Low-carbon ventilation system control method based on air quality online monitoring

Abstract

The invention relates to a low-carbon ventilation system control method based on air quality on-line monitoring. The core of the low-carbon ventilation system control method is a ventilation control scheme based on air quality on-line monitoring. Specifically, the method comprises the following steps: monitoring gas concentration values (such as hydrogen sulfide concentration, ammonia gas concentration, oxygen concentration and carbon dioxide concentration), temperature, humidity, negative oxygen ions and the like in an environment in real time through a gas sensor, and carrying out time sequence analysis on the gas concentration values by adopting an artificial intelligence technology based on deep learning; the significant change rule of each gas concentration in the global time domain is mined, and then the working frequency value of the air purification equipment in the ventilation system is adjusted in a self-adaptive mode based on the principal component time sequence joint characteristics of each gas concentration. Therefore, the ventilation system can be intelligently regulated and controlled according to the change of the concentration of the volatile gas, so that the energy utilization efficiency is improved, the operation cost is reduced, and the purposes of saving energy and reducing carbon are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of volatile gas monitoring, and in particular to a low-carbon ventilation system control method based on online air quality monitoring. Background Art

[0002] With the increasing environmental protection requirements and the shortage of land resources, there are more and more underground sewage treatment plant projects in recent years. Compared with above-ground sewage treatment plants, the investment and energy consumption of ventilation systems in underground sewage treatment plants have greatly increased, which is one of the design focuses for energy conservation and carbon reduction.

[0003] After investigation, we found that the ventilation system in sewage treatment plants is currently controlled by manual control and simple threshold control. Although this method can reduce pollutants in the air to a certain extent, due to the lack of real-time monitoring and intelligent control of actual operating conditions, the ventilation system cannot be effectively adjusted according to actual needs in many cases, resulting in energy waste and increased operating costs. This problem is particularly prominent in environments with large fluctuations in the concentration of volatile organic compounds (VOCs).

[0004] Specifically, the current indoor ventilation design is generally based on full-volume operation with 6 air changes. In actual operation, it is generally either fully open or fully closed to save energy, but this will result in poor air quality. Some ventilation control systems also use weak intelligent control solutions, for example, monitoring air quality and waiting until the air quality drops to a certain level before starting the ventilation system, which will cause control lag and fail to ensure air quality in a timely manner.

[0005] Therefore, in order to improve the intelligence level of the ventilation system, a low-carbon ventilation system control method based on online monitoring of air quality is expected. Summary of the invention

[0006] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In a first aspect, the present application provides a low-carbon ventilation system control method based on online air quality monitoring, the method comprising:

[0008] The time sequence of hydrogen sulfide concentration and the time sequence of ammonia concentration are collected by gas sensors;

[0009] Transmitting the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration to a central controller of an air purification device through a wireless communication module;

[0010] At the central controller of the air purification equipment, extracting time series features based on the local time scale for the time queue of the hydrogen sulfide concentration and the time queue of the ammonia concentration to obtain a sequence of local time series fluctuation feature vectors of the hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of the ammonia concentration;

[0011] Inputting the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and the sequence of local time series fluctuation feature vectors of ammonia concentration into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector;

[0012] Based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, a control instruction for the working frequency of the air purification equipment is generated.

[0013] Optionally, performing time series feature extraction based on a local time scale on the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration to obtain a sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of ammonia concentration includes:

[0014] The time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are segmented according to a predetermined time scale and then input into a sequence encoder based on a 1D-CNN model to obtain a sequence of local temporal fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local temporal fluctuation feature vectors of ammonia concentration.

[0015] Optionally, the sequence of the local time series fluctuation feature vectors of the hydrogen sulfide concentration and the sequence of the local time series fluctuation feature vectors of the ammonia concentration are input into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector, including:

[0016] Calculating a characteristic significance description factor of each hydrogen sulfide concentration local time series fluctuation characteristic vector in the sequence of the hydrogen sulfide concentration local time series fluctuation characteristic vector, wherein the characteristic significance description factor is related to the mean and variance of each hydrogen sulfide concentration local time series fluctuation characteristic vector;

[0017] Taking the last local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration as the current local time-series fluctuation feature vector of hydrogen sulfide concentration, and constructing the characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration based on the distance span between each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration and the current local time-series fluctuation feature vector of hydrogen sulfide concentration;

[0018] Calculating the product of the characteristic significance attenuation factor of each local time series fluctuation characteristic vector of the hydrogen sulfide concentration and its characteristic significance description factor to obtain a sequence of characteristic significance attenuation description factors;

[0019] Inputting the sequence of feature significance attenuation description factors into a gated mask module to obtain a sequence of feature significance attenuation weight factors;

[0020] The sequence of the characteristic significance attenuation weight factors is used as the sequence of weights, and the weighted sum of the sequence of the local time series fluctuation characteristic vectors of the hydrogen sulfide concentration is calculated to obtain the hydrogen sulfide concentration time series significant aggregation representation vector.

[0021] Optionally, calculating the characteristic significance description factor of each hydrogen sulfide concentration local time series fluctuation feature vector in the sequence of hydrogen sulfide concentration local time series fluctuation feature vectors includes:

[0022] The expected value of the fourth power of the difference between each eigenvalue in the local time series fluctuation eigenvector of the hydrogen sulfide concentration and its eigenmean is calculated, and the expected value is divided by the square of the eigenvariance of the local time series fluctuation eigenvector of the hydrogen sulfide concentration to obtain the eigensignificance description factor.

