Smoke detectors and smoke detection methods resistant to nuclear radiation interference

Abstract

This application provides a smoke detector and smoke detection method resistant to nuclear radiation interference. The smoke detector includes a laser detection cavity, a physical shielding unit, and a processing unit. The physical shielding unit is fitted outside the laser detection cavity and completely sealed. The processing unit is located inside the laser detection cavity. A laser emitter and a photoelectric receiver are fixed inside the laser detection cavity, arranged opposite each other in a scattering manner to detect smoke particles in the air and output electrical signals. The physical shielding unit is a multi-layer sealed shielding structure used to attenuate nuclear radiation. It has an air inlet and an air outlet, respectively connected to the laser detection cavity. The processing unit receives and processes the electrical signals and outputs a fire alarm signal. This improves the accuracy of smoke detection in a nuclear radiation environment, ensures stable operation of the detector, and achieves effective fire early warning.

Description

Technical Field

[0001] This application relates to the field of fire safety, and in particular to a smoke detector and smoke detection method that is resistant to nuclear radiation interference. Background Technology

[0002] In locations with continuous or intermittent high-energy nuclear radiation sources, the long-term stability and detection accuracy of fire detection equipment are crucial. Smoke detectors, with their high sensitivity, have become essential for early fire warning in these critical locations.

[0003] Existing smoke detectors mainly consist of a laser detection cavity and a signal processing unit. The laser detection cavity contains a laser emitter and a photoelectric receiver. The detector draws an air sample into the laser detection cavity through a power component. It uses the principle of laser scattering to convert the presence of smoke particles into an electrical signal. The signal processing unit then performs basic analysis on the electrical signal and determines whether to trigger a fire alarm based on a fixed alarm threshold. The entire system relies on the conversion of light and electrical signals and the determination of a fixed threshold to achieve smoke detection. The core components are directly exposed to the external environment.

[0004] Existing smoke detectors have a problem with not being able to stably detect smoke in high nuclear radiation environments. Due to the lack of a dedicated nuclear radiation protection structure, nuclear radiation can directly damage the core optical components of the detector and cause nuclear radiation noise interference in the electrical signals. The signal processing stage of the detector cannot eliminate this kind of noise, which ultimately leads to rapid aging of the detector components and a significant decrease in detection accuracy, making it difficult to stably complete smoke detection in nuclear radiation environments for a long time. Summary of the Invention

[0005] The embodiments of this application provide a smoke detector and smoke detection method that are resistant to nuclear radiation interference, so as to improve the working stability of the detector in a nuclear radiation environment.

[0006] In a first aspect, embodiments of this application provide a smoke detector resistant to nuclear radiation interference, comprising a laser detection cavity, a physical shielding unit, and a processing unit;

[0007] The physical shielding unit is sleeved on the outside of the laser detection cavity and seals the entire laser detection cavity, while the processing unit is disposed inside the laser detection cavity;

[0008] The laser detection cavity is equipped with a laser emitter and a photoelectric receiver. The laser emitter and the photoelectric receiver are arranged opposite each other in a scattering manner. The laser emitter and the photoelectric receiver are used to detect smoke particles in the air and output electrical signals to the processing unit.

[0009] The physical shielding unit is a multi-layer sealed shielding structure used to attenuate nuclear radiation; the physical shielding unit is provided with an air inlet and an air outlet; the air inlet and the air outlet are respectively provided with an air inlet and an air outlet communicating with the laser detection cavity;

[0010] The processing unit is used to receive and process electrical signals and output fire alarm signals.

[0011] In one possible implementation, the physical shielding unit includes an inner nuclear radiation shielding layer and an outer mechanical shielding layer. The inner nuclear radiation shielding layer tightly covers the outer surface of the laser detection cavity, and the outer mechanical shielding layer tightly covers the outer surface of the inner nuclear radiation shielding layer. The inner nuclear radiation shielding layer and the outer mechanical shielding layer are sealed together.

[0012] In one possible implementation, an output board is also included. The output board is electrically connected to the processing unit. The output board is provided with a dry contact signal interface and a signal transmission circuit for fire linkage control. The dry contact signal interface is used to receive fire alarm signals or no alarm signals output by the processing unit and output corresponding switch status signals.

[0013] Secondly, embodiments of this application provide a smoke detection method applied to the processing unit of a smoke detector resistant to nuclear radiation interference as described in the first aspect, comprising:

[0014] The raw electrical signal output from the laser detection cavity is acquired, and the raw electrical signal includes smoke scattering signal, environmental noise and nuclear radiation noise;

[0015] The original electrical signal is filtered and subjected to baseline dynamic processing to obtain the residual signal;

[0016] The residual signal is compared with the features in the preset memory curve library to obtain the abnormal deviation index;

[0017] Extract the target morphological features of the residual signal based on the anomaly deviation index;

[0018] Based on preset noise determination rules, the target morphological features are identified for nuclear radiation noise and a nuclear radiation interference flag is generated.

[0019] The fluctuation characteristics of the residual signal are extracted based on a preset time window, and the alarm threshold is dynamically adjusted according to the nuclear radiation interference flag and the fluctuation characteristics.

[0020] The adjusted alarm threshold is compared with the residual signal to generate a fire alarm signal or no alarm signal.

[0021] In one possible implementation, filtering and baseline dynamic processing of the original electrical signal to obtain a residual signal includes:

[0022] The original electrical signal is smoothed by sliding window mean filtering to obtain a smoothed electrical signal.

[0023] The smoothed electrical signal is dynamically tracked by a preset low-pass filtering algorithm to obtain the real-time background baseline value.

[0024] The residual signal is obtained by performing difference processing between the smoothed electrical signal and the real-time background baseline value.

[0025] In one possible implementation, the smoothed electrical signal is dynamically tracked using a low-pass filtering algorithm to obtain a real-time background baseline value, including:

[0026] The smoothed electrical signal of the current sampling period is weighted and fused with the historical background baseline value of the previous sampling period according to a preset forgetting factor;

[0027] The real-time background baseline value is updated and obtained based on the weighted fusion result.

