Fire smoke detector, test platform and fire smoke detection method

Abstract

The application discloses a fire smoke detector, a test platform and a fire smoke detection method, and relates to the technical field of fire detection. The optical cavity in the fire smoke detector is used for fixing the included angle between the incident light axis of the first light source module and the detector optical axis as a target angle; the first receiving module is used for collecting scattered spectrum signals of multiple discrete channels at the target angle; the first processing unit is used for processing the scattered spectrum signals based on a pre-trained target algorithm and outputting a fire probability; the target angle is determined by a measurement platform; the second receiving module in the measurement platform is used for collecting test scattered spectrum signals of multiple discrete channels under multiple kinds of environmental aerosols within a preset test angle range; and the second processing unit is used for screening out the target angle according to the recognition accuracy of the preset multiple machine learning algorithms at different test angles. The method can select the best scattering angle to realize high-sensitivity recognition and rapid response of fire smoke.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire detection, in particular to a fire smoke detector, a test platform and a fire smoke detection method. BACKGROUND

[0002] Photoelectric smoke detectors usually use a single-wavelength LED light source in combination with a fixed-angle photosensitive device to determine the presence of fire by monitoring the scattering intensity of smoke particles on incident light. Such detectors can usually achieve high sensitivity in standard test environments, but in actual complex scenarios, such as the presence of dust, water mist, cooking fumes and other non-fire particles, false positives or false negatives are easily produced, significantly affecting their reliability and practicality.

[0003] The root cause of the above problems is that the scattering and absorption behavior of aerosol particles on light is influenced by multiple factors, including light source wavelength, scattering angle, chemical composition of particulate matter, particle size distribution and concentration, etc. Traditional detectors only provide low-dimensional signal input based on single wavelength and single angle, which has limited information dimension and is difficult to accurately distinguish the differences in optical response between fire smoke and non-fire interference sources. Such low-dimensional data structure lacks sufficient discrimination ability in actual applications, especially in high-humidity, dusty, kitchen and other complex environments with high false positive rates.

[0004] To improve detection accuracy, multi-wavelength, multi-angle scattering measurement technology is introduced to improve information dimension. For example, two or more wavelengths of light sources are used, and the scattering intensity is measured at different angles to improve recognition ability by using spectral and angle joint features. In related technologies, guided by Mie scattering theory, typical angle combinations such as 45° and 135° are selected, but this angle selection generally relies on theoretical analysis or empirical setting, resulting in limited effectiveness of angle setting in actual applications; or the relative deviation of the spectral response is calculated based on a pre-set aerosol model (e.g. setting particle size distribution or refractive index parameters), and the optimal angle is selected based on the minimization of the deviation. However, fire smoke in real environments is highly dynamic, with particle size and optical properties influenced by multiple factors such as burning materials and ventilation conditions, making it difficult to accurately fit the pre-set model, which in turn leads to insufficient generalization performance of angle selection. At the same time, most of these methods focus on spectral response consistency rather than directly optimizing classification accuracy, and in actual detection applications, they cannot fully reflect the true performance of fire identification.

[0005] In summary, although existing technologies attempt to improve detection accuracy by increasing sensing dimension, there are still many limitations in scattering angle selection, signal discrimination ability and adaptation to complex environments, and further research is needed to find more practical and accurate solutions. SUMMARY

[0006] The present application aims to at least solve one of the technical problems in the related art. To this end, the present application aims to provide a fire smoke detector, a test platform and a fire smoke detection method to achieve high sensitivity identification and rapid response to fire smoke.

[0007] To achieve the above-mentioned purpose, the first aspect of the present application proposes a fire smoke detector, comprising:

[0008] an optical cavity, configured to fix an included angle between an incident light axis of the first light source module and a detector optical axis as a target angle;

[0009] a first receiving module, configured to collect scattered spectrum signals of a plurality of discrete channels at the target angle and output the scattered spectrum signals to a first processing unit;

[0010] a first processing unit, configured to process the scattered spectrum signals based on a pre-trained target algorithm and output a fire probability;

[0011] wherein the target angle is determined by a measurement platform; the measurement platform comprises a second light source module and a second receiving module installed on an optical motion turntable;

[0012] the second light source module is configured to output a test light source;

[0013] the optical motion turntable rotates counterclockwise in a preset test angle range with a set step size;

[0014] the second receiving module is configured to collect test scattered spectrum signals of a plurality of discrete channels under a plurality of environmental aerosols in the preset test angle range as a data set along with the rotation of the optical motion turntable;

[0015] a second processing unit, configured to train a plurality of preset machine learning algorithm data based on the data set, and filter out the target angle in the preset test angle range according to the identification accuracy of the plurality of preset machine learning algorithms at different test angles.

[0016] In addition, the method of the above-mentioned embodiments of the present application can also have the following additional technical features:

[0017] According to one embodiment of the present application, the target algorithm is determined by the measurement platform;

[0018] the second processing unit is further configured to determine the target algorithm from the plurality of preset machine learning algorithms according to the identification effect of the plurality of preset machine learning algorithms in the binary classification task of fire smoke and interference source.

[0019] According to one embodiment of the present application, the first processing unit is further configured to normalize the scattering spectrum signals corresponding to the preset plurality of discrete channels.

[0020] According to one embodiment of the present application, the plurality of discrete channels include 415 nm, 445 nm, 480 nm, 515 nm, 555 nm, 590 nm, 630 nm and 680 nm.

