An ozone centralized air purification and disinfection system based on scene recognition

Abstract

The present invention provides an ozone centralized air purification and disinfection system based on scenario recognition. A scenario data acquisition module is used to obtain real-time scenario parameters of a truck container. The real-time scenario parameters include temperature parameters, disinfection range, virus and bacteria concentration, odor concentration, and formaldehyde concentration. A central control module is used to establish a supervised disinfection model according to the real-time scenario parameters and generate a progressive disinfection task. A supervised disinfection module is used to prepare ozone according to the progressive disinfection task, perform progressive supervised disinfection on the truck container, and output real-time disinfection data.

Description

Technical Field

[0001] The present invention relates to the technical field of container disinfection, and in particular to an ozone centralized air purification and disinfection system based on scene recognition. Background Art

[0002] At present, in the environment where the virus is rampant around the world, cold chain transportation is one of the important channels for the spread of the virus because the virus is more likely to survive in a low temperature environment and cold chain transportation has low temperature conditions.

[0003] At present, the following methods are usually used in the market to disinfect cold chain transportation:

[0004] 1. Take out the cold chain products from the container, spray hydrogen peroxide or other disinfectants on the cold chain products through the disinfection equipment, and then put them back into the container after disinfection;

[0005] 2. Open the container, take out some items, then place the disinfection equipment in the container, turn on the disinfection equipment, close the refrigerated container, let it stand for 30-60 minutes, spray hydrogen peroxide on the cold chain food with the disinfection equipment, then open the container and take out the disinfection equipment;

[0006] 3. Evacuate the container and inject ozone, and ensure that the ozone pressure in the refrigerated container is between 0.8 and 1.2 atmospheres.

[0007] 4. The disinfection personnel use a heavy-duty disinfection sprayer to spray disinfectant on the facade, tires, cockpit, box body and door handles of the transport truck. After receiving the goods, the door must be opened first, and the disinfection personnel will disinfect the goods at the door of the box for a second time, and then close the door for 10-15 minutes before unloading. Manual spraying is carried out again on the pallet, and finally each piece of goods is disinfected and sterilized hexahedron.

[0008] In the above method:

[0009] Containers have a slow turnover rate and are prone to backlogs, leading to a tight supply and demand relationship for containers. Especially for fresh cold chain containers, long queues will also cause the quality of goods to decline or even deteriorate.

[0010] Currently, 90% of disinfection and sterilization are done manually, which requires a large amount of personal protective equipment and disinfectant. In particular, many people are afraid of the "epidemic", and it is becoming increasingly difficult to recruit disinfection operators, resulting in a surge in labor costs.

[0011] The disinfectants currently used in various places are all chlorine-containing disinfectant solutions. They cause headaches, nausea, mucous membrane irritation and other symptoms to operators. In addition, it is generally not recommended to use chlorine-containing chemical disinfection on fresh foods such as vegetables and fruits, as the residue will affect the quality and taste.

[0012] Relying heavily on manual operations, there will inevitably be omissions or uncovered areas. Summary of the Invention

[0013] The present invention provides an ozone centralized air purification and disinfection system based on scene recognition to solve the situation in the above background technology.

[0014] An ozone centralized air purification and disinfection system based on scene recognition, comprising:

[0015] Scene data acquisition module: used to obtain real-time scene parameters of the truck container; wherein,

[0016] The real-time scene parameters include: temperature parameter, disinfection range, virus and bacteria concentration, odor concentration, and formaldehyde concentration;

[0017] Central control module: used to establish a supervised disinfection model according to the real-time scene parameters and generate a progressive disinfection task;

[0018] Supervised disinfection module: According to the progressive disinfection task, ozone is prepared, and the truck container is subjected to progressive supervised disinfection, and real-time disinfection data is output.

[0019] Preferably, the system further includes:

[0020] Vibration simulation module: used to obtain real-time driving data of the truck container, perform driving simulation of the truck container, and generate a driving simulation space; wherein,

[0021] The real-time driving data includes: real-time vibration frequency data, real-time vibration amplitude data, and vibration duration data;

[0022] Ozone generation module: used to calculate the air flow and negative pressure value inside the truck container according to the driving simulation space, and determine the ozone preparation interval according to the air flow and negative pressure value;

[0023] Negative pressure control module: used to monitor the negative pressure value of the truck container according to the progressive disinfection task, and control the stability of the negative pressure inside the truck container by controlling the flow rate;

[0024] Ozone preparation module: used to quantitatively input ozone into the truck container according to the progressive disinfection task when the negative pressure is stable, and perform disinfection on the truck container.

[0025] Preferably, the scene data acquisition module includes:

[0026] Temperature detection unit: used to set multiple temperature sensors inside the truck container, and obtain the average temperature inside the truck container through the multiple temperature sensors;

[0027] Virus detection unit: It is used to set a self-priming virus detection kit inside the truck container and perform self-priming detection on the aerosol inside the truck container based on the self-priming virus detection kit to obtain virus data;

[0028] Bacteria detection unit: It is used to perform environmental air bacteria detection through the bacteria capture device inside the truck container to obtain bacteria data; Among them,

[0029] The bacteria capture device includes a microfluidic chip, and a bacteria capture chamber, a reaction pool, and a fluorescence light source are arranged inside the microfluidic chip;

[0030] Odor detection unit: It is used to detect the odor inside the truck container through the odor sensor set inside the truck container to obtain odor data;

[0031] Formaldehyde concentration detection unit: It is used to obtain the formaldehyde data inside the truck container in real time through the formaldehyde detector set inside the truck container.