[0023] Optionally, based on the distance span between each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration and the current local time-series fluctuation feature vector of hydrogen sulfide concentration, constructing a characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration, including:

[0024] The difference between the maximum eigenvalue of the current local time-series fluctuation characteristic vector of hydrogen sulfide concentration and the maximum eigenvalue of each local time-series fluctuation characteristic vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation characteristic vectors of hydrogen sulfide concentration is calculated, and then the difference is divided by the number of eigenvectors separated by the two to obtain the characteristic significance attenuation factor of each local time-series fluctuation characteristic vector of hydrogen sulfide concentration.

[0025] Optionally, generating a control instruction for the working frequency of the air purification device based on the principal component joint feature of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector includes:

[0026] Inputting the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector;

[0027] The hydrogen sulfide concentration-ammonia concentration main component joint time series aggregation representation vector is input into a decoder-based air purification equipment control module to obtain the control instruction, and the control instruction is used to represent the recommended decoding value of the working frequency of the air purification equipment.

[0028] Optionally, the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector are input into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, including:

[0029] The hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector are normalized to obtain a normalized hydrogen sulfide concentration time series significant aggregation representation vector and a normalized ammonia concentration time series significant aggregation representation vector;

[0030] Respectively calculating the sample covariance matrices of the standardized hydrogen sulfide concentration time series significant aggregation representation vector and the standardized ammonia concentration time series significant aggregation representation vector to obtain a hydrogen sulfide concentration sample covariance matrix and an ammonia concentration sample covariance matrix;

[0031] Performing matrix decomposition-based eigenvector extraction on the hydrogen sulfide concentration sample covariance matrix and the ammonia concentration sample covariance matrix to obtain a set of hydrogen sulfide concentration time series principal component eigenvectors and a set of ammonia concentration time series principal component eigenvectors;

[0032] Inputting the set of the hydrogen sulfide concentration time series principal component feature vectors and the set of the ammonia concentration time series principal component feature vectors into a maximum approximate query matching network to obtain a set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vectors and the ammonia concentration time series principal component feature vectors;

[0033] Input each best matching pair in the set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector into a semantic fine-grained gating joint module to obtain a set of hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors;

[0034] The set of the hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors is cascaded to obtain the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector.

[0035] Optionally, the set of the hydrogen sulfide concentration time series principal component feature vectors and the set of the ammonia concentration time series principal component feature vectors are input into a maximum approximate query matching network to obtain a set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vectors and the ammonia concentration time series principal component feature vectors, including:

[0036] Calculating the cosine similarity between the i-th hydrogen sulfide concentration time series principal component feature vector in the set of hydrogen sulfide concentration time series principal component feature vectors and each ammonia concentration time series principal component feature vector in the set of ammonia concentration time series principal component feature vectors to obtain a set of cosine similarities;

[0037] The ammonia concentration time series principal component feature vector corresponding to the maximum value in the set of cosine similarities and the i-th hydrogen sulfide concentration time series principal component feature vector form the best matching pair.

[0038] Optionally, each best matching pair in the set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector is input into a semantic fine-grained gating joint module to obtain a set of hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors, including:

[0039] Calculate the position point addition, position point subtraction and position point multiplication between the hydrogen sulfide concentration time series principal component eigenvector and the ammonia concentration time series principal component eigenvector in the best matching pair to obtain a first matching fusion result, a second matching fusion result and a third matching fusion result;

[0040] After the first matching fusion result, the second matching fusion result and the third matching fusion result are cascaded into a multi-scale fusion feature vector of the hydrogen sulfide concentration-ammonia concentration main component, one-dimensional convolution processing and maximum pooling processing are performed on them to obtain the hydrogen sulfide concentration-ammonia concentration main component joint feature vector.

[0041] The above technical solution is adopted to monitor the concentration of hydrogen sulfide and ammonia in the environment in real time through gas sensors, and use artificial intelligence technology based on deep learning to perform time series analysis on ammonia concentration data and hydrogen sulfide concentration data, respectively dig out the significant change patterns of hydrogen sulfide concentration and ammonia concentration in the global time domain, and then adaptively adjust the working frequency of the current air purification equipment based on the main component time series joint characteristics of hydrogen sulfide concentration and ammonia concentration. In this way, the ventilation system can be intelligently controlled according to the changes in volatile gas concentration, thereby improving energy efficiency, reducing operating costs, and achieving the goal of energy saving and carbon reduction.

[0042] Other features and advantages of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0044] Figure 1 The present invention is a flow chart showing a method for controlling a low-carbon ventilation system based on online monitoring of air quality according to an exemplary embodiment.

[0045] Figure 2 It is a block diagram of an intelligent control system based on volatile gas monitoring according to an exemplary embodiment.

[0046] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0047] Figure 4 It is an application scenario diagram of a low-carbon ventilation system control method based on online monitoring of air quality according to an exemplary embodiment. DETAILED DESCRIPTION

[0048] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0049] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0050] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0051] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0052] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0053] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0054] With the improvement of environmental protection requirements and the shortage of land resources, there are more and more underground sewage treatment plant projects in recent years. Compared with above-ground sewage treatment plants, the investment and energy consumption of ventilation systems in underground sewage treatment plants have greatly increased, which is one of the design focuses of energy conservation and carbon reduction.

[0055] After investigation and understanding, it is found that there are some common problems in the control of ventilation systems in domestic sewage plants:

[0056] (1) The ventilation system is still basically manually controlled. Although it is equipped with an automatic control system, there is no clear control logic and no clear control objectives;

[0057] (2) Lack of understanding of the environmental characteristics of the space and unclear concepts of the parameters of various instruments;

[0058] (3) The ventilation system is always open 24 hours a day throughout the year or some areas are not open at all, which may cause waste or safety hazards;

[0059] (4) In summer, the ventilation and air-conditioning systems in electrical rooms run simultaneously for a long time, wasting electricity.