[0021] The preset test angle range is 40° to 85° counterclockwise rotation of the optical motion turntable; and the set step is 5°.

[0022] The environmental aerosol includes fire smoke and non-fire interference sources.

[0023] The preset plurality of machine learning algorithms include random forest algorithm, logistic regression algorithm, support vector machine algorithm, XGBoost algorithm and K nearest neighbor algorithm.

[0024] According to one embodiment of the present application, in the initial state, the second light source module and the second processing unit are in the same horizontal line.

[0025] The second light source module emits a light beam when the optical motion turntable is rotated counterclockwise to the starting angle of the preset test angle range, and the second receiving module is configured to collect a background scattering spectrum signal.

[0026] If the difference between the test scattering spectrum signal and the background scattering spectrum signal is not greater than 0, the re-collection of the background scattering spectrum signal is triggered.

[0027] According to one embodiment of the present application, the first light source module and the second light source module each include an LED light source; and the LED light source sequentially outputs a parallel light beam through a collimating mirror, a beam expander and a lens.

[0028] The first receiving module and the second receiving module each include a spectral sensor chip and an aperture; and the front end of the spectral sensor chip is in close proximity to the rear end of the aperture.

[0029] According to one embodiment of the present application, the first processing unit is further configured to:

[0030] If the fire probability is greater than a first set threshold, an audible light alarm is triggered and pushed to the cloud.

[0031] If the fire probability is less than the first set threshold and greater than a second set threshold, a local buzzer alarm is triggered.

[0032] To achieve the above-mentioned purposes, a second embodiment of the present application provides a test platform, which includes:

[0033] a second light source module configured to output a test light source;

[0034] a second receiving module mounted on an optical motion turntable; the optical motion turntable rotates counterclockwise at a set step size within a preset test angle range; the second receiving module is configured to collect test scattering spectrum signals of a plurality of discrete channels under a plurality of environmental aerosols within the preset test angle range as the optical motion turntable rotates, to form a training set;

[0035] a second processing unit configured to train a plurality of preset machine learning algorithm data based on the training set, determine a target algorithm according to recognition effects of the plurality of preset machine learning algorithms in a fire smoke and interference source binary classification task, and filter out a target angle within the preset test angle range according to recognition accuracies of the plurality of preset machine learning algorithms at different test angles; the target algorithm represents an algorithm model for processing scattering spectrum signals collected by a fire smoke detector; and the target angle represents a scattering angle corresponding to the collection of the scattering spectrum signals by the fire smoke detector.

[0036] To achieve the above-mentioned purpose, the third aspect of the present application proposes a fire smoke detection method, applied to the fire smoke detector of the first aspect of the present application, and the method comprises:

[0037] controlling the first light source module to emit a light beam to irradiate the aerosol to be measured, and collecting scattering spectrum signals of a plurality of discrete channels under the aerosol to be measured at the target angle based on the first receiving module;

[0038] performing normalization processing on the scattering spectrum signals, inputting the normalized scattering spectrum signals into the target algorithm for processing, and outputting a fire probability; if the fire probability is greater than a first set threshold, triggering an audible and light alarm and pushing to the cloud;

[0039] if the fire probability is less than the first set threshold and greater than a second set threshold, triggering a local buzzer alarm.

[0040] To achieve the above-mentioned purpose, the fourth aspect of the present application proposes a fire smoke detection method, applied to the test platform of the second aspect of the present application, and the method comprises:

[0041] controlling the optical motion turntable to rotate counterclockwise to a starting angle of a preset test angle range; when the optical motion turntable is in an initial state, the second light source module and the second receiving module are on the same horizontal line;

[0042] controlling the second light source module to emit a light beam, and collecting background scattering spectrum signals based on the second receiving module;

[0043] Different environmental aerosols are introduced into the measurement platform, the optical motion turntable is controlled to rotate counterclockwise at a preset step length within a preset test angle range, and a test scattering spectrum signal of multiple discrete channels under multiple environmental aerosols is collected based on the second receiving module to form a data set;

[0044] If the difference between the test scattering spectrum signal and the background scattering spectrum signal is not greater than 0, the reacquisition of the background scattering spectrum signal is triggered.

[0045] If the difference between the test scattering spectrum signal and the background scattering spectrum signal is greater than 0, a preset plurality of machine learning algorithm data is trained based on the data set, a target algorithm is determined from the preset plurality of machine learning algorithms according to the recognition effect of the preset plurality of machine learning algorithms in a fire smoke and interference source binary classification task, and a target angle is selected from the preset test angle range according to the recognition accuracy of the preset plurality of machine learning algorithms at different test angles; the target algorithm represents an algorithm for processing the scattering spectrum signal collected by the fire smoke detector; and the target angle represents the scattering angle of the fire smoke detector during detection.