[0032] Preferably, the microfluidic chip further includes:

[0033] Composite magnetic nucleic acid purification particles and magnetic nanoparticles are arranged in the bacteria capture chamber of the microfluidic chip, and after bacteria are captured, the bacteria capture chamber is closed;

[0034] The reaction pool includes a first liquid pool, a second liquid pool, a third liquid pool, a fourth liquid pool, and a reaction pool reaction reagent is configured in the reaction pool;

[0035] A washing solution is added to the first liquid pool;

[0036] A bacteria lysate is added to the second liquid pool;

[0037] A nucleic acid purification solution is added to the third liquid pool;

[0038] A nucleic acid elution solution is added to the fourth liquid pool;

[0039] Press the first preset number of times to control the operation chamber of the washing solution, so that the washing solution flows into the bacteria capture chamber to flush other substances not captured by the magnetic nanoparticles in the sample into the waste liquid pool;

[0040] After the fluorescence light source forms a preset-sized incident light spot in the reaction pool, a fluorescence signal picture for bacteria detection is generated.

[0041] Preferably, the central control module includes:

[0042] Ozone dynamic control unit: It is used to record the amount of ozone input into the truck container and the amount of ozone dissipated and consumed, and determine the real-time ozone amount in the truck container;

[0043] Negative pressure calculation unit: used to determine the optimal vacuum negative pressure value inside the truck container according to the real-time ozone amount and adjust the negative pressure value;

[0044] Ozone sterilization calculation unit: used to establish a detection timeline of the bacterial content inside the truck container and calculate the ozone sterilization efficiency through the detection timeline;

[0045] Vacuum pump control unit: used to extract air inside the truck container according to the negative pressure value adjustment and adjust the air flow inside the truck container;

[0046] Model building unit: used to determine the disinfection process and disinfection standards according to the real-time scene parameters inside the truck container and construct a supervised disinfection model;

[0047] Task generation unit: used to perform disinfection evolution according to the supervised disinfection model and generate a time-based progressive disinfection task according to the disinfection evolution and the supervised disinfection model.

[0048] Preferably, the model building unit includes the following model building steps:

[0049] Based on the real-time scene parameters, determine the node topology diagram of the truck container disinfection process and the disinfection ozone amount; where,

[0050] The disinfection process includes: the content requirements of ozone charged into the container at different times and the ozone preparation process;

[0051] The disinfection standard includes: matching the corresponding ozone content standard under different scene parameters of the truck container;

[0052] Perform linear processing on each node topology diagram to determine the corresponding link topology diagram of each node topology diagram;

[0053] Determine the node graph-level features of each node topology diagram and the link graph-level features of each link topology diagram;

[0054] According to all the node graph-level features, determine the node graph-level change features, and according to all the link graph-level features, determine the link graph-level change features;

[0055] Generate a supervised disinfection model according to the node graph-level change features and the link graph-level change features, and perform supervised disinfection on the truck container at each moment; where,

[0056] The supervised disinfection model includes: a scene dynamic supervision model, an ozone charging amount dynamic control model, and a scene ozone matching fitting model.

[0057] Preferably, the task generation unit includes the following task generation process:

[0058] Predict the ozone disinfection range at each moment according to the real-time environmental parameters and the ozone charging threshold range of the truck container, and obtain the prediction results;

[0059] According to the prediction results, perform disinfection evolution on the truck container and predict the ozone charging amount at each moment;

[0060] According to the predicted ozone charging amount at each moment and the supervised disinfection model, formulate the target disinfection parameters at each moment; where,

[0061] The target disinfection parameters include: target ozone charging amount, target environmental data change amount, and target disinfection progress parameters;

[0062] Generate a progressive disinfection task according to the target disinfection parameters at each moment.

[0063] Preferably, the supervised disinfection model block:

[0064] Report data collection unit: used to collect the disinfection scenario data at each moment;

[0065] Template generation unit: used to convert the task progress information in the disinfection scenario data at each moment into a disinfection report template through the disinfection synchronization rule;

[0066] Supervision unit: used to record the disinfection data at each moment through the disinfection report template and perform progressive supervision;

[0067] Summary supervision unit: used to configure the summary rule and summarize the progressive supervision data at each moment to generate real-time disinfection data.

[0068] Preferably, the system further includes:

[0069] Ozone preparation mode control unit: used to decompose the ozone sequence data prepared in the current environment by variational mode decomposition during ozone preparation to obtain multiple modal components; where,

[0070] The modal components represent ozone with different concentrations;

[0071] Residual calculation unit: used to calculate the difference between the ozone sequence data and the sum of the multiple modal components to obtain the remaining residual term;

[0072] Preparation calculation unit: use a neural network to predict each modal component to obtain the final prediction result of the residual term, and determine the ozone preparation concentration adjustment parameter according to the final prediction result of the residual term.