[0060] From the perspective of air environment and safe operation, the control objectives of the underground sewage treatment plant ventilation system are clarified, and the energy-saving potential of the high-efficiency ventilation system is fully utilized, thereby reducing the operating energy consumption of the ventilation system.

[0061] The intelligent environmental control system should have the following functions:

[0062] (1) Automatically adjust and control system operation according to the preset gas concentration and time control strategy;

[0063] (2) Continuously record and display the operating parameters of each ventilation and air conditioning system;

[0064] (3) Calculate and count the continuous and cumulative operating time of the controlled equipment;

[0065] (4) Security mechanisms such as permission setting and access control are provided.

[0066] When the ventilation system also serves as a smoke exhaust system, its monitoring system should be linked with the factory area's automatic fire alarm system and be able to switch to the automatic fire alarm system control state in the event of a fire. The open / closed status of various fire dampers and smoke exhaust valves should be displayed in the fire control room.

[0067] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0068] Figure 1is a flow chart showing a low-carbon ventilation system control method based on online air quality monitoring according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0069] Step S101, collecting a time queue of hydrogen sulfide concentration and a time queue of ammonia concentration through a gas sensor;

[0070] Step S102, transmitting the time queue of the hydrogen sulfide concentration and the time queue of the ammonia concentration to the central controller of the air purification equipment through a wireless communication module;

[0071] Step S103: In the central controller of the air purification equipment, extracting the time series characteristics of the hydrogen sulfide concentration time series and the ammonia concentration time series based on the local time scale to obtain a sequence of local time series fluctuation characteristic vectors of the hydrogen sulfide concentration and a sequence of local time series fluctuation characteristic vectors of the ammonia concentration;

[0072] Step S104, inputting the sequence of the local time series fluctuation feature vectors of the hydrogen sulfide concentration and the sequence of the local time series fluctuation feature vectors of the ammonia concentration into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector;

[0073] Step S105: Generate a control instruction for the working frequency of the air purification equipment based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector.

[0074] In response to the above technical problems, the technical concept of this application is to monitor the hydrogen sulfide concentration and ammonia concentration in the environment in real time through gas sensors, and use artificial intelligence technology based on deep learning to perform time series analysis on ammonia concentration data and hydrogen sulfide concentration data, respectively dig out the significant change patterns of hydrogen sulfide concentration and ammonia concentration in the global time domain, and then adaptively adjust the working frequency of the current air purification equipment based on the main component time series joint characteristics of hydrogen sulfide concentration and ammonia concentration. In this way, the ventilation system can be intelligently controlled according to the changes in volatile gas concentration, thereby improving energy efficiency, reducing operating costs, and achieving the goal of energy saving and carbon reduction.

[0075] Based on this, in the technical solution of the present application, first, the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are collected by gas sensors. It should be understood that the concentration change of volatile organic compounds (VOCs) has a direct impact on the operation requirements of the ventilation system. When the VOCs concentration is high, the operating frequency of the equipment should be increased to quickly reduce the concentration; when the VOCs concentration is low, the operating frequency can be reduced to reduce energy consumption and noise. Ammonia and methane are common volatile organic compounds (VOCs). Therefore, in the technical solution of the present application, ammonia and methane are used as the main monitoring objects, and the operating frequency of the air purification equipment is adaptively adjusted based on the concentration detection of the two.

[0076] Among them, the monitoring content is divided into three types and the corresponding control strategies are shown in Table 1.

[0077] Table 1

[0078]

[0079]

[0080] Relevant detection instruments and alarm devices are installed in underground sewage facilities, and the monitoring contents are shown in Table 2 below.

[0081] Table 2

[0082]

[0083] After collecting the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration, the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are further transmitted to the central controller of the air purification equipment through the wireless communication module to perform real-time analysis and centralized processing of the data.

[0084] Next, considering that directly processing the entire time series data of hydrogen sulfide concentration and ammonia concentration may result in excessive calculation and loss of local detail information due to the long time span. Therefore, in order to capture the local fluctuation characteristics of hydrogen sulfide concentration and ammonia concentration in more detail, in the technical solution of the present application, first, the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are segmented at a predetermined time scale, and the continuous data stream is divided into multiple shorter local time windows, and then the 1D-CNN (one-dimensional convolutional neural network) model is used to perform time series encoding on the data in each local time window to capture the local correlation in the time series data, and to mine the time series fluctuation patterns of hydrogen sulfide concentration and ammonia concentration, thereby generating a sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of ammonia concentration.

[0085] In one embodiment of the present application, time series feature extraction based on local time scale is performed on the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration to obtain a sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of ammonia concentration, including: dividing the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration according to a predetermined time scale and then inputting the divided time queues into a sequence encoder based on a 1D-CNN model to obtain a sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of ammonia concentration.

[0086] Then, in order to further integrate the local time series information of hydrogen sulfide concentration and ammonia concentration, and to dig out the dynamic change pattern of hydrogen sulfide concentration and ammonia concentration in the global time domain, the present application introduces a feature aggregation network based on feature significance attenuation guidance to fuse the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and the sequence of local time series fluctuation feature vectors of ammonia concentration. Specifically, the feature aggregation network first calculates the feature significance description factor of each local time series fluctuation feature vector based on the mean and variance of each local time series fluctuation feature vector in the input sequence, and quantitatively represents the feature importance. Then, a feature significance attenuation factor is constructed based on the distance span between each local time series fluctuation feature vector and the current local time series fluctuation feature vector (the end of the time series), and its feature significance description factor is modulated by this, so that the local time series fluctuation feature vector that is closer to the current moment in the feature space obtains a higher weight, thereby more accurately reflecting the relative importance of each local feature in the overall sequence. Then, the modulated descriptive factors are further screened using activation functions and gating mechanisms, and the input sequence is weighted summed with the screened descriptive factors as weights to integrate the feature information of each local time domain in the input sequence and emphasize the key local feature information, thereby improving the significance and relevance of the feature representation and generating a time series significant aggregation representation vector of hydrogen sulfide concentration and a time series significant aggregation representation vector of ammonia concentration.