[0046] The fire smoke detector, the test platform and the fire smoke detection method of the embodiment of the application have the following advantages: the first light source module outputs parallel light beams, and the angle between the incident light axis and the detector optical axis is fixed as the target angle determined by the measurement platform in combination with the optical cavity, so that the scattering spectrum collection has stable geometric configuration, the consistency and comparability of data collection are enhanced, and the use of the single-angle detector effectively reduces the hardware cost and reduces the volume. The scattering spectrum signal of the multiple discrete channels is collected at the target angle by the first receiving module, and the target algorithm is processed by the first processing unit, so as to improve the recognition accuracy and response speed of the fire smoke. In addition, the target angle and the target algorithm are not artificially set, but rely on the training set data collected by the measurement platform under multiple environmental conditions and different angles, and the second processing unit trains and evaluates multiple machine learning algorithms to automatically select the optimal recognition model and measurement angle, which helps to adapt to complex and variable fire smoke and interference source environment, significantly enhances the intelligent level and adaptability of the system. Overall, the detector has stronger environmental adaptability, sensitivity and discrimination ability, and can realize more reliable and accurate early warning of fire. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 It is a schematic diagram of the fire smoke detector in one embodiment;

[0048] Figure 2 It is a detection principle diagram of the test platform in one embodiment;

[0049] Figure 3Flowchart of a fire smoke detection method applied to a fire smoke detector in an embodiment;

[0050] Figure 4 Flowchart of a fire smoke detection method applied to a measurement platform in an embodiment;

[0051] Figure 5 Accuracy comparison diagram of fire smoke and interference source classification in an embodiment.

[0052] BRIEF DESCRIPTION OF DRAWINGS: Fire smoke detector shell 1, first light source module 10, LED light source 2, collimating mirror 3, beam expander 4, lens 5, first receiving module 20, spectral sensor chip 6, diaphragm 7, second light source module 30, second receiving module 40. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0054] The implementation details of the technical scheme of the embodiment of the present application are described in detail below.

[0055] Figure 1 A schematic diagram of a fire smoke detector is shown. The fire smoke detector mainly consists of a first light source module 10, an optical cavity, a first receiving module 20 and a first processing unit. The working principle of the fire smoke detector will be described in detail below in combination with different embodiments. Figure 1 The working principle of the fire smoke detector is described in detail.

[0056] The first light source module 10 emits parallel light beams to the aerosol to be measured. The light rays of the parallel light beams are basically consistent in direction and have a small divergence angle, which can ensure that the incident light directions received by aerosol particles at different spatial positions are consistent, and further make the subsequent scattering signals have comparability and analysis significance in angle. The aerosol to be measured refers to aerosol particles in a suspended state in the measurement area, i.e. the detection object of the fire smoke detector. In actual application, these aerosols may be smoke particles generated in the early stage of fire, and may also contain other interference sources such as steam, dust and other non-fire particles.

[0057] In order to enhance the difference of different aerosol particles in the scattering direction, so as to improve the discrimination ability of the subsequent algorithm for these different particles, the fire smoke detector selects a specific scattering angle for collecting the spectral signal. To this end, the optical cavity is designed to accurately adjust the included angle between the incident light beam and the receiving path of the detector, so as to limit the included angle between the incident optical axis and the detector optical axis to a preset target angle. The target angle is a specific angle used by the fire delay detector to collect the scattered spectral signal.

[0058] The first receiving module 20 is responsible for acquiring the scattered spectral signals of multiple discrete channels at the target angle, and transmitting the collected scattered spectral signals to the first processing unit.

[0059] The first processing unit is built-in with a target algorithm, which is a machine learning model trained in advance. The target algorithm takes the collected multi-channel scattered spectral signal as input, extracts the spectral features and angle response characteristics, and combines the learned discrimination boundary in the training process to realize accurate classification of fire smoke and common interference sources (such as water vapor, dust, etc.), and output the corresponding fire probability .

[0060] It should be noted that the target algorithm belongs to a classification algorithm in terms of category, which is used to analyze whether the aerosol to be measured belongs to fire smoke or interference according to the input multi-channel scattered spectral signal, and output the corresponding classification probability. The classification probability essentially represents the probability that the aerosol to be measured is fire smoke, which is usually an important basis for fire, i.e. fire probability.

[0061] In one embodiment, the first processing unit is also used for normalizing the scattered spectral signals corresponding to the preset plurality of discrete channels. For example, taking 8 discrete channels as an example, each channel outputs an original spectral intensity value, and the first receiving module 20 synchronously collects the scattered spectral intensity signals of multiple channels at the target angle, respectively denoted as .

[0062] In order to reduce the influence of overall light intensity fluctuation or environmental light change on subsequent recognition and judgment, the first processing unit performs channel normalization processing on the scattered spectral intensity signals of each channel, and the calculation method is as follows:

[0063]

[0064] Wherein, represents the value of the normalized th channel, which represents the proportion of the channel to the overall light intensity; represents the scattered spectral intensity signal of the th channel; represents the sum of the scattered spectral intensity signals of all channels.​

[0065] The normalized structure constitutes a scattering feature vector , which is used to eliminate the absolute intensity difference and only retain the relative distribution characteristics between different bands. The scattering feature vector is taken as the input of the target algorithm for further fire probability prediction.

[0066] In an embodiment, in order to realize intelligent response to different levels of fire, the first processing unit judges the fire probability in stages and controls different alarm strategies based on the set threshold.

[0067] Specifically, when the calculated fire probability value exceeds the first set threshold (such as 0.94), it is considered that there is a high fire risk, and the first processing unit immediately drives the sound and light alarm device to issue an alarm signal and synchronously uploads the alarm information to the cloud platform through the wireless communication module, so that the remote monitoring center or the user terminal can receive the fire notification in real time and take emergency measures in time.

