A weak signal processing method for ultra-low dust meter

Abstract

The present application provides a weak signal processing method for an ultra-low dust monitor. The method obtains a dust monitoring signal set in a space to be detected through an ultra-low dust monitor array, and sends the dust monitoring signal set to a dust monitoring management platform, so that the dust monitoring management platform uses a preset weak signal extraction model and extracts a dust monitoring weak signal from the dust monitoring signal set, and then determines the dust concentration of the space to be detected based on the dust monitoring weak signal and a preset dust concentration calibration curve, thereby effectively improving the sensitivity and accuracy of dust monitoring and realizing effective monitoring of ultra-low dust concentration.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular to a weak signal processing method applied to an ultra-low dust meter. Background Art

[0002] Dust pollution in the air has a serious impact on public health and quality of life. Therefore, monitoring and effective control of dust concentration in the air and emitted into the air has become an important issue in the field of environmental protection.

[0003] Traditional dust monitoring methods mostly use a single monitoring point to collect data. This method works better when the dust concentration is high, but in ultra-low dust concentration environments, it is often difficult to obtain a complete signal because the signal is weak and easily interfered by background noise, and thus accurate and reliable monitoring results cannot be obtained. Summary of the invention

[0004] The present application provides a weak signal processing method applied to an ultra-low dust meter to improve the sensitivity and accuracy of dust monitoring and achieve effective monitoring of ultra-low dust concentration.

[0005] In a first aspect, the present application provides a weak signal processing method applied to an ultra-low dust monitor, which is applied to an environmental dust monitoring system, wherein the environmental dust monitoring system includes a dust monitoring management platform and an ultra-low dust monitor array, wherein each ultra-low dust monitor in the ultra-low dust monitor array is communicatively connected to the dust monitoring management platform; the method includes:

[0006] Obtaining a dust monitoring signal set in the to-be-detected space through the ultra-low dust monitor array, and sending the dust monitoring signal set to the dust monitoring management platform, the to-be-detected space includes an array of to-be-detected grids consisting of a plurality of to-be-detected grids, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively arranged in each to-be-detected grid in the to-be-detected space;

[0007] The dust monitoring management platform uses a preset weak signal extraction model to extract a dust monitoring weak signal from the dust monitoring signal set, wherein the dust monitoring weak signal is a signal whose signal strength is lower than a preset background noise intensity threshold;

[0008] The dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve.

[0009] In the above scheme, the dust monitoring signal set obtained by the ultra-low dust monitor array is transmitted to the dust monitoring management platform in real time, realizing the rapid transmission and real-time processing of data, which not only improves the monitoring efficiency, but also ensures the timeliness and accuracy of the monitoring data. Then, on the dust monitoring management platform side, a weak signal with a signal strength lower than the preset background noise intensity threshold is extracted from the complex monitoring signal set through a preset weak signal extraction model, thereby improving the sensitivity of dust monitoring, so that even in an ultra-low dust concentration environment, effective monitoring signals can be captured, thereby achieving more accurate monitoring of dust concentration. Then, the dust monitoring management platform determines the dust concentration of the space to be detected based on the extracted dust monitoring weak signal and the preset dust concentration calibration curve. Through the calibration curve, an accurate mapping relationship between the monitoring signal and the dust concentration is established, ensuring the accuracy and reliability of the monitoring results. It can be seen that through the above scheme, the sensitivity and accuracy of dust monitoring are effectively improved, and effective monitoring of ultra-low dust concentrations is achieved.

[0010] Optionally, the dust monitoring management platform uses a preset weak signal extraction model to extract a dust monitoring weak signal from the dust monitoring signal set, including:

[0011] The dust monitoring management platform extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set;

[0012] The dust monitoring management platform extracts a candidate feature local signal set within each preset cycle duration from the candidate feature detection signal set according to the preset cycle duration, and the candidate feature local signal set includes the local signal of each candidate feature detection signal in the candidate feature detection signal set within the same preset cycle duration;

[0013] The dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set;

[0014] The dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time.

[0015] In the above scheme, the dust monitoring signal is preliminarily screened by the preset signal frequency range and signal energy range to generate a candidate feature detection signal set, thereby effectively eliminating noise and interference signals and improving the efficiency and accuracy of subsequent processing. Then, the candidate feature local signal set is extracted from the candidate feature detection signal set according to the preset cycle duration, and the continuous monitoring signal is divided into multiple independent local signal segments by dividing the time window, which is convenient for subsequent more refined signal processing and analysis. Then, the feature detection local signal corresponding to the preset cycle duration is generated according to each candidate feature local signal in the candidate feature local signal set, so that the local signal is further processed by a specific algorithm or model to extract a more representative feature signal, which provides a basis for the subsequent generation of dust monitoring weak signals. Finally, the dust monitoring weak signal is generated according to the feature detection local signal within each preset cycle duration, and then the complete dust monitoring weak signal is obtained by integrating the feature detection local signals within multiple cycles, which not only improves the accuracy and stability of signal extraction, but also ensures the accuracy and reliability of the final monitoring results.

[0016] It can be seen that the above scheme realizes efficient extraction of weak signals for dust monitoring, which not only improves the sensitivity and accuracy of dust monitoring, but also enhances the anti-interference ability and stability of the system.

[0017] Optionally, the dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set, including:

[0018] The dust monitoring management platform determines a corresponding candidate feature local signal energy value set according to the candidate feature local signal set;

[0019] The dust monitoring management platform determines the feature detection local signal according to the candidate feature local signal set and the candidate feature local signal energy value set.