[0087] In one embodiment of the present application, the sequence of the local time-series fluctuation feature vectors of the hydrogen sulfide concentration and the sequence of the local time-series fluctuation feature vectors of the ammonia concentration are input into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time-series significant aggregation representation vector and an ammonia concentration time-series significant aggregation representation vector, including: calculating the feature significance description factor of each local time-series fluctuation feature vector of the hydrogen sulfide concentration in the sequence of the local time-series fluctuation feature vector of the hydrogen sulfide concentration, wherein the feature significance description factor is related to the mean and variance of each local time-series fluctuation feature vector of the hydrogen sulfide concentration; taking the last local time-series fluctuation feature vector of the hydrogen sulfide concentration in the sequence of the local time-series fluctuation feature vector of the hydrogen sulfide concentration as the current local time-series fluctuation feature vector of the hydrogen sulfide concentration, based on the hydrogen sulfide concentration; The characteristic significance attenuation factor of each local time series fluctuation feature vector of hydrogen sulfide concentration is constructed based on the distance span between each local time series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time series fluctuation feature vector of concentration and the current local time series fluctuation feature vector of hydrogen sulfide concentration; the product between the characteristic significance attenuation factor of each local time series fluctuation feature vector of hydrogen sulfide concentration and its characteristic significance description factor is calculated to obtain a sequence of characteristic significance attenuation description factors; the sequence of characteristic significance attenuation description factors is input into the gated mask module to obtain a sequence of characteristic significance attenuation weight factors; the sequence of characteristic significance attenuation weight factors is used as the sequence of weights to calculate the weighted sum of the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration to obtain the hydrogen sulfide concentration time series significant aggregation representation vector.

[0088] Furthermore, in one embodiment of the present application, the characteristic significance description factor of each local time-series fluctuation characteristic vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation characteristic vectors of hydrogen sulfide concentration is calculated, including: calculating the expected value of the fourth power of the difference between each characteristic value in the local time-series fluctuation characteristic vector of hydrogen sulfide concentration and its characteristic mean, and dividing the expected value by the square of the characteristic variance of the local time-series fluctuation characteristic vector of hydrogen sulfide concentration to obtain the characteristic significance description factor.

[0089] Furthermore, in one embodiment of the present application, based on the distance span between each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration and the current local time-series fluctuation feature vector of hydrogen sulfide concentration, a characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration is constructed, including: calculating the difference between the maximum eigenvalue of the current local time-series fluctuation feature vector of hydrogen sulfide concentration and the maximum eigenvalue of each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration, and then dividing the difference by the number of eigenvectors separated therebetween to obtain the characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration.

[0090] Specifically, the sequence of the local time series fluctuation feature vectors of the hydrogen sulfide concentration is processed by the following feature significance attenuation guided fusion formula to obtain the hydrogen sulfide concentration time series significant aggregation representation vector, wherein the feature significance attenuation guided fusion formula is:

[0091] X={x1,x2,...,x k ,...,x n}

[0092]

[0093] ws i =mask(w i )

[0094]

[0095] Wherein, X represents the sequence of the characteristic vectors of the local time series fluctuation of the hydrogen sulfide concentration, the value of n is the number of characteristic vectors in the sequence of the characteristic vectors of the local time series fluctuation of the hydrogen sulfide concentration, and x1, x2, x i 、x k and x n represents the first, second, ith, kth and current local time series fluctuation feature vectors of hydrogen sulfide concentration in the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration, max(·) represents the maximum eigenvalue of the feature vector, x i (j) represents the jth eigenvalue of the i-th local time series fluctuation eigenvector of hydrogen sulfide concentration, α i and β i 4 represent the characteristic mean and square of the characteristic variance of the local time series fluctuation characteristic vector of the i-th hydrogen sulfide concentration, E{[x i (j)-μ i ] 4} represents the fourth-order central moment of the ith local time-series fluctuation characteristic vector of hydrogen sulfide concentration, that is, the expected value of the fourth power of the difference between each eigenvalue in the ith local time-series fluctuation characteristic vector of hydrogen sulfide concentration and its characteristic mean, i ranges from 1 to n-1, τ i represents the characteristic significance attenuation factor of the i-th local time series fluctuation characteristic vector of hydrogen sulfide concentration, k i represents the descriptor factor of the i-th feature significance attenuation, e is a natural constant, and w i represents the descriptive factor of the ith normalized feature significance attenuation, ws i represents the i-th feature significance attenuation weight factor, θ is a preset threshold, mask(·) represents mask processing, and V1 represents the hydrogen sulfide concentration time series significant aggregation representation vector. Here, it should be understood that the process of inputting the sequence of the local time series fluctuation feature vectors of the ammonia concentration into the feature aggregation network based on feature significance attenuation guidance to obtain the ammonia concentration time series significant aggregation representation vector can refer to the above-mentioned feature significance attenuation guidance fusion formula.

[0096] In one embodiment of the present application, based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, a control instruction for the operating frequency of an air purification device is generated, including: inputting the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector; inputting the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector into a decoder-based air purification device control module to obtain the control instruction, wherein the control instruction is used to represent a recommended decoded value of the operating frequency of the air purification device.