[0068] If the fire probability value is between the first set threshold (such as 0.94) and the second set threshold (such as 0.86), the current situation is determined as a potential risk state, and the high-priority sound and light alarm is not triggered at this time. The first processing unit controls the local buzzer to issue a prompt sound to remind nearby personnel to pay attention to possible abnormal conditions. Through this staged alarm mechanism, the detector can balance false alarm suppression and response timeliness, avoiding frequent triggering of remote alarms due to slight interference, and enabling rapid response to suspicious smoke conditions, thereby improving the practicality and intelligent level of early fire warning.

[0069] In an embodiment, as shown in Figure 3 , a flowchart of a fire smoke detection method applied to a fire smoke detector is shown, which can include the following steps: Figure 3

[0070] Step S101, control the first light source module to emit a light beam to irradiate the aerosol to be measured, and collect the scattering spectrum signal of the aerosol to be measured in multiple discrete channels based on the first receiving module at the target angle.

[0071] The first light source module 10 emits a light beam at a set time interval and a target angle, and makes the light beam irradiate to the aerosol particles in the current air environment to be measured. The irradiated particles will produce scattered light at different angles. The angle between the incident optical axis of the first light source module 10 and the detector optical axis is fixed as the target angle, that is, the angle between the first light source module 10 and the first receiving module 20 is the target angle, so as to collect the scattering light intensity of multiple discrete channels at the target angle through the first receiving module 20, and form the corresponding multi-channel scattering spectrum signal.​

[0072] Step S102, the scattering spectrum signal is normalized, and the normalized scattering spectrum signal is input into a target algorithm for processing to output a fire probability.

[0073] Since the scattering spectrum data collected by the first receiving module 20 is susceptible to non-specific factors such as light intensity fluctuations and particle concentration changes, the channel signals will be normalized before data processing. Let the scattering spectrum signal of each discrete channel be The normalized signal is represented as:

[0074]

[0075] wherein, is the total number of channels. This normalization method can weaken the influence of overall intensity changes, so that the subsequent algorithm processing pays more attention to the relative scattering characteristics between channels, thereby enhancing the recognition ability of different aerosol types.

[0076] After normalization processing, the normalized scattering spectrum signal is input into the target algorithm trained in advance as a feature vector, and the result output by the target algorithm is the fire probability value corresponding to the current sampling data.

[0077] Step S103, if the fire probability is greater than a first set threshold, a sound and light alarm is triggered and pushed to the cloud.

[0078] According to the comparison result of the fire probability and the set threshold, the corresponding alarm operation is performed. If the fire probability is greater than a first set threshold (such as 0.94), a sound and light alarm device is immediately triggered, and the alarm information is pushed to the cloud platform through a wireless communication module to realize remote alarm and event recording.

[0079] Step S104, if the fire probability is less than the first set threshold and greater than a second set threshold, a local buzzer alarm is triggered.

[0080] If the fire probability is between the first set threshold (such as 0.94) and the second set threshold (such as 0.86), only a local buzzer is triggered for early warning to prompt the user that there is a fire risk at present but it has not reached the alarm level.

[0081] By the fire smoke detection method of the embodiment, the multi-channel scattering spectrum signals collected at the target angle are normalized, which can effectively eliminate the influence of factors such as light source fluctuation, device error or aerosol concentration change on feature extraction results, thereby improving the consistency of input data and the stability of model judgment; based on the target algorithm outputting fire probability and setting a multi-level response mechanism, not only can it realize rapid and accurate identification and early warning in the early stage of fire, but also can provide low-intensity local alarm when there is some uncertainty, reminding users to pay attention to potential risks, avoiding missing reports and false reports, and realizing more flexible and intelligent fire response strategies.

[0082] Through the above design, the fire smoke detector realizes high-precision identification of smoke and interference sources under the structure of only using a single target angle, which not only effectively improves the accuracy of fire detection, but also effectively avoids the high cost and large size problems brought by multi-angle systems.

[0083] It can be understood that, as a key parameter for collecting scattering spectrum signals in a fire smoke detector, the selection of the target angle directly affects the distinguishability of the signal and the classification performance of the identification algorithm, and then determines the final fire judgment accuracy. Therefore, the embodiment builds a rotating disc multi-angle test system through a measurement platform, and quantitatively evaluates the classification performance at different angles to determine the optimal detection angle.

[0084] Figure 2 The detection principle diagram of the test platform is shown. As shown in Figure 2 , the test platform includes a second light source, a second receiving module 40 installed on an optical motion turntable, and a second processing unit for algorithm training and evaluation. Among them, the second light source module 30 is used to output stable and repeatable test light source, to ensure the consistency of incident light conditions in the training process.

[0085] The optical motion turntable can rotate counterclockwise in a preset test angle range at a set step (such as 5°), so that the second receiving module 40 can acquire test light signals at different receiving angles. Specifically, as the turntable rotates, the second receiving module 40 will collect scattering spectrum signals of multiple discrete channels under multiple environmental aerosols at multiple scattering angles, respectively, thereby forming a data set containing rich feature information.

[0086] The second processing unit trains multiple pre-set machine learning algorithms based on the constructed dataset. After training, the recognition accuracy of the different algorithms at various test angles is compared to identify the target angle with the best performance in the binary classification task of fire smoke and interference sources. In practical applications, continuous experimentation ultimately confirmed that 75° is the optimal detection angle. The resulting target angle will be incorporated into the optical path design of fire smoke detectors to achieve high-precision fire identification under single-angle conditions.