[0020] In the above scheme, by calculating the energy values ​​of the candidate feature local signals and generating feature detection local signals based on these energy values, the influence of noise and interference on the signal can be effectively reduced. This method can more accurately reflect the actual characteristics of the dust monitoring signal and provide a more reliable data basis for subsequent signal analysis and dust concentration calculation. In addition, the energy value of each candidate feature local signal represents its intensity and activity in a specific time period. Incorporating these energy values ​​into the generation process of the feature detection local signal can make the final feature detection local signal more distinguishable in both time and energy dimensions, which is important for distinguishing dust monitoring signals of different sources and different intensities. In addition, by using the candidate feature local signals and their energy value sets to generate feature detection local signals, unnecessary comprehensive analysis of the original signal can be avoided, thereby improving the efficiency of signal extraction, reducing the consumption of computing resources, and enabling the dust monitoring management platform to respond and process monitoring data faster. In addition, since the process adopts an energy-based signal processing method, it can better cope with adverse factors such as signal fluctuations and noise interference.

[0021] Optionally, the dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time, including:

[0022] The dust monitoring management platform generates a characteristic detection local signal set according to the characteristic detection local signals within each preset cycle duration;

[0023] The dust monitoring management platform sequentially splices each characteristic detection local signal in the characteristic detection local signal set according to the timing of each preset cycle duration to form the dust monitoring weak signal.

[0024] In the above scheme, a continuous dust monitoring weak signal is formed by splicing the characteristic detection local signals within each preset cycle duration in time sequence. This process ensures the continuity and integrity of the signal, avoids signal breakage or information loss caused by time division, and thus improves the accuracy and reliability of the monitoring results. In addition, since the characteristic detection local signals within each preset cycle duration have been processed and screened, the spliced ​​dust monitoring weak signal has higher stability as a whole. This stability helps to reduce errors caused by signal fluctuations or noise interference, and improves the anti-interference ability and robustness of the monitoring system. In addition, the process decomposes the complex signal processing task into multiple simple subtasks (i.e., the generation of characteristic detection local signals within each preset cycle duration), and integrates the results of these subtasks by splicing. This modular, step-by-step data processing process not only simplifies the operation, but also improves the efficiency and flexibility of data processing. Then, by comprehensively considering the characteristic detection local signals within multiple preset cycle durations, the spliced ​​dust monitoring weak signal can more comprehensively reflect the dust condition in the space to be detected. This comprehensive way of obtaining information helps to improve the accuracy and sensitivity of the monitoring system, making the monitoring results closer to the actual situation.

[0025] Optionally, the dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve, and further includes:

[0026] The dust monitoring management platform determines the characteristic mean of the dust monitoring signal according to the dust monitoring weak signal;

[0027] The dust monitoring management platform determines the dust concentration of the space to be detected according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, wherein the preset dust concentration calibration curve is used to establish a mapping relationship between the characteristic value of the monitoring signal and the dust concentration.

[0028] In the above scheme, by calculating the characteristic mean of the weak signal of dust monitoring and comparing it with the preset dust concentration calibration curve, the dust concentration of the space to be detected can be accurately mapped. This monitoring method based on mathematical models reduces the interference of human factors and improves the accuracy and objectivity of the monitoring results. In addition, the preset dust concentration calibration curve can be derived based on a large amount of experimental data and experience summary, which can effectively reflect the complex relationship between the characteristic value of the monitoring signal and the dust concentration. As environmental conditions change, the system can adapt to new monitoring needs by adjusting or updating the calibration curve, thereby enhancing the adaptability and flexibility of the system. By simplifying the complex dust concentration monitoring process into two steps of signal processing and mathematical calculation, the operation process is greatly simplified, so that the dust monitoring management platform can quickly respond to and process monitoring data, which helps to improve the real-time and dynamic monitoring capabilities of the system, making the monitoring results more timely and reliable.

[0029] Optionally, before the dust monitoring management platform determines the dust concentration of the to-be-detected space according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, it further includes:

[0030] If the dust monitoring management platform determines that the characteristic mean value of the dust monitoring signal exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, a monitoring update indication is sent to the ultra-low dust monitor array so that the ultra-low dust monitor array re-acquires the dust monitoring update signal set in the space to be detected, and sends the dust monitoring update signal set to the dust monitoring management platform.

[0031] In the above scheme, by judging whether the characteristic mean of the dust monitoring signal exceeds the value range of the characteristic value of the monitoring signal in the preset dust concentration calibration curve, the system can promptly discover and identify abnormal or unreliable monitoring data, which helps to avoid using erroneous or invalid data for the calculation of dust concentration, thereby improving the reliability and accuracy of the monitoring data. When the monitoring data is abnormal, the system can automatically trigger the update mechanism and send a monitoring update instruction to the ultra-low dust monitor array, so that the system can respond quickly and adjust the monitoring strategy to re-acquire the updated monitoring signal set. It can be seen that this automated feedback and adjustment process enhances the robustness and self-healing capabilities of the system, ensuring the continuous and stable operation of the monitoring system.

[0032] Optionally, before the dust monitoring management platform extracts the candidate feature local signal sets within each preset period from the candidate feature detection signal set according to the preset period, the method further includes:

[0033] The dust monitoring management platform determines that a proportion of dust monitoring signals in the dust monitoring signal set that include the candidate feature detection signals is greater than a preset proportion threshold.

[0034] In the above scheme, by setting the ratio threshold, the system can pre-evaluate the proportion of valid signals in the dust monitoring signal set. Only when the proportion of valid signals reaches a certain level, the subsequent signal extraction and processing are carried out. This avoids wasting computing resources on unnecessary low-quality signals and improves the efficiency of the entire signal processing. Among them, the setting of the ratio threshold can be regarded as a preliminary screening mechanism for signal quality. Only when the signal set contains a sufficient number of valid candidate feature detection signals, these signals are considered to be able to reflect the real dust condition of the space to be detected, which helps to reduce the monitoring error caused by poor signal quality and improve the accuracy of data processing. In addition, system resources are limited, especially when processing large amounts of data and complex signals. By pre-judging the proportion of valid signals in the signal set, the system can allocate resources more reasonably and give priority to high-quality signal sets. This helps to optimize the utilization efficiency of system resources and improve the overall performance of the system. In addition, in actual applications, due to environmental factors or equipment failures, dust monitoring signals may be interfered with or damaged. By setting the ratio threshold and performing preliminary screening, the system can promptly detect and eliminate these abnormal signals to avoid adverse effects on subsequent processing processes, while also enhancing the robustness and stability of the system.