[0073] Preferably, the system further includes:

[0074] Region setting module: used to divide the space inside the truck container into multiple different regions;

[0075] Wind control module: used to adjust the wind force corresponding to different regions when ozone is filled into the truck container; among them

[0076] Wind force adjustment includes: air supply direction adjustment, air supply volume adjustment and air supply temperature adjustment. The wind direction calculation module: used for one or more regions inside the truck container, calculates the optimal upper and lower angles of the blades of the wind power device to adjust the air supply direction, so that the blown air evenly sends the filled ozone into different regions.

[0077] Other features and advantages of the present invention will be described in the subsequent specification, and partly become obvious from the specification, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0078] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0079] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0080] Figure 1 It is the system block diagram of an ozone centralized air purification and disinfection system based on scene recognition in an embodiment of the present invention;

[0081] Figure 2 It is the overall block diagram of the scene data acquisition module in an embodiment of the present invention;

[0082] Figure 3 It is the actual disinfection scene flow chart in an embodiment of the present invention;

[0083] Figure 4 It is the overall system control diagram in an embodiment of the present invention. Detailed Embodiments

[0084] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0085] An ozone centralized air purification and disinfection system based on scene recognition, including:

[0086] Scene data acquisition module: used to obtain the real-time scene parameters of the truck container; among them,

[0087] The real-time scene parameters include: temperature parameter, disinfection range, virus and bacteria concentration, odor concentration, and formaldehyde concentration;

[0088] Central control module: used to establish a supervised disinfection model based on real-time scene parameters and generate a progressive disinfection task;

[0089] Supervised disinfection module: prepare ozone according to the progressive disinfection task, perform progressive supervised disinfection on the truck container, and output real-time disinfection data.

[0090] The principle of the above technical solution is as follows: The present invention is a system for intelligent disinfection based on ozone. Ozone will penetrate into the interior of various fungi, destroy lipoproteins and lipopolysaccharides, and damage cells. At the same time, it will also degrade the enzymes required for glucose, making the TCA cycle that maintains its life activities impossible to proceed and the required ATP unable to be supplied, causing bacteria to die. When acting on viruses, it will react with the four polypeptide chains of the capsid protein, damaging the protein; destroying its DNA or RNA, resulting in the cessation of metabolism and the death of the virus. It is very suitable for the current transportation environment.

[0091] As shown in Figure 1 、 3 、4, the present invention intelligently adjusts the ozone input amount according to the specific scenario of the truck container, and intelligently monitors the ozone input amount, so as to realize disinfection supervision and disinfection monitoring under the condition of comprehensive disinfection. Based on the principle of cost saving, it can not only perform ozone disinfection, but also realize disinfection data supervision.

[0092] The beneficial effects of the above technical solution are as follows:

[0093] The present invention can realize comprehensive disinfection based on the principle of ozone, and at the same time can always supervise the disinfection data to judge whether the disinfection is completed, realizing comprehensive monitoring and disinfection of the truck container. Progressive supervised disinfection is a kind of intelligent disinfection that always monitors the virus content in the truck container, always controls the ozone input amount and the ozone propagation direction, and controls the inside of the truck container.

[0094] In an optional embodiment of the present invention, the progressive supervised disinfection of the present invention further includes the steps of:

[0095] Step 1: Obtain the current progressive disinfection task and generate a first task model:

[0096]

[0097] where q i represents the execution constant of the i-th task of the progressive disinfection task; k i represents the negative pressure change parameter of the current air volume inside the truck container when the i-th task of the progressive disinfection task is executed; fi Denote the influence parameter of negative pressure in the truck container on ozone disinfection during the execution of the $i$-th task of the progressive disinfection task; $w$ i Denote the influence parameter of the temperature in the truck container on ozone disinfection during the execution of the $i$-th task of the progressive disinfection task; $c$ i Denote the ozone input amount in the truck container during the execution of the $i$-th task of the progressive disinfection task; $y$ i Denote the ozone escape amount in the truck container during the execution of the $i$-th task of the progressive disinfection task; $i\in n$, $i$ is a positive integer; $n$ represents the total number of tasks of the progressive disinfection task;

[0098] Step 2: Obtain the real-time disinfection result data of the current disinfection task, and determine the variable parameters of the progressive disinfection task:

[0099]

[0100] Among them, $B(i + 1)$ represents the execution adjustment parameter of the $(i + 1)$-th task of the progressive disinfection task; $P$ i Denote the expected disinfection result feature of the $i$-th task of the progressive disinfection task; $G$ i Denote the actual disinfection result feature of the $i$-th task of the progressive disinfection task; $F(G$ i ) represents the result feature function under the actual disinfection result feature of the $i$-th task of the progressive disinfection task; $z$ i Denote the execution feature parameter of the $i$-th task of the progressive disinfection task.