[0087] The measurement platform in this embodiment utilizes a second receiving module 40 mounted on an optical motion turntable to collect scattered spectral signals under different aerosol conditions at multiple discrete test angles. This allows for the construction of a comprehensive training dataset covering multiple angles and environments, effectively improving the machine learning model's ability to distinguish between fire smoke and non-fire interference sources. Simultaneously, the second processing unit trains and evaluates multiple preset algorithm models, combining recognition accuracy at different angles to ultimately select the optimal target algorithm and target angle. This helps improve the recognition accuracy and stability of fire smoke detectors under actual deployment conditions, reducing false alarm and missed alarm rates. This provides data support and model assurance for the fire smoke detector's detection angles and deployed learning algorithms, enabling highly reliable intelligent fire identification.

[0088] In one embodiment, the measurement platform is not only used to collect scattered spectrum signals, but also used to evaluate the algorithm effects among multiple candidate machine learning algorithms based on training data, and determine the target algorithm accordingly.

[0089] In actual use, the measurement platform collects multiple sets of scattered spectrum signals, including fire smoke samples and interference source samples, through the second receiving module 40. The second processing unit standardizes the collected data sets according to a unified data preprocessing process. Subsequently, multiple pre-set machine learning algorithms are trained and tested based on the same training and validation sets.

[0090] The second processing unit compares and evaluates the performance of each candidate algorithm in the binary classification recognition task of fire smoke and interference sources. The evaluation indicators include but are not limited to accuracy, recall rate, F1 value and model inference efficiency. Finally, based on the comprehensive performance of each algorithm on multiple indicators, the algorithm that is most suitable for the current acquisition environment and recognition target is determined as the target algorithm. In actual application, after continuous experiments, it was finally verified that the random forest algorithm is the optimal classification model. The random forest algorithm contains 50 decision trees, each tree has a maximum depth of 5 layers, and the model inference delay is less than 3 milliseconds. The target algorithm is parameterized and recorded or loaded into the fire smoke detector for classification and discrimination in the subsequent actual operation process.

[0091] In one embodiment, the wavelengths of multiple discrete channels can be set to 415nm, 445nm, 480nm, 515nm, 555nm, 590nm, 630nm and 680nm, covering the key scattering response areas in the visible light and near-infrared bands, helping to enhance the optical response differences to different types of aerosols, thereby improving the accuracy of classification and identification.

[0092] To achieve multi-angle spectral acquisition, the optical motion turntable on the measurement platform rotates counterclockwise from 40° to 85°, fully covering the characteristic variations of typical aerosols at medium forward scattering angles. To achieve a balance between angular resolution and acquisition efficiency, the turntable's step size is set to 5°, meaning that multi-channel scattering signals are collected every 5°. This allows the second receiving module 40 to acquire test scattering spectral signals at a total of 10 different scattering angles, ranging from 40° to 80°.

[0093] Multiple machine learning algorithms are preset for training and testing. The environmental aerosol samples selected in the experiment include fire smoke (such as n-heptane open flame, polyurethane open flame, smoldering wood fire, smoldering cotton rope fire, burning newspaper fire, etc.) and various non-fire interference sources (such as water mist, loess dust, cement dust, Arizona dust, cooking fumes, etc.) to simulate the complex detection background that may appear in actual application scenarios.

[0094] During operation, the measurement platform collects multi-channel scattering spectral signals at different scattering angles for the 10 different types of ambient aerosol samples described above. Specifically, for each aerosol scattering test, the second receiving module 40 acquires the corresponding 8-channel scattering spectral signals at 10 scattering angles, thereby constructing an 80-dimensional feature matrix (10 angles x 8 channels). Based on these acquisition results, a scattering spectral dataset was constructed, including five standard fire smoke samples and five typical interference sources.

[0095] The measurement platform has multiple preset machine learning algorithms, including random forest algorithm, logistic regression algorithm, support vector machine algorithm, XGBoost algorithm, K nearest neighbor algorithm and other commonly used classification models.

[0096] In one embodiment, reference Figure 2 As shown, when the optical motion turntable is in the initial state, that is, the optical motion turntable is at the 0° position, the second light source module 30 and the second receiving module 40 are located on the same horizontal line.

[0097] During the test, the optical motion dial rotates counterclockwise to the starting angle of the preset test angle range (40° for example). Without aerosol injection, the second light source module 30 is turned on, emitting a beam of light at a preset wavelength into the test space. At this point, since there are no particulate matter in the test space, the second receiving module 40 captures a background scattering spectrum signal, denoted as PB. This background signal reflects the baseline scattering level in the absence of particulate matter in the test environment.

[0098] On this basis, an ambient aerosol is introduced into the test space to ensure that the aerosol is fully distributed in the detection space. The optical motion turntable then rotates gradually within a preset test angle range (e.g., 40° to 85°) from a starting angle of 40° in set steps (e.g., 5°), completing the sampling process within the entire preset test angle range.

[0099] At each angle position, the second light source module 30 emits a light beam, and the second receiving module 40 collects the test scattering spectrum signals of multiple discrete channels (such as 8) corresponding to the angle, which are recorded as .