[0035] In a second aspect, the present application provides an environmental dust monitoring system, comprising: a dust monitoring management platform and an ultra-low dust monitor array, wherein each ultra-low dust monitor in the ultra-low dust monitor array is communicatively connected to the dust monitoring management platform;

[0036] Obtaining a dust monitoring signal set in the to-be-detected space through the ultra-low dust monitor array, and sending the dust monitoring signal set to the dust monitoring management platform, the to-be-detected space includes an array of to-be-detected grids consisting of a plurality of to-be-detected grids, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively arranged in each to-be-detected grid in the to-be-detected space;

[0037] The dust monitoring management platform uses a preset weak signal extraction model to extract a dust monitoring weak signal set from the dust monitoring signal set, wherein the weak signal extracted by the preset weak signal extraction model is a signal whose signal strength is lower than a preset background noise intensity threshold;

[0038] The dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal set and a preset dust concentration calibration curve.

[0039] Optionally, the dust monitoring management platform uses a preset weak signal extraction model to extract a dust monitoring weak signal from the dust monitoring signal set, including:

[0040] The dust monitoring management platform extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set;

[0041] The dust monitoring management platform extracts a candidate feature local signal set within each preset cycle duration from the candidate feature detection signal set according to the preset cycle duration, and the candidate feature local signal set includes the local signal of each candidate feature detection signal in the candidate feature detection signal set within the same preset cycle duration;

[0042] The dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set;

[0043] The dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time.

[0044] Optionally, the dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set, including:

[0045] The dust monitoring management platform determines a corresponding candidate feature local signal energy value set according to the candidate feature local signal set;

[0046] The dust monitoring management platform determines the feature detection local signal according to the candidate feature local signal set and the candidate feature local signal energy value set.

[0047] Optionally, the dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time, including:

[0048] The dust monitoring management platform generates a characteristic detection local signal set according to the characteristic detection local signals within each preset cycle duration;

[0049] The dust monitoring management platform sequentially splices each characteristic detection local signal in the characteristic detection local signal set according to the timing of each preset cycle duration to form the dust monitoring weak signal.

[0050] Optionally, the dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve, and further includes:

[0051] The dust monitoring management platform determines the characteristic mean of the dust monitoring signal according to the dust monitoring weak signal;

[0052] The dust monitoring management platform determines the dust concentration of the space to be detected according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, wherein the preset dust concentration calibration curve is used to establish a mapping relationship between the characteristic value of the monitoring signal and the dust concentration.

[0053] Optionally, before the dust monitoring management platform determines the dust concentration of the to-be-detected space according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, it further includes:

[0054] If the dust monitoring management platform determines that the characteristic mean value of the dust monitoring signal exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, a monitoring update indication is sent to the ultra-low dust monitor array so that the ultra-low dust monitor array re-acquires the dust monitoring update signal set in the space to be detected, and sends the dust monitoring update signal set to the dust monitoring management platform.

[0055] Optionally, before the dust monitoring management platform extracts the candidate feature local signal sets within each preset period from the candidate feature detection signal set according to the preset period, the method further includes:

[0056] The dust monitoring management platform determines that a proportion of dust monitoring signals in the dust monitoring signal set that include the candidate feature detection signals is greater than a preset proportion threshold.

[0057] In a third aspect, the present application provides an electronic device, including:

[0058] processor; and,

[0059] A memory, configured to store executable instructions of the processor;

[0060] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0061] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0062] The weak signal processing method for an ultra-low dust monitor provided in the present application obtains a dust monitoring signal set in a space to be detected through an ultra-low dust monitor array, and sends the dust monitoring signal set to a dust monitoring management platform, so that the dust monitoring management platform uses a preset weak signal extraction model and extracts the dust monitoring weak signal from the dust monitoring signal set, and then determines the dust concentration of the space to be detected based on the dust monitoring weak signal and a preset dust concentration calibration curve, thereby effectively improving the sensitivity and accuracy of dust monitoring and realizing effective monitoring of ultra-low dust concentrations. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0064] Figure 1 This is a flowchart of a weak signal processing method applied to an ultra-low dust meter according to an exemplary embodiment of the present application;

[0065] Figure 2 is a flow chart of a weak signal processing method applied to an ultra-low dust meter according to another exemplary embodiment of the present application;

[0066] Figure 3 is a structural schematic diagram of an environmental dust monitoring system according to an exemplary embodiment of the present application;

[0067] Figure 4 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application.

[0068] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0069] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0070] In order to solve the above problems, the embodiments provided in this application aim to improve the sensitivity and accuracy of the environmental dust monitoring system and realize effective monitoring of ultra-low dust concentration. Specifically, the specific inventive concept of the embodiments provided in this application is embodied as follows:

[0071] System architecture design: The embodiment provided in this application designs an environmental dust monitoring system, which is composed of a dust monitoring management platform and an ultra-low dust monitor array. Each ultra-low dust monitor in the ultra-low dust monitor array is set in each grid to be detected in the space to be detected, and is connected to the dust monitoring management platform to form a complete monitoring network.

[0072] Weak signal collection and transmission: The ultra-low dust monitor array is responsible for real-time collection of dust monitoring signals in the space to be detected, and transmits these signals to the dust monitoring management platform in real time. This step ensures the timeliness and integrity of the monitoring data, laying the foundation for subsequent signal processing.

[0073] Weak signal extraction: The dust monitoring management platform uses a preset weak signal extraction model to extract weak signals with signal strength lower than the preset background noise intensity threshold from the received dust monitoring signal set. This step improves the sensitivity of dust monitoring by eliminating noise and interference signals, allowing the system to capture effective monitoring signals even in ultra-low dust concentration environments.