[0028] In one possible implementation, the fluctuation characteristics of the residual signal are extracted based on a preset time window, including:

[0029] Acquire multiple sets of residual signal data within the preset time window, and obtain the maximum and minimum values ​​among the multiple sets of residual signal data by comparison;

[0030] The difference between the maximum value and the minimum value is calculated to obtain the fluctuation characteristic value, and the fluctuation characteristic value is used as the fluctuation characteristic of the residual signal.

[0031] In one possible implementation, comparing the adjusted alarm threshold with the residual signal to generate a fire alarm signal or no alarm signal includes:

[0032] The residual signal is continuously compared with the adjusted alarm threshold to determine whether the duration for which the residual signal exceeds the adjusted alarm threshold is greater than the preset confirmation duration.

[0033] If the duration of the residual signal exceeding the adjusted alarm threshold is greater than the preset confirmation duration, the fire alarm signal is generated.

[0034] If the duration of the residual signal exceeding the adjusted alarm threshold is less than or equal to the preset confirmation duration, the no-alarm signal is generated, and the feature parameters in the preset memory curve library are updated at a preset update rate.

[0035] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the second aspect and / or various possible implementations of the second aspect.

[0036] Fourthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the second aspect and / or various possible implementations of the second aspect as described above.

[0037] The smoke detector and smoke detection method against nuclear radiation interference provided in this application embodiment encapsulate the laser detection cavity by setting up a multi-layer sealed shielding structure. This, combined with an internally arranged laser emitter and photodetector positioned relative to each other in a scattering manner, and an electrically connected processing unit, achieves nuclear radiation attenuation protection for the core components of the laser detection cavity. Simultaneously, by filtering and dynamically processing the original electrical signal to obtain a residual signal, this signal is compared with a preset memory curve library to extract target morphological features, identify nuclear radiation interference indicators, and extract residual signal fluctuation characteristics. The alarm threshold is then dynamically adjusted and compared with the residual signal. This improves the detector's operational stability in a nuclear radiation environment, accurately distinguishes effective smoke signals from various types of interference noise, reduces false alarms and missed alarms, and ensures the reliability of fire alarm signal output. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0039] Figure 1 A schematic diagram of the external structure of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application;

[0040] Figure 2 A schematic diagram of the internal structure of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application;

[0041] Figure 3 A rear view of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application;

[0042] Figure 4 A schematic diagram of the external connection structure of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application;

[0043] Figure 5 This is a schematic flowchart of the smoke detection method provided in the embodiments of this application;

[0044] Explanation of reference numerals in the attached figures:

[0045] 101 - Laser detection cavity; 102 - Physical shielding unit;

[0046] 1011 - Air inlet; 1012 - Air outlet;

[0047] 1021 - Upper shielding box; 1022 - Lower shielding box; 103 - Circuit board; 104 - Output board;

[0048] 1023 - Air inlet; 1024 - Air outlet;

[0049] 105-Air filter; 106-Suction fan; 107-Sampling pipeline.

[0050] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0051] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0052] In existing technologies, smoke detection using a laser detection cavity without a specific protective structure and a fixed threshold signal processing mode presents technical problems such as the vulnerability of core optical components to damage under nuclear radiation environments, the inability to effectively identify interference noise in electrical signals, and poor alarm judgment accuracy, making it difficult to stably achieve smoke detection.

[0053] The smoke detector and smoke detection method resistant to nuclear radiation interference provided in this application can be applied to the live detection of nuclear industrial facilities, such as nuclear power plants and nuclear waste treatment plants. By setting up a multi-layer sealed shielding structure to encapsulate the laser detection cavity with a physical shielding unit, and matching it with a laser emitter and photoelectric receiver arranged in a scattering manner, and by using filtering and baseline dynamic processing of the original electrical signal, extracting residual signal fluctuation characteristics, identifying nuclear radiation interference signs and dynamically adjusting the alarm threshold, the technical problems of the detector's core components being easily damaged in a nuclear radiation environment, the difficulty in distinguishing interference noise from effective smoke signals, and the high false alarm and false alarm rates of the detection results are solved.

[0054] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0055] Figure 1 A schematic diagram of the external structure of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application; Figure 2 A schematic diagram of the internal structure of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application; Figure 3 A rear view of a smoke detector resistant to nuclear radiation interference provided in an embodiment of this application; Figure 4 This is a schematic diagram of the external connection structure of the smoke detector resistant to nuclear radiation interference provided in the embodiments of this application; as shown. Figures 1 to 4 As shown, the smoke detector resistant to nuclear radiation interference includes: a laser detection cavity 101, a physical shielding unit 102, and a processing unit;

[0056] The physical shielding unit 102 is sleeved on the outside of the laser detection cavity 101 and seals the entire laser detection cavity 101, while the processing unit is located inside the laser detection cavity 101.

[0057] A laser emitter and a photoelectric receiver are fixed inside the laser detection cavity 101. The laser emitter and the photoelectric receiver are arranged opposite each other in a scattering manner. The laser emitter and the photoelectric receiver are used to detect smoke particles in the air and output electrical signals to the processing unit.

[0058] The physical shielding unit 102 is a multi-layer sealed shielding structure used to attenuate nuclear radiation; the physical shielding unit 102 is provided with an air inlet 1023 and an air outlet 1024; the air inlet 1023 and the air outlet are respectively provided with an air inlet 1011 and an air outlet 1012 that are connected to the laser detection cavity 101.

[0059] The processing unit is used to receive and process electrical signals and output fire alarm signals.

[0060] Specifically, the laser detection cavity 101 is a cavity structure that integrates laser emitting and photoelectric receiving components to realize smoke particle detection. A continuous laser beam is emitted by the laser emitter to form a stable detection area inside the cavity. After the air sample enters the cavity, the smoke particles will cause the laser beam to scatter. The photoelectric receiver, which is set relative to the scattering, can efficiently capture the scattered light signal and convert the light signal into an electrical signal that is positively correlated with the smoke particle concentration, thus completing the signal form conversion.

[0061] The laser emitter and photoelectric receiver within the laser detection cavity 101 provide a closed and stable spatial environment for smoke particle detection. Simultaneously, they convert the detected smoke particle information into electrical signals and transmit them to subsequent components. To achieve highly sensitive identification of smoke particles in the air, the output electrical signals can be used for subsequent analysis, providing accurate basic data support for very early fire warnings.