[0100] The second processing unit determines whether the difference between the particle scattering spectrum signal P and the background scattering spectrum signal PB is greater than 0. If the difference is not greater than 0, it indicates that the current background signal may be offset or interfered with. The measurement platform will trigger the re-collection of PB to ensure the accuracy and consistency of subsequent sampling data. If the difference is greater than 0, the next angle sampling process or subsequent normalization and feature analysis will be carried out.

[0101] After collecting scattering spectrum data for one aerosol across all angles, the test space is cleared of aerosol particles and another aerosol is introduced. The above process is repeated, starting from the preset angle starting position, to collect scattering spectrum data for this aerosol at each angle.

[0102] Based on this, in one embodiment, Figure 4 As shown, Figure 4 A flow chart of a fire and smoke detection method applied to a measurement platform is shown, which may include the following steps:

[0103] Step S201 : controlling the optical motion turntable to rotate counterclockwise to a starting angle of a preset test angle range.

[0104] When the optical motion turntable is in its initial position (0°), the second light source module 30 and the second receiving module 40 are aligned horizontally, serving as a calibration reference for the measurement platform. Subsequently, the optical motion turntable is controlled to rotate counterclockwise to the starting angle of a preset test angle range, for example, 40°, which serves as the starting point for the measurement platform's test.

[0105] Step S202, control the second light source module to emit a light beam, and collect a background scattering spectrum signal based on the second receiving module.

[0106] When the optical motion turntable is adjusted to the starting angle, the second light source module 30 is controlled to emit a light beam, and the background scattering spectrum signal PB in the current test space without any aerosol is collected by the second receiving module 40. The background signal can reflect the scattering characteristics of the test space under the condition of no particle medium interference.

[0107] Step S203, different environmental aerosols are introduced into the measurement platform, the optical motion turntable is controlled to rotate counterclockwise at a preset step length in a preset test angle range, and a plurality of test scattering spectrum signals of a plurality of discrete channels under a plurality of environmental aerosols are collected based on the second receiving module to form a data set.

[0108] After obtaining the background signal PB, a plurality of known types of environmental aerosol samples are introduced into the measurement platform in sequence, including five types of typical fire smoke (such as n-heptane open fire, polyurethane open fire, wood smoldering, cotton rope smoldering, and newspaper burning) and five types of non-fire interference sources (such as water mist, loess powder, cement powder, Arizona dust, and kitchen fume).

[0109] In order to ensure comprehensive coverage of the scattering angle information, the optical motion turntable is controlled to rotate counterclockwise at a fixed step length (such as every 5°) in a preset test angle range (such as 40° to 85°), and at each angle, a test scattering spectrum signal P in a plurality of discrete channels (such as 8 channels) is collected by the second receiving module 40, and a multi-dimensional training data set containing angle and channel information is finally formed.

[0110] Step S204, if the difference between the test scattering spectrum signal and the background scattering spectrum signal is not greater than 0, the reacquisition of the background scattering spectrum signal is triggered.

[0111] In each acquisition, the test scattering spectrum signal P and the background signal PB are compared. If the difference is not greater than 0, it indicates that there may be background drift or signal interference at present, and the reacquisition of the background signal PB is triggered to ensure the accuracy and reliability of the training data.

[0112] Step S205, if the difference between the test scattering spectrum signal and the background scattering spectrum signal is greater than 0, a plurality of preset machine learning algorithms are trained based on the data set, a target algorithm is determined from the plurality of preset machine learning algorithms according to the recognition effect of the plurality of preset machine learning algorithms in the fire smoke and interference source binary classification task, and a target angle is selected from the preset test angle range according to the recognition accuracy of the plurality of preset machine learning algorithms at different test angles.

[0113] When the difference is greater than 0, the sampling is determined to be valid and subsequent data processing begins.

[0114] In subsequent data processing, a high-dimensional feature matrix (such as 10 angles × 8 channels, forming an 80-dimensional feature vector) is constructed based on the collected training set, and is input into a variety of preset machine learning algorithms for training, including but not limited to random forest algorithm, logistic regression algorithm, support vector machine algorithm, XGBoost algorithm, K nearest neighbor algorithm, etc., to train the classification model to complete the binary classification recognition task between fire smoke and interference source.

[0115] By comparing the recognition accuracy, stability, and generalization ability of different algorithms in the binary classification task of fire smoke and interference sources, the classification algorithm with the best recognition effect is determined as the target algorithm (for example, the random forest algorithm was selected in the experiment); at the same time, based on the recognition accuracy at different scattering angles, the test angle with the best recognition effect is selected as the target angle (for example, the angle with the highest recognition accuracy is 75°).

[0116] like Figure 5 As shown, Figure 5 This figure shows a comparison of the accuracy of different machine learning algorithms for binary classification of fire smoke and interference sources at different test angles. The horizontal axis represents the test angle of the optical motion turntable, and the vertical axis represents the aerosol classification accuracy of the corresponding machine learning algorithm.

[0117] Depend on Figure 5 As can be seen, the Random Forest algorithm demonstrated high classification accuracy at all test angles. Therefore, Random Forest was selected as the final classification model and integrated into the first processing unit of the fire smoke detector. Furthermore, a comparison of the classification accuracy of different machine learning algorithms at the same test angle revealed that, at a test angle of 75°, the classification accuracy of each algorithm was generally high, with Random Forest achieving the highest accuracy. Therefore, 75° was selected as the target detection angle for this invention and applied to the optical cavity design of the fire smoke detector.

