteristics, a standard deviation is calculated over a 10-second sliding window. This means the standard deviation of the intensity or duration data over the past 10 seconds is calculated every 1 second. This quantifies the signal's dispersion and distinguishes between stable signals and those with significant fluctuations. To extract persistent patterns, both autocorrelation functions and duration statistics can be used. The autocorrelation function calculates the autocorrelation coefficient of the signal at different time lags (e.g., 1, 5, and 10 seconds) to identify periodic patterns, such as electrical signal repetition caused by the periodic starting and stopping of an air conditioner fan. Statistics can be used to measure the length of time the signal strength or duration remains above or below a specific threshold. If the strength remains above a high threshold for 15 consecutive seconds, this may indicate the continued operation of the airflow source device.

[0045] See also Figure 9 , Figure 9 This is a flowchart illustrating the subsequent steps of adjusting the smoke detector's operating mode to monitor smoke signals, according to one embodiment of the present application. Regarding step S140, after the airflow state is in the interference state or the monitoring state, the smoke detector's operating mode is adjusted to monitor smoke signals. This includes, but is not limited to, steps S910 to S950, each of which is described below. Step S910: obtaining the current reading and change rate of the smoke detector; Step S920: When the current reading exceeds a first preset threshold and the rate of change exceeds a second preset threshold, an alarm is triggered.

[0046] In one embodiment, an alarm is triggered when the current reading exceeds a first preset threshold and the rate of change exceeds a second preset threshold. The first threshold represents the critical value at which smoke concentration reaches a dangerous level. Exceeding this threshold indicates that smoke concentration is already high, posing a fire risk. A rate of change exceeding the second threshold indicates that smoke concentration is rapidly increasing, potentially spreading the fire, and requiring immediate action. Only when both conditions are met simultaneously will an alarm be triggered, effectively avoiding false alarms caused by environmental interference or misjudgment, ensuring alarm accuracy and reliability.

[0047] See also Figure 10 , Figure 10 This is a schematic diagram of an indoor smoke concentration detection system provided in one embodiment of the present application. The indoor smoke concentration detection system 1000 includes: The electrical characteristic signal acquisition module 1010 is used to acquire the electrical characteristic signal on the power supply circuit of the smoke detector; The airflow state recognition module 1020 is used to identify the airflow state of the smoke detector's surrounding environment based on the electrical characteristic signal. The airflow state includes the airflow interference state, the static observation state, and the monitoring state. a smoke signal monitoring module 1030 for monitoring the smoke signal and providing the current reading and rate of change of the smoke signal; The automatic baseline correction control module 1040 is used to start the waiting timer when the airflow state is a static observation state, and after the waiting timer ends, obtain the high-frequency sampling data of the smoke detector and perform automatic baseline correction of the smoke concentration detection system according to the high-frequency sampling data.

[0048] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0049] Those skilled in the art will appreciate that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVDs) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media. The above is a detailed description of the preferred implementation of the present application, but the present application is not limited to the above implementation. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the present application.

Claims

1. A method for detecting indoor smoke concentration, characterized in that: include: Obtaining electrical characteristic signals on the smoke detector power supply circuit; Identifying, based on the electrical characteristic signal, an airflow state in an environment surrounding the smoke detector, wherein the airflow state includes an airflow interference state, a static observation state, and a monitoring state; According to the airflow state, the working mode of the smoke detector is adjusted, and the working mode of the smoke detector includes automatic baseline calibration and monitoring of smoke signals, wherein, When the airflow state is an interference state or a monitoring state, adjusting the working mode of the smoke detector to monitor smoke signals; When the airflow state is a static observation state, a waiting timer is started, and after the waiting timer ends, high-frequency sampling data of the smoke detector is obtained, and the working mode of the smoke detector is adjusted to automatic baseline correction according to the high-frequency sampling data.

2. The method according to claim 1, characterized in that Acquiring high-frequency sampling data of the smoke detector and adjusting the working mode of the smoke detector to automatic baseline calibration according to the high-frequency sampling data includes the following steps: Acquiring high-frequency sampling data of the smoke detector; Acquiring micro-fluctuation data based on the high-frequency sampling data; Determining, based on the microscopic fluctuation data, that there is no weak airflow disturbance around the smoke detector; When there is no weak airflow disturbance around the smoke detector, the working mode of the smoke detector is adjusted to automatic baseline calibration.