[0074] Characteristic signal analysis and processing: After extracting weak signals, the management platform further analyzes and processes these signals. First, candidate characteristic detection signals are screened out according to the preset signal frequency range and energy range, and divided into multiple candidate characteristic local signal sets according to the preset cycle length. Then, based on the energy values ​​and other information of these local signals, characteristic detection local signals within the corresponding period are generated. Finally, these characteristic detection local signals are spliced ​​into a complete dust monitoring weak signal. This step further improves the signal quality and analysis accuracy through sophisticated signal processing algorithms.

[0075] Dust concentration calculation and calibration: The management platform calculates the dust concentration of the space to be detected based on the extracted weak dust monitoring signal and the preset dust concentration calibration curve. The calibration curve establishes an accurate mapping relationship between the characteristic value of the monitoring signal and the dust concentration, ensuring the reliability and accuracy of the monitoring results.

[0076] Abnormal monitoring and data update: Before calculating the dust concentration, the management platform will also judge the characteristic mean of the dust monitoring signal. If the characteristic mean exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, the management platform will automatically trigger the update mechanism and send a monitoring update instruction to the ultra-low dust monitor array to re-acquire and process the updated monitoring signal set. This step enhances the robustness and self-healing ability of the system.

[0077] Resource optimization and efficiency improvement: During the entire signal processing process, the management platform preliminarily screens the dust monitoring signal set by setting a ratio threshold and other mechanisms, avoiding wasting computing resources on low-quality signals. This step optimizes the allocation of system resources and improves the efficiency and accuracy of signal processing.

[0078] In summary, the inventive concept of the embodiments provided in this application is to achieve efficient and accurate monitoring of environmental dust concentration through a systematic and automated weak signal processing method. This method not only improves the sensitivity and accuracy of dust monitoring, but also enhances the robustness and stability of the system, providing strong technical support for environmental protection and public health.

[0079] Figure 1 FIG. 1 is a flow chart of a weak signal processing method for an ultra-low dust monitor according to an exemplary embodiment of the present application. Figure 1 As shown, the weak signal processing method applied to the ultra-low dust meter provided in this embodiment includes:

[0080] S101. Obtain a dust monitoring signal set in a space to be detected through an ultra-low dust monitor array, and send the dust monitoring signal set to a dust monitoring management platform.

[0081] The weak signal processing method provided in this embodiment can be applied to an environmental dust monitoring system, which includes a dust monitoring management platform and an ultra-low dust monitor array, and each ultra-low dust monitor in the ultra-low dust monitor array is communicatively connected to the dust monitoring management platform. The system is mainly composed of a dust monitoring management platform and an ultra-low dust monitor array. The ultra-low dust monitor array consists of a plurality of ultra-low dust monitors, which are evenly distributed in each grid to be detected in the space to be detected to form a dense monitoring network. Each ultra-low dust monitor is communicated with the dust monitoring management platform by wireless or wired means to ensure that the monitoring data can be transmitted in real time.

[0082] In this step, the dust monitoring signal set in the space to be detected can be obtained through the ultra-low dust monitor array, and the dust monitoring signal set can be sent to the dust monitoring management platform. The space to be detected includes a grid array to be detected composed of multiple grids to be detected, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively set in each grid to be detected in the space to be detected.

[0083] Specifically, the ultra-low dust monitor array is responsible for continuously monitoring the dust concentration in its respective grid, and collecting the monitored dust signals (including concentration, particle size and other information) in the form of electrical signals. These signals are converted into digital signals by an analog-to-digital converter and transmitted to the dust monitoring management platform in real time through a communication interface. After receiving these signals, the management platform integrates them into a dust monitoring signal set for subsequent processing. In actual applications, the space to be detected can be a large space, such as a park, scenic spot, etc., or a small space, such as a chimney, flue and other spaces.

[0084] S102. The dust monitoring management platform uses a preset weak signal extraction model to extract a dust monitoring weak signal from a dust monitoring signal set.

[0085] In this step, the dust monitoring management platform uses a preset weak signal extraction model to extract dust monitoring weak signals from the dust monitoring signal set, wherein the dust monitoring weak signal is a signal whose signal strength is lower than a preset background noise intensity threshold.

[0086] Specifically, after the management platform receives the dust monitoring signal set, it uses the preset weak signal extraction model to process the signal. The model first screens the signal set according to the preset background noise intensity threshold, and excludes those non-weak signals whose signal strength is higher than the threshold. Then, the remaining signals are further processed by complex algorithms (such as wavelet transform, empirical mode decomposition, etc.) to extract weak signals whose signal strength is lower than the background noise intensity threshold. Although these weak signals are difficult to observe directly, they often contain key information about ultra-low dust concentrations.

[0087] S103. The dust monitoring management platform determines the dust concentration of the space to be detected according to the weak dust monitoring signal and a preset dust concentration calibration curve.

[0088] In this step, the dust monitoring management platform determines the dust concentration of the space to be detected based on the dust monitoring weak signal and the preset dust concentration calibration curve.

[0089] Specifically, after extracting the weak signal, the management platform calculates the dust concentration of the space to be detected in combination with the preset dust concentration calibration curve. The calibration curve is obtained by fitting a large amount of experimental data, which establishes the mapping relationship between the characteristic values ​​of the monitoring signal (such as signal strength, frequency distribution, etc.) and the dust concentration. The management platform converts the extracted weak signal into the corresponding characteristic values, and then maps these characteristic values ​​into dust concentration values ​​according to the calibration curve. In this way, accurate monitoring of ultra-low dust concentration can be achieved.

[0090] In actual applications, in order to ensure the accuracy and reliability of monitoring results, the management platform will also perform anomaly detection on the monitoring data. If it is found that the monitored signal characteristic value deviates significantly from the normal range of the calibration curve, the management platform will consider that the current data is abnormal and trigger the data update mechanism. At this time, the management platform will send a monitoring update instruction to the ultra-low dust monitor array, requiring the re-collection and transmission of monitoring data. In this way, potential monitoring errors can be discovered and corrected in a timely manner, improving the stability and reliability of the monitoring system.

