Air self-adaptive purification control method and device, terminal equipment and storage medium

Abstract

The invention is applicable to the technical field of data processing, and provides an air adaptive purification control method and device, terminal equipment and a storage medium, and the method realizes dynamic adaptive power adjustment by constructing a pollution gas coupling kinetic model. A historical concentration mean value, a nonlinear response mechanism and periodic change characteristic parameters are introduced into the model, low power can be kept in low pollution, the purification efficiency can be rapidly improved in high pollution, the pollution trend can be pre-judged, the power can be adjusted in advance, and energy waste is avoided. The multi-pollutant synergistic effect is considered, interaction of different gases is treated in a cross term mode, the purification priority is distributed according to hazard index differentiation, and energy consumption generated by excessive treatment of low-hazard pollutants is reduced. According to the method, dual-mode switching is achieved in combination with hazard index comparison, dynamic balance of energy consumption and the purification effect is achieved while the purification effect is guaranteed, compared with a traditional linear control and single pollutant treatment mode, energy consumption control is more intelligent and efficient, and energy consumption of the air purification system can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an air adaptive purification control method, apparatus, terminal device and storage medium. Background Art

[0002] Funeral homes are generally divided into body processing areas such as cremation workshops, cosmetic rooms, embalming rooms, and cold storage rooms. Each area will produce pollutant gases such as NH3, CO, TVOC, NO2, and SO2 during use. Currently, the concentration of pollutants is generally monitored by single-point electrochemical sensors. When the concentration of pollutants reaches the threshold, the air purification system is controlled by the PID control method to purify the air so that the air quality reaches normal standards. In order to quickly reduce the concentration of pollutants, the ion generator is generally controlled to run at a higher power, resulting in high energy consumption of the air purification system. Summary of the Invention

[0003] The embodiments of the present application provide an air adaptive purification control method, apparatus, terminal device and storage medium, which can solve the technical problem in the prior art that during the air purification process of a funeral home, the ion generator operates at a high power, resulting in high energy consumption of the air purification system.

[0004] In a first aspect, an embodiment of the present application provides an air adaptive purification control method, comprising:

[0005] Obtaining gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are obtained by monitoring with target sensors;

[0006] According to the gas concentration, the pollutant hazard index of the polluted gas is calculated by an index formula, and the index formula is:

[0007]

[0008] Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases;

[0009] When the pollutant hazard index is greater than a preset hazard value, the operating power of the air purification system is determined according to the gas concentration by a pollutant gas coupling dynamics model, where the pollutant gas coupling dynamics model is:

[0010]

[0011] Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas;

[0012] controlling the operation of the air purification system according to the operating power;

[0013] When the pollutant hazard index is less than or equal to the preset hazard value, the air purification system is controlled to operate in a low power mode.

[0014] Obtaining gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are obtained by monitoring with target sensors;

[0015] According to the gas concentration, the pollutant hazard index of the polluted gas is calculated by an index formula, and the index formula is:

[0016]

[0017] Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases;

[0018] When the pollutant hazard index is greater than a preset hazard value, the operating power of the air purification system is determined according to the gas concentration by a pollutant gas coupling dynamics model, where the pollutant gas coupling dynamics model is:

[0019]

[0020] Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; β i is the impact index of the i-th pollutant gas;

[0021] controlling the operation of the air purification system according to the operating power;

[0022] When the pollutant hazard index is less than or equal to the preset hazard value, the air purification system is controlled to operate in a low power mode.

[0023] Furthermore, when the pollutant hazard index is less than or equal to the preset hazard value, before controlling the air purification system to operate in a low power mode, the method further includes:

[0024] Determining basic hazard thresholds of the multiple pollutant gases based on safe concentration limits of the multiple pollutant gases in the confined space;

[0025] Determine an environmental correction factor based on the average space area of ​​each area of ​​the funeral home, the current space area, the actual ventilation volume of the current area, and the quasi-ventilation volume of the other side;

[0026] Obtaining historical data of people entering the funeral home;

[0027] Classify the crowd according to the historical data of people entering the crowd, and obtain the number of crowd classifications;

[0028] Determine the weight ratio of each group of people based on the historical data of incoming personnel;

[0029] Determine a personnel tolerance correction coefficient based on the number of population categories, the weight ratio of each population category, and the average tolerance index of each population category;

[0030] Determining an initial set hazard value according to the basic hazard threshold, the environmental correction factor, and the human tolerance correction factor;

[0031] Obtaining an average pollutant hazard index within a preset historical period in the funeral home;

[0032] Determining an adjustment coefficient based on the initially set hazard value and the average pollutant hazard index;

[0033] The preset hazard value is determined according to the adjustment coefficient and the initially set hazard value.

[0034] Furthermore, controlling the operation of the air purification system according to the operating power includes:

[0035] Dividing the air purification system into a preset number of purification modules, where the number of purification modules is equal to the amount of polluted gases;

[0036] According to the gas concentrations of the multiple pollutant gases and the corresponding hazard weights, the operating power of each purification module is calculated using the module power formula, which is:

[0037]

[0038] Where, P mi is the operating power of the i-th purification module; P base is the basic power; H0 is the set hazard value; δ j is the hazard weight of the jth type of pollutant gas; C j is the gas concentration of the jth pollutant gas;

[0039] Performing preliminary control on the operating power of each purification module according to the operating power of each purification module;

[0040] Real-time monitoring of the current processing efficiency of each purification module;

[0041] Determining the pre-adjusted power of each purification module according to the current processing efficiency, the preset standard processing efficiency and the power adjustment coefficient;

[0042] The operating power of each purification module is adjusted according to the pre-adjusted power of each purification module.

[0043] Furthermore, before obtaining the gas concentrations of the multiple pollutant gases in the funeral home, the method further includes:

[0044] Defining typical work scenes in the funeral home to obtain a typical work scene set, each scene in the typical work scene set includes a gas concentration feature vector, a personnel activity feature vector, and a time feature vector;

[0045] Calculating the similarity between the current environment feature vector and each scene in the typical work scene set through a scene recognition model;

[0046] Determining the scene type of the current scene based on the similarities of the scenes;

[0047] According to the scenario type, a target operating mode is selected from a preset sensor operating mode library;

[0048] The target sensor is controlled to operate in the target operating mode.

[0049] Furthermore, obtaining the gas concentrations of multiple pollutants in the funeral home includes:

[0050] Obtaining initial gas concentration data of multiple pollutant gases in the funeral home;

[0051] For any initial gas concentration data, extract the integrity score, mutation score, deviation score and consistency score of the initial gas concentration data;

[0052] The quality score of the initial gas concentration data is calculated using a scoring formula according to the integrity score, mutation score, deviation score and consistency score;

[0053] In a case where the mass score is greater than a preset mass score, the initial gas concentration data is used as the gas concentration of the corresponding polluted gas.