[0062] The physical shielding unit 102 is a multi-layered structure component made of radiation-resistant materials to seal and protect the laser detection cavity 101. Through the multi-layered sealed shielding structure design including lead and tungsten alloy layers, the blocking and attenuation characteristics of high-density metal materials such as lead and tungsten alloys against nuclear radiation are utilized. Through the synergistic effect of the multi-layered structure, the penetration ability of external nuclear radiation into the cavity is significantly reduced, preventing nuclear radiation from directly affecting the core optical components.

[0063] The air inlet 1011 and air outlet 1012 form a ventilation structure that penetrates the physical shielding unit 102 and the laser detection cavity 101. The inner walls of the air inlet 1011 and air outlet 1012 are coated with a hydrophobic coating to prevent water vapor condensation from blocking the air passage. Through a channel design with a preset aperture, communication between external air and the interior of the laser detection cavity 101 is achieved, allowing air to smoothly enter the laser detection cavity 101, providing a sample source for smoke detection, while simultaneously ensuring pressure balance inside the laser detection cavity 101 and ensuring stable detection. The vents deliver air samples to the laser detection cavity 101, allowing the air samples to quickly enter the detection area, ensuring the timeliness and accuracy of smoke recognition, and providing basic sample support for subsequent signal processing.

[0064] By sealing the laser detection cavity 101 as a whole, external nuclear radiation is prevented from damaging core components such as the laser emitter and photoelectric receiver. Simultaneously, signal interference caused by nuclear radiation is reduced, ensuring the stability of the detection environment inside the cavity. This significantly reduces the impact of nuclear radiation on core optical components, extends the service life of components, and ensures the long-term stable operation of the laser detection cavity 101 under nuclear radiation conditions.

[0065] The processing unit is a control component that implements signal processing algorithms, electrical signal analysis, and alarm signal output. It performs a series of processing operations on the received electrical signals, including filtering, feature extraction, and threshold comparison. Based on preset algorithm logic, it distinguishes between valid smoke signals and various interference signals, determines whether a fire hazard exists, and then generates and outputs the corresponding fire alarm signal or no alarm signal.

[0066] By receiving and analyzing electrical signals, and outputting accurate alarm signals based on the analysis results, it serves as the terminal execution component for fire early warning. To achieve accurate analysis and identification of electrical signals, effectively distinguish between valid smoke signals and interference signals, ensure the accuracy of alarm signal output, and reduce the probability of false alarms and missed alarms in detection results.

[0067] For example, in one specific embodiment, the physical shielding unit 102 can be two separate shielding boxes joined together, or it can be an integral structure. The design can be tailored to actual needs, and no specific limitations are imposed here. Figure 1 The upper shielding box 1021 and the lower shielding box 1022 are both composed of inner and outer layers. The inner nuclear radiation protection layer and the outer mechanical protection layer can be sealed together by means of adhesive bonding or other methods.

[0068] The laser detection cavity 101 is fixed to the circuit board 103 with screws, forming an integral unit with the circuit board 103. The processing unit is integrated on the circuit board 103. The integral unit consisting of the laser detection cavity 101 and the circuit board is placed inside the cavity of the physical shielding unit consisting of the upper shielding box 1021 and the lower shielding box 1022. The upper shielding box 1021 and the lower shielding box 1022 each have four fixing holes and are fixed to the circuit board of the laser with screws, forming an integral unit with the laser detection cavity 101 and the circuit board. The upper shielding box 1021 and the lower shielding box 1022 are sealed to the circuit board 103 with structural adhesive. This constitutes a protective laser cavity with a physical shielding unit 102, eliminating the possibility of radiation entering from gaps or the back, while increasing mechanical strength through the outer mechanical protective layer.

[0069] The smoke detector resistant to nuclear radiation interference provided in this embodiment of the invention improves the working stability and detection accuracy of the detector in a nuclear radiation environment through the high-sensitivity smoke detection of the laser detection cavity 101, the nuclear radiation attenuation protection of the physical shielding unit 102, and the accurate signal analysis of the processing unit, thereby achieving reliable early warning of fires at the very early stage.

[0070] In one possible implementation, the physical shielding unit 102 includes an inner nuclear radiation shielding layer and an outer mechanical shielding layer. The inner nuclear radiation shielding layer tightly covers the outer surface of the laser detection cavity 101, and the outer mechanical shielding layer tightly covers the outer surface of the inner nuclear radiation shielding layer. The inner nuclear radiation shielding layer and the outer mechanical shielding layer are sealed together.

[0071] Specifically, the inner radiation shielding layer refers to the protective structural layer made of high-density radiation shielding material that directly covers the laser detection cavity 101. The inner radiation shielding layer is a lead layer or a tungsten alloy layer. The lead layer attenuates gamma rays through its high atomic number, while the tungsten alloy layer enhances protection against high-energy particles through its dense structure. Together, they cover different types of nuclear radiation. The outer mechanical shielding layer is a high-strength alloy layer or an engineering plastic layer, providing impact resistance and preventing physical damage during transportation or installation. Due to the inherent blocking and attenuation characteristics of high-density metal materials such as lead and tungsten alloys against nuclear radiation, when external nuclear radiation acts on this layer structure, the radiation particles interact with the material atoms, and the energy is gradually absorbed and consumed, thereby reducing the penetration capability of nuclear radiation into the inner laser detection cavity 101. It directly blocks external nuclear radiation from eroding the core optical components inside the laser detection cavity 101, reduces the performance degradation and signal interference of components caused by nuclear radiation, and provides a stable adhesion base for the outer mechanical protective layer, greatly weakening the damage of nuclear radiation to the laser emitter and photoelectric receiver, ensuring the detection accuracy of the laser detection cavity 101 in the nuclear radiation environment, and extending the service life of the core components.

[0072] The outer mechanical protective layer is a protective structural layer made of high-strength rigid materials and wrapped around the outer side of the inner nuclear radiation shielding layer. Based on the structural strength and impact resistance of high-strength alloys or engineering plastics, it resists physical damage such as mechanical collisions, compression, and dust erosion. Simultaneously, through a sealed design, it isolates external moisture, corrosive gases, and other substances, preventing structural damage to the inner nuclear radiation shielding layer due to external environmental corrosion. This provides physical protection for the inner nuclear radiation shielding layer, preventing deformation or damage during transportation, installation, and use due to external forces, maintaining the integrity of the inner nuclear radiation shielding layer, and enhancing the overall structural stability of the physical shielding unit 102. It effectively improves the anti-interference and anti-damage capabilities of the physical shielding unit 102, ensuring the inner nuclear radiation shielding layer continues to exert its nuclear radiation attenuation effect and extending the overall service life of the physical shielding unit 102.