[0101] In the above Step 1, the present invention constructs a first task model through the progressive disinfection task. In the first task model, $(q$ i $+ k$ i $f$ i ) is used to judge the execution parameter of the disinfection task under the current negative pressure change; $[(q$ i $+ k$ i $f$ i ) $+ w$ i is used to determine the influence parameter of the current negative pressure state and the current temperature on the ozone disinfection efficiency by combining the influence of the current execution parameter with the temperature on the disinfection task; by multiplying the influence parameter by $[c$ i $- y$ i the actual ozone amount that can play a disinfection role, the actual disinfection parameter, that is, the first task model is determined. In Step 2, in order to judge whether there is a change in the task parameter for the next task after the current task, and the specific task parameter $B(i + 1)$; by It is possible to judge the expected execution result under the task execution, that is, the difference between the expected result of ozone disinfection and the actual disinfection result, and judge whether the current task has achieved the expected disinfection goal. When the expected goal is achieved, it is 0. When it is not 0, if it is less than 0, it means that the actual disinfection result is insufficient; when it is greater than 0, it means that the actual disinfection result exceeds the expected result. Whether the actual disinfection result exceeds the expected result or the ozone disinfection effect is not good, the tasks of the next task node need to be adjusted. The specific adjustment parameter (P i |G i )* (P i |G i ) is used to judge whether the characteristics of the actual disinfection result conform to the expected disinfection result characteristics P i . When they do not conform, its value generates a positive or negative deviation coefficient according to the deviation of the result; and then through determine the loss in the corresponding disinfection result, and determine the adjustment parameter during the actual execution of the (i + 1)-th task of the progressive disinfection task through the loss in the disinfection result and the deviation in the result.

[0102] Preferably, the system further includes:

[0103] Vibration simulation module: used to obtain the real-time driving data of the truck container, perform the driving simulation of the truck container, and generate a driving simulation space; wherein,

[0104] The real-time driving data includes: real-time vibration frequency data, real-time vibration amplitude data, and vibration duration data;

[0105] Ozone generation module: used to calculate the air flow and negative pressure value in the truck container according to the driving simulation space, and determine the ozone preparation interval according to the air flow and negative pressure value;

[0106] Negative pressure control module: used to supervise the negative pressure value of the truck container according to the progressive disinfection task, and control the stability of the negative pressure in the truck container through flow control;

[0107] Ozone preparation module: used to quantitatively input ozone into the truck container according to the progressive disinfection task when the negative pressure is stable, and perform disinfection on the truck container.

[0108] The principle of the above technical solution is as follows:

[0109] During the disinfection process of the present invention, dynamic driving simulation of the truck container is also carried out, so as to achieve dynamic disinfection of the truck container during driving. Based on efficiency calculation, through the built driving simulation space, ozone preparation calculation control and negative pressure adjustment are carried out at all times, so as to realize ozone disinfection control through the driving simulation space. The vibration simulation module can simulate the vibration conditions of the truck container at different driving speeds and different road conditions when the truck container is driving, so as to form a simulated driving space for the truck container. The driving simulation space is a simulated driving space for the truck container. When the truck container is driving, the amount of ozone that can be generated can be determined according to the air flow rate and negative pressure value inside the truck container. Since the air flow rate and negative pressure conditions are constantly changing, the determined is the ozone preparation interval.

[0110] The progressive disinfection task is to achieve progressive disinfection by real-time detecting the content of bacteria, viruses, etc. inside the truck container, with real-time monitoring and real-time disinfection. Moreover, during the disinfection process, in order to ensure that the generated ozone can reach the required flow rate, the negative pressure value of the truck container will be monitored, and based on the monitoring of the negative pressure value, the air flow rate will be controlled to ensure the stability of the negative pressure. At the same time as the negative pressure is stable, ozone is quantitatively input into the truck container to achieve comprehensive disinfection of the truck container.

[0111] The beneficial effects of the above technical solutions are as follows:

[0112] The present invention can stabilize the negative pressure inside the truck container through driving simulation under the condition that the truck container vibrates, so as to ensure the disinfection effect of ozone when performing the disinfection task, because the disinfection ability of ozone varies under different negative pressure conditions.

[0113] Preferably, the scenario data acquisition module includes:

[0114] Temperature detection unit: used to set multiple temperature sensors inside the truck container, and obtain the average temperature inside the truck container through the multiple temperature sensors;

[0115] Virus detection unit: used to set a self-aspirating virus detection kit inside the truck container, and based on the self-aspirating virus detection kit, perform self-aspirating detection on the aerosol inside the truck container to obtain virus data;

[0116] Bacteria detection unit: used to perform environmental air bacteria detection through the bacteria capture device inside the truck container to obtain bacteria data; among them,

[0117] The bacteria capture device includes a microfluidic chip, and a bacteria capture chamber, a reaction pool, and a fluorescent light source are arranged inside the microfluidic chip;

[0118] Odor detection unit: It is used to detect the odor inside the truck container through the odor sensors set inside the truck container and obtain odor data;

[0119] Formaldehyde concentration detection unit: It is used to obtain the formaldehyde data inside the truck container in real time through the formaldehyde detector set inside the truck container.

[0120] The principle of the above technical solution is as follows:

[0121] As shown in the appendix Figure 2 During the data collection process of the present invention, the environmental data inside the truck container will be determined, including temperature data, virus data, bacteria data, odor data and formaldehyde data. Through these data, the input amount of ozone is determined, so as to comprehensively control the ozone preparation cost during the disinfection process and prevent excessive cost consumption.