[0054] Furthermore, for any initial gas concentration data, extracting the integrity score, mutation score, deviation score and consistency score of the initial gas concentration data includes:

[0055] For any initial gas concentration data, calculating the concentration change rate according to other adjacent concentrations in the initial gas concentration data;

[0056] Determining an average concentration change rate and a standard deviation of the change rate based on the concentration change rate;

[0057] Determine a dynamic threshold value based on a preset basic threshold value, a first threshold value adjustment coefficient, a second threshold value adjustment coefficient, an average concentration change rate, and a standard deviation of the change rate;

[0058] Obtaining the number of mutations at which the concentration change rate exceeds the dynamic threshold;

[0059] The mutation score of the initial gas concentration data is calculated according to the number of mutations, the number of gas concentrations in the initial gas concentration data, the concentration change rate, and the standard deviation of the change rate using a mutation score formula. The mutation score formula is:

[0060]

[0061] Where S is the mutation score; N e is the number of mutations; N r is the number of gas concentrations; is the average concentration change rate; σR is the standard deviation of the change rate.

[0062] Furthermore, after obtaining the gas concentrations of the multiple pollutant gases in the funeral home, the method further includes:

[0063] For any pollutant gas, the concentration change rate at adjacent moments is calculated based on the gas concentration;

[0064] Obtaining the number of mutations in which the concentration change rate is greater than a preset mutation threshold within a preset time period;

[0065] When the number of mutations is greater than a preset number threshold, the mutation intensity index is calculated using the mutation intensity formula according to the concentration change rate, the hazard weight, and the preset mutation threshold. The mutation intensity formula is:

[0066]

[0067] Where, I mis the mutation intensity; δ i is the hazard weight of the i-th pollutant gas; Rc i (t) is the concentration change rate; θ i is the preset mutation threshold;

[0068] Obtaining the equivalent heights of the multiple pollutant gases and the total amount of pollutants emitted from the pollution sources into the environment per unit time;

[0069] Determining diffusion trend prediction results of the multiple pollutant gases based on the equivalent height and the total amount of pollutants;

[0070] According to the mutation intensity index and the diffusion trend prediction result, the power lead control amount is calculated by an adjustment formula, and the adjustment formula is:

[0071]

[0072] Where ΔP is the power advance control amount; k1 is the first control coefficient; k2 is the second control coefficient; A is the diffusion trend prediction result;

[0073] determining a target control power according to the power advance control amount and the operating power;

[0074] The air purification system is controlled to operate according to the target control power.

[0075] In a second aspect, an embodiment of the present application provides an air adaptive purification control device, comprising:

[0076] An acquisition module is used to acquire the gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are acquired through monitoring by target sensors;

[0077] A calculation module is used to calculate the pollutant hazard index of the polluted gas according to the gas concentration using an exponential formula, where the exponential formula is:

[0078]

[0079] Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases;

[0080] A determination module is configured to determine the operating power of the air purification system according to the gas concentration using a pollutant gas coupling dynamics model when the pollutant hazard index is greater than a preset hazard value. The pollutant gas coupling dynamics model is:

[0081]

[0082] Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas;

[0083] a control module, configured to control the operation of the air purification system according to the operating power;

[0084] The control module is further configured to control the air purification system to operate in a low power mode when the pollutant hazard index is less than or equal to the preset hazard value.

[0085] In a third aspect, an embodiment of the present application provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of the first aspect above when executing the computer program.

[0086] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method of the first aspect above is implemented.

[0087] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0088] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: by constructing a coupled kinetic model of polluted gases, dynamic adaptive power regulation is achieved. In addition, the historical concentration mean, nonlinear response mechanism and periodic change characteristic parameters are introduced into the model, which can maintain low power when pollution is low and quickly improve purification efficiency when pollution is high. It can also predict pollution trends and adjust power in advance to avoid energy waste. On the other hand, the synergistic effect of multiple pollutants is taken into account, the cross-term is used to process the interaction between different gases, and the purification priority is differentiated according to the hazard index, thereby reducing the energy consumption caused by excessive treatment of low-hazard pollutants. Dual-mode switching is achieved by combining the hazard index comparison, which ensures the purification effect while achieving a dynamic balance between energy consumption and purification effect. Compared with traditional linear control and single pollutant treatment methods, energy consumption control is more intelligent and efficient, and can effectively reduce the energy consumption of the air purification system. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0090] Figure 1 This is a flowchart of the implementation of the first embodiment of an air adaptive purification control method provided by the embodiment of the present application;

[0091] Figure 2 This is a flowchart of the second embodiment of the air adaptive purification control method provided in the embodiment of the present application;

[0092] Figure 3 This is a structural block diagram of an air adaptive purification control device provided in an embodiment of the present application;

[0093] Figure 4 This is a structural block diagram of an air adaptive purification control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0094] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0095] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0096] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0097] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0098] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0099] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0100] See also Figure 1 , Figure 1 The following is a flowchart illustrating an implementation of a first embodiment of an adaptive air purification control method provided by an embodiment of the present application, including:

[0101] Step S10: Obtaining gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are obtained by monitoring with target sensors.

[0102] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, or an electronic device capable of implementing the above functions, an adaptive air purification control device, a computer, a tablet computer, etc. The following uses the adaptive air purification control device as an example to illustrate this embodiment and the following embodiments.

[0103] It is understood that pollutant gases include toxic, irritating, or odorous gases such as ammonia (NH3), carbon monoxide (CO), total volatile organic compounds (TVOC), nitrogen dioxide (NO2), and sulfur dioxide (SO2). The target sensor can be a sensor using a multi-spectral gas detection module. This sensor detects the concentrations of gases such as NH3, TVOC, SO2, NO2, and CO by reacting with the gas being measured and generating an electrical signal detection technology that is proportional to the gas concentration. The resolution of NH3 is 1ppm, the resolution of TVOC is 0.1ppb, the resolution of SO2 is 0.1ppm, the resolution of NO2 is 0.1ppm, and the resolution of CO is 1ppm.

[0104] Step S20: Calculate the pollutant hazard index of the polluted gas using an index formula based on the gas concentration. The index formula is:

[0105]

[0106] Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases;

[0107] It is understood that the pollutant hazard index can be a quantitative indicator that combines the concentration of pollutants and their degree of hazard, used to reflect the level of harm the pollutants pose to the environment and personnel. The hazard weight of the pollutants can be a preset weight based on the toxicity, irritation, and other characteristics of the gas (e.g., CO has a higher hazard weight than TVOC).

[0108] Step S30: When the pollutant hazard index is greater than a preset hazard value, the operating power of the air purification system is determined according to the gas concentration through a pollutant gas coupled dynamics model.

[0109] The polluted gas coupled dynamics model is:

[0110]

[0111] Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas;

[0112] It is understood that the preset hazard value can be a pre-set critical value used to determine whether high-power purification is necessary. The polluted gas coupled kinetic model can be a mathematical model that describes the relationship between polluted gas concentration and purification system power. The model adjustment coefficient can be a constant pre-set according to different scenarios, used to balance the power output under different pollution scenarios. The impact index of the polluted gas can be a value set according to the degree of hazard of the gas, with a larger impact index indicating a higher degree of hazard of the polluted gas. The historical concentration average is used to reflect the normal pollution level of the gas.

[0113] Step S40: controlling the operation of the air purification system according to the operating power.

[0114] Step S50: When the pollutant hazard index is less than or equal to the preset hazard value, controlling the air purification system to operate in a low power mode.