[0073] This invention constructs a dual-protection structure system through the synergistic effect of the efficient nuclear radiation attenuation protection of the inner nuclear radiation protection layer and the stable physical protection of the outer mechanical protection layer, thereby improving the comprehensive protection performance of the physical shielding unit 102 and ensuring the stable operation of the laser detection cavity 101 in complex environments.

[0074] In one possible implementation, the physical shielding unit 102 includes at least two metal layers, wherein at least one of them is a high-density metal layer with an atomic number greater than or equal to 82.

[0075] Specifically, the metal layer is a layered component made of metallic materials that constitutes the main structure of the physical shielding unit 102, serving the dual functions of nuclear radiation attenuation and structural protection. Utilizing the dense structure and physical properties of metallic materials, the scattering and absorption of nuclear radiation particles by metal atoms weakens the penetrating power of nuclear radiation. Simultaneously, the structural strength of the metal itself resists external physical damage. The synergistic effect of multiple metal layers further enhances the protective effect. This effectively blocks external nuclear radiation and physical damage, preventing damage to the core components inside the laser detection cavity 101, maintaining the detector's stable detection performance, and extending the detector's service life.

[0076] High-density metal layers with atomic numbers greater than or equal to 82 refer to metal layers made from metals or their alloys with atomic numbers ≥ 82. Common materials include lead (atomic number 82), bismuth (atomic number 83) and their alloys. These materials are characterized by high density and large atomic numbers.

[0077] Metals with higher atomic numbers and greater density have stronger blocking and attenuation capabilities against nuclear radiation. High-density metals with atomic numbers ≥82 can efficiently absorb nuclear radiation energy through strong interactions between atoms and nuclear radiation particles, significantly reducing the penetration rate of nuclear radiation and achieving precise attenuation of nuclear radiation. Its function is to serve as the core nuclear radiation protection layer of the physical shielding unit 102, focusing on attenuating external nuclear radiation, preventing nuclear radiation from penetrating into the laser detection cavity 101, protecting core optical components from nuclear radiation damage, and simultaneously enhancing the overall protection effect in conjunction with other metal layers. This significantly improves the nuclear radiation attenuation capability of the physical shielding unit 102, effectively blocking various types of nuclear radiation from eroding the laser detection cavity 101, ensuring stable operation of the laser detection cavity 101 in a nuclear radiation environment, and guaranteeing that the detection accuracy is not affected by nuclear radiation.

[0078] This invention provides a multi-layered protective structure by setting at least two metal layers and introducing a high-density metal layer with an atomic number greater than or equal to 82 as the core nuclear radiation protection layer. This achieves a dual improvement in nuclear radiation attenuation and physical protection, enhances the comprehensive protection performance of the physical shielding unit 102, provides reliable protection for the laser detection cavity 101, and ensures the long-term stable operation of the detector in a complex nuclear radiation environment.

[0079] In one possible implementation, an output board 104 is also included. The output board 104 is electrically connected to the processing unit. The output board 104 is provided with a dry contact signal interface and a signal transmission circuit for fire linkage control. The dry contact signal interface is used to receive fire alarm signals or no alarm signals output by the processing unit and output corresponding switch status signals.

[0080] Specifically, the dry contact signal interface and signal transmission circuit configured on the output board 104 convert the fire alarm signal or no alarm signal output by the processing unit into a passive switch state signal (closed or open). The dry contact signal itself does not provide power and only completes signal transmission through the change of switch state.

[0081] By adding an output board and configuring a dry contact signal interface, the alarm judgment signal of the detector is converted into a control signal that can be recognized by external devices. For example, it can trigger the automated action of external fire protection facilities such as sprinkler systems, smoke exhaust fans, and audible and visual alarms. This upgrades the detector from a single detection device to a fire early warning linkage node. Furthermore, the passive nature of the dry contact signal avoids power interference between the internal circuitry of the detector and external devices, ensuring the safety and stability of signal transmission in complex environments. This effectively improves the automation level of the fire detection system, enabling linkage between fire detection and emergency response. When the detector detects a fire hazard, subsequent linkage actions can be triggered directly without manual intervention, significantly shortening fire response time and reducing the risk of fire spread. Simultaneously, as a common signal type in the fire protection field, the dry contact signal is compatible with fire linkage equipment, eliminating the need for additional signal conversion modules and reducing system integration costs. In nuclear radiation environments, the passive signal transmission mode effectively avoids interference from nuclear radiation on active signals, ensuring accurate alarm signal transmission and further improving the operational stability and reliability of the detector in special scenarios.

[0082] This invention converts the fire alarm signal or no alarm signal output by the processing unit into a passive switch status signal, thereby enabling the linkage between the detector and the external fire protection system, improving the automation response level of the fire protection system, and enhancing the compatibility of the detector with various external fire protection equipment based on the universal adaptability of dry contact signals, reducing system integration costs. At the same time, by using the passive signal transmission mode, the power interference between the internal circuit and the external equipment is isolated, ensuring the stability and reliability of signal transmission in complex environments such as nuclear radiation.

[0083] In one possible implementation, the air inlet 1011 is connected to the air filter 105, and the end of the air filter 105 away from the laser detection cavity 101 is connected to the suction fan 106; the sampling pipe 107 of the air inlet end of the suction fan 106 faces the outside of the smoke detector, the air outlet end of the suction fan 106 is sealed to the air inlet end of the air filter 105, and the air outlet end of the air filter 105 is sealed to the air inlet of the laser detection cavity 101.

[0084] Specifically, the air filter 105 mainly filters impurities, dust and other particulate matter in the air, and is connected to the air inlet 1011 of the gas to be tested.