[0097] Furthermore, in order to more accurately describe the air quality status, it is necessary to further jointly analyze the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, and mine the joint change pattern of hydrogen sulfide concentration and ammonia concentration in the global time domain to achieve effective integration of multi-source data information. Based on this, the present application introduces a significant fusion network based on feature principal component optimization matching to achieve this goal. Specifically, the significant fusion network first standardizes the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector to ensure that the data is distributed on a zero mean scale and has unit variance, eliminating the effects of different dimensions and magnitudes. Then, the principal component analysis algorithm is used to extract the principal component features of the standardized hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, and the main change features are mined, thereby obtaining a set of hydrogen sulfide concentration time series principal component feature vectors and ammonia concentration time series principal component feature vectors. Furthermore, based on the maximum approximate query matching between feature vectors, the best matching pair is found by calculating and comparing the similarity between the two principal component feature vector sets. Next, the core components of hydrogen sulfide concentration and ammonia concentration in the global time domain are aggregated by performing fine-grained semantic union on each best matching pair and cascading the feature fusion results of each best matching pair to generate a hydrogen sulfide concentration-ammonia concentration principal component joint temporal aggregation representation vector.

[0098] In one embodiment of the present application, the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector are input into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, including: standardizing the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector to obtain a standardized hydrogen sulfide concentration time series significant aggregation representation vector and a standardized ammonia concentration time series significant aggregation representation vector; calculating the sample covariance matrices of the standardized hydrogen sulfide concentration time series significant aggregation representation vector and the standardized ammonia concentration time series significant aggregation representation vector respectively to obtain a hydrogen sulfide concentration sample covariance matrix and an ammonia concentration sample covariance matrix; performing a sparse fusion on the hydrogen sulfide concentration sample covariance matrix and the ammonia concentration sample covariance matrix. The method comprises the following steps: extracting feature vectors based on matrix decomposition to obtain a set of main component feature vectors of hydrogen sulfide concentration time series and a set of main component feature vectors of ammonia concentration time series; inputting the set of main component feature vectors of hydrogen sulfide concentration time series and the set of main component feature vectors of ammonia concentration time series into a maximum approximate query matching network to obtain a set of best matching pairs of main component feature vectors of hydrogen sulfide concentration time series and main component feature vectors of ammonia concentration time series; inputting each best matching pair in the set of best matching pairs of main component feature vectors of hydrogen sulfide concentration time series and main component feature vectors of ammonia concentration time series into a semantic fine-grained gating joint module to obtain a set of joint feature vectors of hydrogen sulfide concentration-ammonia concentration main component; and cascading the set of joint feature vectors of hydrogen sulfide concentration-ammonia concentration main component to obtain a joint time series aggregate representation vector of hydrogen sulfide concentration-ammonia concentration main component.

[0099] Furthermore, in one embodiment of the present application, the set of hydrogen sulfide concentration time series principal component feature vectors and the set of ammonia concentration time series principal component feature vectors are input into a maximum approximate query matching network to obtain a set of best matching pairs of hydrogen sulfide concentration time series principal component feature vectors and ammonia concentration time series principal component feature vectors, including: calculating the cosine similarity between the i-th hydrogen sulfide concentration time series principal component feature vector in the set of hydrogen sulfide concentration time series principal component feature vectors and each ammonia concentration time series principal component feature vector in the set of ammonia concentration time series principal component feature vectors to obtain a set of cosine similarities; and forming the best matching pair with the ammonia concentration time series principal component feature vector corresponding to the maximum value in the set of cosine similarities and the i-th hydrogen sulfide concentration time series principal component feature vector.

[0100] Furthermore, in one embodiment of the present application, each best matching pair in the set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector is input into a semantic fine-grained gated joint module to obtain a set of hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors, including: calculating the position point addition, position point subtraction and position point multiplication between the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector in the best matching pair to obtain a first matching fusion result, a second matching fusion result and a third matching fusion result; after cascading the first matching fusion result, the second matching fusion result and the third matching fusion result into a hydrogen sulfide concentration-ammonia concentration principal component multi-scale fusion feature vector, one-dimensional convolution processing and maximum pooling processing are performed on it to obtain the hydrogen sulfide concentration-ammonia concentration principal component joint feature vector.

[0101] Specifically, the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector are fused using the following principal component query matching formula to obtain the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, wherein the principal component query matching formula is:

[0102]

[0103] C1=U1Λ1U1 T

[0104] C2=U2Λ2U2 T

[0105] U1=[v 11 ,v 12 ,…,v 1m ]

[0106] A1=diag(λ 11 ,λ 12 ,…,λ 1m )

[0107] U2=[v 21 ,v 22 ,…,v 2m ]

[0108] Λ2=diag(λ 21 ,λ 22 ,…,λ 2m )

[0109]

[0110] v f =[v p1 ;v p2 ;...vpm ]