[0115] In one example, the target sensor collects the concentration of polluted gases in various areas of a funeral home in real time (e.g., once every 10 seconds) to form a real-time data sequence. Based on the gas concentration, the pollutant hazard index is calculated using an exponential formula. For example, if the preset hazard value is 1 and the CO concentration is 50 ppm (δ i =0.8), NH3 concentration is 30ppm (δ i =0.6), then max = 50ppm, H = (0.8×50+0.6×30) / 50 = 1.24. When the pollutant hazard index is greater than the preset hazard value, the operating power is calculated using the pollutant gas coupled kinetic model. The numerator in the formula highlights the impact of highly hazardous gases (for example, when the CO concentration is much higher than the average, The term increases, pushing up the operating power. For example, if the CO concentration suddenly changes to 100ppm (far exceeding the average of 50ppm), the model quickly increases the power through the exponential term and the Gaussian penalty term, giving priority to treating highly toxic gases. If the pollutant hazard index is less than the preset hazard value, the control system operates at the basic power, maintaining the minimum purification demand only for the main pollutant gases, and reducing energy consumption by about 30%-50%. System control and feedback: Adjust the power of the purification module according to the calculated operating power. For example, the power of the ion generator is directly proportional to the operating power. Monitor the purification effect in real time (such as the gas concentration at the outlet), dynamically fine-tune the model parameters, and form a closed-loop control.

[0116] It should be noted that this embodiment differs from the linear response of traditional single-point sensors and PID control. This solution uses nonlinear formulas and historical data references to accurately match pollution dynamics, avoiding over-purification or delayed response. It also intelligently switches modes based on the hazard index, significantly reducing energy consumption while ensuring safety. This is particularly suitable for funeral homes, where pollution fluctuates intermittently. The data processing in this embodiment can be performed by edge servers.

[0117] In one example, an adaptive air purification control device obtains the gas concentrations of various pollutants within a funeral home and sends these concentrations to an edge server. The edge server calculates the pollutant hazard index based on the gas concentrations using a preset exponential formula. If the pollutant hazard index exceeds a preset hazard value, the edge server calculates the operating power of the air purification system based on the gas concentrations using a preset coupled kinetic model of polluted gases. The adaptive air purification control device controls the operation of the air purification system based on the operating power. When the pollutant hazard value is less than or equal to the preset hazard value, the adaptive air purification control device controls the air purification system to operate in low-power mode.

[0118] It is understandable that the advantages of using the polluted gas coupled dynamic model to calculate the operating power in this embodiment are as follows: and summation terms Quantify the coupling relationship between the concentration of different polluting gases and the historical average to avoid the limitations of independent treatment of a single pollutant. For example, when multiple gases exceed the standard at the same time, the model amplifies the total power demand through the exponential superposition effect to improve the overall purification efficiency, rather than simply linear superposition. By affecting the index and model adjustment coefficient, the power output is made more sensitive to changes in the concentration of highly hazardous gases (such as highly toxic CO). For example, when the concentration of a gas exceeds the historical average, The term grows exponentially, driving the system to increase power quickly and avoiding the lag of linear control. The Gaussian penalty term is introduced: Quantify the current concentration distribution and historical fluctuations (standard deviation σ i) deviation, apply additional power compensation for sudden pollution (such as concentration mutation), and suppress excessive response to regular fluctuations, balancing energy consumption and purification effect. Using the historical concentration mean as a benchmark, the model adapts to the regular pollution level in each area of ​​the funeral home (such as the crematorium's normal CO concentration is higher), avoiding misjudgment caused by a unified threshold. For example, if the historical mean of TVOC in a certain area is low, even if it occasionally exceeds the standard, the model will pass Calibration to avoid excessive power fluctuations. Through the optimization of coefficients such as α, γ, and λ based on historical data, the model automatically learns the pollution patterns of different time periods (such as cremation peak / off-peak periods), dynamically adjusts the power output strategy, and improves long-term adaptability. When the concentrations of all gases are close to the historical mean, the fractional terms in the formula approach the equilibrium state, and the power output maintains the basic level (controlled by α and γ) to avoid "over-purification". For example, when pollution is lower during non-cremation periods, the system runs at low power and energy consumption can be reduced by more than 40%. Through the synergistic effect of the coupling term and the Gaussian penalty term, the system prioritizes high-hazard gases (β i The system allocates power to the larger one instead of fully activating all modules, thus reducing invalid energy consumption while ensuring the purification effect.

[0119] In some optional implementations, before step S50, it also includes: determining the basic hazard threshold of the multiple pollutants based on the safety concentration limits of the multiple pollutants in the confined space; determining the environmental correction coefficient based on the average space area of ​​each area of ​​the funeral home, the current space area, the actual ventilation volume of the current area and the quasi-ventilation volume on the other side; obtaining the historical data of people entering the funeral home; classifying the crowd according to the historical data of people entering to obtain the number of crowd categories; determining the weight ratio of each category of people according to the historical data of people entering; determining the personnel tolerance correction coefficient according to the number of crowd categories, the weight ratio of each category of people and the average tolerance index of each category of people; determining the initial set hazard value according to the basic hazard threshold, the environmental correction coefficient and the personnel tolerance correction coefficient; obtaining the average pollutant hazard index within a preset historical time in the funeral home; determining the adjustment coefficient according to the initial set hazard value and the average pollutant hazard index; determining the preset hazard value according to the adjustment coefficient and the initial set hazard value.

[0120] It is understandable that the preset hazard value can be the critical value for judging whether the air purification system needs to operate at high power, and is dynamically adjusted through the basic hazard threshold, environmental correction factor, and personnel tolerance correction factor. The formula is H0=H 0-init ×ΔK. Basic hazard threshold H base is the initial hazard limit based on industry safety standards, and the formula is CL iis the actual safe concentration limit of the i-th pollutant gas in the funeral home environment (for example, the actual safe value of NH3 needs to take into account the length of time people stay). i The environmental correction factor K is the general standard safety concentration limit of the gas (such as the confined space safety value specified by WHO or national standards). env The formula to reflect the impact of environmental differences in different areas of funeral homes on hazard assessment is: V avg V is the average space volume of each area of ​​the funeral home (such as the average volume of the cremation workshop and the embalming room). area V is the spatial volume of the current area (such as the actual volume of the anti-corrosion room). vent The actual ventilation volume of the current area (unit: m 3 / h). V vent-std is the standard ventilation volume (the benchmark ventilation efficiency specified by the industry). Historical data on personnel entering the funeral home include the age, health status, length of stay, and other data of the staff (such as cremators, embalmers) and occasional entrants (such as family members), which are used for crowd tolerance assessment. The number of crowd classifications (q) is the total number of people classified according to age and health status (such as sensitive groups and general populations), for example, divided into 3 categories: staff (long-term contact), elderly family members, and general visitors. Weight ratio (W j )) is the flow rate ratio of the jth group of people in the funeral home (e.g. staff account for 20% and visitors account for 80%). Average tolerance index (T j ) is the quantitative value of the tolerance of the jth group of people to polluted gases determined through medical evaluation (the higher the value, the stronger the tolerance. For example, due to long-term adaptation, the tolerance index of staff is higher than that of ordinary visitors). Personnel tolerance correction factor K per is the weighted coefficient of comprehensive population tolerance difference, and the formula is Initial setting of hazard value (H 0-init ) is the preliminary threshold value combining the basic hazard threshold and the environmental and population correction coefficients, and the formula is H 0-init =H base ×K env ×K per Average pollutant hazard index is the average value of pollution hazards within a preset historical period (such as the past 30 days), and the formula is Reflects the long-term pollution level. The adjustment coefficient (ΔK) is a dynamic factor that adjusts the threshold according to the real-time pollution trend. The formula is η is the adjustment sensitivity coefficient, which is used to control the threshold adjustment amplitude.