[0122] The temperature monitoring unit can determine the average temperature inside the truck container through multiple temperature sensors distributed inside the truck container. Based on the average temperature inside the truck container, it judges the influence of temperature on the ozone disinfection ability and then adjusts the ozone amount. The virus detection unit can judge the virus concentration inside the truck container through a self-aspirating virus test kit, and then judge the ozone amount for disinfection according to the virus concentration. Bacteria detection also judges the required ozone amount for disinfection based on the concentration and quantity of bacteria. As for the odor data and formaldehyde concentration data, they both have a certain impact on ozone disinfection. Through comprehensive consideration of temperature, virus concentration, bacteria concentration, odor and formaldehyde, the final required ozone amount is determined.

[0123] Preferably, the microfluidic chip further includes:

[0124] Composite magnetic nucleic acid purification particles and magnetic nanoparticles are provided in the bacteria capture cavity of the microfluidic chip, and after the bacteria are captured, the bacteria capture cavity is closed;

[0125] The reaction pool includes a first liquid pool, a second liquid pool, a third liquid pool, a fourth liquid pool, and a reaction pool. Enzyme digestion reaction reagents are configured in the reaction pool;

[0126] A washing solution is added to the first liquid pool;

[0127] A bacterial lysate is added to the second liquid pool;

[0128] A nucleic acid purification solution is added to the third liquid pool;

[0129] A nucleic acid elution solution is added to the fourth liquid pool;

[0130] Pressing the first preset number of times is used to control the operation cavity of the washing solution to make the washing solution flow into the bacteria capture cavity to remove other substances in the sample that are not captured by the magnetic nanoparticles

[0131] After the fluorescent light source forms an incident light spot of a preset size in the reaction cell, a fluorescence signal picture for bacteria detection is generated.

[0132] The principle of the above technical solution is as follows:

[0133] The chip of the present invention is a bacteria detection chip. The lysis solution flows into the bacteria capture chamber to lyse the captured target bacteria; then the nucleic acid purification solution flows into the bacteria capture chamber to enable the composite magnetic nucleic acid purification particles to adsorb the nucleic acid of the lysed target bacteria.

[0134] Finally, the washing solution flows into the bacteria capture chamber to flush the substances not adsorbed by the composite magnetic nucleic acid purification particles in the bacteria capture chamber into the waste liquid pool; and the nucleic acid elution solution flows into the bacteria capture chamber to flush the purified nucleic acid of the target bacteria into the amplification pool; the purified nucleic acid of the target bacteria undergoes an amplification reaction for a first preset time at a preset temperature; the amplified nucleic acid of the target bacteria flows into the reaction cell to enable the amplified nucleic acid of the target bacteria to undergo an enzyme digestion reaction for a second preset time; thereby realizing bacteria detection.

[0135] The beneficial effect of the above technical solution is as follows:

[0136] By capturing the bacteria content inside the truck container through the above microfluidic chip, the bacteria that need to be disinfected and killed inside the truck container can be quantified, and then the required ozone disinfection concentration and ozone disinfection amount can be determined.

[0137] Preferably, the central control module includes:

[0138] Ozone dynamic control unit: used to record the ozone input amount and the dissipated and consumed ozone amount inside the truck container, and determine the real-time ozone amount of the truck container;

[0139] Negative pressure calculation unit: used to determine the optimal vacuum negative pressure value inside the truck container according to the real-time ozone amount, and adjust the negative pressure value;

[0140] Ozone sterilization calculation unit: used to establish a detection timeline of the bacteria content inside the truck container, and calculate the ozone sterilization efficiency through the detection timeline;

[0141] Vacuum pump control unit: used to extract air inside the truck container according to the negative pressure value adjustment, and adjust the air flow inside the truck container;

[0142] Model building unit: used to determine the disinfection process and disinfection standards according to the real-time scene parameters inside the truck container, and construct a supervised disinfection model;

[0143] Task generation unit: It is used to perform disinfection evolution according to the supervised disinfection model, and generate a time-based progressive disinfection task based on the disinfection evolution and the supervised disinfection model.

[0144] The principle of the above technical solution is as follows:

[0145] Through ozone dynamic control, the present invention controls the ozone dynamics by time, so as to perform negative pressure adjustment under the condition of negative pressure adjustment, calculate the disinfection efficiency, control the air volume in the truck container, and thus perform disinfection. The ozone dynamic control unit can determine the real-time ozone amount, the real-time dissipated and consumed ozone amount, and the real-time ozone amount input into the truck container inside the truck container. The negative pressure calculation unit can judge the most suitable negative pressure value for disinfection under the current ozone amount according to the ozone amount and ozone concentration in the truck container, and then adjust the negative pressure state in the truck container. The way of negative pressure adjustment is determined by the air input and output amount. The ozone disinfection calculation unit can calculate the disinfection efficiency at the current ozone concentration during the disinfection process according to the bacteria content detected in the truck container in real time. The vacuum pump control unit is used to adjust the disinfection efficiency by adjusting the air content in the truck container. According to the real-time scene parameters, determine the disinfection process and disinfection standards. The disinfection process is the control steps of different devices and the expected ozone input amount at each moment during the ozone disinfection process at different times on the time axis. The disinfection standard is the lowest value that the detected bacteria, viruses, odors, etc. in the truck container need to reach under the condition of meeting the target disinfection requirements, and the lowest value can be 0. The supervised disinfection model can determine the control parameters and expected detection parameters during the evolution disinfection process by simulating and evolving the entire disinfection process, and then, through the supervised disinfection model, supervise the actual disinfection data to determine whether the expected detection parameters that should be obtained at each moment are accurate.