[0091] In addition, when designing the system, issues such as resource optimization and efficiency improvement can also be considered. For example, by evenly distributing ultra-low dust monitors in the grid to be detected, the comprehensiveness and representativeness of the monitoring data can be ensured; at the same time, through the preset signal processing model and calibration curve, unnecessary computing overhead and storage requirements can be reduced. In addition, the management platform can also adjust the monitoring frequency and data transmission volume according to actual needs to balance the relationship between monitoring accuracy and system load. With the combined effect of these measures, the entire monitoring system can achieve efficient dust concentration monitoring tasks with lower resource consumption.

[0092] In this embodiment, a dust monitoring signal set in the space to be detected is obtained through an ultra-low dust monitor array, and the dust monitoring signal set is sent to a dust monitoring management platform, so that the dust monitoring management platform uses a preset weak signal extraction model to extract the dust monitoring weak signal from the dust monitoring signal set, and then determines the dust concentration of the space to be detected based on the dust monitoring weak signal and a preset dust concentration calibration curve, thereby effectively improving the sensitivity and accuracy of dust monitoring and realizing effective monitoring of ultra-low dust concentration.

[0093] Figure 2 FIG. 1 is a flow chart of a weak signal processing method applied to an ultra-low dust monitor according to another exemplary embodiment of the present application. Figure 2 As shown, the weak signal processing method applied to the ultra-low dust meter provided in this embodiment includes:

[0094] S201. Obtain a dust monitoring signal set in the space to be detected through an ultra-low dust monitor array, and send the dust monitoring signal set to a dust monitoring management platform.

[0095] In this step, the dust monitoring signal set in the space to be detected can be obtained through the ultra-low dust monitor array, and the dust monitoring signal set can be sent to the dust monitoring management platform. The space to be detected includes a grid array to be detected composed of multiple grids to be detected, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively set in each grid to be detected in the space to be detected.

[0096] Specifically, the ultra-low dust monitor array is responsible for continuously monitoring the dust concentration in its respective grid, and collecting the monitored dust signals (including concentration, particle size and other information) in the form of electrical signals. These signals are converted into digital signals by analog-to-digital converters and transmitted to the dust monitoring management platform in real time through the communication interface. After receiving these signals, the management platform integrates them into a dust monitoring signal set for subsequent processing.

[0097] S202. The dust monitoring management platform extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set.

[0098] Specifically, after receiving the dust monitoring signal set, the dust monitoring management platform first preliminarily screens the signal according to the preset signal frequency range and signal energy range. These preset ranges are determined based on the characteristics of the dust monitoring signal and are intended to eliminate noise and other non-dust related signal interference. The management platform traverses the entire signal set and checks the frequency and energy of each signal. If the frequency and energy of the signal meet the preset frequency range and energy range at the same time, it will be marked as a candidate feature detection signal and added to the candidate feature detection signal set.

[0099] S203. The dust monitoring management platform extracts a candidate feature local signal set within each preset cycle duration from the candidate feature detection signal set according to the preset cycle duration.

[0100] In this step, the dust monitoring management platform extracts a set of candidate feature local signals within each preset cycle length from the candidate feature detection signal set according to the preset cycle length. The candidate feature local signal set includes the local signals of each candidate feature detection signal in the candidate feature detection signal set within the same preset cycle length.

[0101] Specifically, the management platform further processes the candidate feature detection signal set according to the preset cycle duration. This preset cycle duration is set according to the time characteristics of the dust concentration change to ensure that the dynamic changes in dust concentration can be captured within each cycle. The management platform divides each signal in the candidate feature detection signal set according to the preset cycle duration to generate a candidate feature local signal set within each cycle. Each candidate feature local signal set contains local fragments of all candidate feature detection signals within the cycle.

[0102] S204. The dust monitoring management platform generates a feature detection local signal corresponding to a preset cycle duration according to each candidate feature local signal in the candidate feature local signal set.

[0103] Specifically, the management platform performs fine processing on the candidate feature local signal set within each preset cycle to generate the corresponding feature detection local signal. This step may involve a variety of signal processing technologies, such as Fourier transform, wavelet transform, etc., to extract key features from the signal. The management platform uses a specific algorithm model to generate a feature detection local signal with a higher signal-to-noise ratio and representativeness based on the waveform, frequency distribution, energy change and other characteristics of the candidate feature local signal.

[0104] In a possible implementation, the dust monitoring management platform collects candidate feature local signals Determine the corresponding candidate feature local signal energy value set ,in, is the set of candidate feature local signals The candidate feature local signals, is the set of candidate feature local signals The Candidate feature local signals The corresponding candidate feature local signal energy value, is the set of candidate feature local signals The number of candidate feature local signals in ;

[0105] The dust monitoring management platform uses formula 1 and sets the candidate feature local signal And the candidate feature local signal energy value set Determine feature detection local signal , Formula 1 is:

[0106]

[0107] in, Detect local signals for features.

[0108] In the above scheme, by calculating the energy value of each candidate feature local signal, the strength and activity of the signal in different time windows can be quantified, thereby more accurately reflecting the actual characteristics of the dust monitoring signal. These energy values ​​are used for weighted processing, so that the higher energy part of the signal is more reflected in the final feature detection local signal, which improves the representativeness and accuracy of the signal.

[0109] Moreover, by calculating the energy value and weighting the signal, the influence of noise and interference on the signal is effectively reduced. The noise signal with low energy value is relatively weakened in the weighting process, while the dust monitoring signal with high energy value is enhanced, thereby improving the signal-to-noise ratio of signal processing and enhancing the anti-interference ability of the system.