[0121] In one example, industry safety standards for each pollutant gas (such as SL for NH i =25ppm, SL of CO i=50ppm and the actual safety limit of the funeral home (such as the CL of NH in the antiseptic room i =20ppm, due to the long stay time of personnel). Through the formula Calculation, for example, when there are 2 gases: Measure the volume of the current area (such as cremation workshop V area =500m 3 ), average regional volume (V avg =300m 3 ), actual ventilation volume (V vent =1000m 3 / h) and standard ventilation volume (V vent-std =800m 3 / h). The environmental correction factor is calculated by the formula: Classify the crowd (q=2) into categories (staff, visitors), weight ratio W1=0.3, W2=0.7, tolerance index T1=0.8, T2=0.5. Calculate the personnel tolerance correction coefficient by the formula H 0-init =1.6×0.9375×0.59≈0.88. Average hazard index collection and adjustment statistics for the past 30 days The default value is η = 0.5, The final preset hazard value H0 = 0.88 × 1.068 ≈ .94.

[0122] It should be noted that this embodiment uses the environment (volume, ventilation), population (tolerance difference), historical trends Triple correction makes the preset hazard value more suitable for the actual scenario. For example, the hazard value of poorly ventilated areas is automatically reduced to trigger high-power purification in advance. The threshold is self-updated through ΔK. When the long-term pollution level rises (such as ), automatically lowering the preset hazard value to maintain purification intensity and avoid threshold failure due to environmental changes.

[0123] In some optional implementations, step S40 may be implemented by dividing the air purification system into a preset number of purification modules, where the number of purification modules is equal to the number of polluted gases; and calculating the operating power of each purification module using a module power formula based on the gas concentrations of the multiple polluting gases and the corresponding hazard weights, where the module power formula is:

[0124]

[0125] Where, P mi is the operating power of the i-th purification module; P base is the basic power; H0 is the set hazard value; δ j is the hazard weight of the jth type of pollutant gas; Cj is the gas concentration of the jth type of pollutant gas; based on the operating power of each purification module, the operating power of each purification module is preliminarily controlled; the current processing efficiency of each purification module is monitored in real time; based on the current processing efficiency, the preset standard processing efficiency and the power adjustment coefficient, the pre-adjusted power of each purification module is determined; and based on the pre-adjusted power of each purification module, the operating power of each purification module is adjusted.

[0126] It is understandable that the air purification system can be an integrated device composed of multiple independent purification modules, each module is designed for a specific pollutant gas (such as an activated carbon module to treat TVOC, a catalytic oxidation module to treat CO), and the power can be adjusted independently. The number of modules is equal to the number of pollutant gas types (such as monitoring 5 gases, it is divided into 5 modules), to achieve "one-to-one" targeted purification. The current processing efficiency is the amount of pollutants removed per unit time by each purification module (such as the mass of CO treated by a module per hour), which is monitored in real time by sensors (such as calculation of the difference in air outlet concentration). The preset standard processing efficiency is the theoretical processing efficiency of the module under the design conditions, which serves as the efficiency evaluation benchmark. The power adjustment coefficient can be a parameter used to adjust the power compensation amplitude (such as ξ = 0.5 means that the power is adjusted by 5% for every 10% deviation in efficiency). The pre-adjusted power can be a temporary power value calculated based on the efficiency deviation, and the formula is Where ΔE is the difference between the current efficiency and the standard efficiency.

[0127] In one example, the air purification system is divided into n modules (e.g., n=3, corresponding to CO, NH, and TVOC), and each module has an initialization power P base (e.g. 15kW). Real-time acquisition of gas concentrations (e.g. CO = 80ppm, δ i =0.9); NH3 = 40ppm, δ i =0.7), calculate the total hazard weighted concentration and ∑δ j C j =0.9×80+0.7×40=72+28=100.

[0128] Calculating CO module power (Assuming H = 1.2, H0 = 1.0, and a 20% power increase in priority purification mode) Initial control and efficiency monitoring start the module according to the calculated power (e.g., 12.96kW for the CO module and 5.04kW for the NH3 module). Real-time monitoring of module processing efficiency. For example, if the current efficiency of the CO module is 90mg / h and the standard efficiency is 100mg / h, then ΔE = -10mg / h. Power adjustment is calculated based on the pre-adjusted power according to the efficiency deviation: Adjust the module power to 12.312kW to form a closed-loop feedback.

[0129] It should be noted that the advantages of using the module power formula are as follows: (1) Accurate allocation of hazard priorities: Item, so that the modules corresponding to high-hazard and high-concentration gases can obtain higher power. For example, when the CO concentration is high and the hazard weight is high, its module power share can reach more than 70%, ensuring priority treatment of lethal gases, which is better than the traditional "equal power distribution" or "single module full open" mode. (2) Purification priority mode: When H>H0, through The power is increased by 50% when H exceeds 50% of H0, and the response speed is more than 30% faster than the fixed power mode. Energy consumption priority mode (H≤H0): Automatically remove the power of low-hazard gas modules (such as is a negative value or zero), only necessary purification is maintained, and energy consumption can be reduced by 40%-60%. (3) Each module is adjusted independently to avoid the chain reaction of "one rise and all rise, one fall and all fall". For example, when the TVOC concentration meets the standard, its corresponding module can be reduced to the lowest power, while other modules that exceed the standard maintain high power operation, thereby improving the flexibility of the system. Efficiency feedback optimization ensures that the module always operates in the high efficiency range through real-time efficiency monitoring and power adjustment. Experimental data show that this closed-loop control can increase the average treatment efficiency by 15%-20%, avoiding the decline in purification capacity due to equipment aging or load changes. Scalability and maintainability When adding new pollutants, only the corresponding modules need to be added and the formula parameters updated, without the need to reconstruct the entire system. At the same time, the failure of an independent module does not affect the operation of other modules, and the maintenance cost is reduced by about 30%. (4) Differences from existing technologies Existing technologies mostly use unified power control or simple group control, which cannot accurately match the real-time needs of a single pollutant.

[0130] In some optional implementations, before step S10, it also includes: defining typical work scenes in the funeral home to obtain a typical work scene set, each scene in the typical work scene set contains a gas concentration feature vector, a personnel activity feature vector and a time feature vector; calculating the similarity between the current environment feature vector and each scene in the typical work scene set through a scene recognition model; determining the scene type of the current scene based on the similarity of each scene; selecting a target working mode from a preset sensor working mode library based on the scene type; and controlling the operation of the target sensor through the target working mode.