[0085] Air filter 105 is used to filter impurities, dust, and harmful particulate matter from the air. The activated carbon filter can adsorb organic gases and odors, ensuring the purity of the air sample entering the laser detection cavity. By utilizing the interception and adsorption properties of the filter media, dust, impurities, and fine particulate matter in the air sample are removed, preventing impurities from entering the laser detection cavity 101 and affecting the detection accuracy, while also preventing impurities from damaging the core optical components.

[0086] The intake fan 106 is a device that provides power for air circulation. Driven by a motor, the fan blades rotate to generate negative pressure, drawing in outside air and pushing it to the air filter. This creates a stable airflow path, ensuring a continuous and stable entry of air samples into the laser detection cavity 101. It provides stable aerodynamics to the entire detection system, ensuring that air samples can smoothly pass through the filter and enter the detection cavity, enabling effective detection of smoke particles in the air. Maintaining a stable supply of air samples ensures continuous detection and avoids detection interruptions or accuracy degradation due to poor airflow.

[0087] The intake fan 106 provides the power for airflow, drawing in outside air and pushing it to the air filter. After the filter purifies the air, the air sample is sent into the laser detection cavity 101, realizing air intake, filtration, and detection. The detection cavity obtains a stable air supply, avoiding interference from impurities and dust on the detection signal, and improving the accuracy and stability of the detection.

[0088] This invention establishes a stable air sample supply system by setting up an air filter 105 and an air intake fan 106. Combined with the detection function of the laser detection cavity 101, it effectively removes impurities and interference from the air sample, ensuring that the air entering the detection cavity meets the detection requirements, guaranteeing the accuracy of smoke detection, protecting the internal components of the laser detection cavity 101, extending the service life of the equipment, and improving the operational stability and reliability of the entire system.

[0089] Figure 5 This is a flowchart illustrating the smoke detection method provided in this application embodiment. The execution entity of this embodiment can be the processing unit in the previous embodiments.

[0090] like Figure 5 As shown, the smoke detection method includes the following steps:

[0091] Step S501: Obtain the raw electrical signal output by the laser detection cavity. The raw electrical signal includes smoke scattering signal, environmental noise and nuclear radiation noise.

[0092] Specifically, smoke scattering signal refers to the electrical signal generated after laser light is scattered by smoke particles in the air; environmental noise refers to the irregular electrical signal generated by interference from the surrounding environment; and nuclear radiation noise refers to the electrical signal generated by interference factors such as nuclear radiation. The laser emitter inside the photodetector cavity emits laser light, which is scattered by smoke particles and received by the photodetector, converted into an electrical signal. This electrical signal is the raw electrical signal, containing multiple signal components. The raw electrical signal is collected at a preset sampling frequency to provide the original data foundation for subsequent signal processing, ensuring that signal processing has a clear data source. For example, a fixed sampling frequency... (e.g., 10Hz) Continuously acquire the voltage signal output by the photodetector. The signal includes smoke scattering signals, background light noise, circuit noise, and possibly nuclear radiation-induced white noise.

[0093] Step S502: Filter the original electrical signal and perform baseline dynamic processing to obtain the residual signal.

[0094] Specifically, environmental interference noise in the original electrical signal is removed using filtering techniques, and the influence of signal baseline drift is eliminated through baseline dynamic calibration, highlighting the effective signal components related to smoke. By purifying and calibrating the original electrical signal, invalid interference is removed, and the effective signal components related to smoke detection are extracted, resulting in a pure and stable residual signal, thus eliminating the influence of environmental noise and baseline drift on the detection results.

[0095] For example, a smoothed signal can be obtained by using a sliding window of length N (e.g., N=50) to perform mean filtering on the original signal. :

[0096]

[0097] A low-pass filtering algorithm is used to track the baseline value of the smoothed signal in real time. :

[0098]

[0099] in A preset forgetting factor (typically 0.01~0.001) controls the response speed of baseline tracking. This baseline value represents the normal background signal level in the current smoke-free environment.

[0100] The residual signal is obtained by calculating the deviation between the real-time signal and the baseline value. :

[0101]

[0102] In ideal conditions with no fire and no interference, It should approach zero.

[0103] Step S503: Compare the residual signal with the features in the preset memory curve library to obtain the abnormal deviation index.

[0104] Specifically, a pre-defined memory curve library The system stores signal features corresponding to different smoke concentrations. By comparing these features, the deviation of the residual signal from the standard features is quantified, yielding an anomaly deviation index. Through feature comparison, effective smoke-related information in the residual signal is identified, the degree of signal deviation from the standard features is quantified, and anomaly deviation data is accurately obtained. This provides a quantitative basis for subsequent noise identification and threshold adjustment, improving the accuracy of signal identification. The comparison process is as follows:

[0105] The residual signal of the current time period The abnormal deviation is calculated by comparing the features of the corresponding time period with those in the memory curve library. :

[0106]

[0107] in: This represents the average residual for the corresponding time period in the memory curve; This represents the standard deviation of the residuals for the corresponding time period in the memory curve; This indicates the multiple of the current anomaly relative to historical normal fluctuations.

[0108] Step S504: Extract the target morphological features of the residual signal based on the abnormal deviation index.

[0109] Specifically, based on the anomaly deviation index, features related to smoke particles in the residual signal are screened out, invalid features corresponding to noise are eliminated, and target morphological features that can reflect the presence of smoke are extracted. Effective signal features are accurately located, and the feature differences between smoke signals and interference signals are distinguished, resulting in target morphological features that accurately reflect the presence of smoke. This provides a clear basis for subsequent nuclear radiation noise identification and threshold adjustment.

[0110] Step S505: Based on the preset noise judgment rules, identify the nuclear radiation noise of the target morphological features and generate a nuclear radiation interference mark.

[0111] Specifically, the preset noise judgment rules include characteristic parameters of nuclear radiation noise. By comparing the target morphological features with the characteristic parameters of nuclear radiation noise, it determines whether nuclear radiation interference exists and generates a corresponding flag. By clearly distinguishing between smoke signals and nuclear radiation interference signals, it avoids nuclear radiation noise being misjudged as smoke signals, accurately identifies the signal characteristics corresponding to nuclear radiation interference, provides a basis for subsequent threshold adjustment, and prevents interference signals from affecting the detection results.