[0146] Preferably, the model building unit includes the following model building steps:

[0147] Based on the real-time scene parameters, determine the node topology diagram of the disinfection process and disinfection ozone amount of the truck container; wherein,

[0148] The disinfection process includes: the content requirements for ozone charged into the container at different times and the ozone preparation process;

[0149] The disinfection standard includes: matching the corresponding ozone content standard under different scene parameters of the truck container;

[0150] Perform linear processing on each node topology diagram to determine the link topology diagram corresponding to each node topology diagram;

[0151] Determine the node graph-level features of each node topology diagram and the link graph-level features of each link topology diagram;

[0152] Determine the node graph-level change features based on all node graph-level features, and determine the link graph-level change features based on all link graph-level features;

[0153] Generate a supervised disinfection model based on the node graph-level change features and the link graph-level change features, and perform supervised disinfection on the truck container at each moment; where

[0154] The supervised disinfection model includes: a scene dynamic supervision model, an ozone charging amount dynamic control model, and a scene ozone matching fitting model.

[0155] The principle of the above technical solution is as follows:

[0156] Real-time scene parameters, that is, parameters such as bacteria and viruses inside the truck container, as well as the amount of odor and formaldehyde, can determine the specific disinfection process for the inside of the truck container. Through the specific disinfection process of the truck container, the overall disinfection process of the truck container is determined in the form of a node topology graph. The prior processing of each node topology graph is to linearly process the specific disinfection process according to the disinfection parameters corresponding to each node in the node topology graph, generating the link graph-level features of the overall disinfection process. The link graph-level features are the program features between different disinfection control processes. The node graph-level features represent the features of the change of the control parameters of the disinfection tasks corresponding to each node. Furthermore, during the disinfection process, through the change features of each node and the change features of the disinfection control steps, dynamic supervision is carried out on the entire disinfection process, generating a dynamic supervised disinfection model. Through the method of dynamic supervision, the disinfection process of the truck container is supervised to ensure the smoothness of the disinfection process. It can also realize that when the environment inside the truck container changes dynamically, the disinfection tasks change dynamically, and the supervised disinfection model corresponds to the dynamic changes.

[0157] Preferably, the task generation unit includes the following task generation process:

[0158] Predict the ozone disinfection range at each moment according to the real-time environmental parameters and the ozone charging threshold range of the truck container, and obtain the prediction result;

[0159] Perform disinfection evolution on the truck container according to the prediction result, and predict the ozone charging amount at each moment;

[0160] Formulate the target disinfection parameters at each moment according to the predicted ozone charging amount at each moment and the supervised disinfection model; where

[0161] The target disinfection parameters include: the target ozone charging amount, the target environmental data change amount, and the target disinfection progress parameter;

[0162] Generate a progressive disinfection task according to the target disinfection parameters at each moment.

[0163] The principle of the above technical solution lies in that when the present invention generates a task, it determines the disinfection parameters through the implementation environment parameters, thereby performing disinfection evolution, and then realizing supervised disinfection. According to the evolution data, corresponding disinfection tasks are specified, and then global disinfection is carried out.

[0164] The prediction results obtained by the present invention are the prediction results of the contents of viruses, bacteria, odors, formaldehyde, etc. in the truck container after disinfection. Disinfection evolution means that when the disinfection result is known, the amount of ozone injected at different times is evolved. Then, based on these prediction data, the target control parameters, which are also the target disinfection parameters, are specified during the disinfection process, and then a progressive disinfection task based on each moment is generated. For the node topology graph, each node corresponds to a moment, so as to ensure that during the disinfection process, the disinfection data is not only accurate, but also the time consumed by the entire disinfection process is not wasted, and there is a corresponding disinfection task at each moment.

[0165] Preferably, the supervised disinfection model module:

[0166] Report data collection unit: used to collect the disinfection scenario data at each moment;

[0167] Template generation unit: used to convert the task progress information in the disinfection scenario data at each moment into a disinfection report template through the disinfection synchronization rule according to the progressive disinfection task;

[0168] Supervision unit: used to record the disinfection data at each moment through the disinfection report template and perform progressive supervision;

[0169] Summary supervision unit: used to configure the summary rule and summarize the progressive supervision data at each moment to generate real-time disinfection data.

[0170] The principle of the above technical solution lies in:

[0171] The disinfection model of the present invention determines the disinfection status in the truck container by collecting the scene monitoring data of disinfection at each moment, so as to perform synchronous disinfection based on the task progress by the template generation unit, and thus generate the corresponding disinfection report template, and disinfect the truck container at each moment.