[0131] It is understandable that the typical work scene set can be a pre-defined set of representative environmental patterns in a funeral home, and each scene contains the following features: Gas concentration feature vector: the concentration distribution pattern of common pollutant gases in the scene (such as high CO and high NH3 concentrations in the cremation workshop). Personnel activity feature vector: the intensity and type of personnel activities in the scene (such as frequent operations of staff during the cremation period and occasional visitors during the non-cremation period). Time feature vector: the time pattern of the scene (such as 9:00-11:00 every day is the cremation peak period, and 14:00-16:00 is the embalming period). Example: S = {S1 (cremation scene), S2 (embalming scene), S3 (low-peak scene)}. Current environment feature vector (E): a combination of environmental data collected in real time, including C E : The current real-time concentration value of each pollutant gas. E : The activity status of people in the current area (such as the movement frequency of people detected by infrared sensors). E : Current time (such as specific time, date type (weekday / weekend)). The scene recognition model can be an algorithm model used to determine what typical scene the current environment belongs to. It uses an improved K-nearest neighbor (KNN) algorithm to calculate the similarity between the current environment feature vector and each typical scene to determine the most matching scene type. Similarity Sim (S i , E) can be a quantitative indicator to measure the degree of match between the current environment and the typical scene. The higher the value, the higher the match. For example, when the high CO concentration in the cremation scene matches the currently detected high CO concentration, the similarity can reach above 0.9. The preset sensor working mode library (M) can be a set of pre-configured sensor working modes, each mode including: Sampling frequency (f): the interval at which the sensor collects data (such as high-frequency sampling in the cremation scene: once every 5 seconds; low-frequency sampling in the low-peak scene: once every 30 seconds). Sampling duration (t s ): Duration of each sampling (e.g., in fast response mode, the sampling time is extended to 2 seconds to ensure data stability). Sleep period (t d ): The sensor's sleep time between sampling cycles (extending the sleep period in off-peak scenarios to save power). Example: M = {M1 (high-frequency mode), M2 (medium-frequency mode), M3 (low-frequency mode)}, corresponding to cremation, embalming, and off-peak scenarios, respectively. Target sensors can be electrochemical sensors deployed in various areas of a funeral home to perform specific pollutant gas concentration collection tasks, such as CO sensors and NH sensors.

[0132] In one example, three typical scenarios are defined: Cremation scenario (S1): The time is from 9:00 to 11:00 on weekdays, characterized by high CO > 100 ppm, NH3 > 50 ppm, and frequent personnel activities. Embalming scenario (S2): The time is from 13:00 to 17:00 on weekdays, characterized by TVOC > 800 μg / m 3 , NH3 is between 30-50ppm, and personnel operations are intensive. Low-peak scenario (S3): The time is non-cremation period (such as nighttime), characterized by the concentration of each gas close to the background value, and very few personnel activities. Construct a feature vector for each scenario, such as the gas concentration feature of S1 is [150ppm (CO), 60ppm (NH3), 300μg / m 3 (TVOC)]. Real-time acquisition of current environmental data through sensors: CO = 120ppm, NH3 = 55ppm, TVOC = 280μg / m 3 . H E The personnel movement frequency is 10 times / minute (detected by infrared sensor). E : Monday morning at 10:00 (belongs to the cremation period on weekdays). Scene recognition and similarity calculation uses the improved KNN algorithm to calculate the similarity between the current environment and each typical scene: Sim(S1, E) = 0.92 (high CO and high NH3 match the cremation scene). Sim(S2, E) = 0.45 (low TVOC concentration does not match the anti-corrosion scene). Sim(S3, E) = 0.18 (frequent personnel activities, excluding low-peak scenes). The current scene is determined to be S1 (cremation scene). Working mode matching and sensor control Based on the scene recognition results, the corresponding mode M1 (high-frequency mode) is selected from the mode library: the sampling frequency is 5 seconds / time to ensure timely capture of pollution mutations during the cremation process. The sampling time is 1.5 seconds, and the average of multiple groups of samples is used to reduce noise. The sleep period is 3 seconds (sleep most of the time during the sampling interval to reduce power consumption). Send a command to the target sensor to start M1 mode.

[0133] It should be noted that existing sensors typically sample at a fixed frequency (e.g., every 10 seconds), which is inadequate for the fluctuating pollution patterns of funeral homes, with high pollution levels during peak periods and low pollution levels during off-peak periods. This solution dynamically adjusts the sampling strategy through scenario recognition: high-frequency sampling during cremation events avoids missing sudden pollution spikes; low-frequency sampling during off-peak events reduces sensor energy consumption by over 60%. Multi-dimensional feature fusion combines gas concentration, human activity, and time to avoid single-dimensional misjudgment. For example, if a cremation event is identified based solely on time, but actual gas concentration is not elevated (e.g., due to a temporary equipment shutdown), the system will exclude cremation scenarios based on concentration features, preventing ineffective high-frequency sensor operation. The flexibility of the predefined pattern library allows for expansion of scenario types based on the specific business processes of funeral homes (e.g., adding a "body handling scenario"). By updating feature vectors and operating modes, new requirements can be quickly adapted without requiring hardware modifications. Sensor power consumption in off-peak events is reduced from 5W in the fixed mode to below 2W, saving approximately 4,000 kWh of electricity annually. Improved data effectiveness: The delay in detecting sudden pollution changes in high-frequency mode has been reduced from 10 seconds to within 5 seconds, and the missed collection rate of key data has been reduced from 15% to below 3%. Simplified maintenance: Automatic scene matching reduces manual intervention, and the sensor calibration cycle has been extended from once a month to once a quarter.

[0134] The method provided in this embodiment realizes dynamic adaptive power regulation by constructing a coupled kinetic model of polluted gases. In addition, the historical concentration mean, nonlinear response mechanism and periodic change characteristic parameters are introduced into the model, which can maintain low power when pollution is low and quickly improve purification efficiency when pollution is high. It can also predict pollution trends and adjust power in advance to avoid energy waste. On the other hand, the synergistic effect of multiple pollutants is taken into account, the cross-term is used to process the interaction between different gases, and the purification priority is differentiated according to the hazard index to reduce the energy consumption caused by excessive treatment of low-hazard pollutants. Dual-mode switching is achieved by combining the comparison of hazard indices, which achieves a dynamic balance between energy consumption and purification effect while ensuring the purification effect. Compared with traditional linear control and single pollutant treatment methods, energy consumption control is more intelligent and efficient, and can effectively reduce the energy consumption of the air purification system.

[0135] In the optional implementation of each embodiment of the present application, before the above step S10, the following steps S01-S04 may also be included. Figure 2 This is a flowchart for implementing the second embodiment of the air adaptive purification control method provided in an embodiment of the present application.

[0136] Step S01: Acquire initial gas concentration data of various pollutant gases in the funeral home.

[0137] It is understandable that the initial gas concentration data may be the original polluted gas concentration values ​​(such as CO concentration of 50 ppm and NH3 concentration of 30 ppm) collected in real time by sensors deployed in the funeral home, which may contain noise, outliers or missing values.

[0138] Step S02: for any initial gas concentration data, extract the integrity score, mutation score, deviation score and consistency score of the initial gas concentration data.

[0139] It is understandable that the completeness score can be an indicator for evaluating whether there are missing data. For example, if 60 samples should be collected within an hour (1 sample per minute) and 58 samples are actually collected, the integrity score is 96.7%. The mutation score can be used to detect whether there are unreasonable and drastic fluctuations in the data. The deviation score can be used to evaluate the degree of deviation of the data from the historical trend, which is obtained by calculating the relative deviation between the current value and the historical mean. For example, if the historical mean CO2 value in a certain area is 40ppm, the standard deviation is 5ppm, and the current value is 60ppm, then the relative deviation is 4 standard deviations, and the deviation score is reduced. The consistency score can be used to verify the logical consistency of data from different sensors in the same area or between different areas. The formula is: For example, the CO concentration in adjacent areas should change in a gradient. If the data from a certain sensor differs from the surrounding area by more than 50%, it is judged to be inconsistent.