[0112] Noise feature parameter extraction (nuclear radiation interference identification), simplified formula:

[0113]

[0114] in, (Window length, approximately 2 seconds); This is the threshold for the normal fluctuation range, which can be calibrated according to the environment; for example, it can be 3 times the normal fluctuation range.

[0115] Criteria for determining nuclear radiation:

[0116]

[0117] Step S506: Extract the fluctuation characteristics of the residual signal based on the preset time window, and dynamically adjust the alarm threshold according to the nuclear radiation interference indicator and fluctuation characteristics.

[0118] Specifically, signal fluctuations within a time window can reflect the differences between noise and smoke signals. Combined with nuclear radiation interference indicators, the threshold is dynamically adjusted to adapt to different interference scenarios. Based on signal fluctuations and nuclear radiation interference, the alarm threshold is adjusted to avoid false alarms caused by fixed thresholds, ensuring the alarm threshold matches the actual signal state, improving the reasonableness of the threshold, and reducing the probability of false alarms.

[0119] Dynamic alarm threshold calculation: When nuclear radiation white noise is detected ( The system enters anti-nuclear radiation mode and dynamically calculates the real-time alarm threshold based on the current noise level. :

[0120]

[0121] in, This is the basic alarm threshold in a nuclear radiation-free environment; Rrang represents the fluctuation range within the current window, indicating noise intensity; k is the safety factor (usually taken as 1, Rrang is already the actual fluctuation value); when there is no nuclear radiation interference, ( The system maintains a basic threshold: Th(t) = Th0.

[0122] Step S507: Compare the adjusted alarm threshold with the residual signal to generate a fire alarm signal or no alarm signal.

[0123] Specifically, by comparing signals, it is determined whether the residual signal meets the fire detection criteria. If the criteria are met, an alarm signal is output; otherwise, no alarm signal is output. Accurate fire warning signals are output to ensure timely fire detection, while avoiding false alarms when there is no fire, thus guaranteeing the reliability of the detection results.

[0124] The smoke detection method provided in this invention provides a multi-layered protective structure to ensure the detection foundation. By combining signal processing, noise recognition, and dynamic threshold adjustment, it achieves accurate identification and reliable alarm of smoke signals, effectively improving the accuracy and stability of smoke detection, reducing false alarms and missed alarms, and ensuring the timeliness and reliability of fire early warning.

[0125] This embodiment provides a detailed description of the process in the above embodiments of filtering the original electrical signal and performing baseline dynamic processing to obtain the residual signal. The specific implementation of this process includes the following steps:

[0126] Step a1: Smooth the original electrical signal by using a sliding window mean filter to obtain a smoothed electrical signal.

[0127] Specifically, sliding window mean filtering is a filtering method that averages the original electrical signal segment by segment by setting a sliding window of fixed length. By covering continuous data points of the original electrical signal with the sliding window, and calculating the average value of the signal within the window, high-frequency interference and random noise in the original electrical signal are weakened, and the signal fluctuation amplitude is reduced. This provides initial purification of the original electrical signal, filtering out some high-frequency interference noise, reducing signal fluctuations, making the original electrical signal more stable, reducing meaningless signal fluctuations, improving signal processability, and preventing interference signals from affecting subsequent analysis.

[0128] Step a2: Perform baseline dynamic tracking on the smoothed electrical signal using a preset low-pass filtering algorithm to obtain the real-time background baseline value.

[0129] Specifically, low-pass filtering algorithms are filtering methods that allow low-frequency signals to pass through while blocking high-frequency interference signals. This effectively preserves valid smoke-related signals and filters out high-frequency interference. Based on the signal frequency characteristics, a reasonable filtering threshold is pre-set to allow low-frequency signals related to smoke detection to pass through while blocking high-frequency interference signals. Simultaneously, the baseline position is dynamically adjusted based on the changing trend of the electrical signal to establish a stable signal baseline. This provides a reference standard for subsequent difference calculations, distinguishes between valid and interference signals, and yields a stable real-time background baseline value. This provides an accurate reference for calculating the residual signal and avoids signal misjudgment caused by baseline offset.

[0130] The specific implementation of baseline dynamic tracking is as follows: the smoothed electrical signal of the current sampling period is weighted and fused with the historical background baseline value of the previous sampling period according to a preset forgetting factor α, where the value of α ranges from 0.001 to 0.01. This forgetting factor α controls the response speed of baseline tracking; a smaller α value can adapt to slow environmental changes, while a larger α value can quickly respond to sudden noise fluctuations.

[0131] Step a3: Perform difference processing on the smoothed electrical signal and the real-time background baseline value to obtain the residual signal.

[0132] Specifically, by calculating the difference between the smoothed electrical signal and the real-time background baseline value, background interference is removed, the effective signal components related to smoke are highlighted, and the influence of baseline offset is eliminated. The effective signal components that can reflect the presence of smoke are extracted, irrelevant interference is eliminated, the core characteristics of the smoke signal are identified, and a pure residual signal is obtained, which clearly presents the changes of smoke-related signals, providing accurate data support for subsequent signal comparison and alarm judgment.

[0133] This invention employs a sliding window mean filtering method to smooth the signal, a low-pass filtering algorithm to calibrate the baseline, and a difference processing method to obtain the residual signal, thus constructing a complete signal processing flow. This effectively filters out interference noise, calibrates the signal baseline, and extracts effective smoke signals, improving the accuracy and stability of signal processing, ensuring the reliability of subsequent alarm judgments, and providing strong support for accurate fire early warning.

[0134] This embodiment provides a detailed description of the process in the above embodiment of obtaining the real-time background baseline value by dynamically tracking the baseline of a smoothed electrical signal using a low-pass filtering algorithm. The specific implementation of this process includes the following steps:

[0135] Step b1: The smoothed electrical signal of the current sampling period is weighted and fused with the historical background baseline value of the previous sampling period according to a preset forgetting factor.

[0136] Specifically, the preset forgetting factor refers to a weighting coefficient pre-set in the weighted fusion calculation of baseline dynamic processing to balance the real-time performance of the smoothed electrical signal in the current sampling period with the stability of the historical background baseline value in the previous sampling period. Based on the real-time performance of the smoothed electrical signal and the stability of the historical background baseline value, reasonable weights are assigned to both. The fusion of the two is achieved through weighted calculation, preserving the real-time performance of the current smoothed electrical signal while maintaining the stability of the historical background baseline value, thus avoiding the impact of fluctuations in a single data point.