[0110] In addition, by calculating the energy value of the candidate feature local signal and performing weighted processing, the comprehensive and indiscriminate analysis of the original signal is avoided, and unnecessary calculations are reduced, so that the key feature signal can be extracted more quickly, the efficiency of signal processing is improved, and the consumption of computing resources is reduced. Moreover, the feature detection local signal after weighted processing more accurately represents the change of dust concentration in the space to be detected. This processing method makes the monitoring results more reliable, reduces the errors caused by noise and interference, and improves the overall performance of the dust monitoring system.

[0111] Moreover, in actual applications, the dust monitoring environment is often complex and changeable, with many noise and interference factors. By using energy values ​​for weighted processing, the system can better adapt to these complex environments and accurately extract weak dust monitoring signals even in high noise levels, ensuring the accuracy of monitoring results.

[0112] In another possible implementation, the dust monitoring management platform collects candidate feature local signals Determine the corresponding candidate feature local signal energy value set ,in, is the set of candidate feature local signals The candidate feature local signals, is the set of candidate feature local signals The Candidate feature local signals The corresponding candidate feature local signal energy value, is the set of candidate feature local signals The number of candidate feature local signals in ;

[0113] The dust monitoring management platform uses formula 2 and sets the local signal energy values ​​of the candidate features. Determine the first energy feature threshold And the second energy feature threshold , Formula 2 is:

[0114]

[0115] The dust monitoring management platform is based on the first energy characteristic threshold And the second energy feature threshold Determine the energy characteristic value range;

[0116] The dust monitoring management platform is based on the energy characteristic value range and candidate characteristic local signal set Determine the local signal set of target candidate features , where the target candidate feature local signal set The Local signal of target candidate features The corresponding signal energy value is within the energy characteristic value range. ;

[0117] The dust monitoring management platform collects local signals based on target candidate features And the candidate feature local signal energy value set Determine the local signal energy value set of target candidate features

[0118] The dust monitoring management platform uses formula 3 and sets local signals based on the target candidate features And the target candidate feature local signal energy value set Determine feature detection local signal , Formula 3 is:

[0119]

[0120] in, Detect local signals for features.

[0121] It is worth noting that by calculating the energy value of each candidate feature local signal and setting the first energy feature threshold and the second energy feature threshold according to these energy values, the system can screen out signals whose energy values ​​are within a reasonable range and exclude those abnormal signals whose energy is too low or too high. These abnormal signals may be generated by noise or other interference sources. Through the screening process, the accuracy of signal extraction is effectively improved. By setting the energy feature threshold, the system can automatically adapt to different monitoring environments and signal characteristics, reducing monitoring errors caused by environmental changes or equipment differences. This method improves the stability and reliability of the system under different conditions and enhances the robustness of the system. In addition, in the candidate feature local signal set, the target candidate feature local signal is screened out by the energy threshold, reducing the amount of data for subsequent processing. This not only speeds up the signal processing speed, but also reduces the consumption of computing resources and improves the processing efficiency of the system.

[0122] Then, by weighting the target candidate feature local signals, the feature detection local signals are generated. This process takes into account the energy characteristics of the signal, so that the final generated feature detection local signals more realistically reflect the actual situation of the dust monitoring signal. This method reduces the impact of noise and interference on the monitoring results and improves the accuracy of the monitoring results.

[0123] In practical applications, the monitoring environment may contain a variety of complex factors, such as background noise, multipath effects, etc. Through energy threshold screening and weighted processing methods, the system can better adapt to these complex environments, extract more reliable and accurate dust monitoring signals, and meet the needs of different monitoring scenarios.

[0124] S205. The dust monitoring management platform generates a dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time.

[0125] Specifically, the management platform splices the characteristic detection local signals within each preset cycle duration to form a continuous dust monitoring weak signal. This step ensures the continuity and integrity of the signal and avoids signal breakage or information loss due to time division. The management platform splices the characteristic detection local signals within each cycle in sequence according to the time sequence of the preset cycle duration to obtain the final dust monitoring weak signal. This signal contains detailed information on the changes in dust concentration in the space to be detected, providing a reliable data basis for subsequent dust concentration calculations.

[0126] In a possible implementation, the dust monitoring management platform generates a characteristic detection local signal set according to the characteristic detection local signals within each preset period. ,in, Local signal set for feature detection Middle The characteristic detection local signal corresponding to the preset cycle length, is the number of preset cycle durations;

[0127] The dust monitoring management platform detects local signal sets based on the timing of each preset cycle length. The local signals of each characteristic detection are spliced ​​in turn to form a weak signal for dust monitoring.

[0128] S206. The dust monitoring management platform determines the dust concentration of the space to be detected according to the weak dust monitoring signal and a preset dust concentration calibration curve.

[0129] In this step, the dust monitoring management platform determines the dust concentration of the space to be detected based on the dust monitoring weak signal and the preset dust concentration calibration curve.

[0130] Specifically, after extracting the weak signal, the management platform calculates the dust concentration of the space to be detected in combination with the preset dust concentration calibration curve. The calibration curve is obtained by fitting a large amount of experimental data, which establishes the mapping relationship between the characteristic values ​​of the monitoring signal (such as signal strength, frequency distribution, etc.) and the dust concentration. The management platform converts the extracted weak signal into the corresponding characteristic values, and then maps these characteristic values ​​into dust concentration values ​​according to the calibration curve. In this way, accurate monitoring of ultra-low dust concentration can be achieved.

[0131] In a possible implementation, the dust monitoring management platform determines the characteristic mean of the dust monitoring signal based on the weak dust monitoring signal;

[0132] The dust monitoring management platform determines the dust concentration of the space to be detected based on the characteristic mean of the dust monitoring signal and a preset dust concentration calibration curve, wherein the preset dust concentration calibration curve is used to establish a mapping relationship between the characteristic value of the monitoring signal and the dust concentration.

[0133] On the basis of the above embodiment, before the dust monitoring management platform determines the dust concentration of the space to be detected according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, it also includes:

[0134] If the dust monitoring management platform determines that the characteristic mean value of the dust monitoring signal exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, a monitoring update indication is sent to the ultra-low dust monitor array so that the ultra-low dust monitor array can re-acquire the dust monitoring update signal set in the space to be detected, and send the dust monitoring update signal set to the dust monitoring management platform.