[0140] Step S03: According to the integrity score, mutation score, deviation score and consistency score, a quality score of the initial gas concentration data is calculated using a scoring formula.

[0141] It can be understood that the quality score can be a comprehensive scoring result of the above four dimensions, obtained by weighted summation, and the calculation formula is: quality score = w1×integrity score + w2×mutation score + w3×deviation score + w4×consistency score, where w1, w2, w3, and w4 are preset weights.

[0142] Step S04: When the mass score is greater than a preset mass score, the initial gas concentration data is used as the gas concentration of the corresponding polluted gas.

[0143] It should be noted that this embodiment has the following advantages: (1) Comprehensively evaluate data quality from four dimensions: integrity, mutation, deviation, and consistency, to avoid missing anomalies from a single indicator (e.g., only detecting mutations may ignore long-term data drift). (2) The thresholds of each scoring dimension can be dynamically adjusted according to the actual environmental characteristics of the funeral home (e.g., the mutation threshold of the cremation workshop can be higher than that of the office area), thereby improving adaptability. (3) Through quality screening, the error rate of sensor data is reduced from 15% of the traditional method to below 3%, significantly improving the accuracy of purification system control. (4) When the quality score of a certain sensor data is continuously lower than the threshold, a maintenance warning (such as "sensor calibration abnormality") is automatically triggered, reducing the cost of manual inspections.

[0144] In some optional implementations, step S02 may be implemented by the following steps: for any initial gas concentration data, calculating the concentration change rate based on other adjacent concentrations in the initial gas concentration data; determining the average concentration change rate and the standard deviation of the change rate based on the concentration change rate; determining the dynamic threshold based on a preset basic threshold, a first threshold adjustment coefficient, a second threshold adjustment coefficient, the average concentration change rate and the standard deviation of the change rate; obtaining the number of mutations in which the concentration change rate exceeds the dynamic threshold; and calculating the mutation score of the initial gas concentration data using a mutation score formula based on the number of mutations, the number of gas concentrations in the initial gas concentration data, the concentration change rate and the standard deviation of the change rate, wherein the mutation score formula is:

[0145]

[0146] Where S is the mutation score; N e is the number of mutations; N r is the number of gas concentrations; is the average concentration change rate; σR is the standard deviation of the change rate.

[0147] It is understandable that other adjacent concentrations can be concentration values ​​at the previous or next moment adjacent to the current data point. The concentration change rate can be the relative change amplitude of the concentration at adjacent moments. For example, the CO concentration rises from 40ppm to 44ppm, with a change rate of 10%. The average concentration change rate can be the average value of the concentration change rate within a preset time window (such as the last 10 minutes), reflecting the overall trend of data fluctuations. The standard deviation of the change rate is used to reflect the degree of discreteness of the concentration change rate within the time window. The larger the standard deviation, the more drastic the concentration fluctuation. The dynamic threshold can be a mutation judgment threshold adjusted in real time based on historical fluctuation characteristics, and the formula is: θ baseis the basic threshold (such as the preset upper limit of normal fluctuation of 20%). α and β are adjustment coefficients (such as α = 1.5 and β = 1, which are used to amplify or reduce the influence of standard deviation and mean. The number of mutations can be the number of times the concentration change rate exceeds the dynamic threshold within the time window, such as 3 times of change rate > 30% within 10 minutes. The number of gas concentrations can be the total number of sampling points within the time window (such as 10 data points collected in 10 minutes). The mutation score can be an indicator to measure the degree of data mutation. The higher the score, the fewer mutations and the more stable the data.

[0148] It's important to note that existing technologies often use fixed thresholds to detect sudden changes (e.g., a change rate >30% is considered abnormal), which can be easily affected by fluctuations caused by routine funeral home operations (such as cremation operations). This solution, through a triple mechanism of dynamic thresholds, statistical features, and exponential correction, achieves the goal of "accommodating normal fluctuations while accurately identifying sudden changes," reducing the data misjudgment rate by approximately 40% compared to traditional methods.

[0149] In some optional implementations, after step S10, the method further includes: calculating, for any pollutant gas, a concentration change rate at adjacent moments based on the gas concentration; obtaining the number of mutations in which the concentration change rate is greater than a preset mutation threshold within a preset time period; and, when the number of mutations is greater than the preset threshold, calculating a mutation intensity index using a mutation intensity formula based on the concentration change rate, the hazard weight, and the preset mutation threshold, wherein the mutation intensity formula is:

[0150]

[0151] Where, I m is the mutation intensity; δ i is the hazard weight of the i-th pollutant gas; Rc i (t) is the concentration change rate; θ i is a preset mutation threshold; obtaining the equivalent height of the multiple pollutant gases and the total amount of pollutants emitted from the pollution source into the environment per unit time; determining the diffusion trend prediction results of the multiple pollutant gases based on the equivalent height and the total amount of pollutants; calculating the power lead control amount through an adjustment formula based on the mutation intensity index and the diffusion trend prediction result, the adjustment formula is:

[0152]

[0153] In the formula, ΔP is the power advance control amount; k1 is the first control coefficient; k2 is the second control coefficient; A is the diffusion trend prediction result; according to the power advance control amount and the operating power, the target control power is determined; and the operation of the air purification system is controlled according to the target control power.

[0154] It is understood that the concentration change rate between adjacent moments can be the ratio of the concentration difference between two consecutive sampling moments to the concentration at the previous moment, reflecting the rate of concentration change. The preset mutation threshold can be the critical value for determining whether a concentration change is a "mutation," set based on the historical fluctuation characteristics of the gas (e.g., the normal fluctuation threshold for CO is 20% / minute, and the mutation threshold is set at 50% / minute). The number of mutations can be the cumulative number of times the concentration change rate exceeds the preset mutation threshold within a preset time period (e.g., 10 minutes), used to determine whether mutations are persistent. The mutation intensity index can be a quantitative indicator that combines the hazard weight of the pollutant gas and the concentration change rate. A higher value indicates a greater hazard of the mutation (e.g., mutations of the highly hazardous gas CO are assigned a higher weight). The equivalent height (effective source height, H) can be an equivalent value to the actual emission height of the pollutant gas, taking into account the physical height of the emission source and the lifting effect of airflow (e.g., the physical height of the crematorium discharge port is 5 meters, but due to the rising effect of hot air, the equivalent height may be 8 meters). The total amount of pollutants (source intensity, Q) can be the mass of pollutants released from the pollution source into the environment per unit time (e.g., the mass of CO emitted by a crematorium per hour is 2 kg / h). The diffusion trend prediction result can be a prediction of the diffusion range and concentration distribution of pollutant gases in space (e.g., after CO leaks in the crematorium, it is predicted that it will diffuse to the southeast, and the concentration peak will reach the operating area after 10 minutes). The power advance control amount can be the additional power of the purification system added to respond to pollution diffusion in advance, so that the system can improve its processing capacity before the pollution peak arrives. The target control power can be the final power value that combines the current operating power and the advance control amount, which is used to drive the operation of the air purification system.