[0118] Ultimately, the determined target algorithm and target angle will serve as the basis for embedding models and configuration parameters in fire smoke detectors to achieve high-precision classification and identification of unknown aerosol samples in subsequent online detection tasks.

[0119] In this embodiment, by controlling the rotation of the optical motion turntable and collecting the scattered spectral signals of different environmental aerosols at multiple angles, and performing difference judgment in combination with the background scattered spectral signals, invalid background data can be effectively eliminated and the quality of the training data set can be improved; further, the data set is trained using multiple preset machine learning algorithms, and the optimal target algorithm and target angle are screened out based on the comprehensive recognition accuracy, which helps to achieve high-precision classification and recognition of fire smoke and interference sources, significantly improve the accuracy and stability of subsequent fire smoke detection, and provide data support and decision-making basis for the angle optimization and algorithm selection of the detector.

[0120] In one embodiment, Figure 1 As shown, the first light source module 10 uses an LED light source 2 as the emission unit. This LED light source 2 offers stable and adjustable output, providing continuous spectral radiation over a wide wavelength range (e.g., 400nm to 700nm), meeting the requirements of multi-channel spectral detection. To achieve a high-quality incident beam with excellent parallelism and controllable divergence, the light emitted by the LED light source 2 is sequentially processed by a collimator 3, a beam expander 4, and a lens 5.

[0121] Among them, the collimator 3 is responsible for initially shaping the divergent light guided by the optical fiber bundle into collimated light, the beam expander 4 further adjusts the beam diameter and divergence angle to improve the spatial coverage of the beam, and the lens 5 is used to converge and correct the beam to ensure that the light intensity incident on the aerosol area is uniform and the direction is stable, which helps to improve the efficiency and accuracy of obtaining subsequent scattered signals.

[0122] although Figure 2 The specific schematic diagram of the second light source module 30 is not shown in detail, but the configuration of the second light source module 30 is similar to that of the first light source module 10 .

[0123] In practice, the LED light source 2 features a front adjustment knob that allows for exponential adjustment of the output light intensity from 0 to 100%. It also accepts an included fiber bundle. This bundle is clamped in a fixed V-mount, with its output end precisely positioned behind the collimator 3 using screws. The beam expander 4, with a 3X beam expansion ratio, is secured at both ends by an auto-centering barrel. The lens 5 can be mounted directly in a standard threaded cage mounting plate.

[0124] like Figure 1 As shown, the first receiving module 20 integrates a spectral sensor chip 6 and an aperture 7 positioned in front of the spectral sensor chip 6. The spectral sensor chip 6 can collect scattered light signals at multiple wavelengths with high sensitivity. To improve the signal-to-noise ratio of the received signal and suppress stray light interference, the adjustable aperture 7 is used to limit the incident light flux. The aperture can be adjusted according to actual testing requirements to optimize angular resolution.

[0125] The diaphragm 7 in the first receiving module 20 is integrally installed with the optical spectrum sensing chip on the fire smoke detector housing 1, and the receiving optical axis forms a target angle with the incident light axis emitted by the first light source module 10. The diaphragm in the second receiving module 40 is integrally installed with the optical spectrum sensor chip on the optical motion turntable, and can realize optical spectrum signal collection at different scattering angles by moving the turntable.

[0126] It should be noted that, although Figure 2 The specific schematic diagram of the second receiving module 40 is not shown in detail, but the configuration of the second receiving module 40 is similar to that of the first receiving module 20.

[0127] In the above embodiment, the fire smoke detector introduces a target angle determined by the measurement platform, so that the included angle between the incident direction of the light source in the detector and the receiving direction is kept at the optimal angle optimized by screening, thereby significantly enhancing the response capability of the detector to the scattering characteristics of different types of aerosols. At the same time, the use of a receiving module with multi-channel spectrum resolution helps to capture more abundant spectral information, providing a solid data foundation for subsequent feature extraction and classification judgment. Further, the processing unit can more accurately identify fire smoke and assess its occurrence probability by calling the target algorithm trained based on a large-scale measured data set, effectively reducing the false alarm rate and the missed alarm rate, and improving the reliability and practicality of the detector in complex environments. The scheme not only realizes the directional optimization of the optical structure, uses a single-angle detector to realize the classification of fire smoke and interference sources, effectively reduces the hardware cost and reduces the size, but also introduces the data-driven optimization strategy of the machine learning algorithm, taking into account the synergistic improvement of optical design and intelligent discrimination.

[0128] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0129] In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0130] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and that changes, modifications, substitutions and variations can be made by those skilled in the art without departing from the scope of the present application.

Claims

1. A fire smoke detector, characterized in that: include: A first light source module is used to output a parallel light beam to the aerosol to be measured; an optical cavity, used to fix the angle between the incident light axis of the first light source module and the detector optical axis to a target angle; a first receiving module, configured to collect scattered spectrum signals of a plurality of discrete channels at the target angle, and output the scattered spectrum signals to a first processing unit; a first processing unit, configured to process the scattered spectrum signal based on a pre-trained target algorithm and output a fire probability; Wherein, the target angle is determined by a measuring platform; the measuring platform includes a second light source module and a second receiving module installed on an optical motion turntable; The second light source module is used to output a test light source; The optical motion turntable rotates counterclockwise within a preset test angle range at a set step length; The second receiving module is used to collect test scattering spectrum signals of multiple discrete channels under multiple environmental aerosols within a preset test angle range as the optical motion turntable rotates to form a data set; The second processing unit is used to train the preset multiple machine learning algorithm data based on the data set, and screen out the target angle in the preset test angle range according to the recognition accuracy of the preset multiple machine learning algorithms at different test angles.