[0135] In the above scheme, by judging whether the characteristic mean of the dust monitoring signal exceeds the value range of the characteristic value of the monitoring signal in the preset dust concentration calibration curve, the system can promptly discover and identify abnormal or unreliable monitoring data, which helps to avoid using erroneous or invalid data for the calculation of dust concentration, thereby improving the reliability and accuracy of the monitoring data. When the monitoring data is abnormal, the system can automatically trigger the update mechanism and send a monitoring update instruction to the ultra-low dust monitor array, so that the system can respond quickly and adjust the monitoring strategy to re-acquire the updated monitoring signal set. It can be seen that this automated feedback and adjustment process enhances the robustness and self-healing capabilities of the system, ensuring the continuous and stable operation of the monitoring system.

[0136] Furthermore, before the dust monitoring management platform extracts the candidate feature local signal sets within each preset cycle duration from the candidate feature detection signal set according to the preset cycle duration, it also includes:

[0137] The dust monitoring management platform determines that the proportion of dust monitoring signals having candidate feature detection signals in the dust monitoring signal set is greater than a preset proportion threshold.

[0138] In the above scheme, by setting the ratio threshold, the system can pre-evaluate the proportion of valid signals in the dust monitoring signal set. Only when the proportion of valid signals reaches a certain level, the subsequent signal extraction and processing are carried out. This avoids wasting computing resources on unnecessary low-quality signals and improves the efficiency of the entire signal processing. Among them, the setting of the ratio threshold can be regarded as a preliminary screening mechanism for signal quality. Only when the signal set contains a sufficient number of valid candidate feature detection signals, these signals are considered to be able to reflect the real dust condition of the space to be detected, which helps to reduce the monitoring error caused by poor signal quality and improve the accuracy of data processing. In addition, system resources are limited, especially when processing large amounts of data and complex signals. By pre-judging the proportion of valid signals in the signal set, the system can allocate resources more reasonably and give priority to high-quality signal sets. This helps to optimize the utilization efficiency of system resources and improve the overall performance of the system. In addition, in actual applications, due to environmental factors or equipment failures, dust monitoring signals may be interfered with or damaged. By setting the ratio threshold and performing preliminary screening, the system can promptly detect and eliminate these abnormal signals to avoid adverse effects on subsequent processing processes, while also enhancing the robustness and stability of the system.

[0139] Figure 3 FIG. 1 is a schematic diagram of the structure of an environmental dust monitoring system according to an exemplary embodiment of the present application. Figure 3 As shown, the environmental dust monitoring system 300 provided in this embodiment includes: a dust monitoring management platform 310 and an ultra-low dust monitor array 320, each ultra-low dust monitor in the ultra-low dust monitor array 320 is communicatively connected with the dust monitoring management platform 310;

[0140] The dust monitoring signal set in the to-be-detected space is obtained through the ultra-low dust monitor array 320, and the dust monitoring signal set is sent to the dust monitoring management platform 310, wherein the to-be-detected space includes an array of to-be-detected grids composed of a plurality of to-be-detected grids, and each ultra-low dust monitor in the ultra-low dust monitor array 320 is respectively arranged in each to-be-detected grid in the to-be-detected space;

[0141] The dust monitoring management platform 310 uses a preset weak signal extraction model to extract a dust monitoring weak signal set from the dust monitoring signal set, wherein the weak signal extracted by the preset weak signal extraction model is a signal whose signal strength is lower than a preset background noise intensity threshold;

[0142] The dust monitoring management platform 310 determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal set and a preset dust concentration calibration curve.

[0143] Optionally, the dust monitoring management platform 310 uses a preset weak signal extraction model to extract a dust monitoring weak signal from the dust monitoring signal set, including:

[0144] The dust monitoring management platform 310 extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set;

[0145] The dust monitoring management platform 310 extracts a candidate feature local signal set within each preset cycle duration from the candidate feature detection signal set according to the preset cycle duration, and the candidate feature local signal set includes the local signal of each candidate feature detection signal in the candidate feature detection signal set within the same preset cycle duration;

[0146] The dust monitoring management platform 310 generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set;

[0147] The dust monitoring management platform 310 generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time.

[0148] Optionally, the dust monitoring management platform 310 generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set, including:

[0149] The dust monitoring management platform 310 determines a corresponding candidate feature local signal energy value set according to the candidate feature local signal set;

[0150] The dust monitoring management platform 310 determines the feature detection local signal according to the candidate feature local signal set and the candidate feature local signal energy value set.

[0151] Optionally, the dust monitoring management platform 310 generates the dust monitoring weak signal according to the characteristic detection local signal within each preset period, including:

[0152] The dust monitoring management platform 310 generates a characteristic detection local signal set according to the characteristic detection local signals within each preset period;

[0153] The dust monitoring management platform 310 sequentially splices each characteristic detection local signal in the characteristic detection local signal set according to the timing of each preset cycle duration to form the dust monitoring weak signal.

[0154] Optionally, the dust monitoring management platform 310 determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve, and further includes:

[0155] The dust monitoring management platform 310 determines the characteristic mean of the dust monitoring signal according to the dust monitoring weak signal;

[0156] The dust monitoring management platform 310 determines the dust concentration of the space to be detected according to the characteristic mean of the dust monitoring signal and the preset dust concentration calibration curve, wherein the preset dust concentration calibration curve is used to establish a mapping relationship between the characteristic value of the monitoring signal and the dust concentration.

[0157] Optionally, before the dust monitoring management platform 310 determines the dust concentration of the to-be-detected space according to the characteristic mean of the dust monitoring signal and the preset dust concentration calibration curve, it further includes:

[0158] If the dust monitoring management platform 310 determines that the characteristic mean value of the dust monitoring signal exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, a monitoring update indication is sent to the ultra-low dust monitor array 320 so that the ultra-low dust monitor array 320 re-acquires the dust monitoring update signal set in the space to be detected, and sends the dust monitoring update signal set to the dust monitoring management platform 310.