[0155] In one example, the concentration change rate of each pollutant gas is monitored in real time. For example, the CO concentration is 50 ppm at t = 0 and rises to 80 ppm at t = 1 (1 minute interval), with a change rate of 60% / minute, exceeding the preset mutation threshold (50% / minute). If the change rate exceeds the standard for 3 consecutive moments (3 minutes), it is determined that a continuous mutation has occurred and an early warning is triggered. The mutation intensity assessment is based on the hazard weight of CO (δ i=0.9) and the rate of change (60%) are used to calculate the mutation intensity index (the higher the value, the more dangerous). For example, a weighted summation yields a "high" intensity level. Diffusion trend prediction inputs parameters such as equivalent height (8 meters), total pollutant volume (2kg / h), and current wind speed (2m / s). Using a diffusion model, it predicts that CO will diffuse throughout the crematorium within 15 minutes, with concentrations in the central area potentially reaching 150ppm (exceeding the safety limit). Advance control calculation and power adjustment automatically calculate the required additional power based on the mutation intensity and diffusion prediction results (e.g., if the current power is 50kW, the advance control amount is 20kW). The target control power is adjusted to 70kW, and high power mode is immediately activated, prioritizing increased operating intensity for the CO purification module. Effectiveness verification and feedback: Ten minutes later, the peak CO concentration was monitored at 120ppm (below the predicted 150ppm), indicating that advance control effectively suppressed pollution diffusion. The system then fine-tunes control parameters for the next mutation based on the actual results (e.g., increasing or decreasing the advance power ratio).

[0156] It should be noted that this solution, through mutation detection and diffusion prediction, activates high-power mode 10-15 minutes in advance, improving response speed by over 50% and preventing personnel from being exposed to highly polluted environments. Precisely targeted control allocates power to specific mutated gases (such as CO), rather than global purification, reducing ineffective energy consumption. For example, if only the CO module power is increased by 40%, while other modules remain at normal levels, overall energy consumption will increase by approximately 25%, but purification efficiency will increase by 60%. Dynamic risk assessment combines hazard weights and diffusion range to quantify the mutation risk level (low, medium, and high), achieving dynamic "risk-power" matching. For example, mutations in low-hazard gases only trigger low-amplitude power adjustments, avoiding overreaction. Compatibility and scalability allow integration into existing air purification systems without hardware modifications. When new pollutants are added, only the hazard weights and diffusion parameters need to be updated for rapid adaptation. 5. Differences from Existing Technologies Existing technologies often use a passive control model of "concentration exceeds the standard → feedback adjustment", which is unable to cope with the rapid spread of sudden pollution. This solution uses a proactive process of **"mutation detection → trend prediction → proactive control"** to change the control logic from "post-event processing" to "pre-event prevention." It is particularly suitable for sudden pollution outbreaks such as cremation workshops in funeral homes, significantly improving environmental safety and system responsiveness.

[0157] See also Figure 3 , Figure 3 This is a structural block diagram of an air adaptive purification control device 400 provided in an embodiment of the present application. In this embodiment, the air adaptive purification control device includes various units for executing Figure 1-Figure 2 Each step in the corresponding embodiment. Please refer to Figure 1-Figure 2 as well as Figure 1-Figure 2For the convenience of explanation, only the parts related to this embodiment are shown. Figure 3 , the air adaptive purification control device 400 includes:

[0158] An acquisition module 401 is used to acquire gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are acquired through monitoring by target sensors;

[0159] The calculation module 402 is configured to calculate the pollutant hazard index of the polluted gas using an exponential formula according to the gas concentration. The exponential formula is:

[0160]

[0161] Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases;

[0162] The determination module 403 is configured to determine the operating power of the air purification system according to the gas concentration using a pollutant gas coupled dynamics model when the pollutant hazard index is greater than a preset hazard value. The pollutant gas coupled dynamics model is:

[0163]

[0164] Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas;

[0165] A control module 404 is configured to control the operation of the air purification system according to the operating power;

[0166] The control module 404 is further configured to control the air purification system to operate in a low power mode when the pollutant hazard index is less than or equal to the preset hazard value.

[0167] The device achieves dynamic adaptive power regulation by constructing a coupled kinetic model of polluted gases. The model introduces historical concentration mean values, nonlinear response mechanisms, and periodic variation characteristic parameters, which can maintain low power when pollution is low and quickly improve purification efficiency when pollution is high. It can also predict pollution trends and adjust power in advance to avoid energy waste. Taking into account the synergistic effects of multiple pollutants, cross-terms are used to process the interactions between different gases, and purification priorities are differentiated according to the hazard index to reduce energy consumption caused by excessive treatment of low-hazard pollutants. Dual-mode switching is achieved by combining hazard index comparison to ensure a dynamic balance between energy consumption and purification effect while ensuring the purification effect. Compared with traditional linear control and single pollutant treatment methods, energy consumption control is more intelligent and efficient, which can effectively reduce the energy consumption of the air purification system.

[0168] It should be understood that Figure 3 In the block diagram of the air adaptive purification control device shown, each unit is used to perform Figure 1-Figure 2 The steps in the corresponding embodiments, and Figure 1-Figure 2 Each step in the corresponding embodiment has been explained in detail in the above embodiment. Figure 1-Figure 2 as well as Figure 1-Figure 2 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0169] Figure 4 This is a structural block diagram of a terminal device provided by another embodiment of the present application. Figure 4 As shown, the terminal device 500 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501, such as a program for the air adaptive purification control method. When the processor 501 executes the computer program 503, the steps in each embodiment of the air adaptive purification control method described above are implemented, such as Figure 1 Alternatively, the processor 501 executes the computer program 503 to implement the above Figure 3 For details on the functions of each unit in the corresponding embodiment, please refer to Figure 3 The relevant descriptions in the corresponding embodiments are not repeated here.

[0170] Exemplarily, the computer program 503 may be divided into one or more units, one or more of which are stored in the memory 502 and executed by the processor 501 to complete the present application. The one or more units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 503 in the terminal device 500.

[0171] The terminal device may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 4It is only an example of the terminal device 500 and does not constitute a limitation of the terminal device 500. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the turntable terminal device may also include input and output terminal devices, network access terminal devices, buses, etc.

[0172] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0173] The memory 502 can be an internal storage unit of the terminal device 500, such as a hard disk or memory of the terminal device 500. The memory 502 can also be an external storage terminal device of the terminal device 500, such as a plug-in hard disk equipped on the terminal device 500, a SmartMediaCard (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 502 can also include both the internal storage unit of the terminal device 500 and an external storage terminal device. The memory 502 is used to store computer programs and other programs and data required by the turntable terminal device. The memory 502 can also be used to temporarily store data that has been output or is about to be output.

[0174] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0175] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium can be non-volatile or volatile. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable storage media may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0176] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An air adaptive purification control method, characterized in that: The method comprises: Obtaining gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are obtained by monitoring with target sensors; According to the gas concentration, the pollutant hazard index of the polluted gas is calculated by an index formula, and the index formula is: Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases; When the pollutant hazard index is greater than a preset hazard value, the operating power of the air purification system is determined according to the gas concentration by a pollutant gas coupling dynamics model, where the pollutant gas coupling dynamics model is: Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas; controlling the operation of the air purification system according to the operating power; When the pollutant hazard index is less than or equal to the preset hazard value, the air purification system is controlled to operate in a low power mode.