[0111] Wherein, V1 represents the significant aggregation representation vector of the hydrogen sulfide concentration time series, μ1 and σ1 represent the mean and standard deviation of the significant aggregation representation vector of the hydrogen sulfide concentration time series, respectively. 1norm represents the time series significant aggregation representation vector of the standardized hydrogen sulfide concentration, V2 represents the time series significant aggregation representation vector of the ammonia concentration, μ2 and σ2 represent the mean and standard deviation of the time series significant aggregation representation vector of the ammonia concentration, respectively, V 2norm represents the standardized ammonia concentration time series significant aggregation representation vector, the value of n1 is the length of the hydrogen sulfide concentration time series significant aggregation representation vector, the value of n2 is the length of the ammonia concentration time series significant aggregation representation vector, C1 represents the hydrogen sulfide concentration sample covariance matrix, C2 represents the ammonia concentration sample covariance matrix, U1 represents the matrix composed of the set of principal component eigenvectors of the hydrogen sulfide concentration time series obtained by performing eigenvalue decomposition on the hydrogen sulfide concentration sample covariance matrix, Λ1 represents the diagonal matrix composed of the set of principal component eigenvalues ​​of the hydrogen sulfide concentration time series obtained by performing eigenvalue decomposition on the hydrogen sulfide concentration sample covariance matrix, v 11 、v 12 、v 1i and v 1m represent the first, second, i-th and m-th principal component eigenvectors of the hydrogen sulfide concentration time series in the set of principal component eigenvectors of the hydrogen sulfide concentration time series, respectively, 11 , 12 and λ 1m represents the first, second and mth main component eigenvalues ​​of the hydrogen sulfide concentration time series in the set of main component eigenvalues ​​of the hydrogen sulfide concentration time series, respectively, the value of m is the number of main component eigenvalues ​​of the hydrogen sulfide concentration time series, U2 represents the matrix composed of the set of main component eigenvectors of the ammonia concentration time series obtained by performing eigenvalue decomposition on the ammonia concentration sample covariance matrix, Λ2 represents the diagonal matrix composed of the set of main component eigenvalues ​​of the ammonia concentration time series obtained by performing eigenvalue decomposition on the ammonia concentration sample covariance matrix, v 21 、v 22 、v 2j 、v 2k and v 2m represents the first, second, jth, kth and mth ammonia concentration time series principal component eigenvectors in the set of ammonia concentration time series principal component eigenvectors, respectively, 21 , 22 and λ 2mrepresents the first, second and mth ammonia concentration time series principal component eigenvalues ​​in the set of ammonia concentration time series principal component eigenvalues, respectively; diag is a diag function used to construct a diagonal matrix; <·> represents an inner product; ||·|| represents the modulus of the eigenvector; argmax(·) represents the index corresponding to the maximum value; k represents the index of the ammonia concentration time series principal component eigenvector that forms the best matching pair with the i-th hydrogen sulfide concentration time series principal component eigenvector; [·,·] represents a cascade operation; MaxPool(·) represents a maximum pooling operation; conv1D(·) represents a one-dimensional convolution operation; ⊙ represents a dot product; Indicates point addition, Indicates point minus, v pi represents the joint eigenvector of the principal component of hydrogen sulfide concentration and ammonia concentration, v f A vector representing the combined time series aggregation of the main components of the hydrogen sulfide concentration and the ammonia concentration.

[0112] Next, the hydrogen sulfide concentration-ammonia concentration main component joint time series aggregation representation vector is input into a decoder-based air purification equipment control module to obtain a control instruction, and the control instruction is used to represent a recommended decoding value of the working frequency of the air purification equipment.

[0113] In a preferred example, it is considered that the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector respectively represent the full-time domain time series aggregation features of the local time series fluctuation characteristics of the hydrogen sulfide concentration based on the node feature significance attenuation guidance and the full-time domain time series aggregation features of the local time series fluctuation characteristics of the ammonia concentration based on the node feature significance attenuation guidance. Therefore, when performing significant fusion based on feature principal component optimization matching, due to the time series correlation feature distribution difference of the source time series distribution difference and the node feature significance attenuation difference superimposed, the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector will also have a time series feature diversified set expression distribution. Therefore, it is expected to improve the balance between the regression mapping accuracy and completeness of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector when inputting the decoder-based air purification equipment control module for decoding regression, thereby improving the accuracy of the obtained control instructions.

[0114] Based on this, in the preferred example, the hydrogen sulfide concentration-ammonia concentration main component joint time series aggregation representation vector is input into the decoder-based air purification equipment control module to obtain the control instruction, which specifically includes:

[0115] Calculate the absolute value sum of each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector to obtain a first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation spatial structure value, and calculate the square root of the sum of the squares of each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector to obtain a second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation spatial structure value;

[0116] Multiply each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector by the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation space structure value and the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation space structure value respectively to obtain a first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation structure reference value and a second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation structure reference value corresponding to each eigenvalue;

[0117] Multiply each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector by the length of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector and the square root of the length to obtain a first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation scale transformation value and a second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation scale transformation value corresponding to each eigenvalue;

[0118] Dividing the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation structure reference value by the difference between the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation space structure value and the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation scale transformation value to obtain the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value;

[0119] Dividing the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation structure reference value by the difference between the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation space structure value and the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation scale transformation value to obtain the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value;

[0120] Calculating a weighted sum of the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value and the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value to obtain each eigenvalue of the optimized hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector;

[0121] The optimized hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector is passed through a decoder-based target object position changer to obtain a target object position change decoding value.

[0122] Here, the hydrogen sulfide concentration-ammonia concentration main component joint time series aggregation representation vector, denoted as V, is optimally represented as:

[0123]

[0124] v 4i =(α×v i ) / (α-L×v i )

[0125]

[0126] vx∈V∈R 1×L

[0127] v 3i ∈V3∈R 1×L

[0128] v 4i ∈V4∈R 1×L

[0129] Wherein, V is the principal component joint time series aggregation representation vector of hydrogen sulfide concentration and ammonia concentration, R represents a real number set, and v i represents the eigenvalue of the i-th position of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, L represents the length of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, α represents the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation spatial structure value, β represents the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation spatial structure value, ⊙ represents the point multiplication by position, represents addition by position, V3 represents the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment vector, v 3i represents the second hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value, V4 represents the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment vector, v 4i represents the first hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation transformation adjustment value, ω represents the weighted hyperparameter, and V' represents the optimized hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector.