[0137] By combining the advantages of current signals and historical baselines, reliable basic data is provided for subsequent baseline updates, ensuring the continuity and stability of baseline adjustments, achieving a smooth transition between current signals and historical baselines, avoiding abrupt changes in the baseline, ensuring baseline stability, and providing an accurate basis for the generation of subsequent real-time background baseline values.

[0138] Step b2: Update and obtain the real-time background baseline value based on the weighted fusion result.

[0139] Specifically, the real-time background baseline value serves as a reference value for signal comparison. Based on the weighted fusion result, the baseline position is dynamically adjusted to adapt to subtle changes in the electrical signal, maintaining consistency with the signal level under normal smoke-free conditions and ensuring baseline accuracy. This provides a stable and accurate reference for subsequent residual signal calculation, distinguishing between valid and interfering signals. The baseline value adapts to signal changes in real time, avoiding signal misjudgment due to a fixed baseline and ensuring the accuracy of smoke detection.

[0140] This invention achieves accurate generation of real-time background baseline values ​​through weighted fusion signal integration and baseline updates, providing a reliable benchmark for subsequent residual signal calculation. At the same time, it ensures the dynamic adaptability of the baseline, avoids detection deviations caused by fixed baselines, and improves the accuracy and stability of overall signal processing.

[0141] This embodiment provides a detailed description of the process for extracting the fluctuation characteristics of the residual signal based on a preset time window in the above embodiments. The specific implementation of this process includes the following steps:

[0142] Step c1: Obtain multiple sets of residual signal data within a preset time window, and obtain the maximum and minimum values ​​among the multiple sets of residual signal data by comparison.

[0143] Specifically, a time window refers to a fixed time interval set to define the scope of signal analysis and ensure the targetedness and accuracy of signal feature extraction. The analysis interval is defined according to the set time length, and multiple sets of residual signal data within this interval are collected simultaneously. By comparing each set of data one by one, the signal data with the largest value is selected as the maximum value, and the signal data with the smallest value is selected as the minimum value, completing the initial screening of signal extrema. To lock onto residual signal data within a specific time range, extrema screening provides basic data support for subsequent fluctuation feature analysis, ensuring the targeted nature of fluctuation feature extraction. It provides a reliable data basis for accurately obtaining the extrema information of the residual signal within the time window and for subsequent fluctuation feature quantification, avoiding feature extraction bias caused by data ranges that are too wide or too narrow.

[0144] Step c2: Calculate the difference between the maximum and minimum values ​​to obtain the fluctuation characteristic value, and use the fluctuation characteristic value as the fluctuation characteristic of the residual signal.

[0145] Specifically, fluctuation characteristic values ​​are numerical indicators used to quantify the fluctuation amplitude of residual signals. By calculating the difference between the maximum and minimum values, the fluctuation range of the residual signal within a set time window is transformed into a specific quantified value, intuitively reflecting the degree of signal fluctuation. This transforms the fluctuation of the residual signal into a quantifiable indicator, accurately quantifying the fluctuation amplitude of the residual signal, clearly presenting the fluctuation pattern of the signal, and providing referenceable quantitative data for subsequent signal comparison and judgment, thereby improving the accuracy of signal analysis.

[0146] This invention achieves accurate extraction of residual signal fluctuation characteristics by setting a time window to lock the analysis range, extracting the extreme values ​​of the residual signal, and calculating the fluctuation characteristic values. This effectively captures the signal fluctuation pattern, provides reliable support for subsequent signal comparison and judgment, and ensures the accuracy and stability of smoke detection.

[0147] This embodiment provides a detailed description of the process in the above embodiment of comparing the adjusted alarm threshold with the residual signal to generate a fire alarm signal or no alarm signal. The specific implementation of this process includes the following steps:

[0148] Step d1 involves continuously comparing the residual signal with the adjusted alarm threshold to determine whether the duration for which the residual signal exceeds the adjusted alarm threshold is greater than the preset confirmation duration.

[0149] Specifically, the alarm threshold refers to the critical value for judging whether the smoke signal has reached the fire warning standard. By collecting the residual signal value in real time and continuously comparing it with the adjusted alarm threshold, and combining the duration of the signal exceeding the threshold, it is determined whether there is a fire hazard. This ensures the continuity and accuracy of the comparison process and avoids misjudgment due to instantaneous signal fluctuations.

[0150] By capturing abnormal changes in signals, core evidence is provided for subsequent fire assessments. Real-time monitoring of residual signals is achieved, signal anomalies are captured promptly, misjudgments caused by momentary interference are avoided, accurate data support is provided for subsequent alarm signal generation, and the reliability of comparison results is ensured.

[0151] Step d2: If the duration of the residual signal exceeding the adjusted alarm threshold is greater than the preset confirmation duration, a fire alarm signal is generated.

[0152] Specifically, when the residual signal exceeds the adjusted alarm threshold and the duration is longer than the preset confirmation duration, it indicates that the smoke concentration in the air has reached the fire warning standard. At this time, the alarm logic is triggered to generate the corresponding fire alarm signal, transmit the fire warning information, and issue a warning signal in a timely manner to remind relevant personnel to pay attention and take countermeasures. This connects the key processes of signal comparison and alarm output, ensuring that the warning information is transmitted in a timely manner, buying time for fire response, reducing the losses caused by the fire, protecting the safety of people and property, and improving the timeliness and effectiveness of fire warning.

[0153] Step d3: If the duration of the residual signal exceeding the adjusted alarm threshold is less than or equal to the preset confirmation duration, generate a no-alarm signal and update the feature parameters in the preset memory curve library at the preset update rate.

[0154] Specifically, when the duration of the residual signal exceeding the alarm threshold does not reach the preset confirmation duration, it is determined to be a non-fire hazard and an alarm-free signal is generated; at the same time, based on the current signal characteristics, the feature parameters in the preset memory curve library are updated at a fixed rate to achieve dynamic optimization of the curve library.