[0172] The present invention matches the disinfection scene data after disinfection with the execution progress of the progressive disinfection task to generate a disinfection report template. The disinfection synchronization rule is that during the disinfection process, the disinfection execution steps and the expected effects to be achieved after disinfection are synchronized. Then, through the disinfection report, the supervision data of the entire disinfection process can be reported to judge whether the disinfection meets the disinfection standard.

[0173] Preferably, the system further includes:

[0174] Ozone preparation mode control unit: When preparing ozone, it uses variational mode decomposition to decompose the ozone sequence data prepared in the current environment to obtain multiple mode components; among them,

[0175] The mode components represent ozone with different concentrations;

[0176] Residual calculation unit: It is used to calculate the difference between the ozone sequence data and the sum of the multiple mode components to obtain the remaining residual term;

[0177] Preparation calculation unit: It uses a neural network to predict each mode component to obtain the final prediction result of the residual term, and determines the ozone preparation concentration adjustment parameter according to the final prediction result of the residual term.

[0178] The principle of the above technical solution is as follows:

[0179] When the present invention prepares ozone, through variational mode decomposition, when determining the preparation of ozone, through the mode components, it determines the mode control parameters required for preparing ozone with different concentrations, that is, the specific efficiency of preparing ozone with different concentrations. The residual calculation unit can calculate the possible losses and the causes of the losses in the process of ozone preparation when determining the preparation of ozone with different concentrations. Under which environmental project parameters, losses occur, that is, the remaining residual term. Furthermore, a neural network is used to predict the preparation of ozone with different concentrations, and determine the items that may cause preparation losses during ozone preparation for adjustment.

[0180] Preferably, the system further includes:

[0181] Region setting module: It is used to divide the space inside the truck container into multiple different regions;

[0182] Wind force control module: It is used to adjust the wind force corresponding to different regions when the truck container is filled with ozone; among them

[0183] The wind force adjustment includes: air supply direction adjustment, air supply volume adjustment and air supply temperature adjustment,

[0184] Wind direction calculation module: It is used to calculate the optimal upper and lower angles of the wind turbine blades in one or more regions inside the truck container to adjust the air supply direction so that the sent air evenly sends the filled ozone into different regions.

[0185] The principle of the above technical solution is as follows:

[0186] In order to achieve comprehensive disinfection during disinfection, the present invention comprehensively divides the regions inside the truck container, and by constantly adjusting the wind force and wind direction, the ozone can comprehensively cover the entire space of the truck container, so as to achieve global disinfection of the truck container.

[0187] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An ozone centralized air purification and disinfection system based on scenario recognition, characterized in that Including: Scene data acquisition module: used to obtain real-time scene parameters of the truck container; among them, The real-time scene parameters include: temperature parameter, disinfection range, virus and bacteria concentration, odor concentration, and formaldehyde concentration; Central control module: used to establish a supervised disinfection model based on the real-time scene parameters and generate a progressive disinfection task; Supervised disinfection module: According to the progressive disinfection task, prepare ozone, perform progressive supervised disinfection on the truck container, and output real-time disinfection data; The system further includes: Vibration simulation module: used to obtain real-time driving data of the truck container, perform driving simulation of the truck container, and generate a driving simulation space; among them, The real-time driving data includes: real-time vibration frequency data, real-time vibration amplitude data, and vibration duration data; Ozone generation module: used to calculate the air flow and negative pressure value inside the truck container according to the driving simulation space, and determine the ozone preparation interval according to the air flow and negative pressure value; Negative pressure control module: used to supervise the negative pressure value of the truck container according to the progressive disinfection task, and control the stability of the negative pressure inside the truck container by controlling the flow rate; Ozone preparation module: used to quantitatively input ozone into the truck container according to the progressive disinfection task when the negative pressure is stable, and perform disinfection on the truck container.

2. The ozone centralized air purification and disinfection system based on scene recognition according to claim 1, wherein The scene data acquisition module includes: Temperature detection unit: used to set multiple temperature sensors inside the truck container and obtain the average temperature inside the truck container through the multiple temperature sensors; Virus detection unit: used to set a self-aspirating virus detection kit inside the truck container and perform self-aspirating detection on the aerosol inside the truck container based on the self-aspirating virus detection kit to obtain virus data; Bacteria detection unit: used to perform environmental air bacteria detection through the bacteria capture device inside the truck container to obtain bacteria data; among them, The bacteria capture device includes a microfluidic chip, and a bacteria capture chamber, a reaction pool, and a fluorescence light source are arranged inside the microfluidic chip; Odor detection unit: used to detect the odor inside the truck container through the odor sensor arranged inside the truck container to obtain odor data; Formaldehyde concentration detection unit: used to obtain the formaldehyde data inside the truck container in real time through the formaldehyde detector arranged inside the truck container.