2. The method according to claim 1, wherein Before controlling the air purification system to operate in a low-power mode when the pollutant hazard index is less than or equal to the preset hazard value, the method further includes: Determining basic hazard thresholds of the multiple pollutant gases based on safe concentration limits of the multiple pollutant gases in the confined space; Determine an environmental correction factor based on the average space area of ​​each area of ​​the funeral home, the current space area, the actual ventilation volume of the current area, and the quasi-ventilation volume of the other side; Obtaining historical data of people entering the funeral home; Classify the crowd according to the historical data of people entering the crowd, and obtain the number of crowd classifications; Determine the weight ratio of each group of people based on the historical data of incoming personnel; Determine a personnel tolerance correction coefficient based on the number of population categories, the weight ratio of each population category, and the average tolerance index of each population category; Determining an initial set hazard value according to the basic hazard threshold, the environmental correction factor, and the human tolerance correction factor; Obtaining an average pollutant hazard index within a preset historical period in the funeral home; Determining an adjustment coefficient based on the initially set hazard value and the average pollutant hazard index; The preset hazard value is determined according to the adjustment coefficient and the initially set hazard value.

3. The method according to claim 1, wherein The step of controlling the operation of the air purification system according to the operating power includes: Dividing the air purification system into a preset number of purification modules, where the number of purification modules is equal to the amount of polluted gases; According to the gas concentrations of the multiple pollutant gases and the corresponding hazard weights, the operating power of each purification module is calculated using the module power formula, which is: Where, P mi is the operating power of the i-th purification module; P base is the basic power; H0 is the set hazard value; δ j is the hazard weight of the jth type of pollutant gas; C j is the gas concentration of the jth pollutant gas; Performing preliminary control on the operating power of each purification module according to the operating power of each purification module; Real-time monitoring of the current processing efficiency of each purification module; Determining the pre-adjusted power of each purification module according to the current processing efficiency, the preset standard processing efficiency and the power adjustment coefficient; The operating power of each purification module is adjusted according to the pre-adjusted power of each purification module.

4. The method according to claim 1, wherein Before obtaining the gas concentrations of the multiple pollutant gases in the funeral home, the method further includes: Defining typical work scenes in the funeral home to obtain a typical work scene set, each scene in the typical work scene set includes a gas concentration feature vector, a personnel activity feature vector, and a time feature vector; Calculating the similarity between the current environment feature vector and each scene in the typical work scene set through a scene recognition model; Determining the scene type of the current scene based on the similarities of the scenes; According to the scenario type, a target operating mode is selected from a preset sensor operating mode library; The target sensor is controlled to operate in the target operating mode.

5. The method according to any one of claims 1 to 4, characterized in that The method of obtaining the gas concentrations of various pollutants in the funeral home includes: Obtaining initial gas concentration data of multiple pollutant gases in the funeral home; For any initial gas concentration data, extract the integrity score, mutation score, deviation score and consistency score of the initial gas concentration data; The quality score of the initial gas concentration data is calculated using a scoring formula according to the integrity score, mutation score, deviation score and consistency score; In a case where the mass score is greater than a preset mass score, the initial gas concentration data is used as the gas concentration of the corresponding polluted gas.

6. The method according to claim 5, wherein The extracting, for any initial gas concentration data, the integrity score, mutation score, deviation score, and consistency score of the initial gas concentration data includes: For any initial gas concentration data, calculating the concentration change rate according to other adjacent concentrations in the initial gas concentration data; Determining an average concentration change rate and a standard deviation of the change rate based on the concentration change rate; Determine a dynamic threshold value based on a preset basic threshold value, a first threshold value adjustment coefficient, a second threshold value adjustment coefficient, an average concentration change rate, and a standard deviation of the change rate; Obtaining the number of mutations at which the concentration change rate exceeds the dynamic threshold; The mutation score of the initial gas concentration data is calculated according to the number of mutations, the number of gas concentrations in the initial gas concentration data, the concentration change rate, and the standard deviation of the change rate using a mutation score formula. The mutation score formula is: Where S is the mutation score; N e is the number of mutations; N r is the number of gas concentrations; is the average concentration change rate; σR is the standard deviation of the change rate.

7. The method according to any one of claims 1 to 4, characterized in that After obtaining the gas concentrations of the multiple polluting gases in the funeral home, the method further includes: For any pollutant gas, the concentration change rate at adjacent moments is calculated based on the gas concentration; Obtaining the number of mutations in which the concentration change rate is greater than a preset mutation threshold within a preset time period; When the number of mutations is greater than a preset number threshold, the mutation intensity index is calculated using the mutation intensity formula according to the concentration change rate, the hazard weight, and the preset mutation threshold. The mutation intensity formula is: Where, I m is the mutation intensity; δ i is the hazard weight of the i-th pollutant gas; Rc i (t) is the concentration change rate; θ i is the preset mutation threshold; Obtaining the equivalent heights of the multiple pollutant gases and the total amount of pollutants emitted from the pollution sources into the environment per unit time; Determining diffusion trend prediction results of the multiple pollutant gases based on the equivalent height and the total amount of pollutants; According to the mutation intensity index and the diffusion trend prediction result, the power lead control amount is calculated by an adjustment formula, and the adjustment formula is: Where ΔP is the power advance control quantity; k1 is the first control coefficient; k2 is the second control coefficient; A is the diffusion trend prediction result; determining a target control power according to the power advance control amount and the operating power; The air purification system is controlled to operate according to the target control power.

8. An air adaptive purification control device, characterized in that: The device comprises: An acquisition module is used to acquire the gas concentrations of various polluting gases in the funeral home, wherein the gas concentrations are acquired through monitoring by target sensors; A calculation module is used to calculate the pollutant hazard index of the polluted gas according to the gas concentration using an exponential formula, where the exponential formula is: Where H is the pollutant hazard index; δ i is the hazard weight of the i-th pollutant gas; C i is the gas concentration of the i-th pollutant gas; max(C1, C2, ..., C n ) is the maximum gas concentration among n types of polluting gases; A determination module is configured to determine the operating power of the air purification system according to the gas concentration using a pollutant gas coupling dynamics model when the pollutant hazard index is greater than a preset hazard value. The pollutant gas coupling dynamics model is: Where, P is the operating power; α is the first model adjustment coefficient; γ is the second model adjustment coefficient; λ is the third model adjustment coefficient; ρ is the fourth model adjustment coefficient; β i is the impact index of the i-th pollutant gas; is the historical mean concentration of the i-th pollutant gas; η i is the concentration nonlinear index, reflecting the nonlinear response characteristics of different pollutant gases; ω i is the angular frequency of the concentration change of the i-th pollutant gas; φ i is the initial phase of the concentration change of the i-th pollutant gas; σ i is the standard deviation of the gas concentration of the i-th pollutant gas; a control module, configured to control the operation of the air purification system according to the operating power; The control module is further configured to control the air purification system to operate in a low power mode when the pollutant hazard index is less than or equal to the preset hazard value.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images