2. The fire smoke detector according to claim 1, characterized in that: The target algorithm is determined by the measurement platform; The second processing unit is further used to determine the target algorithm from among the preset multiple machine learning algorithms based on the recognition effects of the preset multiple machine learning algorithms in the fire smoke and interference source binary classification task.

3. The fire smoke detector according to claim 1, characterized in that: The first processing unit is further configured to perform normalization processing on the scattering spectrum signals corresponding to a plurality of preset discrete channels.

4. The fire smoke detector according to claim 1, characterized in that: The wavelengths of the plurality of discrete channels include 415 nm, 445 nm, 480 nm, 515 nm, 555 nm, 590 nm, 630 nm, and 680 nm; The preset test angle range is 40° to 85° when the optical motion turntable rotates counterclockwise; the setting step is 5°; The environmental aerosols include fire smoke and non-fire interference sources; The preset multiple machine learning algorithms include random forest algorithm, logistic regression algorithm, support vector machine algorithm, XGBoost algorithm, and K nearest neighbor algorithm.

5. The fire smoke detector according to claim 1, characterized in that: In an initial state, the second light source module and the second processing unit are on the same horizontal line; The second light source module emits a light beam when the optical motion turntable rotates counterclockwise to a starting angle of the preset test angle range, and the second receiving module is used to collect background scattering spectrum signals; If the difference between the test scattering spectrum signal and the background scattering spectrum signal is not greater than 0, re-collection of the background scattering spectrum signal is triggered.

6. The fire smoke detector according to claim 1, characterized in that: The first light source module and the second light source module respectively include an LED light source; the LED light source sequentially outputs a parallel light beam through a collimator, a beam expander and a lens; The first receiving module and the second receiving module respectively include a spectrum sensor chip and an aperture; the front end of the spectrum sensor chip is closely adjacent to the rear end of the aperture.

7. The fire smoke detector according to claim 1, characterized in that: The first processing unit is further configured to: If the fire probability is greater than a first set threshold, an audible and visual alarm is triggered and pushed to the cloud; If the fire probability is less than the first set threshold and greater than the second set threshold, a local buzzer alarm is triggered.

8. A measuring platform, characterized in that: The measurement platform includes: A second light source module, used for outputting a test light source; A second receiving module mounted on an optical motion turntable; the optical motion turntable rotates counterclockwise within a preset test angle range at a set step size; the second receiving module is configured to collect test scattering spectral signals of multiple discrete channels under multiple ambient aerosols within the preset test angle range as the optical motion turntable rotates, thereby forming a training set; The second processing unit is used to train the preset multiple machine learning algorithm data based on the training set, determine the target algorithm according to the recognition effect of the preset multiple machine learning algorithms in the fire smoke and interference source binary classification task; and screen out the target angle within the preset test angle range according to the recognition accuracy of the preset multiple machine learning algorithms at different test angles; the target algorithm represents the algorithm model used to process the scattered spectrum signal collected by the fire smoke detector; the target angle represents the scattering angle corresponding to the fire smoke detector when collecting the scattered spectrum signal.

9. A fire smoke detection method, characterized in that: Applied to the fire smoke detector according to any one of claims 1 to 7, the method comprises: Controlling the first light source module to emit a light beam to illuminate the aerosol to be measured, and collecting scattered spectrum signals of the aerosol to be measured in multiple discrete channels at a target angle based on the first receiving module; Normalizing the scattered spectrum signal, inputting the normalized scattered spectrum signal into a target algorithm for processing, and outputting a fire probability; wherein, if the fire probability is greater than a first set threshold, triggering an audible and visual alarm and sending the information to the cloud; If the fire probability is less than the first set threshold and greater than the second set threshold, a local buzzer alarm is triggered.

10. A fire smoke detection method, characterized in that: Applied to the measurement platform of claim 8, the method comprises: Controlling the optical motion turntable to rotate counterclockwise to a starting angle of a preset test angle range; wherein, when the optical motion turntable is in an initial state, the second light source module and the second receiving module are on the same horizontal line; controlling the second light source module to emit a light beam, and collecting a background scattering spectrum signal based on the second receiving module; introducing different ambient aerosols into the measurement platform, controlling the optical motion turntable to rotate counterclockwise within the preset test angle range with a set step length, and collecting test scattering spectrum signals of multiple discrete channels under multiple ambient aerosols based on the second receiving module to form a data set; If the difference between the test scattering spectrum signal and the background scattering spectrum signal is not greater than 0, triggering re-collection of the background scattering spectrum signal; If the difference between the test scattering spectrum signal and the background scattering spectrum signal is greater than 0, the preset multiple machine learning algorithm data are trained based on the data set, and the target algorithm is determined among the preset multiple machine learning algorithms according to the recognition effect of the preset multiple machine learning algorithms in the fire smoke and interference source binary classification task; and according to the recognition accuracy of the preset multiple machine learning algorithms at different test angles, the target angle is screened out within the preset test angle range; the target algorithm represents the algorithm used to process the scattering spectrum signal collected by the fire smoke detector; the target angle represents the scattering angle at which the fire smoke detector is detecting.

Images