3. The method according to claim 2, characterized in that The step of determining, based on the microscopic fluctuation data, that there is no weak airflow disturbance around the smoke detector comprises: Performing time-frequency analysis on the micro-fluctuation data to obtain energy distribution of the micro-fluctuation data at different frequencies; identifying, based on the energy distribution, a specific frequency range associated with the movement of air particles under the influence of the airflow; Calculating an energy value within the specific frequency range based on the energy distribution and the specific frequency range; When the energy value within the specific frequency range is less than a preset energy threshold, it is determined that there is no weak airflow disturbance around the smoke detector.

4. The method according to claim 3, characterized in that The step of identifying a specific frequency range associated with the movement of air particles under the influence of airflow includes: Analyzing the time series of energy distribution of the microscopic fluctuation data at different frequencies; identifying, based on the time series, dynamic characteristics of different airflow patterns presented by the energy distribution over the time series; Based on the dynamic characteristics, a specific frequency range associated with the movement of air particles in the current airflow pattern is determined.

5. The method according to claim 1, wherein The system further includes an airflow source device; and the step of identifying the airflow state of the surrounding environment of the smoke detector according to the electrical characteristic signal includes: Obtaining energy distribution of the electrical characteristic signal at different frequencies and changes in the time dimension; Determining, based on the energy distribution of the electrical characteristic signal at different frequencies and its change in the time dimension, that the electrical characteristic signal is an electrical fingerprint associated with the operating mode of the airflow source device, wherein the electrical fingerprint includes an electrical fingerprint corresponding to a variable frequency, low power consumption, or intermittent operating mode; determining an operating state of the airflow source device according to the electrical fingerprint; The airflow state of the surrounding environment of the smoke detector is identified according to the operating state of the airflow source device.

6. The method according to claim 5, characterized in that The step of determining, based on the energy distribution of the electrical characteristic signal at different frequencies and the change in the time dimension, that the electrical characteristic signal is an electrical fingerprint related to the operation mode of the airflow source device comprises: extracting frequencies or harmonic frequencies associated with mechanical vibrations of the airflow source device from the energy distribution; Extracting an electrical response related to a start-up or stop process of the airflow source device from the change in the time dimension; Extracting frequencies or pulses related to non-airflow source equipment or environmental electromagnetic interference from the energy distribution and the changes in the time dimension; Comparing the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with the non-airflow source device or environmental electromagnetic interference to obtain a first difference result; The electrical feature is determined to be an electrical fingerprint associated with an operating mode of the airflow source device according to the first difference result.

7. The method according to claim 6, characterized in that The step of comparing the frequency associated with the mechanical vibration of the airflow source device, the electrical response associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequency or pulse associated with the non-airflow source device or environmental electromagnetic interference to obtain a first difference result includes: Performing time series analysis on the frequencies associated with the mechanical vibration of the airflow source device, the electrical responses associated with the start-up or stop process of the airflow source device, and the intensity and duration of the frequencies or pulses associated with non-airflow source devices or environmental electromagnetic interference; Extracting dynamic features of the intensity and duration in a time dimension based on the results of the time series analysis, wherein the dynamic features include a change trend, a fluctuation characteristic, and a persistence pattern; A first difference result is obtained according to the dynamic feature and a preset dynamic feature threshold for distinguishing an airflow source device from a preset non-airflow source interference.

8. The method according to claim 7, characterized in that The step of extracting the dynamic characteristics of the intensity and duration in the time dimension based on the results of the time series analysis, wherein the dynamic characteristics include change trends, fluctuation characteristics, and persistence patterns, comprises: Extracting a change trend by calculating a moving average based on the results of the time series analysis; Extracting fluctuation characteristics by calculating standard deviation or variance based on the results of the time series analysis; The persistent pattern is extracted based on the results of the time series analysis by using an autocorrelation function or duration statistics.

9. The method according to claim 1, characterized in that When the airflow state is an interference state or a monitoring state, after adjusting the working mode of the smoke detector to monitor smoke signals, the method further includes: Obtaining the current reading and rate of change of the smoke detector; An alarm is triggered when the current reading exceeds a first preset threshold and the rate of change exceeds a second preset threshold.

10. An indoor smoke concentration detection system, characterized in that: The system includes: An electrical characteristic signal acquisition module is used to acquire electrical characteristic signals on a power supply circuit of a smoke detector; an airflow state recognition module, configured to recognize the airflow state of the surrounding environment of the smoke detector based on the electrical characteristic signal, wherein the airflow state includes an airflow interference state, a static observation state, and a monitoring state; A smoke signal monitoring module is used to monitor smoke signals and provide current readings and change rates of smoke signals; The automatic baseline correction control module is used to start a waiting timer when the airflow state is a static observation state, and after the waiting timer ends, obtain the high-frequency sampling data of the smoke detector, and adjust the working mode of the smoke detector to automatic baseline correction according to the high-frequency sampling data.

Images