3. The ozone centralized air purification and disinfection system based on scenario recognition according to claim 2, characterized in that, The microfluidic chip further includes: Composite magnetic nucleic acid purification particles and magnetic nanoparticles are arranged in the bacteria capture chamber of the microfluidic chip, and after the bacteria are captured, the bacteria capture chamber is closed; The reaction pool includes a first liquid pool, a second liquid pool, a third liquid pool, a fourth liquid pool, and a reaction pool; Enzyme digestion reaction reagents are configured in the reaction pool; A washing solution is added to the first liquid pool; A bacterial lysate is added to the second liquid pool; A nucleic acid purification solution is added to the third liquid pool; A nucleic acid elution solution is added to the fourth liquid pool; Press the first preset number of times to control the operation chamber of the washing solution to make the washing solution flow into the bacteria capture chamber to flush other substances in the sample that are not captured by the magnetic nanoparticles into the waste liquid pool; After the fluorescence light source forms a preset-sized incident light spot in the reaction pool, a fluorescence signal picture for bacteria detection is generated.

4. The ozone centralized air purification and disinfection system based on scenario recognition according to claim 1, characterized in that, The central control module includes: Ozone Dynamic Control Unit: It is used to record the amount of ozone input into the truck container and the amount of ozone dissipated and consumed, and determine the real-time ozone amount in the truck container; Negative Pressure Calculation Unit: It is used to determine the optimal vacuum negative pressure value in the truck container according to the real-time ozone amount, and adjust the negative pressure value; Ozone Sterilization Calculation Unit: It is used to establish a detection timeline of the bacterial content in the truck container, and calculate the ozone sterilization efficiency through the detection timeline; Vacuum Pump Control Unit: It is used to extract air from the truck container according to the negative pressure value adjustment, and adjust the air flow in the truck container; Model Building Unit: It is used to determine the disinfection process and disinfection standards according to the real-time scenario parameters in the truck container, and construct a supervised disinfection model; Task Generation Unit: It is used to perform disinfection evolution according to the supervised disinfection model, and generate a time-based progressive disinfection task according to the disinfection evolution and the supervised disinfection model.

5. The ozone centralized air purification and disinfection system based on scene recognition according to claim 4, characterized in that, The Model Building Unit includes the following model building steps: Based on the real-time scenario parameters, determine the node topology diagram of the disinfection process and the ozone amount for disinfection in the truck container; where, The disinfection process includes: the content requirements for ozone charged into the container at different times and the ozone preparation process; The disinfection standard includes: matching the corresponding ozone content standards under different scenario parameters of the truck container; Perform linear processing on each node topology diagram to determine the link topology diagram corresponding to each node topology diagram; Determine the node graph-level features of each node topology diagram and the link graph-level features of each link topology diagram; According to all the node graph-level features, determine the node graph-level change features, and according to all the link graph-level features, determine the link graph-level change features; According to the node graph-level change features and the link graph-level change features, generate a supervised disinfection model to perform supervised disinfection on the truck container at each moment; where, The supervised disinfection model includes: a scenario dynamic supervision model, an ozone charging amount dynamic control model, and a scenario ozone matching fitting model.

6. The ozone centralized air purification and disinfection system based on scene recognition according to claim 4, characterized in that, The Task Generation Unit includes the following task generation process: According to the real-time environmental parameters and the ozone charging threshold interval of the truck container, predict the ozone disinfection range at each moment, and obtain the prediction result; According to the prediction result, perform disinfection evolution on the truck container and predict the ozone charging amount at each moment; According to the predicted ozone charging amount at each moment and the supervised disinfection model, formulate the target disinfection parameters at each moment; where, The target disinfection parameters include: the target ozone charging amount, the target environmental data change amount, and the target disinfection progress parameter; Generate a progressive disinfection task according to the target disinfection parameters at each moment.

7. The ozone centralized air purification and disinfection system based on scenario recognition according to claim 1, characterized in that, The Supervised Disinfection Model Block: Report Data Collection Unit: It is used to collect the disinfection scenario data at each moment; Template Generation Unit: It is used to convert the task progress information into a disinfection report template through the disinfection synchronization rule by using the disinfection scenario data at each moment and the task progress information of the progressive disinfection task; Supervision Unit: It is used to record the disinfection data at each moment through the disinfection report template and perform progressive supervision; Summary Supervision Unit: It is used to configure the summary rule and summarize the progressive supervision data at each moment to generate real-time disinfection data.

8. The ozone centralized air purification and disinfection system based on scenario recognition according to claim 1, characterized in that, The system further includes: An ozone preparation mode control unit: When preparing ozone, it is used to decompose the ozone sequence data prepared in the current environment by variational mode decomposition to obtain multiple modal components; where The modal components represent ozone with different concentrations; A residual calculation unit: It is used to calculate the difference between the ozone sequence data and the sum of the multiple modal components to obtain a remaining residual term; A preparation calculation unit: It uses a neural network to predict each modal component to obtain a final prediction result of the residual term, and determines an ozone preparation concentration adjustment parameter according to the final prediction result of the residual term.

9. The ozone centralized air purification and disinfection system based on scenario recognition according to claim 1, wherein, The system further includes: A region setting module: It is used to divide the space inside the truck container into multiple different regions; A wind force control module: When the truck container is filled with ozone, it is used to adjust the wind force corresponding to different regions; where The wind force adjustment includes: adjusting the air supply direction, adjusting the air supply volume, and adjusting the air supply temperature, A wind direction calculation module: It is used to calculate the optimal up and down angles of the blades of the wind power device in one or more regions inside the truck container, and adjusts the air supply direction through the optimal angles to evenly send ozone into different regions.

Images