[0130] Therefore, in the preferred example, for the spatial structure information of the feature set of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector in the high-dimensional space, the scale-based frame transformation of each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector is performed by taking the class-norm space structured representation of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector as the reference window, and realizing the spatial structure-based frame attention weight adjustment of each eigenvalue of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, so as to ensure the spatial transformation (translation, scaling and rotation) invariance of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector under feature space interaction, so as to realize the balanced executable property between mapping accuracy and mapping completeness in the decoding regression process based on the discrete feature distribution of the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, and improve the accuracy of the control instructions obtained by the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector input into the decoder-based air purification equipment control module.

[0131] In summary, the above scheme is adopted to monitor the hydrogen sulfide concentration and ammonia concentration in the environment in real time through gas sensors, and use artificial intelligence technology based on deep learning to perform time series analysis on ammonia concentration data and hydrogen sulfide concentration data, respectively dig out the significant change patterns of hydrogen sulfide concentration and ammonia concentration in the global time domain, and then adaptively adjust the working frequency of the current air purification equipment based on the main component time series joint characteristics of hydrogen sulfide concentration and ammonia concentration. In this way, the ventilation system can be intelligently controlled according to the changes in volatile gas concentration, thereby improving energy efficiency, reducing operating costs, and achieving the goal of energy saving and carbon reduction.

[0132] Figure 2 It is a block diagram of an intelligent control system based on volatile gas monitoring according to an exemplary embodiment.

[0133] like Figure 2 As shown, the intelligent control system 200 includes:

[0134] The gas concentration collection module 201 is used to collect the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration through a gas sensor;

[0135] A gas concentration value transmission module 202, used to transmit the time queue of the hydrogen sulfide concentration and the time queue of the ammonia concentration to the central controller of the air purification device through a wireless communication module;

[0136] The time series feature extraction module 203 is used to extract the time series features of the hydrogen sulfide concentration time series and the ammonia concentration time series based on the local time scale in the central controller of the air purification equipment to obtain a sequence of local time series fluctuation feature vectors of the hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of the ammonia concentration;

[0137] A feature aggregation module 204 is used to input the sequence of the local time series fluctuation feature vectors of the hydrogen sulfide concentration and the sequence of the local time series fluctuation feature vectors of the ammonia concentration into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector;

[0138] The control instruction generation module 205 is used to generate a control instruction for the working frequency of the air purification equipment based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector.

[0139] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0140] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0141] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0142] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0143] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0144] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0145] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0146] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0148] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0149] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0150] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] Figure 4 is an application scenario diagram of a low-carbon ventilation system control method based on online air quality monitoring according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the time queue of ammonia concentration is collected by the gas sensor (for example, Figure 4 C1) and the time series of hydrogen sulfide concentrations (e.g., Figure 4 Then, the obtained time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are input to a server (for example, Figure 4 In the S) shown in FIG, the server is capable of processing the time queue of the hydrogen sulfide concentration and the time queue of the ammonia concentration based on the intelligent control algorithm of volatile gas monitoring to generate control instructions for the working frequency of the air purification equipment.

[0152] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0153] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0154] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. A low-carbon ventilation system control method based on online air quality monitoring, characterized in that: include: The time sequence of hydrogen sulfide concentration and the time sequence of ammonia concentration are collected by gas sensors; Transmitting the time queue of hydrogen sulfide concentration and the time queue of ammonia concentration to a central controller of an air purification device through a wireless communication module; At the central controller of the air purification equipment, extracting time series features based on the local time scale for the time queue of the hydrogen sulfide concentration and the time queue of the ammonia concentration to obtain a sequence of local time series fluctuation feature vectors of the hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of the ammonia concentration; Inputting the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and the sequence of local time series fluctuation feature vectors of ammonia concentration into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector; Based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, a control instruction for the working frequency of the air purification equipment is generated.

2. The low-carbon ventilation system control method based on online air quality monitoring according to claim 1 is characterized in that: The time series feature extraction based on the local time scale is performed on the time series of the hydrogen sulfide concentration and the time series of the ammonia concentration to obtain a sequence of local time series fluctuation feature vectors of the hydrogen sulfide concentration and a sequence of local time series fluctuation feature vectors of the ammonia concentration, including: The time queue of hydrogen sulfide concentration and the time queue of ammonia concentration are segmented according to a predetermined time scale and then input into a sequence encoder based on a 1D-CNN model to obtain a sequence of local temporal fluctuation feature vectors of hydrogen sulfide concentration and a sequence of local temporal fluctuation feature vectors of ammonia concentration.

3. The low-carbon ventilation system control method based on online air quality monitoring according to claim 2 is characterized in that: Inputting the sequence of local time series fluctuation feature vectors of hydrogen sulfide concentration and the sequence of local time series fluctuation feature vectors of ammonia concentration into a feature aggregation network based on feature significance attenuation guidance to obtain a hydrogen sulfide concentration time series significant aggregation representation vector and an ammonia concentration time series significant aggregation representation vector, including: Calculating a characteristic significance description factor of each hydrogen sulfide concentration local time series fluctuation characteristic vector in the sequence of the hydrogen sulfide concentration local time series fluctuation characteristic vector, wherein the characteristic significance description factor is related to the mean and variance of each hydrogen sulfide concentration local time series fluctuation characteristic vector; Taking the last local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration as the current local time-series fluctuation feature vector of hydrogen sulfide concentration, and constructing the characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration based on the distance span between each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration and the current local time-series fluctuation feature vector of hydrogen sulfide concentration; Calculating the product of the characteristic significance attenuation factor of each local time series fluctuation characteristic vector of the hydrogen sulfide concentration and its characteristic significance description factor to obtain a sequence of characteristic significance attenuation description factors; Inputting the sequence of feature significance attenuation description factors into a gated mask module to obtain a sequence of feature significance attenuation weight factors; The sequence of the characteristic significance attenuation weight factors is used as the sequence of weights, and the weighted sum of the sequence of the local time series fluctuation characteristic vectors of the hydrogen sulfide concentration is calculated to obtain the hydrogen sulfide concentration time series significant aggregation representation vector.