[0159] Optionally, before the dust monitoring management platform 310 extracts the candidate feature local signal sets within each preset period from the candidate feature detection signal set according to the preset period, it also includes:

[0160] The dust monitoring management platform 310 determines that the proportion of dust monitoring signals including the candidate feature detection signals in the dust monitoring signal set is greater than a preset proportion threshold.

[0161] Figure 4 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, an electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein:

[0162] The memory 402 is used to store computer programs, and the memory may also be a flash memory.

[0163] The processor 401 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0164] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0165] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:

[0166] The bus 403 is used to connect the memory 402 and the processor 401 .

[0167] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0168] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0169] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0170] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A weak signal processing method applied to ultra-low dust monitor, characterized in that: Applied to an environmental dust monitoring system, the environmental dust monitoring system includes a dust monitoring management platform and an ultra-low dust monitor array, each ultra-low dust monitor in the ultra-low dust monitor array is communicatively connected to the dust monitoring management platform; the method includes: The dust monitoring signal set in the to-be-detected space is obtained through the ultra-low dust monitor array, and the dust monitoring signal set is sent to the dust monitoring management platform, the to-be-detected space includes a to-be-detected grid array composed of a plurality of to-be-detected grids, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively arranged in each to-be-detected grid in the to-be-detected space, and the ultra-low dust monitor array collects the monitored dust signals in the form of electrical signals; The dust monitoring management platform extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set; The dust monitoring management platform extracts a candidate feature local signal set within each preset cycle length from the candidate feature detection signal set according to the preset cycle length; The dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set; The dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle duration, wherein the dust monitoring weak signal is a signal whose signal strength is lower than a preset background noise intensity threshold; The dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve.

2. The weak signal processing method applied to the ultra-low dust meter according to claim 1 is characterized in that: The candidate feature local signal set includes local signals of each candidate feature detection signal in the candidate feature detection signal set within the same preset period duration.

3. The weak signal processing method applied to the ultra-low dust meter according to claim 2 is characterized in that: The dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set, including: The dust monitoring management platform determines a corresponding candidate feature local signal energy value set according to the candidate feature local signal set; The dust monitoring management platform determines the feature detection local signal according to the candidate feature local signal set and the candidate feature local signal energy value set.

4. The weak signal processing method applied to the ultra-low dust meter according to claim 3 is characterized in that: The dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle time, including: The dust monitoring management platform generates a characteristic detection local signal set according to the characteristic detection local signals within each preset cycle duration; The dust monitoring management platform sequentially splices each characteristic detection local signal in the characteristic detection local signal set according to the timing of each preset cycle duration to form the dust monitoring weak signal.

5. The weak signal processing method applied to the ultra-low dust meter according to claim 4 is characterized in that: The dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal and a preset dust concentration calibration curve, and further includes: The dust monitoring management platform determines the characteristic mean of the dust monitoring signal according to the dust monitoring weak signal; The dust monitoring management platform determines the dust concentration of the space to be detected according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, wherein the preset dust concentration calibration curve is used to establish a mapping relationship between the characteristic value of the monitoring signal and the dust concentration.

6. The weak signal processing method applied to the ultra-low dust meter according to claim 5 is characterized in that: Before the dust monitoring management platform determines the dust concentration of the to-be-detected space according to the characteristic mean value of the dust monitoring signal and the preset dust concentration calibration curve, the method further includes: If the dust monitoring management platform determines that the characteristic mean value of the dust monitoring signal exceeds the value range of the monitoring signal characteristic value in the preset dust concentration calibration curve, a monitoring update indication is sent to the ultra-low dust monitor array so that the ultra-low dust monitor array re-acquires the dust monitoring update signal set in the space to be detected, and sends the dust monitoring update signal set to the dust monitoring management platform.

7. The weak signal processing method for ultra-low dust monitor according to any one of claims 2 to 6, characterized in that: Before the dust monitoring management platform extracts the candidate feature local signal sets within each preset period from the candidate feature detection signal set according to the preset period, the method further includes: The dust monitoring management platform determines that a proportion of dust monitoring signals in the dust monitoring signal set that include the candidate feature detection signals is greater than a preset proportion threshold.

8. An environmental dust monitoring system, characterized in that: include: A dust monitoring management platform and an ultra-low dust monitor array, wherein each ultra-low dust monitor in the ultra-low dust monitor array is communicatively connected with the dust monitoring management platform; The dust monitoring signal set in the to-be-detected space is obtained through the ultra-low dust monitor array, and the dust monitoring signal set is sent to the dust monitoring management platform, the to-be-detected space includes a to-be-detected grid array composed of a plurality of to-be-detected grids, and each ultra-low dust monitor in the ultra-low dust monitor array is respectively arranged in each to-be-detected grid in the to-be-detected space, and the ultra-low dust monitor array collects the monitored dust signals in the form of electrical signals; The dust monitoring management platform extracts candidate feature detection signals from each dust monitoring signal in the dust monitoring signal set according to a preset signal frequency range and a preset signal energy range to generate a candidate feature detection signal set; The dust monitoring management platform extracts a candidate feature local signal set within each preset cycle length from the candidate feature detection signal set according to the preset cycle length; The dust monitoring management platform generates a feature detection local signal corresponding to a preset period duration according to each candidate feature local signal in the candidate feature local signal set; The dust monitoring management platform generates the dust monitoring weak signal according to the characteristic detection local signal within each preset cycle duration, wherein the dust monitoring weak signal is a signal whose signal strength is lower than a preset background noise intensity threshold; The dust monitoring management platform determines the dust concentration of the to-be-detected space according to the dust monitoring weak signal set and a preset dust concentration calibration curve.

9. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images