[0155] To avoid invalid alarms when there is no fire hazard and reduce unnecessary interference, the memory curve library parameters are updated to keep the library synchronized with actual signal states, improving the accuracy of subsequent signal comparisons. Maintaining stable operation of the detection system reduces the probability of invalid alarms, optimizes the adaptability of the memory curve library, and provides more realistic parameter support for subsequent smoke detection and alarm judgment, thereby improving overall detection accuracy.

[0156] Comparison of real-time residual signal with dynamic threshold:

[0157]

[0158] alarm confirmation time The second is used to prevent false alarms due to transient spikes.

[0159] when Further analysis of the morphological characteristics of the smoke curve was conducted:

[0160] rate of increase Smoldering flames rise slowly, while open flames rise rapidly.

[0161] Duration: The length of time that remains above the threshold;

[0162] Fluctuation characteristics: Real fire signals typically rise smoothly, while nuclear radiation noise is chaotic.

[0163] When it is confirmed that there are no abnormalities ( Furthermore, in the absence of nuclear radiation interference, the memory curve is updated at an extremely slow rate to adapt to long-term, slow environmental changes.

[0164]

[0165] Among them, memory update rate .

[0166] This invention achieves accurate identification of smoke signals and reasonable control of alarm output by using signal comparison logic, clarifying alarm signal generation conditions and parameter update mechanisms. It effectively balances detection accuracy and operational stability, ensuring the reliability and timeliness of fire early warning, while also dynamically optimizing the memory curve library to provide more practical support for subsequent detection work.

[0167] In the above embodiments, it should be understood that the processing unit can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0168] The processing unit may also be connected to at least one memory via a bus. The memory may include high-speed memory (Random Access Memory, RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0169] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0170] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0171] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0172] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0173] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0174] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0175] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0177] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0178] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0179] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A smoke detector resistant to nuclear radiation interference, characterized in that, include: Laser detection cavity, physical shielding unit, and processing unit; The physical shielding unit is sleeved on the outside of the laser detection cavity and seals the entire laser detection cavity, while the processing unit is disposed inside the laser detection cavity; The laser detection cavity is equipped with a laser emitter and a photoelectric receiver. The laser emitter and the photoelectric receiver are arranged opposite each other in a scattering manner. The laser emitter and the photoelectric receiver are used to detect smoke particles in the air and output electrical signals to the processing unit. The physical shielding unit is a multi-layer sealed shielding structure used to attenuate nuclear radiation; the physical shielding unit is provided with an air inlet and an air outlet; the air inlet and the air outlet are respectively provided with an air inlet and an air outlet communicating with the laser detection cavity; The processing unit is used to receive and process electrical signals and output fire alarm signals.

2. The smoke detector resistant to nuclear radiation interference according to claim 1, characterized in that, The physical shielding unit includes an inner nuclear radiation shielding layer and an outer mechanical shielding layer. The inner nuclear radiation shielding layer tightly covers the outer surface of the laser detection cavity, and the outer mechanical shielding layer tightly covers the outer surface of the inner nuclear radiation shielding layer. The inner nuclear radiation shielding layer and the outer mechanical shielding layer are sealed together.

3. The smoke detector resistant to nuclear radiation interference according to claim 1, characterized in that, It also includes an output board, which is electrically connected to the processing unit. The output board is equipped with a dry contact signal interface and a signal transmission circuit for fire linkage control. The dry contact signal interface is used to receive the fire alarm signal or no alarm signal output by the processing unit and output the corresponding switch status signal.

4. A smoke detection method, characterized in that, The processing unit applied to the smoke detector resistant to nuclear radiation interference as described in claim 1 includes: The raw electrical signal output from the laser detection cavity is acquired, and the raw electrical signal includes smoke scattering signal, environmental noise and nuclear radiation noise; The original electrical signal is filtered and subjected to baseline dynamic processing to obtain the residual signal; The residual signal is compared with the features in the preset memory curve library to obtain the abnormal deviation index; Extract the target morphological features of the residual signal based on the anomaly deviation index; Based on preset noise determination rules, the target morphological features are identified for nuclear radiation noise and a nuclear radiation interference flag is generated. The fluctuation characteristics of the residual signal are extracted based on a preset time window, and the alarm threshold is dynamically adjusted according to the nuclear radiation interference flag and the fluctuation characteristics. The adjusted alarm threshold is compared with the residual signal to generate a fire alarm signal or no alarm signal.

5. The smoke detection method according to claim 4, characterized in that, The original electrical signal is filtered and subjected to baseline dynamic processing to obtain a residual signal, including: The original electrical signal is smoothed by sliding window mean filtering to obtain a smoothed electrical signal. The smoothed electrical signal is dynamically tracked by a preset low-pass filtering algorithm to obtain the real-time background baseline value. The residual signal is obtained by performing difference processing between the smoothed electrical signal and the real-time background baseline value.

6. The smoke detection method according to claim 5, characterized in that, The real-time background baseline value is obtained by performing baseline dynamic tracking on the smoothed electrical signal using a low-pass filtering algorithm, including: The smoothed electrical signal of the current sampling period is weighted and fused with the historical background baseline value of the previous sampling period according to a preset forgetting factor; The real-time background baseline value is updated and obtained based on the weighted fusion result.

7. The smoke detection method according to claim 4, characterized in that, The fluctuation characteristics of the residual signal are extracted based on a preset time window, including: Acquire multiple sets of residual signal data within the preset time window, and obtain the maximum and minimum values ​​among the multiple sets of residual signal data by comparison; The difference between the maximum value and the minimum value is calculated to obtain the fluctuation characteristic value, and the fluctuation characteristic value is used as the fluctuation characteristic of the residual signal.

8. The smoke detection method according to claim 7, characterized in that, The adjusted alarm threshold is compared with the residual signal to generate a fire alarm signal or no alarm signal, including: The residual signal is continuously compared with the adjusted alarm threshold to determine whether the duration for which the residual signal exceeds the adjusted alarm threshold is greater than the preset confirmation duration. If the duration of the residual signal exceeding the adjusted alarm threshold is greater than the preset confirmation duration, the fire alarm signal is generated. If the duration of the residual signal exceeding the adjusted alarm threshold is less than or equal to the preset confirmation duration, the no-alarm signal is generated, and the feature parameters in the preset memory curve library are updated at a preset update rate.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 4-8.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method as described in any one of claims 4-8.

Images