4. The low-carbon ventilation system control method based on online air quality monitoring according to claim 3 is characterized in that: Calculating the characteristic significance description factor of each hydrogen sulfide concentration local time series fluctuation characteristic vector in the sequence of hydrogen sulfide concentration local time series fluctuation characteristic vectors includes: The expected value of the fourth power of the difference between each eigenvalue in the local time series fluctuation eigenvector of the hydrogen sulfide concentration and its eigenmean is calculated, and the expected value is divided by the square of the eigenvariance of the local time series fluctuation eigenvector of the hydrogen sulfide concentration to obtain the eigensignificance description factor.

5. The low-carbon ventilation system control method based on online air quality monitoring according to claim 4 is characterized in that: Based on the distance span between each local time-series fluctuation feature vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation feature vectors of hydrogen sulfide concentration and the current local time-series fluctuation feature vector of hydrogen sulfide concentration, constructing a characteristic significance attenuation factor of each local time-series fluctuation feature vector of hydrogen sulfide concentration, including: The difference between the maximum eigenvalue of the current local time-series fluctuation characteristic vector of hydrogen sulfide concentration and the maximum eigenvalue of each local time-series fluctuation characteristic vector of hydrogen sulfide concentration in the sequence of local time-series fluctuation characteristic vectors of hydrogen sulfide concentration is calculated, and then the difference is divided by the number of eigenvectors separated by the two to obtain the characteristic significance attenuation factor of each local time-series fluctuation characteristic vector of hydrogen sulfide concentration.

6. The low-carbon ventilation system control method based on online air quality monitoring according to claim 5 is characterized in that: Based on the principal component joint features of the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector, a control instruction for the working frequency of the air purification equipment is generated, including: Inputting the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector; The hydrogen sulfide concentration-ammonia concentration main component joint time series aggregation representation vector is input into a decoder-based air purification equipment control module to obtain the control instruction, and the control instruction is used to represent the recommended decoding value of the working frequency of the air purification equipment.

7. The low-carbon ventilation system control method based on online air quality monitoring according to claim 6 is characterized in that: Inputting the hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector into a significant fusion network based on feature principal component optimization matching to obtain a hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector, including: The hydrogen sulfide concentration time series significant aggregation representation vector and the ammonia concentration time series significant aggregation representation vector are normalized to obtain a normalized hydrogen sulfide concentration time series significant aggregation representation vector and a normalized ammonia concentration time series significant aggregation representation vector; Respectively calculating the sample covariance matrices of the standardized hydrogen sulfide concentration time series significant aggregation representation vector and the standardized ammonia concentration time series significant aggregation representation vector to obtain a hydrogen sulfide concentration sample covariance matrix and an ammonia concentration sample covariance matrix; Performing matrix decomposition-based eigenvector extraction on the hydrogen sulfide concentration sample covariance matrix and the ammonia concentration sample covariance matrix to obtain a set of hydrogen sulfide concentration time series principal component eigenvectors and a set of ammonia concentration time series principal component eigenvectors; Inputting the set of the hydrogen sulfide concentration time series principal component feature vectors and the set of the ammonia concentration time series principal component feature vectors into a maximum approximate query matching network to obtain a set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vectors and the ammonia concentration time series principal component feature vectors; Input each best matching pair in the set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector into a semantic fine-grained gating joint module to obtain a set of hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors; The set of the hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors is cascaded to obtain the hydrogen sulfide concentration-ammonia concentration principal component joint time series aggregation representation vector.

8. The low-carbon ventilation system control method based on online air quality monitoring according to claim 7 is characterized in that: Inputting the set of the hydrogen sulfide concentration time series principal component feature vectors and the set of the ammonia concentration time series principal component feature vectors into a maximum approximate query matching network to obtain a set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vectors and the ammonia concentration time series principal component feature vectors, including: Calculating the cosine similarity between the i-th hydrogen sulfide concentration time series principal component feature vector in the set of hydrogen sulfide concentration time series principal component feature vectors and each ammonia concentration time series principal component feature vector in the set of ammonia concentration time series principal component feature vectors to obtain a set of cosine similarities; The ammonia concentration time series principal component feature vector corresponding to the maximum value in the set of cosine similarities and the i-th hydrogen sulfide concentration time series principal component feature vector form the best matching pair.

9. The low-carbon ventilation system control method based on online air quality monitoring according to claim 8 is characterized in that: Inputting each best matching pair in the set of best matching pairs of the hydrogen sulfide concentration time series principal component feature vector and the ammonia concentration time series principal component feature vector into a semantic fine-grained gating joint module to obtain a set of hydrogen sulfide concentration-ammonia concentration principal component joint feature vectors, including: Calculate the position point addition, position point subtraction and position point multiplication between the hydrogen sulfide concentration time series principal component eigenvector and the ammonia concentration time series principal component eigenvector in the best matching pair to obtain a first matching fusion result, a second matching fusion result and a third matching fusion result; After the first matching fusion result, the second matching fusion result and the third matching fusion result are cascaded into a multi-scale fusion feature vector of the hydrogen sulfide concentration-ammonia concentration main component, one-dimensional convolution processing and maximum pooling processing are performed on them to obtain the hydrogen sulfide concentration-ammonia concentration main component joint feature vector.

Images